Why Gemfury?
Push, build, and install
RubyGems
npm packages
Python packages
Maven artifacts
PHP packages
Go Modules
Debian packages
RPM packages
NuGet packages
Repository URL to install this package:
|
Version:
1.26.4 ▾
|
Ïúíþ X
( __TEXT __text __TEXT 8K `þ 8K __stubs __TEXT I < I __stub_helper __TEXT ÔO T ÔO __const __TEXT (V (V __cstring __TEXT @Ö Ò& @Ö __unwind_info __TEXT ý è ý __DATA_CONST @ @ __got __DATA_CONST
__DATA @ @ @ @ __la_symbol_ptr __DATA @ ( @ ¥ __data __DATA (D ø (D __common __DATA N __bss __DATA (N @ H __LINKEDIT @ x
P numpy/random/mtrand.cpython-312-iphonesimulator.so " 0 x Ø ð è
ø[ P t t u ¥ @
* n±Z8W1±i]ã342 þ* 0 @ /usr/lib/libc++.1.dylib 8 >8 /usr/lib/libSystem.B.dylib & ) às
À, ø_¼©öW©ôO©ý{©ýà ô ª @ù eBù? ±@ T? ë` Th !@ù @ùA °!Ãÿ ± eù ±À T °GùÓ ´h@¹ 1¢
Th ¹k A °! àª@ ´õ ª
ó ª¨@ùÈ ø7 ñ¨ ùa T઼ ´àªüÿ ´õ ªA °!0àª, À ´ö ªA °!Làªâª}ÿ ÷ ªÈ@ùÈ ø7 ñÈ ùa Tત ø7A °!xàª
´ö ªA °!àªâªiÿ ÷ ªÈ@ùÈ ø7 ñÈ ùa Tàª
ø7A °!¸àª ´ö ªA °!ÔàªâªUÿ ÷ ªÈ@ùÈ ø7 ñÈ ùa Tàª|
ø7A °!àªðÿ ` ´ô ªh q@ù ë@ TA °!pàªâª=ÿ õ ª@ù¨ ø6 R@ù ø7 ñ ù TUø7àªý{C©ôOB©öWA©ø_ĨÀ_ÖàªY ÿÿ60 Ò. h @ù @ù+ÿ 4&ÿ A °!xàªÄÿ õÿµh @ù @ù ÿ À 4ÿ A °!¸àª¹ÿ Àöÿµh @ù @ùÿ ` 4ÿ A °!મÿ à÷ÿµh @ù @ù
ÿ 4ÿ àªý{C©ôOB©öWA©ø_ĨÀ_Öàª
Òàªý{C©ôOB©öWA©ø_ĨÀ_ÖÿÑüo©úg©ø_©öW©ôO©ý{©ýÃh y@ù@ù¨ø °èGùh ´ ëÀÁTh 5@ù @ùA °! ôþ 8 àù @¹ 1B T ¹Cÿ 'ùÀÍ´ @¹ 1B T ¹@ ° L ÿ >´ @¹) 1B T ¹ )ù@ ° p üþ ¾´ @¹ 1B T ¹ ÖB9À ùàGùÂ@ùA °!¬ sÿ ½ù7h e@ù@ù =pa R?
ëà T ýXÓ]SJ °Jñ °k±ë+©Rk Rë+ ©é#©B °B¸ àCR+ÿ 5 RáC Ò" R±þ àÀù7 Òqÿ 1ùàÇ´ ¬ Òbþ h ð 5ù`Ç´ ¬ ҇ÿ h ð 9ùàÆ´ ä /¯þ ùÀ´ n ªþ ù ´HÒF¼òÈ1Ïò¨Èçò g¡þ ù Á´(Òhq»ò
Àòþçò gþ ùà¿´ ÒÀþ ù@¿´5 R Rºþ ¡ù@´@ , Ò R¸þ ¥ù½´ þ ©ù༴h ð!N¹ 4àGù M@ù@ùÿ ¶ù7þ ¿´ó ª !°+þ à µâGù !°àª4þ Ðù7Ó^CùÀ@ù@ùI@ùY ð9[@ù᪠끽T Ò# RGÿ ½´ ¡ùӂAùÀ@ù@ùI@ù᪠ë!½T Ò# R:ÿ ½´ ¥ùÓvAùÀ@ù@ùI@ù᪠롽T Ò# R-ÿ ½´ ©ùÓ^AùÀ@ù@ùI@ù᪠ë!½T Ò# R ÿ ½´ ®ùӾEùÀ@ù@ùI@ù᪠롼T Ò# Rÿ ¼´ ±ùÓr@ùÀ@ù@ùI@ù᪠ë!¼T Ò# Rÿ ¼´ @·ùӖ@ùÀ@ù@ùI@ù᪠롻T Ò# Rùþ »´ ¹ùÓ~AùÀ@ù@ùI@ù᪠끻T Ò# Rìþ »´ ¾ùÓæEùÀ@ù@ùI@ù᪠ë»T Ò# Rßþ »´ ÁùÓ~@ùÀ@ù@ùI@ù ᪠ëaºT Ò# RÑþ `º´`ÇùÓz@ùÀ@ù@ùI@ù ᪠롺T Ò# RÄþ º´ÀÊù Ö" È@ùè ù3 R Rþ .ù »´ ÖB È@ùè ù3 R Rvþ .ù £´ ÖâÈ@ùè ù3 R Rmþ ÀÞù¢´v ðÖB=È@ùè ù3 R Rdþ Àù`¡´ ÖÂ
È@ùè ù3 R R[þ Àjù@ ´ sâh@ù®Gùè' ©@ RRþ `jù@ ´ Ö"È@ùè ù3 R RIþ ÀÊù ´ Öb.È@ùè ù3 R R@þ Àùà´ ւ.È@ùè ù3 R R7þ Àù´ Öb*È@ùè ù3 R R.þ ù ´ s¢h@ùiZDùè' ©@ R%þ `ªù ´ sh@ùi.Dùè' ©@ R þ `rù´H ðq@ùè£ ©è ù` Rþ åù`´s ðs>h@ùI·Gùè' ©@ R
þ `*ù@´ Öâ4È@ùÉ
@ùè' ©@ Rþ ÀR ù ´ 9Ã(@ùè ù3 R Røý ùà´ 9ã(@ùè ù3 R Rïý ù´ 9£(@ùè ù3 R Ræý 'ù ´ 9(@ùè ù3 R RÝý /ù´ 9c!(@ùè ù3 R RÔý ×ù`´ 9c(@ùè ù3 R RËý ;ù@´ 9#(@ùè ù3 R RÂý ù ´ 9c#(@ùè ù3 R R¹ý £ù ´ 9£#(@ùè ù3 R R°ý ùà´y ð9£<(@ùè ù3 R R§ý ù ´y ð9Ã=(@ùè ù3 R Rý cù ´y ð9ã<(@ùè ù3 R Rý ù´y ð99(@ùè ù3 R Rý óù`´ ZH@ùè ù3 R Rý @§ù@
´ ZÃH@ùè ù3 R Rzý @3ù ´ ZcH@ùè ù3 R Rqý @Ãù ´ ZãH@ùè ù3 R Rhý @7ùà´ Z# H@ùè ù3 R R_ý @sù ´ Z#H@ùè ù3 R RVý @×ù ´ Z#
H@ùè ù3 R RMý @ù~´ ZH@ùè ù3 R RDý @ãù`}´S ðsr@ùàªáªâª0ý Éù`}´ {c h@ùè ù: R R2ý `Ûùà´ ZC
H@ù®Gùè' ©@ R)ý @£ù {´H@ùè ù4 R R"ý @§ù`´ B6@ùèO ©@ Rý ù@y´ "$@ùè ù3 R Rý Òù w´ ¢@ùè ù3 R Rý fùàu´ B@ùè ù3 R Rÿü VùÀt´ sbh@ù©¾Gùè' ©@ Röü `ÖùÀt´È@ùI ð)i@ùè' ©@ Rîü ÀÊ ùÀs´ ¢3@ùè ù3 R Råü ö ùq´ sb hDùi@ùè' ©@ RÜü `Bùq´ö ª5S@©:çDù;Fù ¬ ÒÇû k´ó ªô©hVRè; ¹ûï©õë©ö× ©õ ù R R RC R Re Ræªçªêü ô ªh@ùÈ ø7 ñh ùa Tàªý yùôl´5S@©6çDù: Cù ¬ ңû h´ó ªô©hYRè; ¹úë©õÛ©õ× ©õ ù R R R R Re RæªçªÆü ô ªh@ùÈ ø7 ñh ùa Tàªßü }ùth´ s"
h@ùi.Dùè' ©@ Rü `.ù@g´ö ª5S@©:çDù;Fù ¬ Òuû b´ó ªô©¨\Rè; ¹ûï©õë©ö× ©õ ù R R RC R Re Ræªçªü ô ªh@ùÈ ø7 ñh ùa T઱ü ù´b´ sh@ùiÚAùè' ©@ R\ü `vùa´ö ª5S@©:çDù;ïEù ¬ ÒGû ]´ó ªô©h`Rè; ¹ûï©õë©ö× ©õ ù R R RC R RåRæªçªjü ô ªh@ùÈ ø7 ñh ùa Tàªü
ùô\´5S@©6GHù:çDù;¯Eù ¬ Ò"û ÀX´ó ªô©HaRè; ¹ûï©õë©ö× ©õ ù R R RC R RåRæªçªEü ô ªh@ùÈ ø7 ñh ùa Tàª^ü ùTX´F `qù7s qù7 àqù7ì rù7 !Dù¹ r´ô ªu ðµ"9 @ù¡þDùâªû Sù7@ùÈ ø7 ñ ùa Tàª@ü ]Fù¦ p´ô ª @ù¡:Gùâªû Rù7@ùÈ ø7 ñ ùa Tàª/ü 3 R RTû o´ô ª Ȋ@ù @¹) 1b T ¹Ȋ@ù@ù( ù Aù᪠R ó ªÀm´@ùÈ ø7 ñ ùa Tàªü J@ùàª9 Àl´ô ª @ù¡fAùâªØú @Mù7@ùÈ ø7 ñ ùa Tàªü h@ùÈ ø7 ñh ùa Tàªûû Dùa j´ó ª @ù¡ÒDùâªÀú Jù7h@ùÈ ø7 ñh ùa Tàªêû 4 R Rû i´ó ªv ðȲGù @¹) 1b T ¹ȲGùi@ù( ù qCùáª" R× h´ô ªh@ùÈ ø7 ñh ùa TàªÎû rGùàªô ó ªÀf´ @ù¡@ùâªú àEù7h@ùÈ ø7 ñh ùa Tઽû @ùÈ ø7 ñ ùa Tશû 0 1ÀdTh ðGù @ý³ú d´ô ªs Ðs<h@ù
@ùaÊDùâªtú Cù7@ùÈ ø7 ñ ùa Tàªû h Ð GùVû H ÐQ@ù @¹) 1B T ¹h ù`@ùÿ©èC! ðÒ*- a´ô ª @ù¡vEùâªVú à?ù7@ùÈ ø7 ñ ùa Tàªû v ðDù @`´ô ªh ð%Aù@ùI@ù`´àª ?Öó ª `´@ùÈ ø7 ñ ùa Tàªkû @ù¡Bùâª5ú @<ù7h@ùÈ ø7 ñh ùa Tàª_û Dùò ^´ó ªh ð1Aù@ùI@ùè]´àª ?Öô ªà]´h@ùÈ ø7 ñh ùa TàªKû @ù¡Bùâªú 8ù7@ùÈ ø7 ñ ùa Tàª?û DùÒ à[´ô ªh ðMAù@ùI@ù¨[´àª ?Öó ª [´@ùÈ ø7 ñ ùa Tàª+û @ù¡*Bùâªõù @ù7h@ùÈ ø7 ñh ùa Tઠû Dù² ÀY´ó ªh ðqAù@ùI@ùY´àª ?Öô ªY´h@ùÈ ø7 ñh ùa Tઠû @ù¡NBùâªÕù @Dù7@ùÈ ø7 ñ ùa Tàªÿú Dù W´ô ªh ð}Aù@ùI@ùHW´àª ?Öó ª@W´@ùÈ ø7 ñ ùa Tàªëú @ù¡ZBù⪵ù À@ù7h@ùÈ ø7 ñh ùa Tàªßú Dùr Y´ó ªh ðÉAù@ùI@ùHY´àª ?Öô ª@Y´h@ùÈ ø7 ñh ùa TàªËú @ù¡¦Bùâªù =ù7@ùÈ ø7 ñ ùa Tિú DùR @W´ô ªh ðBù@ùI@ùW´àª ?Öó ª W´@ùÈ ø7 ñ ùa Tફú @ù¡ÞBùâªuù :ù7h@ùÈ ø7 ñh ùa Tàªú Dù2 U´ó ªh ð
Bù@ùI@ùèT´àª ?Öô ªàT´h@ùÈ ø7 ñh ùa Tàªú @ù¡êBùâªUù 6ù7@ùÈ ø7 ñ ùa Tàªú Dù àR´ô ªh ð)Bù@ùI@ù¨R´àª ?Öó ª R´@ùÈ ø7 ñ ùa Tàªkú @ù¡Cùâª5ù 5ù7h@ùÈ ø7 ñh ùa Tàª_ú Dùò ÀP´ó ªh ðUBù@ùI@ùP´àª ?Öô ªP´h@ùÈ ø7 ñh ùa TàªKú @ù¡2Cùâªù `2ù7@ùÈ ø7 ñ ùa Tàª?ú DùÒ N´ô ªh ð=Bù@ùI@ùHN´àª ?Öó ª@N´@ùÈ ø7 ñ ùa Tàª+ú @ù¡Cùâªõø 0ù7h@ùÈ ø7 ñh ùa Tઠú Dù² `L´ó ªh ðeBù@ùI@ù(L´àª ?Öô ª L´h@ùÈ ø7 ñh ùa Tઠú @ù¡BCùâªÕø -ù7@ùÈ ø7 ñ ùa Tàªÿù Dù J´ô ªh ðyBù@ùI@ùèI´àª ?Öó ªàI´@ùÈ ø7 ñ ùa Tàªëù @ù¡VCù⪵ø À*ù7h@ùÈ ø7 ñh ùa Tàªßù Dùr H´ó ªh ðéBù@ùI@ùÈG´àª ?Öô ªÀG´h@ùÈ ø7 ñh ùa TàªËù @ù¡ÆCùâªø (ù7@ùÈ ø7 ñ ùa Tિù DùR ÀE´ô ªh ð)Cù@ùI@ùE´àª ?Öó ªE´@ùÈ ø7 ñ ùa Tફù @ù¡Dùâªuø %ù7h@ùÈ ø7 ñh ùa Tàªù Dù2 C´ó ªh ð5Cù@ùI@ùhC´àª ?Öô ª`C´h@ùÈ ø7 ñh ùa Tàªù @ù¡DùâªUø à"ù7@ùÈ ø7 ñ ùa Tàªù Dù `A´ô ªh ðACù@ùI@ù(A´àª ?Öó ª A´@ùÈ ø7 ñ ùa Tàªkù @ù¡ Dùâª5ø À ù7h@ùÈ ø7 ñh ùa Tàª_ù Dùò @?´ó ªh ð}Cù@ùI@ù?´àª ?Öô ª ?´h@ùÈ ø7 ñh ùa TàªKù @ù¡ZDùâªø ù7@ùÈ ø7 ñ ùa Tàª?ù DùÒ =´ô ªh ðCù@ùI@ùÈ<´àª ?Öó ªÀ<´@ùÈ ø7 ñ ùa Tàª+ù @ù¡fDùâªõ÷ ` ù7h@ùÈ ø7 ñh ùa Tઠù Dù² à:´ó ªh ðCù@ùI@ù¨:´àª ?Öô ª :´h@ùÈ ø7 ñh ùa Tઠù @ù¡DùâªÕ÷ @ ù7@ùÈ ø7 ñ ùa Tàªÿø Dù 8´ô ªh ðÑCù@ùI@ùh8´àª ?Öó ª`8´@ùÈ ø7 ñ ùa Tàªëø @ù¡®Dù⪵÷ ù7h@ùÈ ø7 ñh ùa Tàªßø Dùr 6´ó ªh ðÝCù@ùI@ùH6´àª ?Öô ª@6´h@ùÈ ø7 ñh ùa TàªËø @ù¡ºDùâª÷ àù7@ùÈ ø7 ñ ùa Tિø DùR @4´ô ªh ðéCù@ùI@ù4´àª ?Öó ª 4´@ùÈ ø7 ñ ùa Tફø @ù¡ÆDùâªu÷ Àù7h@ùÈ ø7 ñh ùa Tàªø Dù2 2´ó ªh ð1Dù@ùI@ùè1´àª ?Öô ªà1´h@ùÈ ø7 ñh ùa Tàªø @ù¡EùâªU÷ ù7@ùÈ ø7 ñ ùa Tàªø Dù à/´ô ªh ð=Dù@ùI@ù¨/´àª ?Öó ª /´@ùÈ ø7 ñ ùa Tàªkø @ù¡Eùâª5÷ `ù7h@ùÈ ø7 ñh ùa Tàª_ø Dùò À-´ó ªh ðMDù@ùI@ù-´àª ?Öô ª-´h@ùÈ ø7 ñh ùa TàªKø @ù¡*Eùâª÷ ù7@ùÈ ø7 ñ ùa Tàª?ø DùÒ +´ô ªh ðaDù@ùI@ùH+´àª ?Öó ª@+´@ùÈ ø7 ñ ùa Tàª+ø @ù¡>Eùâªõö ù7h@ùÈ ø7 ñh ùa Tઠø Dù² `)´ó ªh ðDù@ùI@ù()´àª ?Öô ª )´h@ùÈ ø7 ñh ùa Tઠø @ù¡nEùâªÕö À ù7@ùÈ ø7 ñ ùa Tàªÿ÷ Dù '´ô ªh ð¡Dù@ùI@ùè&´àª ?Öó ªà&´@ùÈ ø7 ñ ùa Tàªë÷ @ù¡~Eù⪵ö
ù7h@ùÈ ø7 ñh ùa Tàªß÷ Dùr %´ó ªh ðDù@ùI@ùÈ$´àª ?Öô ªÀ$´h@ùÈ ø7 ñh ùa TàªË÷ @ù¡Eùâªö `ù7@ùÈ ø7 ñ ùa Tિ÷ DùR À"´ô ªh йDù@ùI@ù"´àª ?Öó ª"´@ùÈ ø7 ñ ùa Tફ÷ @ù¡Eùâªuö @ù7h@ùÈ ø7 ñh ùa Tàª÷ Dù2 ´ó ªh ÐÁDù@ùI@ùh ´àª ?Öô ª` ´h@ùÈ ø7 ñh ùa Tàª÷ @ù¡EùâªUö ù7@ùÈ ø7 ñ ùa Tàª÷ Dù ` ´ô ªh ÐÍDù@ùI@ù( ´àª ?Öó ª ´@ùÈ ø7 ñ ùa Tàªk÷ @ù¡ªEùâª5ö àù7h@ùÈ ø7 ñh ùa Tàª_÷ Dùò ´ó ªh ÐíDù@ùI@ùè´àª ?Öô ªà´h@ùÈ ø7 ñh ùa TàªK÷ @ù¡ÊEùâªö ÿø7@ùÈ ø7 ñ ùa Tàª?÷ DùÒ à´ô ªh ÐEEù@ùI@ù¨´àª ?Öó ª ´@ùÈ ø7 ñ ùa Tàª+÷ @ù¡"Fùâªõõ ýø7h@ùÈ ø7 ñh ùa Tઠ÷ Dù² ´ó ªh ÐYEù@ùI@ùh´àª ?Öô ª`´h@ùÈ ø7 ñh ùa Tઠ÷ @ù¡6FùâªÕõ @ûø7@ùÈ ø7 ñ ùa Tàªÿö Dù `´ô ªh ÐEù@ùI@ù(´àª ?Öó ª ´@ùÈ ø7 ñ ùa Tàªëö @ù¡fFù⪵õ ùø7h@ùÈ ø7 ñh ùa Tàªßö Dùr ´ó ªh ÐEù@ùI@ùè´àª ?Öô ªà´h@ùÈ ø7 ñh ùa TàªËö @ù¡rFùâªõ àöø7@ùÈ ø7 ñ ùa Tિö DùR à´ô ªh СEù@ùI@ù¨´àª ?Öó ª ´@ùÈ ø7 ñ ùa Tફö @ù¡~Fùâªuõ Àôø7h@ùÈ ø7 ñh ùa Tàªö Dù2 ´ó ªh ÐEù@ùI@ùh´àª ?Öô ª`´h@ùÈ ø7 ñh ùa Tàªö @ù¡FùâªUõ òø7@ùÈ ø7 ñ ùa Tàªö Dù ` ´ô ªh йEù@ùI@ù( ´àª ?Öó ª ´@ùÈ ø7 ñ ùa Tàªkö @ù¡Fùâª5õ `ðø7h@ùÈ ø7 ñh ùa Tàª_ö Dùò
´ó ªh ÐFù@ùI@ùè ´àª ?Öô ªà ´h@ùÈ ø7 ñh ùa TàªKö @ù¡âFùâªõ îø7@ùÈ ø7 ñ ùa Tàª?ö DùÒ à´ô ªh Ð)Fù@ùI@ù¨´àª ?Öó ª ´@ùÈ ø7 ñ ùa Tàª+ö @ù¡Gùâªõô ìø7h@ùÈ ø7 ñh ùa Tઠö Dù² ´ó ªh Ð=Fù@ùI@ùh´àª ?Öô ª`´h@ùÈ ø7 ñh ùa Tઠö @ù¡GùâªÕô Àéø7@ùÈ ø7 ñ ùa Tàªÿõ Dù `´ô ªh ÐIFù@ùI@ù(´àª ?Öó ª ´@ùÈ ø7 ñ ùa Tàªëõ @ù¡&Gù⪵ô çø7h@ùÈ ø7 ñh ùa Tàªßõ Dùr ´ó ªh ÐaFù@ùI@ùè ´àª ?Öô ªà ´h@ùÈ ø7 ñh ùa TàªËõ @ù¡>Gùâªô `åø7@ùÈ ø7 ñ ùa Tિõ DùR àþ ´ô ªh ÐFù@ùI@ù¨þ ´àª ?Öó ª þ ´@ùÈ ø7 ñ ùa Tફõ @ù¡^Gùâªuô @ãø7h@ùÈ ø7 ñh ùa Tàªõ t ЂDù` ° 6 Ò ÒEô þ ´ó ª @ù¡Fùâª`ô `âø7h@ùÈ ø7 ñh ùa Tàªõ Dù` ° 6 Ò Ò1ô `ü ´ó ª @ù¡*CùâªLô áø7h@ùÈ ø7 ñh ùa Tàªvõ Dù` ° 7 Ò Ò ô Àú ´ó ª @ù¡Fùâª8ô ààø7h@ùÈ ø7 ñh ùa Tàªbõ Dù` ° 7 Ò Ò ô ù ´ó ª @ù¡úEùâª$ô àø7h@ùÈ ø7 ñh ùa TàªNõ Dù` ° 8 Ò Òõó ÷ ´ó ª @ù¡ºEùâªô `ßø7h@ùÈ ø7 ñh ùa Tàª:õ R`ô `ö ´ó ªh Ð )Aù*@¹J 1b T* ¹ )Aùèª
AøI ùj ÐI5Aù+@¹k 1b T+ ¹I5Aù
@ùI ùj ÐIQAù+@¹k 1b T+ ¹IQAù
@ùI ùj ÐIuAù+@¹k 1b T+ ¹IuAù
@ùI
ùj ÐIAù+@¹k 1b T+ ¹IAù
@ùI ùj ÐIÍAù+@¹k 1b T+ ¹IÍAù
@ùI ùj ÐIBù+@¹k 1b T+ ¹IBù
@ùI ùj ÐIBù+@¹k 1b T+ ¹IBù
@ùI ùj ÐI-Bù+@¹k 1b T+ ¹I-Bù
@ùI! ùj ÐIABù+@¹k 1b T+ ¹IABù
@ùI% ùj ÐIQBù+@¹k 1b T+ ¹IQBù
@ùI) ùj ÐIYBù+@¹k 1b T+ ¹IYBù
@ùI- ùj ÐIiBù+@¹k 1b T+ ¹IiBù
@ùI1 ùj ÐI}Bù+@¹k 1b T+ ¹I}Bù
@ùI5 ùj ÐIíBù+@¹k 1b T+ ¹IíBù
@ùI9 ùj ÐI-Cù+@¹k 1b T+ ¹I-Cù
@ùI= ùj ÐI9Cù+@¹k 1b T+ ¹I9Cù
@ùIA ùj ÐIECù+@¹k 1b T+ ¹IECù
@ùIE ùj ÐICù+@¹k 1b T+ ¹ICù
@ùII ùj ÐICù+@¹k 1b T+ ¹ICù
@ùIM ùj ÐI±Cù+@¹k 1b T+ ¹I±Cù
@ùIQ ùj ÐIÕCù+@¹k 1b T+ ¹IÕCù
@ùIU ùj ÐIáCù+@¹k 1b T+ ¹IáCù
@ùIY ùj ÐIíCù+@¹k 1b T+ ¹IíCù
@ùI] ùj ÐI5Dù+@¹k 1b T+ ¹I5Dù
@ùIa ùj ÐIADù+@¹k 1b T+ ¹IADù
@ùIe ùj ÐIQDù+@¹k 1b T+ ¹IQDù
@ùIi ùj ÐIeDù+@¹k 1b T+ ¹IeDù
@ùIm ùj ÐIDù+@¹k 1b T+ ¹IDù
@ùIq ùj ÐI¥Dù+@¹k 1b T+ ¹I¥Dù
@ùIu ùj ÐI±Dù+@¹k 1b T+ ¹I±Dù
@ùIy ùj ÐI½Dù+@¹k 1b T+ ¹I½Dù
@ùI} ùj ÐIÅDù+@¹k 1b T+ ¹IÅDù
@ùI ùj ÐIÑDù+@¹k 1b T+ ¹IÑDù
@ùI
ùj ÐIáDù+@¹k 1b T+ ¹IáDù
@ùI ùj ÐIñDù+@¹k 1b T+ ¹IñDù
@ùI ùj ÐI!Eù+@¹k 1b T+ ¹I!Eù
@ùI ùj ÐI5Eù+@¹k 1b T+ ¹I5Eù
@ùI ùj ÐIAEù+@¹k 1b T+ ¹IAEù
@ùI ùj ÐIIEù+@¹k 1b T+ ¹IIEù
@ùI ùj ÐI]Eù+@¹k 1b T+ ¹I]Eù
@ùI¡ ùj ÐIEù+@¹k 1b T+ ¹IEù
@ùI¥ ùj °IEù+@¹k 1b T+ ¹IEù
@ùI© ùj °I¥Eù+@¹k 1b T+ ¹I¥Eù
@ùI ùj °I±Eù+@¹k 1b T+ ¹I±Eù
@ùI± ùj °I½Eù+@¹k 1b T+ ¹I½Eù
@ùIµ ùj °I Fù+@¹k 1b T+ ¹I Fù
@ùI¹ ùj °I-Fù+@¹k 1b T+ ¹I-Fù
@ùI½ ùj °IAFù+@¹k 1b T+ ¹IAFù
@ùIÁ ùj °IMFù+@¹k 1b T+ ¹IMFù
@ùIÅ ùj °IeFù+@¹k 1b T+ ¹IeFù
@ùIÉ ùj °I
Fù+@¹k 1b T+ ¹I
Fù@ù Í ùi (ÉGù
@¹J 1b T
¹(ÉGùi@ù(Ñ ù @ù¡ÆAùâª"ò `£ø7h@ùÈ ø7 ñh ùa TàªLó R8ó ¹ ´ó ªh °A@ùñDùò £ø7h °@ùDùàª
ò à£ø7h ?@ù)Bùàªò $ø7h °¡@ùIEùàªüñ ¥ø7h °!@ùEùàªõñ ¦ø7h °¡@ùuDùàªîñ `§ø7h >@ù
Aùàªçñ @¨ø7h Á>@ùAùàªàñ ©ø7h °a@ùÅEùàªÙñ ¬ø7h °@ùmDùàªÒñ ¬ø7h °Á@ù}DùàªËñ ¬ø7h °á@ùDùàªÄñ ¬ø7h °á@ùYEùઽñ ¬ø7h °á @ùÕCùશñ ¬ø7h °Á@ùQEùયñ ¬ø7h A?@ùIBùનñ ¬ø7h !?@ù1Bùડñ «ø7h °Á @ùÍCùàªñ «ø7h ¡>@ù¥Aùàªñ ªø7h °¡ @ùÅCùàªñ ªø7h °@ùAEùàª
ñ ©ø7h °@ùaEùàª~ñ ©ø7h °@ùÕEùàªwñ ¨ø7h °@ùDùàªpñ ¨ø7h °Á@ùñEùàªiñ §ø7h °a@ù=Dùàªbñ §ø7h Á?@ùùBùàª[ñ ¦ø7h ?@ù}BùàªTñ ¦ø7h á?@ù5CùàªMñ ¥ø7h ° @ù=CùàªFñ ¥ø7h °!@ù±Dùàª?ñ ¤ø7h °¡@ùÝEùàª8ñ ¤ø7h °A@ù¥Eùàª1ñ £ø7h a>@ùmAùàª*ñ £ø7h ° @ù¥Cùàª#ñ ¢ø7h °A@ù-Dùઠñ ¢ø7h °á@ù
Fùàªñ ¡ø7h a?@ùYBùàªñ ¡ø7h ¡?@ùBùàªñ ø7h °! @ùECùઠñ ø7h °a @ù
Cùàªùð ø7h °A @ù}Cùàªòð ø7h á>@ùõAùàªëð ø7h °a@ùEùàªäð ø7h °!@ù!DùàªÝð ø7 @ù¡ÒFùâªØð @ø7h@ùÈø7 ñh ùa Tàªò 0 R1 R )ùö֎R Rh -ùR R6R5 RàGù ´'Gù ñèi R(*H 7 ° à ã °c áªâª
àGù ´ÿù @ùÈø7 ñ ùa TÛñ ¿ð à µH !@ù @ù! °!à ¾ð èGù ñàZ¨ZøI )y@ù)@ù?ëa$ Tý{W©ôOV©öWU©ø_T©úgS©üoR©ÿÀ_ÖR 5 RVݎR3 RÉÿÿ R؎RÆÿÿR R R R( ù5 RöގR3 R¹ÿÿ ÒÖáRu Rì ÒVãR Rè öގRõª®ÿÿÖåRµ Râ vçRõ Rç 5 RöގRóª¤ÿÿöéRuRØ RvRÿÿ R¶֎Rÿÿ ÒUR¶ìRÎ Ò5PR¶ïRÊ uPRñRÏ ҕPRvóRà RَRÿÿ R6َR
ÿÿ RVَRÿÿ RvRÿÿ5 RÖݎR3 R|ÿÿ' ´ ?ÖàBþµ¾ Oð t °=` ´ ùq (& ´ ?Ö@Cþµ´ Eð t °"=àþÿµH -@ù @ùó ù! °!X 2ð ù` h$ ´ ?ÖÀBþµ£ 4ð t °B=Àüÿµïÿÿ¨# ´ ?Ö@Cþµ +ð t °b= ûÿµæÿÿè" ´ ?ÖÀCþµ "ð t °=úÿµÝÿÿ(" ´ ?Ö@Dþµ ð t °¢=`ùÿµÔÿÿh! ´ ?ÖÀDþµ ð t °Â=@øÿµËÿÿµPRVõRp H ´ ?ÖàDþµs ð t °â=Àöÿµ¿ÿÿ ´ ?Ö`Eþµj ûï t °> õÿµ¶ÿÿÈ ´ ?Ö Fþµa òï µH -@ù @ùó ù! °!X áï Çù H ´ ?ÖÀEþµR ãï µH -@ù @ùó ù! °!X Òï ßÊù5 R¶ގR3 RþþÿöގRõªûþÿöގRõªóª÷þÿöގRõªóªóþÿ ÒÕPR6÷R& õPRùR+ 5 RގR3 Rèþÿ ÒQRöúR 5QRÖüR ÒUQR¶þR 5 RߎRóªÙþÿ5 R¶ߎRóªÕþÿ5 RÖߎRóªÑþÿ5 RöߎRóªÍþÿ3 RáRu RÉþÿuQR R 3 RãR RÂþÿ ҕQRvRõ äRµ R»þÿ6åRµ Rï åRµ Rô ©ð µQRVRð 3 R6çRõ Rþÿ ÒÕQR6Rà ¶èRuRóª¥þÿVéRuRá ¶éRuRÖ õQRRÛ 3 RVëR5
Rþÿ3 RURvìRþÿ ÒRRö RÇ 3 R5PRvïRþÿ5RRÖ RÈ 3 RuPRöðR
þÿàªëï ó ª@ þµuPR6ñRµ ÒURR¶
R± 3 RPRÖòRvþÿàªÜï ô ª`¢þµPRóR® uRRR« 3 RµPR¶ôRhþÿàªÎï ó ª ¤þµµPRöôR ҕRRvR 3 RÕPRöRYþÿિï ô ª&þµÕPRÖöR µRRVR 3 RõPRvøRKþÿ઱ï ó ª ©þµõPR¶øR{ «ï þµÉþÿ¨ï @ þµÐþÿ¥ï þµÞþÿ¢ï À þµäþÿï !þµêþÿï @"þµðþÿï #þµöþÿï À$þµÿþÿï &þµÿÿï `'þµ ÿÿï (þµÿÿ ÒÕRR6RV 3 RQRVúRþÿàªï ô ª §þµQRúRS õRRRP 3 R5QR6üR
þÿàªsï ó ª@©þµ5QRvüR= ÒSRöR9 3 RUQRþRþýÿàªdï ô ª`«þµUQRVþR6 5SRÖR3 3 RuQRöÿRðýÿàªVï ó ª þµuQR6 R ÒUSR¶ R 3 RQRÖRáýÿàªGï ô ª/þµQRR uSR R 3 RµQR¶RÓýÿàª9ï ó ª ²þµµQRöR ҕSRv Rÿ 3 RÕQRRÄýÿàª*ï ô ª ´þµÕQRÖRü µSRV"Rù 3 RõQRvR¶ýÿઠï ó ª`¶þµõQR¶Ræ ÒÕSR6$Râ 3 RRRV R§ýÿàª
ï ô ª¸þµRR Rß õSR&RÜ 3 R5RR6 Rýÿàªÿî ó ª:þµ5RRv RÉ ÒTRö'RÅ 3 RURR
Rýÿàªðî ô ªà¼þµURRV
R 5TRÖ)R¿ 3 RuRRöR|ýÿàªâî ó ª ¿þµuRR6R¬ ÒUTR¶+R¨ 3 RRRÖRmýÿàªÓî ô ª@ÁþµRRR¥ uTR-R¢ 3 RµRR¶R_ýÿàªÅî ó ªÃþµµRRöR ҕTRv/R 3 RÕRRRPýÿશî ô ª ÅþµÕRRÖR µTRV1R
3 RõRRvRBýÿનî ó ªàÇþµõRR¶Rr ÒÕTR63Rn 3 RSRVR3ýÿàªî ô ª ÊþµSRRk õTR5Rh 3 R5SR6R%ýÿàªî ó ª@Ìþµ5SRvRU ÒURö6RQ 3 RUSR Rýÿàª|î ô ª`ÎþµUSRV RN 5URÖ8RK 3 RuSRö Rýÿàªnî ó ª ÐþµuSR6 R8 ÒUUR¶:R4 3 RSRÖ Rùüÿàª_î ô ªÀÒþµSR R1 uUR<R. 3 RµSR¶!RëüÿàªQî ó ª ÕþµµSRö!R ҕURv>R 3 RÕSR#RÜüÿàªBî ô ª ×þµÕSRÖ#R µURV@R 3 RõSRv%RÎüÿàª4î ó ª`ÙþµõSR¶%Rþ ÒÕUR6BRú 3 RTRV'R¿üÿàª%î ô ªÛþµTR'R÷ õURDRô 3 R5TR6)R±üÿàªî ó ªÀÝþµ5TRv)Rá ÒVRöERÝ 3 RUTR+R¢üÿàªî ô ªàßþµUTRV+RÚ 5VRÖGR× 3 RuTRö,Rüÿàªúí ó ª âþµuTR6-RÄ uVRVIRÉ 3 RTRÖ.Rüÿàªìí ô ª`äþµTR/R¾ uYRÖJR» 3 RµTR¶0RxüÿàªÞí ó ª æþµµTRö0R¨ µ\RVLR 3 RÕTR2RjüÿàªÐí ô ªàèþµÕTRÖ2R¢ u`RÖMR 3 RõTRv4R\üÿàªÂí ó ª ëþµõTR¶4R UaRVOR 3 RURV6RNüÿ઴í ô ª`íþµUR6R 5bR¶dR 3 R5UR68R@üÿદí ó ª ïþµ5URv8Rp 5 RöeRu 3 RUUR:R2üÿàªí ô ªàñþµUURV:Rj 5 RfRg 3 RuURö;R$üÿàªí ó ª ôþµuUR6<RT 5 R6fRY 3 RURÖ=Rüÿàª|í ô ª`öþµUR>RN 5 RVfRK 3 RµUR¶?Rüÿàªní ó ª øþµµURö?R8 5 RvfR= 3 RÕURARúûÿàª`í ô ªàúþµÕURÖAR2 5 RfR/ 3 RõURvCRìûÿàªRí ó ª ýþµõUR¶CR 5 R¶fR! 3 RVRVERÞûÿàªDí ô ª`ÿþµVRER 5 RÖfR 3 R5VR6GRÐûÿàª6í ó ª ÿµ5VRvGR@ùÈ ø7 ñ ùa Tàªµí ´h@ùÈ ø7 ñh ùa Tàªí 3 R¹ûÿ5 RöfRõÿÿ3 RuVRIR²ûÿ5 RgRîÿÿ3 RuYRJR«ûÿ5 R6gRçÿÿ3 Rµ\RLR¤ûÿ5 RVgRàÿÿ3 Ru`RMRûÿ5 RvgRÙÿÿ3 RUaRORûÿ5 RgRÒÿÿ3 R5bRPRûÿ5 R¶gRËÿÿ3 R5 R¶eRûÿ5 RÖgRÄÿÿ5 RögRÁÿÿ5 RhR¾ÿÿ5 R6hR»ÿÿ5 RVhR¸ÿÿ5 RvhRµÿÿ5 RhR²ÿÿ5 R¶hR¯ÿÿ5 RÖhR¬ÿÿ5 RöhR©ÿÿ5 RiR¦ÿÿ5 R6iR£ÿÿ5 RViR ÿÿ5 RviRÿÿ5 RiRÿÿ5 R¶iRÿÿ5 RÖiRÿÿ5 RöiRÿÿ5 RjRÿÿ5 R6jRÿÿ5 RVjRÿÿ5 RvjR
ÿÿ5 RjRÿÿ5 R¶jRÿÿ5 RÖjR|ÿÿ5 RöjRyÿÿ5 RkRvÿÿ5 R6kRsÿÿ5 RVkRpÿÿ5 RvkRmÿÿ5 RkRjÿÿÀ ´ @ù ø7 ñ ù@ TÀ_Öí ÿÑüo©úg©ø_©öW©ôO©ý{©ýÃh a>) Ð);êªI ø
ù) ð)q* ðJ! ) ©S ðsBV ðӒùiª@ù ´* @ù_ ñ+ TH ðùBùH ´( I Ñ @ùj¥B96! ) ñaÿÿT
H ðuBù) J Ñ+@ùl¥B9,6l@ùÌ µ)! J ñ!ÿÿTéë õ ªhV@ùx²hV ùàªì ô ªhV@ùùvhV ùU 4àë ´ø7ԒGù@ù µJ@ù( ðY@ù?ëa TJ ùԒGù` ° @ Ò Ò|ë ´ó ª@ùx Dùâªë h@ùÀø7 ø7 ñh ù@ TԒGùª@ù@ù ´ Rµ @ùÈÿÿµ h
@ù) ð)A@ù @ùè ù! °!¤=¯ ણì ԒGùª@ù@ùÈýÿµ R¨ }}Âì ó ª ù( @ù ñk T¿ q T(c é#©´~}Ó< R }@( @ù ëÍ Tè@ùy|ø
@ùDùÿë Àþÿ´ö ª Ò2ë õ ª µbë à µ( ð5@ù @ù! Ð!Üaë È@ùÈ ø7 ñÈ ùa Tàªnì 5üÿ´ Òè @ù@ùvj{øß ± T@@ùDùàë ´÷ ª Òë ö ª` µCë ´è@ùø7 ñè ù¡ TàªUì Òh % ©ßë@øÿTö ´H{# ëáûÿT¼ÿÿ( ð5@ù @ù! Ð!Ü.ë è@ùèüÿ6íÿÿè'A©@ù
@ù)y|ø)
@ù* ðJA@ù@@ùè' ©! Ð!ð ë àªIì ; 6c 7 R: ðZ7@ù4 ДÞ è }@( @ù ëM TÈzwø
@ùDùë àþÿ´õ ª ÒÏê ` µ ë ´¨@ùèýÿ7 ñ¨ ùýÿTàªì éÿÿ@@ùáªúê ¨@ùüÿ7õÿÿáê ઠì h GùH ð<5@ù@ùë `ø7 R
i
@ù* ðJA@ù@@ùè' ©! °!@>Óê ý{G©ôOF©öWE©ø_D©úgC©üoB©ÿÀ_Öèþÿ7 ñh ùþÿTàªçë ñÿÿôO¾©ý{©ýC L ùê % ´ó ª! !L â ðBpsR$ RDÍ H ð =ù`" ´h@ùÈ ø7 ñh ùa TàªÍë L ãê @" ´ó ª! !L " ÐBxR$ R.Í H ð Aù ´h@ùÈ ø7 ñh ùa Tષë ð L Íê ´ó ª ð!L " °BR$ RÍ H Ð Eùà ´h@ùÈ ø7 ñh ùa Tડë à Ð ·ê À ´ó ªá Ð!â ÐB RD RÍ H Ð Iù ´á Ð!" °B¬àªIRD R÷Ì H Ð MùÀ ´á Ð!" °BÐàªFRD RìÌ H Ð Qù` ´á Ð!" °Bøàª
RD RáÌ H Ð Uù ´á Ð!" °BàªR$ RÖÌ H Ð Yù ´á Ð!" °B8àªR$ RËÌ H Ð ]ù@ ´á Ð!" °BTàªR$ RÀÌ H Ð aùà ´á Ð!" °BtàªR$ RµÌ H Ð eù ´á Ð!" °B¬àªR$ RªÌ H Ð iù ´á Ð!" °BìàªR$ RÌ H Ð mùÀ
´á Ð!" °B àªR$ RÌ H Ð qù` ´á Ð!" °B0àªR$ RÌ H Ð uù ´á Ð!" °BpàªR$ R~Ì H Ð yù ´á Ð!" °BàªR$ RsÌ H Ð }ù@ ´á Ð!" °B¼àªRD RhÌ H Ð ùà ´h@ùÈ ø7 ñh ùa Tàªñê ° Ôê À ´ó ª! °!Ô ðB¼ R$ RRÌ H Ð
ù ´! °!Ô" °B@àªR$ RGÌ H Ð ùÀ ´ @ùÌ H ð ù ´! °!Ô" °BtàªR$ R7Ì H Ð ùÀ ´h@ùø7 R R h@ù(ø7 ñh ù Tý{A©ôO¨À_Ö ý{A©ôO¨À_Öલê àªý{A©ôO¨À_Ö Rý{A©ôO¨À_ÖôO¾©ý{©ýC ° ¼ ½é ` ´ó ª! °!
B ðBà<ã Ðc´^Ì ø7! °!P
b Bà ã Ðc´àªUÌ àø7! °!¬
b B # °cÌ
àªLÌ Àø7h@ùHø7 R R ñh ùÁ Tàªê àªý{A©ôO¨À_Öh@ù(ø7 ñh ùþÿTý{A©ôO¨À_Ö ý{A©ôO¨À_Ö Rý{A©ôO¨À_ÖôO¾©ý{©ýC °
|é ´ó ª! °!
B ðB`?# °cÈ
{Ì @ø7! °! B ðB?# °cÈ
àªrÌ ø7! °!@B ðB ?# °cÈ
àªiÌ ø7! °!tB ðBÀ?# °cÈ
àª`Ì àø7! °!¤B ðBà?# °cÈ
àªWÌ Àø7! °!ÐB ðB ?# °cÈ
àªNÌ ø7! °! B ðBà># °cÈ
àªEÌ ø7! °!0B ðB ?# °cÈ
àª<Ì `
ø7! °!`B ðB@?# °cÈ
àª3Ì @ ø7h@ùÈ ø7 ñh ùa Tàª
ê ° ¼ é ´ó ª! °!b B # °cÐ Ì À ø7! °!øb B@ # °cTàªÌ ø7! °! b B # °cÈàª
Ì ø7! °!8B ðB># °chàªÌ `ø7! °!tb B` # °cÌàªûË @ø7! °!lB ðB ># °càªòË ø7! °!üb B # °càªéË ø7! °!p b B # °c´ àªàË àø7! °!($b BÀ # °c´ àª×Ë À ø7h@ùø7 R R h@ù(ø7 ñh ù Tý{A©ôO¨À_Ö ý{A©ôO¨À_Öઠé àªý{A©ôO¨À_Ö Rý{A©ôO¨À_Öø_¼©öW©ôO©ý{©ýà ô ª¤è à ´ó ªH ð}Eù@ùI@ù6 ÐÖZ@ù ëA T Ò# Rué õ ª@ ´H ðBù¨@ùI@ù ë¡ T7 RઠÒ# Rhé ö ª ´( Ðu@ùßë T) Ð)m@ùß ë T) Ð)q@ùß ë Tàªïè ßëà` 5 R¨@ùÈ ø7 ñ¨ ùa Tàª[é W 7 ÒÈ@ùÈ ø7 ñÈ ùa TàªRé µ'è àªý{C©ôOB©öWA©ø_ĨÀ_Ö/è ´ è ¨ ´ ?Öõ ª øÿµ ðÿÿàªH ´ ?Öö ªàøÿµ 7 R¨@ùûÿ6Üÿÿ¨@ùÈ ø7 ñ¨ ùa Tàª/é h@ùÈ ø7 ñh ùa Tàª(é ïç à ´õ ªH Ð%Gùàªâª Ò R:è ó ª¨@ùùÿ7 ñ¨ ù!ùÿTàªé àªý{C©ôOB©öWA©ø_ĨÀ_Ö Òàªý{C©ôOB©öWA©ø_ĨÀ_Ö~è õ ª ðÿµÄÿÿzè ö ªÀñÿµÇÿÿöW½©ôO©ý{©ý ôªõªö ªÁç ` ´ó ªH Ð%Gùàªâªãªäª è ô ªh@ù ø7 ñh ùÀ Tàªý{B©ôOA©öWèÀ_Öàªãè àªý{B©ôOA©öWèÀ_Ö Òàªý{B©ôOA©öWèÀ_ÖÿCÑø_©öW©ôO©ý{©ýóªô ª@ùI@ù¨ ´àªáª ?Öõ ª ´àªý{D©ôOC©öWB©ø_A©ÿCÀ_Öàªáª4è õ ª þÿµ( Ð@ù @ùç 4ç àªúç @ ´
è ô ª@ ´H ð½@ùàªsè ö ª ´àªáªnè ÷ ªÀ ´àª¶ç õ ªàªûÿàªûÿàªûÿúÿµ( Ð!@ù @ùó ù! °!x&qç ÒËÿÿ Ò Ò Ò Ò Òêÿÿ Ò Òçÿÿ ÒåÿÿÿÑúg©ø_©öW©ôO©ý{©ýÃÿ©ÿ ùsè õ ª4@ù) Ð)q@ù@ù ñdIúa T@ùhÿÿµ Ò Ò Ò ° '
ç @ µ\ h@¹ 1B Th ¹v@ùÈ@¹ 1B TÈ ¹àªZç ô ª ° 'tç ´ø ª! °!'Ïç ÷ ª@ù ø7 ñ ùà T7 ´è@ù) Ð)
@ù ë T( Ð5@ù @ù! °!¼'0ç è@ùø7 ñè ù! Tàª=è ( Ð @ù@ù 2@ùÒ à 5] ઠÒææ X ð Ûùè@ùè ø7 ñè ù Tàª*è ÛGù` ´9R r @ù ?Ö ká TÛGùMCù ?Ö 0 q T( Ð5@ù@ùÛGùMCù ?֨Rè ©! °!à)p àªè 7øÿµ( Ð @ù@ù 2@ù¤ 4 ° Ð& ðcD mRÂzR² ᣠâ ãc àª9 ø7H ð ÉGùH ð±Fù ÒÏ ´÷ ª è@ùÈ ø7 ñè ùa Tàªìç WrR{R WpRøzR ( Ð5@ù @ù! °!H(Ìæ ( Ð @ù@ù 2@ùu @úÿ5mRØzR 6@ùáªâªãª à@ùà ´ @ù¨ ø7 ñ ùA TËç à@ùà ´ @ù¨ ø7 ñ ùA TÃç à@ùà ´ @ù¨ ø7 ñ ùA T»ç Ð& ÐcD áªâªd ý{G©ôOF©öWE©ø_D©úgC©ÿÀ_Ö( °5@ù@ùÛGù@ù ?Öù ©! !´(àª~æ ( ° @ù@ù 2@ù6 `òÿ5ÁÿÿÛGùICù ?Ö q T( °5@ù 5 @ù! !.®ÿÿ ´È@ùÈ ø7 ñÈ ùa Tàªç ´h@ùÈ ø7 ñh ùa Tàª~ç Ô ´@ù ø7 ñ ùà T RÄÿÿ @ù! !$/ÿÿàªpç R¼ÿÿ×qRÿÿôO¾©ý{©ýC ó ªH ° %Gùb@ùáªNç ´ @¹ 1B T ¹ý{A©ôO¨À_Ö@æ µàªý{A©ôO¨g Òý{A©ôO¨À_ÖÿÑüo©úg©ø_©öW©ôO©ý{©ýÃõªóª÷ªö ª;ç ô ªw 4[ °h/Gù ´2@ù2 ùº ´Y@ù(@¹ 1B T( ¹X@ù ´@¹ 1¢ T ¹ Ò Ò\ °c9@ù ç gBù ´ @ù" @ùç ´( °m@ù ë` T( °u@ù ë T¦æ 5 `/GùT ` ´û ªæ ( °m@ù) °)u@ù q h@ù(ýÿ7ü ª ñh ùa Tàªç à ªáÿÿÚå @ùgBù" °Bl@ùæ R ´H@ù ëÁ$ T2@ù2 ùà ´ @ù¨ ø7 ñ ùA Tðæ ´(@ùÈ ø7 ñ( ùa Tàªèæ ´@ùÈ ø7 ñ ùa Tàªàæ ÿ q{Z\ ðI Ð[ 4'@ù ´)!O¹+ q T
Q+J @¹_k
T2@ù2 ùº
´Y@ù(@¹ 1B T( ¹X@ù¸ ´@¹ 1B T ¹ 4(
3èß ©ö ù à2æ à ´ö ªzæ ´á ªàªâªpå õ ªÈ@ùè
ø7 ñÈ ù
Tબæ Q 4
R ! M ï ªëªÿ
kÍ Tj
K_ qJ¥ª N}|in¸ï
ªßk¬þÿTKþÿT
R @¹ßkJ¥_ k
øÿT Ñ*) @¹?k÷ÿTI}@)í|Óiiø¨@¹ 1B T¨ ¹H °%Gùàªáª ҇å ø ª ´+ ¹àª*æ ¨@ù ø7 ñ¨ ù TX ´@ùø7 ñ ù¡ Tàªý{G©ôOF©öWE©ø_D©úgC©üoB©ÿgæ àªeæ þÿµ Ò Ò×óÿ5àªáªâªå õ ªÕ
´ ´H@ù ëá T2@ù2 ùà ´ @ù¨ ø7 ñ ùA TMæ ´(@ùÈ ø7 ñ( ùa TàªEæ ´@ùÈ ø7 ñ ùa Tàª=æ ûöÿ4'@ùX Р
´#O¹ qD T
P)J @¹öª_kë T 4 R
é
ª¿ k
T, K q¥v Ì~|Lil¸íªk¬þÿT
TË í ªñÿÿ R @¹k֦ßkª T Ð6) @¹?k` TI Ð))O¹ kA Tá~|Iå Àðÿ´H Ð< ù ¹@¹ kM T
}@É~@ Ð(J Ñ`ß<`<_ ëÿÿT É~@ ; ¹5 ù #¹kÿÿÈ@ùÈ ø7 ñÈ ùa Tàªíå ´(@ùÈ ø7 ñ( ùa Tàªåå ´H@ùÈ ø7 ñH ùa TàªÝå íÿµý{G©ôOF©öWE©ø_D©úgC©üoB©ÿÀ_ÖàªáªÏä 2@ù2 ù ÛÿµÞþÿ Rå èÿ´H Ð< ù R ¹) R ¹ ¹ ù7ÿÿàªáª»ä 2@ù2 ù íÿµmÿÿÈ~@ í|Óhiøh)ø @ùÉåÿ7) ñ ùaåÿTમå (ÿÿüoº©úg©ø_©öW©ôO©ý{©ýCÿ@ÑÿÃÑ( °y@ù@ù¨øJ °J¡<È Ðaê£ ©ô# R(Rèÿ©) RéS yÿ« 9È Ðe K! ë#©hRè© Rë£ yéK9HA Ì Ќ± 賩ÜRüÿ©éó yÿë9Ha Ì ЌI è3©Rö ©ëCyé9H Ì Ќy è³
©nRîÿ ©ëyé+9H¡ Ì Ќ¥ è3
©ÈRè©éãyÿË9HÁ Ì Ќ 賩-Ríÿ©ë3yék9Há Ï ÐïÁ è?© Rì©ëyé 9Hè¿©ìÿ©éÓyé«9È Ðá O!ï#©Rð©é#yÿK9HAÏ Ðïq è¿©ÆRæÿ©ësyéë9HaÏ Ðï© è? ©hRè ©éÃyÿ9È ÐÕ"Oï£ ©öÿ ©ëyé+9O¡ï ùèùöùÿùécyéË9HÁè ùÈ Ð#è#ù(Rè'ù!Rÿ+ùé³yÿk 9Háè3ùÈ Ð#è7ù§Rç;ùÿ?ùéyÿ
9HèGùÈ Ðý#èKùWR÷OùÿSùéSyÿ«
9H!è[ùÈ Ð
$è_ùÓRócùÿgùé£yÿK 9HAèoùÈ Ðý$èsù÷wùÿ{ùéóyÿë 9HaÑ Ð1%èùñùoRïùÿùéCyÿ 9HèùÈ Ð&èùHRèùÿ£ùéyÿ+
9H¡è«ùÈ Ðy&è¯ùó³ùÿ·ùéãyÿË
9HÁè¿ùÈ Ðñ&èÃù÷ÇùÿËùé3yÿk9HáèÓùÈ Ðy'è×ùñRñÛùÿßùéyÿ 9HÀ Ð ô'èçùàëùèRèïùãRÿóùéÓyÿ«9H!èûùÈ Ð(èÿùRèùÿùé#yÿK9@AàùÀ Ð )àùáùÿùésyÿë9@aà#ùÀ Ð )à'ù÷+ùÿ/ùéÃyÿ9@à7ùÀ Ð *à;ù÷?ùÿCùé yÿ+9@¡àKùÀ Ð ¤*àOùðSùÿWùéc yÿË9@Áà_ùÀ Ð 4+àcùRàgùÿkùé³ yÿk9Aá ÐBä+ásùâwùARá{ùÿùé
yÿ 9AáùÁ Ð!,áù¡RáùÿùéS
yÿ«9A!áùÁ Ð!@-áù¾Rþ£ùÿ§ùé£
yÿK9AA ÐBÔ-á¯ùâ³ùñ·ùÿ»ùéó
yÿë9AaáÃùÁ Ð!P.áÇùñËùÿÏùéC yÿ9A ÐBÌ.á×ùâÛùðßùÿãùé yÿ+9P¡ðëùÐ Ð^/ðïùèóùÿ÷ùéã yÿË9PÁÁ Ð!Ü/ðÿùáùóùÿ ùé3 yÿk9PáðùÐ ÐV0ðùçùÿ ùé yÿ 9PÁ Ð!È0ð'ùá+ùñ/ùÿ3ùéÓ yÿ«9P!ð;ùÐ ÐF1ð?ùóCùÿGùé#
yÿK9PAÁ Ð!¼1ðOùáSùRõWùÿ[ùés
yÿë9PaðcùÐ Ð^2ðgùþkùÿoùéÃ
yÿ9PðwùÐ Ðò2ð{ù!Ráùÿùéyÿ+ 9P¡ðùÐ Ðv3ðùRðùÿùécyÿË 9PÁðùÐ Ðæ3ð£ùè§ùÿ«ùé³yÿk 9Páð³ùÐ Ðf4ð·ùõ»ùÿ¿ùéyÿ 9PðÇùÐ Ð5ðËùàÏùÿÓùéSyÿ« 9P!ðÛùРж5ðßùããùÿçùé£yÿK 9PAðïùÐ ÐR6ðóùõ÷ùÿûùéóyÿë 9PaðùÐ Ðò6ðùï ùÿùéCyÿ 9PðùÐ Ð~7ðùè ùÿ#ùéyÿ+!9P¡ð+ùÐ °þ7ð/ùï3ùÿ7ùéãyÿË!9PÁð?ùÐ °8ðCùèGùÿKùé3yÿk"9PáðSùÐ °
9ðWùá[ùÿ_ùéyÿ #9PðgùÐ °9ðkùçoùÿsùéÓyÿ«#9P!ð{ùÐ °:ðùèùÿùé#yÿK$9PAðùÐ °:ðùçùÿùésyÿë$9Pað£ùÐ °ö:ð§ùPð·ùÐ °b;ð»ùåRP¡ðËùÐ °;ðÏùPÁðßùÐ °Â;ðãùÐ'RðçùPáðóùРк ð÷ùPðùРРð ùðRðùP!ðùÐ ÐÞð ù Rð#ùPAð/ùÐ Ðð3ùPR@aàCùÀ Ð 4àGù@àWùÀ Ð ¸à[ù@¡àkùÀ Ð èàoù@ÁàùÀ ° ¬àù@áàùÀ Ð àù@! à»ù@A àÏù@a àãù@¡ à ù@Á à ùÀ Ð Dà#ù@á à3ùÀ Ð Äà7ù Rà;ù@!
à[ùÀ Ð äà_ù@A
àoùÀ Ð |àsù Ràwù@a
àùÀ Ð Pàù R@
àùÀ Ð `àù@¡
à«ùÀ Ð pà¯ù@Á
Á Ð!à¿ùáÃù@á
àÓùÀ Ð ´à×ùÀ RA áçùÁ Ð!ÌáëùA! áûùÁ Ð!øáÿùAA áùÁ Ð!áùã RAa á#ùÁ Ð!$á'ù¡ RD ä7ùÄ Є8ä;ùD¡ äKùÄ ЄPäOùDÁ ä_ùÄ ЄäcùDá Ù Ð9¿äsùùwùD äùÄ ЄØäùY! õãù¤ ð0és:yùùUAõùäùåùÿùÕ е åùÿùë#:yIë39õùUA IK39Y!ù{ùäùõ¯ùÄ ðØáoùÿsùëÓ9yI«29U °9ë#õgùùkù °µÂ#õWùð[ùÿ_ùé9yUÁõ?ùé39y_ 29UáõSù5dR 9?ùCùõGùÿKùu е®ã3ùÿ7ùéã8yIk19ÿ#ùë8yY¡IË09ù+ùõ/ùYùùY!I+09õùã ù µ õùì ùÿùëC8yUAõï
ùéó7y_/9Uaõù µJõó
ùµRõ÷
ùÿû
ùùÛ
ùäß
ùðã
ùÿç
ùé£7yIë.9Ua YáðÏ
ùÿÓ
ùëS7yIK.9ù³
ùYùÇ
ù[RI«-9äË
ùä | ä·
ùû»
ùÿ¿
ùé7yõÃùU û§
ùÿ«
ùë³6yI -9õ×ùUÁõ
ùUIk,9ä£
ù 8ä
ùâ
ùÿ
ùëc6yI++9õw
ùé6y_Ë+9D¡ä
ùdïRõ ðµN7õ{
ùä
ùÿ
ùÄ ð¸_K9ðk
ùÿo
ùéÃ5yUÁ
äËùÄSRäÏùÿÓùéS#yDá
ä³ùé#yI«9DäÇùä Єø)I 9ä·ùà»ùÿ¿ùõùUÁ ä£ùà§ùÿ«ùë³"yD
äwùIË9ÿùëc"yIk9D¡
äùÄ ð äùàùÄ ðä{ùãùÿùë"yD!
ä;ùI9ÿoùëÃ!yI+9Da
äcùä 4ägùåkùÄ ðLäSùæWùÿ[ùés!yDA
äOùÄ Є@ é#!y_ë9ä?ùdàRäCù ð9SÿGùõÿùù+ùí/ùÿ3ùéÓ yIK9D
ä'ùDá ÿ ùë yI« 9äùdRä«ùI 9ùùíùÕ е" õùìùÿ ùë3 yU¡ õëùáóùÿ÷ùéã yª?9õ µ õÛùë y
?9õïùÕ е õ³ùj>9áßùÿãùõÇùY Réë=9ùËùÿÏùéC yÿ¯ùéÃyéK=9ù·ùÿ»ùëó yÿ%9å¿ùÿ«<9á£ùÿ§ùë£ yÿÃùëyé <9îùÿùéS yé+&9íÓùék;9ã{ùÿùë yÿ×ùëcyÿË:9ìgùÿkùë³ yéË&9ÿëùé+:9xRøSùÿWùéc yé³yÿk'9é99à?ùÿCùë yùûùÿÿùéë89á+ùÿ/ùëà yëyé (9éK89ãùÿùës yÿùéSyÿ«79âùÿùë# yÿ«(9ÿ'ùé 79îïùÿóùéÓyé£yÿK)9ék69àÛùÿßùëyð7ùÿ;ùéË59íÇùÿËùë3yëóyéë)9é+59ì³ùÿ·ùëãy5RõKùÿOùé49âùÿ£ùëyéCyÿ*9ÿë39âùÿùëCyö_ùÿcùëyÿK39ÿ{ùéóyé++9îsùÿ«29ücùÿgùé£yÿ?ùéyÿ 29U
ÿSùéSyõGùÕ еõKù RüOùÿwùëãyéË+9éùé³yÿk19ÿùè'ùÈ Ð=éË09ÿ+ùé3yé+09èùùùÿùécyÿk,9èûùH ùÿùÿùëyè÷ùÈ Ð5ÿïùëÃyé/9ùùèçùÈ Ð-ÿë.9ùëùèÓùÈ Ð%ù×ùÿÛùésyÿùè¿ùùÃùÿÇùë#yéK.9éyÿ -9H ÿ³ùéÓyÿ«-9è§ùÈ Ð è«ùù¯ùH!èÛùÈ ð1èßù_ë9HAèïùHaè ùÈ ðÑèóùI9è ùHè ùÈ ðñI+9è ùH¡è+ ùÈ ðIË9è/ ùHÁè? ùÈ ðAIk 9èC ùRèG ù_
9HáèS ùHèg ù( Ð4èW ùI«
9èk ùH!è{ ùÈ ðIK 9è ùÈ&Rè ùé#&y_ë 9HAè ùHaè£ ùè Ð4è ùã ùÿ ùës&yI 9è§ ùã« ùÿ¯ ùéÃ&yI+
9Hè· ùÈ ðé6è» ù蹁Rè¿ ùÿÃ ùé'y_Ë
9H¡èË ùè %.èÏ ùðÓ ùÿ× ùëc'yIk9HÁèß ùè M.èã ùûç ùÿë ùë³'yI 9Háèó ùè .è÷ ùøû ùxRÿÿ ùë(yI«9Hè
ùè á.è
ùIK9H!è
ùè !/è
ùIë9HAè/
ùè 5/è3
ùI9HaèC
ùè m/èG
ùI+9HèW
ùè }/è[
ùþ_
ù_Ë9H¡èk
ùè 0èo
ùhRès
ù_k9HÁè
ùè Ý0è
ùI 9Háè
ùè ù0è
ùUõ§
ùu RI«9è«
ùH!è»
ùHAèÏ
ùè 1IK9è¿
ùIë9èÓ
ùI9Haèã
ùHè÷
ùè 1èç
ùI+9èû
ùIË9H¡è ùHÁè ùÈ Ð¹>è ùIk9è# ùð' ùÿ+ ùé³,yI 9Háè3 ùè 51è7 ù(Rè; ùÿ? ùé-y_«9HèG ùè °¹"èK ùìO ùÿS ùéS-y_K9H!è[ ùè °Ù"è_ ùâc ùÿg ùë£-yIë9HAèo ùè µès ùãw ùÿ{ ùëó-yI9Haè ùè è ùà ùÿ ùëC.yI+ 9Hè ùè °é"è ùà ùÿ£ ùë.yIË 9H¡è« ùè °#è¯ ùî³ ùÿ· ùëã.yIk 9HÁè¿ ùè °-#èà ùãÇ ùÿË ùé3/y_ 9HáèÓ ùè °I#è× ùðÛ ùÿß ùI« 9Hèç ùè °q#èë ùâï ùëÓ/yH!èû ùè °#IK 9èÿ ùà ùÿ ùë#0yIë 9HAè ùè °#è ùí ùÿ ùës0yI 9Haè# ùHè7 ùè +è' ùö+ ùÿ/ ùëÃ0yI+!9è; ùö? ùH¡èK ùè °½#èO ù¨RRèS ùHÁè_ ùHáès ù( °1èc ùèw ùHè ùè Ðè ùÁRè ùH!è ùè Ðè ùHAè¯ ùè Ðè³ ùHaèà ùè бèÇ ùHè× ùè ÐÑèÛ ùH¡èë ùHáè
ùè Ðíè
ù聁Rè
ùHè'
ùè Ð)7è+
ùH!è;
ùè ÐA7è?
ùHAèO
ùHaèc
ù¨ ° %èS
ùèg
ùHaè£ù ý#è§ùÈ
Rè«ùHè·ù °µ%ÿ
ùè»ùH¡èËù °Á%é4yèÏùHÁèßù °Ý%à/
ùèãùHáèóù ° &éÓ4yè÷ùHèù °!&õC
ùè ùH!èù °Y&é#5yè ùHAè/ù °q&ðW
ùè3ùHaèCù °&ës5yèGùHèWù °¡&I*9è[ùH¡èkù °µ&èoùásùHÁèù °É&ÿ[
ùèùHáèù °ñ&_ë)9èùHè§ù °'ÿG
ùè«ùH!è»ù °-'IK)9è¿ùHAèÏù °Q'ÿ3
ùèÓùHaèãù °u'_«(9èçùHè÷ù °¡'ÿC ùèûù ðÞßé34yI (9IË!9þï ùàó ùÿ÷ ùëã3yIk'9ÿW ùéc1yãß ùÿã ùë3yIË&9_k"9ùg ùìË ùÿÏ ùëC3yI+&9ÿk ùë³1yà· ùÿ» ùëó2yI%9I #9ù{ ù࣠ùÿ§ ùë£2yIë$9ÿ ùé2yI«#9ÿ ùéS2y_K$9I49_+59IË59Ik69I 79I«79IK89Ië89I99I+:9IË:9Ik;9_ <9I«<9IK=9Ië=9I>9I+?9Kã yIË?9H¡è ù °µ'é1yèùHÁèÿ ùHÁè ùHáè3ù °Ù'è#ùè7ùHèGù °ñ'èKùH!è[ù °(è_ùHAèoù ° (èsùHaèùHèù °%(èùèùH¡è«ùHÁè¿ùh E è¯ùèÃùHáèÓù °5(è×ùHºRèÛùHèçù Ð} ÿó ùèëùH!èûù Ð ë/yèÿùHAèù ÐÁ èùHaè#ù Ðù è'ùHè7ù Ð è;ù
Rè?ùH¡èKù Ðe!èOùHÁè_ù Ð¥!ècùHáèsù ÐÁ!èwùH èù ÐÕ!èùH! èùHA è¯ù Ð"èùè³ùHa èÃù Ð"èÇùH è×ù Ð%"èÛùH¡ èëùHÁ èÿùh ÐM!èïùèùHá èù ÐQ"èùRèùH è'ùH! è;ùh ð1è+ùè?ùHA èOù ðèSùÈ9RèWùHa ècùH èwù¨ ð%ègùè{ùH¡ èù( IèùÈ~RèùHÁ èù( °! è£ùHá è³ù( °1 è·ùH èÇù( °U èËùH! èÛùHA èïù( ° èßùèóùHa èù( ° èùH èù( °9 èùRÿ ùëc,yè
ùÿ
ùëS(yÿ ùé,yð ùá#
ùÿ'
ùë£(yÿï
ùëÃ+yàÿ
ùæ7
ùÿ;
ùëó(yÿÛ
ùés+yàë
ùâK
ùÿO
ùëC)yÿÇ
ùë#+yà×
ùÿc
ùé)yÿw
ùÿ³
ùéÓ*yàÃ
ùéã)yã
ùÿ
ùõ
ùÿ
ùõ¯
ùë*yä ùD¡ ä+ù$ °¤ ë3*yä/ùDÁ ä?ù$ °¸ äCùDá äSù$ °ì äWùD ägùD! ä{ù$ °
äkùäùDA äùDa ä£ùÄ °D
äùä§ùD ä·ù$ °
ä»ù$Rä¿ùD¡ äËùDÁ äßù¤ ð$5äÏùäãùDá äóù$ °`>ä÷ù¾RäûùD äùD! äù$ ð0ä ùä ùDA ä/ù$ ð8ä3ùDa äCùD äWù$ ð\äGùä[ùD¡ äkù$ ðpäoùDÁ äùDá äù ðäùäùD!ä§ù$ ðä«ù°Rä¯ùD!!ä»ùD ä¿ùDA!äÏùDa!äãùD ¸ äÓùäçùD!ä÷ùD Ð äûùäRäÿùD¡!ä ùDÁ!ä ùD ,
äùä#ùDá!ä3ùD"äGù$ Єä7ùäKùD!"ä[ùD @
ä_ù$RäcùDA"äoùDa"äù$c
Rj$x$ ¨>äsùäùD"äùD D=äù®RäùD¡"ä«ùDÁ"ä¿ù$r
Rj$x °À)ä¯ùäÃùDá"äÓùD °3ä×ùDúRäÛùD#äçùD ЄL2äëùÿçùé£#yì÷ùéÓ%yÿ ùÿûùëó#yì ùë%yðo ùÿs ùÿ ùéC$yì ùé3%yð[ ùÿ_ ùÿ# ùë$yö3 ùÿ7 ùëã$yÿK ùÿ¯ùéÃ:yõ¿ùÿÃùë;yãÓùÿ×ùéc;yîçùÿëùë³;yàûùÿÿùë<yæùÿùëS<yà#ùÿ'ùë£<yà7ùÿ;ùëó<yàKùÿOùëC=yá_ùÿcùë=yõoùõùõïùÿóùD!#äûùDA#äùD ЄX2äÿùäùDa#ä#ùÄ ðä'ùD#ä7ùD Єx2ä;ùäRä?ùD¡#äKùD Є3äOù÷SùD Є3UÁ#õ_ùäcùDá#Õ µ²äsùõwùRäÓùäçùä{ùD$äùÄ äùRüùU!$õùU еÒ3õùUA$õ¯ùU еò3õ³ùURõ·ùUa$õÃùU еú6 yõÇùU$õ×ùU¡$õëùU е 7õÛùõïùUÁ$õÿùU е&7õùUá$õùU%õ'ùU °µ-õùõ+ùU!%õ;ùU е7õ?ùõþRõCùUA%õOùUa%õcùÕ ðµFöùõSùõgù·Röùö«ù(+9÷ùÿùÀ+9ÿ£ù0yh,9ã³ùÿ·ùy-9ãÇùöWùökù5ۅRj5xU%õwùU ðµj7õ{ùRõùU¡%õùu µ* õùUÁ%õùUá%õ³ùµ µÊ
õ£ùõ·ùU&õÇùu µJ õËùõ?RõÏùU!&õÛùu µF3 9õßù5R÷wùÿ{ùyõÏùè)9ÿgù@y*9õãùUA&õïùu µ3õóùUa&õù¶RH)9öOùÿSùðyP y¨ 9¨(9ö;ùÿ?ù y yH9(9á'ùÿ+ùPyð yè9h'9áùÿù y@y9yÈ&9ÿù°y(9ày(&9àëùÿïù`yÈ90y%9à×ùÿÛùyh9yè$9÷ÃùÿÇùÀy9Ðy¨9H$9ÿ³ùpy yH9¨#9ûùÿù ypyè9#9ûùÿùÐyÀy9h"9ásùÿwùyy(9È!9á_ùÿcù0y`yÈ9(!9áKùÿOùày°yh 9 9í7ùÿ;ùy y
9è 9ù#ùÿ'ù@yPy¨
9H 9ùùÿùðy yH 9ðy¨ 9ÿÿù yè 9@y 9 9ÿëùPyy(
9àyh 9ÿ×ù yÈ
9îßùÿãùÈ 9ÿÃù°y0yh9íóù( 9ÿ¯ù`yÿ÷ùy99ÿùyíùÿ ùÐyè9ÿùÀ
y¨9ÿ ù yH9ÿsùp
yH9ð/ù¨9í[ùÿ_ù
yÿ3ùpy9÷GùÿKùÐ yè9ðCùh9á3ùÿ7ù yÿGùÀy9È9ÿ#ù0 yÿ[ù y(9ï ùÿùà y(9ðkù9á÷ùÿûù yÿoù` yè9áãùÿçù@ yÈ9ðùÿùH9ÿÓùð
y° yh9¨9í»ùÿ¿ù
yÿù
y9â§ùÿ«ùP
y -9 yH.9pyè.9Ày/9y(09`yÈ09°yh19 y29Py¨29 yH39ðyè39@y49y(59àyÈ590yh69y79Ðy¨79 yH89p yè89À y99 y(:9À:9° yh;9 y<9P y¨<9 yH=9ð yè=9@ y>9 y(?9à yÈ?9D&äùD Єl%äùäùáËùÿÏùþ
ùD¡&ä+ùD ð3ä/ù¾Rä3ùDÁ&ä?ùd X+äCùâ·ùÿ»ùïGùDá&äSùd ä+äWùÿùâ£ùÿ§ùORïùï[ùD'ägùd L,äkùãgùÿkùá{ùÿùîùóoùD!'ä{ùd Ä,äùDA'äùDa'ä£ùd Ø,äùä§ùD'ä·ùd ð,ä»ùÿ£ùì³ùÿ·ùèSùÿWùìÇùÿËùÿßùáïùÿóùÿCùÿùæùÿùã+ùÿ/ùç¿ùD¡'äËùd d-äÏùDÁ'äßùd -äãùDá'äóùD(äùä Є|$ä÷ùä ùD!(äùd ¸-ä ùDA(ä/ùd Ð-ä3ù$Rä7ùDa(äCùD(äWùÄ ð <äGùä[ùD¡(äkùd ?äoùÄnRäsùDÁ(äùDá(äùä ЄT6äùäùD)ä§ùd °l-ä«ù%Rä¯ùD!)ä»ùDA)äÏùÄ Є ä¿ùäÓùDa)äãùD)ä÷ùä ð äçùäûùD¡)ä ùd Є äùdbRäùDÁ)ä ùDá)ä3ùÄ °3ä#ùä7ùRÿwùÿùâùëã=yðùÿùé3>yÿ{ùâùíùÿùë>yà¯ùÿgùùwùÿ³ùëÓ>yíÃùÿÇùÿSùãcù?yí×ùÿÛùb?yÿ?ùâOùîëùÿïù²?yáÿùÿ+ùà;ùÿùíùÿùà'ùÿËùæ'ùæ;ùD*äGùd ЄX>äKùրRäOùD!*ä[ùd ð(ÿßùä_ùøcùDA*Æ ÐÆ<7äoùæsùDa*äùæùD*f ðÆtäùæùd ðF¡*æ«ùä¯ùDÁ*f ðƐä¿ùæÃùDá*äÓùæ×ùD+äçùDRf ðƤæëùäïùD!+Æ Ƽ8äûùæÿùDA+ Æ$äùæù @Fa+æ#ùä'ùD+ Æ`ä7ùæ;ùD¡+ ƀäKùæOùDÁ+ ƴä_ùæcùDá+ ÆØäsùæwùD,äùæùD!, ÆðäùæùDA,Æ Ðƀ5ä¯ùæ³ùDa,äÃùæÇùD, Æä×ùæÛùD¡,äëùæïùDÁ, Æ äÿùæ ùÄ è8Fá,æ ùä ùF-æ' ùä+ ùD!-ä; ù Pä? ùé0yD¡/äË ùD0ä ùDA0ä/ ù °è
ä3 ùDa0äC ùDa2 ðƨ1ä ùÿ ùë° yéh;9D!2æ ù ðƄ1éÈ:9â ùæs ù ðÆd1íw ùÿ{ ùë` yä[ ùÿg ùë yé(:9DA2äo ùDá1æ_ ù ðÆD1é99ìc ùä3 ùæK ùD2ìO ùÿS ùëÀ yäG ù ðÀ0ÿ? ùép yÿè89ä7 ùDÁ1/Rï; ù ðïE0ÿH89ä ùï# ùO1ñ' ùÿ+ ùé yQ¡1ñ ùà ùÿ ùéÐyé¨79 ð1.0ÿ ùëyé79ñ ùï÷ ùO1ñû ùQA1ÿh69àÿ ùñÏ ùéàyQ0Rñë ùÿï ùé0yQa1éÈ59ñã ù Ð1&*ñç ù1 Ð1:3é(59ñÓ ùî× ùÿÛ ùï§ ùO¡0ñ¿ ùîà ùÿÇ ùëyQ!1ñ» ù Ð1>é@yÿ49ñ« ùQRñ¯ ù 1ÿ³ ùïk ùñ ùè ùÿ ùéðyéè39Oá0ï ùOÁ0ÿ ùë yéH39ï ùñ ù °ïÁÿ¨29è ùåÓùïo ùïcRïs ùÿw ùéPyO0ïW ùå_ ùÿc ùé yé29 °ï%)ÿO ùë°yéh19ï[ ùèëùïG ùÏ °ïe0ÿÈ09åK ùцRñ7 ùÑ ð1ÿ; ùé`yèÿùñ ùö# ùÿ' ùéyé(09ñ ùÿ ùëÀyQ!0é/9ñ ù 12!ö ù ä!ÿè.9ä÷ ù$HRäû ùDÁ/ÿÿ ùépyäß ùÿë ùé yDá/éH.9äó ù$ Єô ëÐyé¨-9äã ùèç ùäÏ ù ¤!é-9èÓ ùÿ× ùHa/è£ ùë0yî¿ ùÿà ùëyéh,9H/è· ù ¹!è» ùèNRä§ ù !á« ùÿ¯ ùèC ùä ùí ùÿ ùëàyéÈ+9é*9HA/è ùH!/ëyé(+9è{ ù m!è ùá ùÿ ùHá.èS ùëðyáo ùÿs ùë@yéè)9H/èg ù Y!èk ùHA-ñW ù 1!ð[ ùÿ_ ùèO ùñC ùàG ùÿK ùé yéH)9HÁ.è? ùH¡.ÿ7 ùëPyé¨(9è+ ù !é(9ñ/ ùà3 ùQ.ñ ùè ùá ùÿ# ùë yHa. 1Fÿ ùé°yÿh'9è ùñ ùRè ùHA.éÈ&9é(&9èï ùïó ùì÷ ùÿû ùé`yHá-ïß ùO.ìã ùÿç ùëyïÇ ùÿÓ ùéÀyé%9O!.ïÛ ù ï-ëpyéè$9ïË ùàÏ ùè³ ùHa-ÿH$9ï· ùà» ùÿ¿ ùO¡-ï ùOÁ-é¨#9ÿ« ùé yï ù ï-
ï£ ùRï§ ùÏ °ïÁï ùð ùÿ ùéÐyèc ùï{ ùð ùÿ ùëyé#9ûW ùûk ùÿo ùéh"9H-èw ùÈ Ð]*ÿ[ ùëàyéÈ!9èg ùèS ù÷gù÷SùÿG ùéyÿ(!9ãËùÿÏùá/ ùÿ3 ùé@yé 9àßùÿãùá ùÿ ùëðyéè 9àóùÿ÷ùéPyé¨ 9ë yéH 9÷ ùÿ ùH2è ù ð¹1è ùH¡2è« ù ð2è¯ ùRè³ ùHÁ2è¿ ù ðq5é 9èà ùHá2èÓ ù ð5ë yè× ùH3èç ù ð5éh 9èë ùH!3èû ù ð¹5é°yèÿ ùHA3è ù ðÙ5è ùé yã·ùÿ»ùë`yéÈ 9é 9éP yá£ùÿ§ùëyé( 9ÿ¨ 9é yàùÿùéÀ
yé9ÿH9éð yà{ùÿùëp
yéè9ÿè9é@yígùÿkùë
yéH9ÿ9ëyé(9ÿWùëÐ yé¨9ëàyéÈ9ì?ùÿCùë yé9é0yéh9ì+ùÿ/ùë0 yéh9éyÿ9ãùÿùëà yéÈ9ëÐyé¨9îùÿùë yé(9é yéH9ëpyÿóùé@ yÿ9éè9éÀyíÛùÿßùéð
yéè9é9ëyíÇùÿËùë
yéH9é(9é`yà³ùÿ·ùëP
yé¨9ÿÈ9ë°yàùÿ£ùë
yé9éh 9é yáùÿùé° yéh9é
9éPyáwùÿ{ùë` yéÈ9ÿ¨
9ë yéH 9ÿgùë yé(9éðyéè 9é@yÿSùéÀyÿ9ÿ 9ãÃùÿÇùÿ?ùépyéè9ëyé(
9ã×ùÿ+ùë yéH9ÿÛùéàyéÈ
9ÿùéÐyÿ¨9ÿïùë0yéh9ÿùéyé9é yÿ<9éP yÿ¨<9ë yéH=9ëð yéè=9ë@ yé>9ë yé(?9ëà yéÈ?9Ha3è# ù Ðé5è' ùhªRè+ ùH3è7 ùH¡3èK ùh ðõ0è; ùèO ùÿ³ùàùÿùî? ùîS ùHÁ3è_ ù ð5 èc ùQRèg ùHá3ès ùÈ °qèw ùH4è ù ðe5è ùãùàùÿùã/ùâ÷ùà«ùÿ¯ùÿÃùÿwùÿ×ùàçùÿëùáûùì_ùÿcùÿÿùáùÿùà#ùìKùÿOùÿ'ùÿ;ùâÇ ùâ ùâ ùH!4è ù ðu5è ù㣠ùHA4è¯ ù ð5è³ ùã· ùHa4èà ù ð5èÇ ùãË ùH4è× ù ðÉ5èÛ ùH¡4èë ùHÁ4èÿ ùè á+èï ùè!ùHá4è!ù ðá5è!ùèÁRè!ùH5è'!ù¨ ].è+!ùã/!ùH!5è;!ù¨ y.è?!ùãC!ùHA5. ÐÎm9èO!ùîS!ùHa5èc!ùîg!ùH5èw!ùh R® Ε.î{!ùè!ùh ð5N¡5î!ùè!ùNÁ5î!ùè£!ùHá5è³!ùhmR® °Ρ"î·!ùè»!ùH6® ÐÎMèÇ!ùîË!ùH!6èÛ!ùîß!ùHA6® ÐÎaèï!ùîó!ùíËùáùàùÿùÿùíï ùíW!ùík!ùí÷!ùHa6è"ùH6è"ùH -è"ùè"ùìùìùì£ùìùÿsùì§ùì»ùÿ_ùì ùìó ùì!ùì "ùì "ùH¡6è+"ù¨ Ð
ÿKùè/"ùȽRè3"ùHÁ6è?"ù¨ ð=èC"ùùßùùóùÿ7ùÿûùà ùÿùà ùÿ#ùðG"ùHá6èS"ù¨ ðeèW"ùÈRù["ùL7ìg"ù¬ ðmìk"ùìRìo"ùL!7ì{"ù¬ ð) è ùì"ùè"ùHA7¬ ð è"ùì"ùà+ùà
ùàß ùà"ùHa7è£"ù Rÿùÿçùÿ«ùÿ¿ùÿÓù Q y Ay áy 1y y Ñy !y y ±y ¡y y 1y y qy Áy ± y
yK7ë·"ù Ðkå5ë§"ùë»"ùÿùáÛ ùá{ ùá!ùá§!ùáÏ!ùáã!ùá«"ùá¿"ùÿoùJ¡7êË"ùª ðJ êÏ"ù*yRêÓ"ùÿÏùÿãùÿ÷ùÿ ùÿ[ùÿ ùÿ3ùÿGù y © 9 ¡ y I9 ñ y 9 y É9 i9 9 ©9 I9 qy é9 Áy )9 ay É9 i 9 y
9 Qy I 9 ñy é 9 Ay )
9 áy É
9 i9 9 Ñy ©9 !y é9 9 y a y i9 9 Q
y ©9 ¡
yÿùÿ»ùÿùÿ/ùÿCùÿWùÿkùÿ§ùÿùÿùÿ£ ùÿ· ùÿË ùÿß ùÿó ùÿ ùÿ ùÿ/ ù 9ÿC ùÿW ùÿk ù é9ÿ ùÿ ù )9ÿ§ ùÿ» ùÿÏ ùÿã ùÿ÷ ùÿ !ùÿ !ù 9ÿ3!ùÿG!ùÿ[!ùÿo!ùÿ!ù ©
9ÿ!ùÿ«!ùÿ¿!ù 9ÿÓ!ùÿç!ùÿû!ùÿ"ùÿ#"ùÿ7"ù I9ÿK"ùÿ_"ùÿs"ù )9ÿ"ù É9ÿ"ùÿ¯"ùÿÃ"ù I9ó@ùÿ×"ùÿ
ùÿï"ù ä oè@% ñ<è@å ñ<S ´¢ BøÓ ´"~©_8_8I *é 4¢_8I 4íÕ ` ù@ µôÿÿ ѹÔ ` ù µïÿÿ_ø Ñ ´ ÒÑÕ ` ù µçÿÿÙÕ ` ùüÿ´Õ âÿÿ¨Zø °)y@ù)@ù?ëA Tÿ@ÿÃý{E©ôOD©öWC©ø_B©úgA©üoƨÀ_ÖòÕ ÿà ÑôO©ý{©ý ó ª( ° )Gù@ùI@ù °)Y@ù᪠ë! T Ò# RÏÕ ´ý{B©ôOA©ÿà À_ÖH ´ ?Ö@ÿÿµ) ºÔ µ °-@ù @ùó ùá Ð!X ©Ô Òý{B©ôOA©ÿà À_Ö<Õ ýÿµïÿÿý{¿©ý @ùI@ù °)Y@ù ë¡ T Ò# Rý{h©Õ ¨ ´ ?֠ ´ý{hÀ_Ö(Õ ÿÿµ Òý{hÀ_ÖôO¾©ý{©ýC Õ ó ª 0@ùÀ ´ °@ù@ù@ù ë T)@ù)U@ùiÐ7
@ùJB9ê86
B9ª06ø6)¬B9I06 @ù) ´( @ù ñ T)a *@ù_ë T)! ñaÿÿT 2 ù @ù ë T¨ÿÿµ °@ù? ëà 5 àªZÔ 4`2@ù2 ùÀ ´ @ù ø7 ñ ù Tý{A©ôO¨À_Öý{A©ôO¨kÕ àªL þÿ5÷ÿÿ ´ @ù ë T(@ùU@ù¨Ð7 @ù)B9)86 ¬B9é 06È ø6(¬B9 06Ú RÀ_Ö4Ô 6 öW½©ôO©ý{©ý óªõªôªö ª ´¨@ù ëa TÀ2@ùÕ2 ùà ´ @ù¨ ø7 ñ ùA T>Õ Ô ´@ù ø7 ñ ù` TÓ ´h@ù ø7 ñh ù Tý{B©ôOA©öWèÀ_Öàª,Õ ³þÿµùÿÿàªý{B©ôOA©öWè%Õ àªáª Ô À2@ùÕ2 ùûÿµáÿÿÿà Ñý{©ý )@ù? ñ T Ò*` Kyhø ë@ T ?ëaÿÿT Ò °c @ùAybø? ë T@ùB9¨86¬B9h06(@ùU@ù¨ø6+¬B9k06 ¬@ùë ªì ´ @ù ñ Ta l@ùë Tk! ñaÿÿT RB _ ëaüÿT[ k@ù( Rëà'@©ê @ù¢_ø
Tà' ©ê ù¢ øËþÿµ °@ù? ëè hÐ6+@ù ñ ýÿTìªðªî
ªï ªí ª Ò1` )zhø?
ëà T ëaÿÿT Ò ¢ øé« ©à ù§Ó è ªà'@©ê @ù¢_ø °c @ùÈùÿ4& ! ? ëà
ªéªêªâªã ª øÿT)zaø(@ùB9¨þ?6(B9hþ76?
ëÀ Tê
ª @ù ´@ù ñkýÿT
` @@ù ë TJ! ñaÿÿTãÿÿJ@ù( R_ ë@ Tÿÿµ? ëûÿT( Ràªý{B©ÿà À_Ö Ràªý{B©ÿà À_Ö ëa T RÀ_Ö@ùB9h86¬B9(06(@ùU@ù ø6)¬B9I 06 H Ð6 ^Ó ë Tè ª ¬@ùé ´( @ù ñ T)a *@ù_ëÀ T)! ñaÿÿT RÀ_Ö RÀ_Ö R¨ ´@ù ë¡ÿÿT °@ù? ëàÀ_Ö)@ù? ñ T Ò*` Kyhø ë T ?ëaÿÿT Ò °@ù Rk ë@ TMykø¨@ùB9(ÿ?6¨B9èþ76¿ ëÀ T¬@ùî ª ´è @ù ñëýÿTîa Ï@ùÿ
ë TÎ! ñaÿÿTçÿÿ@ù( Rß
ë Tÿÿµ¿ ëüÿT RÀ_Ö RÀ_ÖàªÀ_Ö ë Tè ª ¬@ùé ´( @ù ñ T)a *@ù_ëÀ T)! ñaÿÿT RÀ_Ö RÀ_Ö R¨ ´@ù ë¡ÿÿT °@ù? ëàÀ_ÖöW½©ôO©ý{©ý õªô ª( @¹ 1B T¨ ¹@ù @ù¨ ø7 ñ ùA TûÓ ù( Ð]Aù¨@ùI@ù(
´àª ?Öó ª
´á Ð!¼ àª£Ò ` 4á Ð!¼ àªÒ ö ª` µËÒ µ À@É@ù"©
@ù@ùઠ?ր ´ @ù¨ ø7 ñ ùA TÔÓ ( Ð!Cù¨@ùI@ù
´àª ?Öõ ª
´v@ù @ù ø7 ñ ù Tv ù °r@ù@¹ 1B T ¹h@ù ø7 ñh ùÀ Tàªý{B©ôOA©öWèÀ_Öàª²Ó àªý{B©ôOA©öWèÀ_֬Ó v ù r@ù@¹ 1ýÿTèÿÿàªÓ ó ª öÿµ ҃æÿà ° ð £ °c AWRÂRHìÿ Òàªý{B©ôOA©öWèÀ_Ö( ° ¥Gù( °½Fù Òe ´ô ª @ùÈ ø7 ñ ùa TàªÓ ´[R5R
T`RµR
àªðÒ õ ªÀõÿµ´aRÕR ô]RuR ÒUæÿà ° ð £ °c áªâªìÿ ҫÿÿ4[Ræÿÿ P ¹ , ù q@ù @¹) 1B T ¹ p@ùÀ_Öüoº©úg©ø_©öW©ôO©ý{©ýC7 Ñÿ ñk Tóªôªõªöª yûËàªáª÷Ç PàªáªâªoÓ àªáªâªkÓ àªáªâªgÓ 9÷ ñÁýÿT q@ù @¹) 1B T ¹ p@ùý{E©ôOD©öWC©ø_B©úgA©üoƨÀ_ÖöW½©ôO©ý{©ý óªôªõ ª@ùA@ù6 ´à ° Ø! Ó À 5àªáªâªÀ?Öó ªüÒ ³ ´àªý{B©ôOA©öWèÀ_Öàªáªâªý{B©ôOA©öWènÒ ìÑ à ´ Òàªý{B©ôOA©öWèÀ_Ö =@ù @ùá °!T"åÑ Òàªý{B©ôOA©öWèÀ_ÖÿÑöW©ôO©ý{©ýÃ ó ª @ùT@ùÈð7h ø6h®B9(07 A@ù @ùá °!$ý{C©ôOB©öWA©ÿÉÑ áªý{C©ôOB©öWA©ÿÀÑ ҇Ò ´õ ªàªáª Ò6Ò ô ª¨@ùÈ ø7 ñ¨ ùa TàªÇÒ Ô ´@ù B9i07 )A@ù @ùó# ©á °! #Ñ @ùè ø6 àªáªÑ @ù ø7 ñ ùÀ Tý{C©ôOB©öWA©ÿÀ_Öàªý{C©ôOB©öWA©ÿ¦Ò ôO¾©ý{©ýC ó ª@ùÅ@ù( µàªÒ `@ù ´ ù @ù¨ ø7 ñ ùA TÒ `v@ùà ´v ù @ù ø7 ñ ùà Th@ù¡@ùàªý{A©ôO¨ օÒ h@ù¡@ùàªý{A©ôO¨ ÖàªíÑ Àûÿ5h@ù@ù )q ëûÿTàªÞÑ úÿ4ý{A©ôO¨À_ÖÿÑø_©öW©ôO©ý{©ýCö ª y@ù@ùè ù( °ÕEù@ùI@ùh ´àª ?Öô ª` ´@ù ÷V@ù ë T@ù ´
@ù¨@¹ 1ã Th@¹ 1 T@ù(ø6
¨ ¹h@¹ 1BÿÿTh ¹@ùÈ ø7 ñ ùa Tàª?Ò " Rôªè# ! õÿ ©
ËàªÓ ó ª ´¨@ùÈ ø7 ñ¨ ùa Tàª.Ò 3 ´@ùÈ ø7 ñ ùa Tàª&Ò ( °¡ @ùAù@ùI@ù ´ ?Öõ ª ´( ° ¡Gùè# ! ÿÛ ©âA²± ` ´ö ª¨@ù ëA T·@ù· ´´
@ùè@¹ 1ã T@¹ 1 T¨@ù(ø6
è ¹@¹ 1BÿÿT ¹¨@ùÈ ø7 ñ¨ ùa TàªøÑ ( Rõªé# )! ÷Û ©!M(Ë àª ô ª ´è@ùÈ ø7 ñè ùa TàªæÑ È@ùÈ ø7 ñÈ ùa TàªßÑ t ´¨@ùÈ ø7 ñ¨ ùa Tàª×Ñ àªáª Ñ õ ª` ´h@ù ø7 ñh ùà T@ù(ø7 ñ ùÁ TàªÆÑ è@ù )y@ù)@ù?ë TV àª½Ñ @ù(þÿ6è@ù )y@ù)@ù?ë Tàªý{E©ôOD©öWC©ø_B©ÿÀ_Öàª"Ñ ô ªàéÿµùR1 Ò Òiÿÿ ÒüR ÒdÿÿÑ õ ª@ðÿµ ҖüR ÒÖüR R ҟÿÿvÿR RÿÿöÿRh@ùÈ ø7 ñh ùa TàªÑ ´@ùÈ ø7 ñ ùa TàªÑ ´¨@ùÈ ø7 ñ¨ ùa TàªxÑ à Ð ` £ °c áªR!êÿ Òè@ù )y@ù)@ù?ëÀöÿTlÑ ø_¼©öW©ôO©ý{©ýà õ ª6 °JAù@ùI@ù ´àª ?Öô ª ´7 °áCù@ùI@ù¨ ´àª ?Öó ª ´@ùÈ ø7 ñ ùa TàªJÑ @ùJAù@ùI@ù ´ ?Öõ ª ´áCù¨@ùI@ù ´àª ?Öô ª ´¨@ùÈ ø7 ñ¨ ùa Tàª3Ñ ( ° ±@ùáª{Ð À
´õ ª@ùÈ ø7 ñ ùa Tàª&Ñ ( °µ@ùàªnÐ ` ´ô ª¨@ùÈ ø7 ñ¨ ùa TàªÑ àªáªeÐ
´õ ª@ù ø7 ñ ù Th@ùhø7 ñh ù TàªÑ àªÑ h@ùèþÿ6¨@¹ 1B T¨ ¹óªh@ù ø7 ñh ùà Tàªý{C©ôOB©öWA©ø_ĨÀ_ÖàªñÐ àªý{C©ôOB©öWA©ø_ĨÀ_Öàª_Ð ô ªÀñÿµà Ð
£ °c áRbRéÿ Òàªý{C©ôOB©öWA©ø_ĨÀ_ÖàªMÐ ó ª ðÿµ5 RvR' GÐ õ ªÀñÿµà Ð
£ °c Á
RRxéÿÊÿÿàª;Ð ô ª@ñÿµ R u R Ô R¨@ùÈ ø7 ñ¨ ùa TષРà Ð
£ °c áªR`éÿ ұÿÿ5 RR@ùÈ ø7 ñ ùa TથРà Ð
£ °c áªâªNéÿ Òóóÿµ£ÿÿöW½©ôO©ý{©ý ôªóªõ ª @ù ´áª`?֠ 4ý{B©ôOA©öWèÀ_֠v@ù ´áª`?Ö ÿÿ5 Rý{B©ôOA©öWèÀ_ÖôO¾©ý{©ýC ó ª @ù r@ùt ù@¹ 1B T ¹À ´ @ù ø7 ñ ù T`v@ùtv ù@¹ 1B T ¹À ´ @ù ø7 ñ ù T Rý{A©ôO¨À_Ö^Ð `v@ùtv ù@¹ 1þÿTðÿÿWÐ Rý{A©ôO¨À_ÖÿCÑø_©öW©ôO©ý{©ýó ª y@ù@ù¨ ø( °)4@ùèÿ© ÷r@ù÷ ùb ´õª´ ´ ñA T6 @ùö ùàª Ï t ´5 ñÀ T4
´è4ªýÓé Ð)y ê ÐJU ñI±
JA@ù@@ùª °Jë Ðk© j±êÓ©é£ ©è Ð9<è ùá Ð!¸ øÎ ׃Rà Ð \<£ °c RÄèÿ Ör@ùàªâÎ µ ñK T( °1Eù" @ùàªñÏ À ´ö ªà ùઠñj Tßë T( °aAù(@ùB9h
6È@ùI@ù¨ ´àª ?֠ ´ @ù¨ ø7 ñ ùA TíÏ È@¹ 1B TÈ ¹ôªÂ 6 @ùö ùßëÁüÿT( !9@ù @ù@ùáªÇÏ ´õ ª @¹ 1B T¨ ¹¨@ù )U@ù ëà T Ò Òèã ! öÿ©
Ëàªe ô ª ´È@ùÈ ø7 ñÈ ùa TàªÀÏ 4 ´¨@ùø7 ñ¨ ù¡ TઠΠ# µå °¥8<âã ãà ઠÒ䪾q ø7ö@ùßë¡õÿTÇÿÿAՃRÿÿè ðA@ù @ùá °! =Î âRáãRà ° \<£ c ÿÿàªÏ ôÿµmÎ ð!9@ù @ù@ùáªzÏ @ ´õ ª @¹ 1B T¨ ¹¨@ùø ðW@ù ë T Ò Òèã ! ÷ÿ©
Ëઠô ª ´è@ùÈ ø7 ñè ùa TàªsÏ t ´¨@ùÈ ø7 ñ¨ ùa TàªkÏ ( Cù@ùI@ùH ´àª ?Öõ ª@ ´¨@ù ëA T·@ù× ´¸
@ùè@¹ 1ã T@¹ 1 T¨@ù(ø6
è ¹@¹ 1BÿÿT ¹¨@ùÈ ø7 ñ¨ ùa TàªGÏ ( Rõªéã )! ÷Û©!M(Ë àªÚ ö ª ´è@ùÈ ø7 ñè ùa Tàª5Ï V ´¨@ùÈ ø7 ñ¨ ùa Tàª-Ï È@ùÈ ø7 ñÈ ùa Tàª&Ï h
@ù@ùàªáª ?ր ´ @ù¨ ø7 ñ ùA TÏ R@ùÈ ø7 ñ ùa TàªÏ ¨\øé ð)y@ù)@ù?ë Tàªý{H©ôOG©öWF©ø_E©ÿCÀ_֢RðRà ° \<£ c ®çÿ äÿÿáÍ µàª
ùÿõ ª äÿµÂRaރRUÿÿ¶@ùÖ ´´
@ùÈ@¹ 1C T@¹ 1c T¨@ùø6 óàRÖR4 È ¹@¹ 1âþÿT ¹¨@ùÈ ø7 ñ¨ ùa TàªØÎ " RõªÿÿºÍ µàªãøÿõ ªàèÿµRAåR.ÿÿ·@ù7 ´´
@ùè@¹ 1c T@¹ 1 T¨@ù¨ø61 ÓçRR
àª1Î õ ª ëÿµ"RéR´ÿÿ R ÒoÿÿìR6R¨@ùÈ ø7 ñ¨ ùa TàªªÎ à ° \<£ c áªâªSçÿ 4ñÿµÿÿ RZÿÿ¡ԃRþÿè ¹@¹ 1ÂúÿT ¹¨@ùÈ ø7 ñ¨ ùa TàªÎ " Rõª ÿÿÎ Ҽþÿ Òÿÿý{¿©ý ¨B9è 7@ù Ò ?Ö ´( ÍGùè ðq@ù © @¹* 1 Tt ùý{hÀ_Ö
¹t ù) 1@ T ¹ý{hÀ_Öè ð@ù@ù ð!1Gù Ò ?ÖàüÿµöÿÿöW½©ôO©ý{©ý ôªó ªUø@ò@ T¿ ñá T`@ùè ð @ù ë Tá ð!@ù Î À 4h
@ù @¹i6(7s@ù3 `@ùè ð @ù ë Tá ð!@ùüÍ à 4h
@ù @¹ 6 (7s@ù ઠΠ@ ´ä ªàªáªâª Òý{B©ôOA©öWè Ö ´àªáªâª Òý{B©ôOA©öWèÅÍ Ò@ùà Ø!Î 5ઠҀ?Öó ªÎ ó µ# Ҕ@ù@ùà Ø!úÍ À 5àªáª ?Öó ª÷Í Ó ´àªý{B©ôOA©öWèÀ_Ö ð1Gùh@ùA@ù ´à Ø!æÍ @ 5àªáª Ҡ?Öó ªâÍ ýÿµÞÌ À ´ Òàªý{B©ôOA©öWèÀ_Öàªáª Òý{B©ôOA©öWèQÍ è ð=@ù @ùá !T"ÐÌ Òàªý{B©ôOA©öWèÀ_ÖnûÿÿÑöW©ôO©ý{©ýC_ ñ
Tó ªÃ
µ( UBùh@ùI@ùH ´àª ?Öô ª@ ´Ì ó ª ´( Cùâ ðBl@ùàªÌ `ø7 ð1Gù@ùA@ùö ´à Ø!Í
5àªáªâªÀ?Öõ ªÍ u ´@ù ø7 ñ ù Th@ùÈø7 ñh ùa Tàª¥Í àªý{E©ôOD©öWC©ÿÀ_ÖõR@ùÈ ø7 ñ ùa TàªÍ ´h@ùÈ ø7 ñh ùa TàªÍ à ° ì
£ c áª"R8æÿ Òàªý{E©ôOD©öWC©ÿÀ_ÖàªÍ h@ùúÿ6àªý{E©ôOD©öWC©ÿÀ_Öè ðA@ù @ùè °© è©è ° é °)É
èÿ ©é ùá °!¸ EÌ àÿÿh@ùHòÿ´á °!È
ઠR;o ñÿ5×ÿÿàªÒÌ ô ª òÿµuRÊÿÿµR¹ÿÿàªáªâª¹Ì õ ª ôÿµ 4Ì ` ´R®ÿÿè ð=@ù @ùá !T"1Ì øÿÿÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýôªó ªè ðy@ù@ùè' ù( !.èÿ©C ´õª6 4 ´ ñ! T7 @ù÷ ù¸
@ùB ña T7 @ù÷ ù( EEùh@ùI@ù µµ º
@ùX ñ T Ò( ÅEù»b h{yø ë` T9 _ëaÿÿT Òa{yøàªB Røo 59 _ë!ÿÿTîË ` ´!%R è ðA@ù @ù¨ * RèÓ©è ° é °)ý
è« ©é ùá °!¸ ÒË !'Rà ° £ c bRåÿ ÒW `üÿ7×zyø÷ ùüÿ´ ñª
T( EEùh@ùI@ùè ´àª ?Öó ªà ´h@ùé ð)U@ù ë!
Tt@ùt ´u
@ù@¹ 1ã T¨@¹ 1 Th@ù(ø6
¹¨@¹ 1BÿÿT¨ ¹h@ùÈ ø7 ñh ùa TàªÀÌ ( Róªéã )! ôß©!M(Ë àªSþÿõ ª ´@ùÈ ø7 ñ ùa Tàª®Ì 5 ´h@ù ø7 ñh ù T¨@ùhø7 ñ¨ ù Tàª¡Ì àªÌ ¨@ùèþÿ6à ð p@ù @¹ 1B T ¹è'@ùé ð)y@ù)@ù?ëa Tý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_Ö Ò RÈÿÿh@ùÈ ø7 ñh ùa Tàª~Ì a/R R½ÿÿå °¥ü
âã ãà àªáªäªn @ø7÷@ù( EEùh@ùI@ùhñÿµàªßË ó ª`ñÿµá,Rà ° £ c RrÿÿÁ%Rkÿÿ`Ì ÿÑüo©úg©ø_©öW©ôO©ý{ ©ýCè ðy@ù@ùè ù_ ñ, Tù ªc. µ @ù( ùDù@ùI@ùè. ´ ?Öü ªà. ´@ùé ð)U@ù ëa/ T@ù³0 ´ @ùh@¹ 1ã T@¹ 1 T@ù(ø6
h ¹@¹ 1BÿÿT ¹@ùÈ ø7 ñ ùa Tà ª'Ì " Rüªè£ ! óÿ©
Ëà ª»ýÿø ª ´h@ùÈ ø7 ñh ùa TàªÌ * ´@ùÈ ø7 ñ ùa Tà ªÌ @ùé ð)]@ù ëa* T @ù
ñ¡8 Tc
£ T@ù3@ù@ù¨@¹ 1B T¨ ¹h@¹ 1ã T@¹ 1 T@ù(ø6
h ¹@¹ 1BÿÿT ¹@ùÈ ø7 ñ ùa TàªçË R
Ë à* ´ø ª: HÛDù @¹) 1b T ¹HÛDù @ù( ù( IDùÊ ö ª) ´ ð%Gùàªâªãª$ RêÊ ÷ ªÈ@ùÈ ø7 ñÈ ùa TàªÆË ( ´@ùÈ ø7 ñ ùa Tàª¾Ë AÛDùàªäâÿö ª@' ´È@¹ 1B TÈ ¹È@ù ø7 ñÈ ù Tè@ùhø7 ñè ù Tàª©Ë àª¦Ë è@ùèþÿ6àª Ò R Rjo `$ ´÷ ª@ RMË @% ´ø ª ù¨@¹ 1B T¨ ¹ ù ðUBù(@ùI@ùH$ ´àª ?Ö÷ ª@$ ´QÊ û ª$ ´ ðCùâ ÐBl@ùàªOÊ ø7 Ð1Gùè@ùA@ù# ´À ð Ø!]Ë $ 5àªáªâª@?Öü ªYË # ´è@ùÈ ø7 ñè ùa TàªiË h@ùÈ ø7 ñh ùa TàªbË ` RË ÷ ª! ´È@¹ 1B TÈ ¹öâ©ü ù¨@ùèø6C ÒYRZLR@ùÈ ø7 ñ ùa TàªKË àªáªóªõ ª Òøªóªõ ª ´@ùÈ ø7 ñ ùa Tà ª;Ë ´@ùÈ ø7 ñ ùa Tàª3Ë ´è@ùÈ ø7 ñè ùa Tàª+Ë ´h@ùÈ ø7 ñh ùa Tàª#Ë à ðc áªâªÌãÿ Ò ´¨@ùÈ ø7 ñ¨ ùa TàªË ´h@ùÈ ø7 ñh ùa Tàª Ë ´@ùÈ ø7 ñ ùa TàªË ´È@ùÈ ø7 ñÈ ùa TàªûÊ è @ùé Ð)y@ù)@ù?ë Tàªý{I©ôOH©öWG©ø_F©úgE©üoD©ÿÀ_Öè ÐA@ù @ùè © è©è © )½8èÿ ©é ùá !¸ ºÉ Òáÿÿh@ù¨Ñÿ´¡ !¼8ઠR¯l àÐÿ5 Ò×ÿÿFÊ ü ª`Ñÿµà ðc A<RâRwãÿ ÒËÿÿ Ò Ҟþÿ Ò Ò Ò Ò Ò ÒÚ>RùRxÿÿ ғþÿé Ð)M@ù ë Tàª0Ê û ª` ´@ùÈ ø7 ñ ùa Tàª¨Ê h@ùq@ùàªÀ?Öõ ªà ´àªÀ?Öó ª ´àªÀ?Ö ´ô ªàªÀ?Öa R n Àø7h@ù¨Õÿ7øª ñh ù!ÕÿT¦þÿ Ò"R¡GR Ò Ò Ò Ò Ò Ò9RZHR/ÿÿ ҺHR9RKÿÿBRJRà ðc %ãÿ Ҩ@ùhëÿ6_ÿÿ ÒÚJRYR<ÿÿàªáÉ ÷ ª Üÿµ Ò ÒYRÚKRÿÿ ÒYRLRÿÿàªáªâªÃÉ ü ª`Ýÿµ >É À ´ ÒYRzLRÿÿ ÒYRúLRþþÿ @ù
ña T@ù !
A T@ù3@ù@ù¨@¹ 1ãÈÿTGþÿ ñ+ Tè ÐE@ù @ùh Rè ùá !Ì Èø·é Ð)E@ù @ùé )© ðJ ñIè' ©á !pÉ Ò Ò Ò Ò Ò Ò ÒùR@RÏþÿ ҚDRùRüªøª÷ª Ò Ò ÒÕþÿÊ Ò Ò Ò Ò Ò ÒùRZCR»þÿ Ò Òô ª ð®6 R ô ª V Rh@ùÈ ø7 ñh ùa TàªùÉ ¥m 5è ÐE@ù @ùöS ©á !pÍÈ Ò Ò Ò Ò ÒùRER Òüªøªóªõ ª\Ôÿµ¨þÿè Ð=@ù @ùÁ ð!T"ÈÈ
ÿÿÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýõªô ªè Ðy@ù@ù ð))è' ùéÿ©ó Ðsr@ùó ùC ´öª7 U ´¿ ñá T8 @ùø ùÙ
@ùT U ´¿ ñ T8 @ùø ù@ù¨@¹ 1#
TQ è5ªýÓé )y ê JU ¿ ñI±ê ÐJA@ù@@ù ðJë k© j±ê×©é£ ©¨ é8è ùá !¸ xÈ !uRà ðc RDâÿ ҭ Ù
@ù: ñ« T Ò ð1EùÜb {{ø ëÀ T{ ?ëaÿÿT ҁ{{øàªB Rkl 5{ ?ë!ÿÿT ø Ðs@ù@ù¨@¹ 1C T À ø7øz{ø ´ø ùùª SÈ µø Ðs@ù? ñJ T@ù¨@¹ 1B T¨ ¹ Ð!9@ù @ùâ@ùáªGÉ @ ´ö ª @¹ 1B TÈ ¹àªáªØÈ 1à T÷ ª¨@ù ø7 ñ¨ ù TÈ@ùhø7 ñÈ ù TàªDÉ àªAÉ È@ùèþÿ67 4@ù ð Cù@ùI@ù( ´ ?Öõ ª ´¨@ùé Ð)U@ù ëá T¶@ùv ´·
@ùÈ@¹ 1ã Tè@¹ 1 T¨@ù(ø6
È ¹è@¹ 1BÿÿTè ¹¨@ùÈ ø7 ñ¨ ùa TàªÉ ( Rõªéã )! öã©!M(Ë àª«úÿ÷ ª ´È@ùÈ ø7 ñÈ ùa TàªÉ ÷
´¨@ù ø7 ñ¨ ù Tè@ùhø7 ñè ù TàªùÈ àªöÈ è@ùèþÿ6
@ù@ùઠ?ÖÀ
´ @ù ø7 ñ ù Th@¹ 1B Th ¹è'@ùé Ð)y@ù)@ù?ëÁ Tàªý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_ÖÖÈ h@¹ 1£ýÿTíÿÿ·Ç à
µàªàòÿö ªàîÿµS ³{R R¨@ùÈø6" ð ©Gù ðÁFù ҙõÿ ´ö ªËõÿÈ@ùø7Ó}R4 R -È õ ª ðÿµRT R- Ò Rÿÿ ғRT R¨@ùÈ ø7 ñ¨ ùa Tàª¥È ö ´È@ù¨ø7 ñÈ ùA TàªÈ R
ÿÿ3Rt R ¥ ¥è8âã ãà àªáªäªj ø7ø@ù@ù¨@¹ 1ÃäÿT&ÿÿÓ}R4 Rà ðc áªâªëþÿasRäþÿÁrRâþÿ}È Òs{R R¨@ùùÿ6ÐÿÿS}RìÿÿÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýôª÷ ªè Ðy@ù@ù ð)è' ùé©ø Ðw@ùø# ùC ´õª6 4 ´ ñÁ T3 @ùó# ù¹
@ùR 4 ´ ñá T3 @ùó# ùh@¹ 1ã TO è4ªýÓé )y ê JU ñI±ê ÐJA@ù@@ù ðJë k© j±êÓ©é£ ©¨ °Ùè ùá !¸ Ç Rà ðc ¢ RÜàÿ Ò} ¹
@ù: ñ« T Ò ðCù¼b {{ø ë T{ ?ëaÿÿT ҁ{{øàªB Rk ` 5{ ?ë!ÿÿT
ó Ðsv@ùh@¹ 1# T À ø7Óz{ø ´ó# ùùª ìÆ @J µó Ðsv@ù? ñJ> Th@¹ 1B Th ¹à@ù ðÅEù@ùI@ù(+ ´ ?Öô ª + ´@ùù Ð9@ù ð?Aùઠë!+ T5l ö ª + ´ еGùàªb RÏj +ø7õ ªÈ@ùÈ ø7 ñÈ ùa TàªÛÇ û Ð{o@ùú ÐZs@ù ÐÖ"95 4ë Të@ Të TàªTÇ `?ø7à
4Õ:GùøªÀ@ù¢@ùáª¯Ç @: ´ö ª @¹ 1B TÈ ¹ ðUFùÈ@ùI@ùè9 ´àª ?Öõ ªà9 ´È@ùÈ ø7 ñÈ ùa Tàª®Ç ÐÅFù¨@ù A@ù<9 ´À Ð Ø!Ç À9 5àªáª Ҁ?Öö ªÇ ¶8 ´¨@ùÈ ø7 ñ¨ ùa TàªÇ È@ù ÐÈ ø7 ñÈ ùa TàªÇ h@¹ 1B Th ¹h@ùÈ ø7 ñh ùa TàªÇ ó °sn@ùàR¹±Æ ö ª µ Ò Ò Ò ÒڡR{%R® ëà`õÿ5øªàR¹¢Æ ö ª@þÿ´ ÐqBùàªâªÇ ø7È@ùÈ ø7 ñÈ ùa TàªbÇ à.@ýdÆ ö ª ´ Ð5BùàªâªðÆ @ ø7È@ùÈ ø7 ñÈ ùa TàªQÇ ëdZúè °u@ùdHúû Tëà àªÍÆ `(ø7À 4ö@ùÈ@¹ 1B TÈ ¹@ù @ùâ@ùáª$Ç ´õ ª @¹ 1B T¨ ¹àªáªµÆ 1À T÷ ªÈ@ùÈ ø7 ñÈ ùa Tàª&Ç ¨@ùÈ ø7 ñ¨ ùa Tàª Ç 4Û 4è °u@ùëà àªÆ #ø7
4@ù?AùઠëÁ TXk õ ªÀ ´@ù ÐËEùઠëá TOk ö ªà ´È@ù Ð!ÕBùઠëá TFk ÷ ªà ´È@ùÈ ø7 ñÈ ùa TàªóÆ @ùËEùઠë T7k ö ª ´È@ù Ð!]Dùઠëá T.k ø ªà ´È@ùÈ ø7 ñÈ ùa TàªÛÆ @ù Ð!qBùઠëÁ T k ö ªÀ ´@ù Ð!5Bùઠë Tk ù ª ´ RyÆ ´ú ªÜ©Ø© ù @¹ 1B T ¹úª@ùÈ ø7 ñ ùa TàªµÆ h@ùÈ ø7 ñh ùa Tàª®Æ è'@ùé °)y@ù)@ù?ëá Tàªý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_ÖÆ ô ª Õÿµ Ò Ò Ò Ò Ò:R»$RË Æ ö ª Õÿµ Ò Ò Ò ҺRÁ Ò Ò Ò ÒúR» Ò Ò Ò Ò¢R{%Rµ Ò Ò Ò ÒZ£R%R® Ò Ò Ò Қ£R%R§ UÅ À µàª~ðÿõ ª çÿµº Ò Ò Ò¦R»%R Ð ¥Gù ÐÍFù Ò6óÿõ ª@ ´àªgóÿ¨@ùÈ ø7 ñ¨ ùa TàªRÆ Ò Ò Ò Ò Òz¨RÛ%R ÅÅ õ ªçÿµ Ò Ò Ò Ò¬R{&Rw »Å ö ª`çÿµ Ò Ò ÒZ¬R{&Rn ²Å ÷ ª`çÿµ Ò Қ¬R{&Rf ªÅ ö ª@èÿµ Ò Òú¬R{&R^ ¢Å ø ª`èÿµ Ò:R{&RW Å ö ªéÿµ Қ®R&RP Å ù ªÀéÿµڮR&RJ °R{&RG ¥ ¥Øâà ãàªáªäªh @
ø7ó#@ùh@¹ 1ÃÀÿTþÿ Ò Ò Ò Ò ÒڤR»%R1 Ò Ò Ò Ò ҺªR[&R) ×Ä À µàª ðÿö ªàÅÿµJ àª_Å õ ª`Æÿµ Ò Ò ҚRû$R àªáª ÒDÅ ö ªÀÇÿµ ¿Ä À ´ Ò Ò Ò ÒúRû$R Ò Ò Ò Ò ÒښRÛ$RબØÿપØÿનØÿદØÿતØÿÀ ð Ðc áªâªiÞÿ ҔßÿµÿÿORýÿ!Rýÿ´Å Ò Ò Ò ÒڥR»%Ráÿÿ Ò Ò Ò Òú§RÛ%RÚÿÿ Ò Ò Ò Ò ÒZRû$RÒÿÿè °=@ù @ùÁ Ð!T"Ä ½ÿÿÿÑé#müo©úg©ø_©öW ©ôO
©ý{ ©ýÃóªõ ªè °y@ù@ùè' ù Ð!.è©C ´öª7 ´ ñ T4 @ùô# ùØ
@ùí ñÁ T4 @ùô# ù@ùU@ùh è6 Ð=Aùàª
Å à8ø7@
4 ÐÉEùàªÅ Hø7 4@¹ Ò 1B T ¹ ÐáJBù@ùI@ùè5 ´àª ?Öù ªà5 ´ ÐÝFù(@ùA@ùX< ´À Ð Ø!4Å à< 5àªáª Ò ?Öö ª0Å Ö; ´(@ùÈ ø7 ñ( ùa Tàª@Å È@ùé °)I@ù ëÀ Tàª:Ä @` b !` T] Ú
@ùX ñ T Ò ÐÅEùÛb h{yø ë` T9 _ëaÿÿT Òa{yøàªB R h 59 _ë!ÿÿTÄ ` ´!R è °A@ù @ù Ð* RèÏ©È ð © )Áè« ©é ùÁ ð!¸ æà !RÀ ð H Ðc â&R" Ð¥Gù ÐÑFùh@ùA@ùU? ´À Ð Ø!ÝÄ à? 5àªáª Ҡ?Öó ªÙÄ Ó> ´àªüñÿh@ùÈ ø7 ñh ùa TàªçÄ ¢-R¡̄RÀ ð H Ðc Ýÿ Ҩ È
@ý b !` a T¾Ã : µÈ@ùÈ ø7 ñÈ ùa TàªÐÄ ¨. ýáJBù@ùI@ùH- ´àª ?Öö ª@- ´ ÐáFùÈ@ùA@ù- ´À Ð Ø!¤Ä - 5àªáª Ò ?Öù ª Ä , ´È@ùÈ ø7 ñÈ ùa Tàª°Ä àª.i ö ª 1a Tà À6 µ(@ùÈ ø7 ñ( ùa Tàª¢Ä ¶R ¹ @ù ÐÅEù@ùM@ùè) ´âª ?Öà)ø7õ °µr@ù¨@¹ 1B T¨ ¹÷ªÑ `îÿ7ôzyøô# ùîÿ´ ñ! T@ùU@ùèâï7 gò - Tàª Ò R# RKh ´ù ª °µGùb Reg @ø7ó ª(@ùÈ ø7 ñ( ùa TàªqÄ 57à ´÷ ªàª Ò R# R3h ö ª ´ Ð=Aùàªâª/à ø7È@ùÈ ø7 ñÈ ùa TàªYÄ Ã ö ª`& ´àª! R R# R h ø ª & ´ ÐÕBùàªâªÃ @ ø7@ùÈ ø7 ñ ùa TàªBÄ àªA R R# Rh ø ª@& ´ Ð]DùàªâªÃ
ø7@ùÈ ø7 ñ ùa Tàª.Ä ÐÉEùàªâª÷ ø7È@ùÈ ø7 ñÈ ùa Tàª!Ä àª¹Ã ± & T ñ
Tàªa R R# Rág % ´ù ª ÐqBùàªâª¦Ã %ø7(@ùÈ ø7 ñ( ùa TàªÄ ઠR R# RÍg @$ ´ù ª Ð5BùàªâªÃ à#ø7(@ùÈ ø7 ñ( ùa Tàªóà è@¹ 1B Tè ¹óª; Ò ҕۄRÚ.R ÒU݄R ÒÕ݄Rú.Rùª Ò(@ùÈ ø7 ñ( ùa TàªÙà ´È@ùÈ ø7 ñÈ ùa TàªÑà ´@ùÈ ø7 ñ ùa TàªÉà À ð H Ðc áªâªrÜÿ ÒW ´è@ùø7 ñè ù¡ Tહà z Ò ÒބRËÿÿ Òôª °áJBù@ùI@ùhÊÿµàª!à ù ª`Êÿµ¢/RæR_ -RáɄR¿þÿb.R¡քR¼þÿ Ò Ò Ò ÒõքRz.Rºÿÿ ° ¥Gù °ÙFù ÒlðÿÀ ´ó ªðÿh@ùÈ ø7 ñh ùa TàªÃ .RÁR¢þÿÂ.RۄRþÿ Ò ÒUۄRÿÿ
ð¥Àâà ãàªáªäªe ø7ô#@ù@ùU@ùÝï6þÿàªáª ÒÔ ö ª Äÿµ OÂ à ´ Ò ÒÕæRº/R÷ªÿÿàªÖ ö ª ÓÿµÂ/RèR àªáª Ҿ ù ªàÓÿµ 9 ´ ÒÕèRÚ/R÷ªvÿÿâªÜ `Öÿ6â/RêR÷ªÀ Ð H °c òÛÿ Òè@ùHðÿ6 ´h@ùÈ ø7 ñh ùa Tàª7à è'@ùé )y@ù)@ù?ë Tàªý{K©ôOJ©öWI©ø_H©úgG©üoF©é#EmÿÀ_ւ-R¡ʄR@þÿ Ò ÒÕ܄R>ÿÿ Ò݄R;ÿÿ ° ©Gù °ÕFù Òðïÿ`
´ó ª"ðÿh@ùÈ ø7 ñh ùa Tàª
à ".RaԄR&þÿ ҕ݄R%ÿÿ Ò5çRº/R÷ª+ÿÿàªáª ÒeÂ ó ª Áÿµ àÁ ´¢-R!̄RþÿÁRíýÿ Ò Ò5éRÚ/R÷ªÿÿ Ò/R߄R¤ÿÿ Ò"/RáàR ÿÿ Ò Ò Ò5áR:/Rÿÿ ÒB/RaâRÿÿ Ò Ò ҵâRZ/R÷þÿØ .RARîýÿè =@ù @ùÁ °!T"¸Á dÿÿè =@ù @ùÁ °!T"±Á sÿÿ".RáӄRÝýÿè =@ù @ùÁ °!T"§Á ÂÿÿÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýôªó ªè y@ù@ù °)¡+è' ùé©è q@ùè# ùC ´õª6 4 ´ ñÁ T" @ùâ# ù¸
@ùS 4 ´ ñá T" @ùtv@ù@¹ 1#
TQ è4ªýÓÉ Ð)y Ê ÐJU ñI±ê JA@ù@@ù °JË Ðk© j±êÓ©é£ © ð3è ùÁ Ð!¸ XÁ á÷RÀ Ð ( °c "0R$Ûÿ ÒB ¸
@ù ñ« T Ò °uEù»b h{zø ëÀ TZ ëaÿÿT Òa{zøàªB RKe 5Z ë!ÿÿT â Bp@ùtv@ù@¹ 1C T À ø7Âzzø ´â# ùøª 3Á µâ Bp@ù ñ Ttv@ù@¹ 1B T ¹ °ÑGùa @ Ð à2ä p@ù㪠?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàª1 è'@ùé )y@ù)@ù?ëA Tàªý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_ÖÈ ø7 ñ ùa Tઠ À Ð ( °c ÁýR¢6R¡ÿÿ
ð¥3âà ãàªáªäª d à ø7â#@ùtv@ù@¹ 1øÿTÄÿÿ!öRÿÿõRÿÿ ÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýôªó ªè y@ù@ù °)¡+è' ùé©è q@ùè# ùC ´õª6 ´ ñá T7 @ù÷# ù¸
@ùX ´ ñ T7 @ù °ÍDùh@ùI@ùÈ
µ> è4ªýÓÉ Ð)y Ê ÐJU ñI±ê JA@ù@@ù °JË Ðk© j±êÓ©é£ ©¨ è ùÁ Ð!¸ À !
RÀ Ð à °c â6Rx ¸
@ù ñ« T Ò °uEù»b h{zø ë TZ ëaÿÿT Òa{zøàªB Rd @ 5Z ë!ÿÿT ÷ ÷r@ù °ÍDùh@ùI@ù µàªÁ ô ª µõ
RN À ø7×zzø ´÷# ùøª uÀ µ÷ ÷r@ù ñÊ T °ÍDùh@ùI@ùHýÿ´àª ?Öô ª@ýÿ´HÀ ó ª ´ °uEùàªâªGÀ ø7 1Gù@ùA@ù ´À ° Ø!UÁ 5àªáªâªÀ?Öõ ªQÁ ´@ùÈ ø7 ñ ùa TàªaÁ h@ùèø7 ñh ù TàªZÁ u
R@ùÈ ø7 ñ ùa TàªQÁ ´h@ùÈ ø7 ñh ùa TàªIÁ À Ð à °c áªÂ7RòÙÿ Òè'@ùé )y@ù)@ù?ëa Tàªý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_Ö5
RÙÿÿàªáªâªÀ õ ª`øÿµ À ´
RÎÿÿ¥ ¥ âà ãàªáªäª-c ø7÷#@ù °ÍDùh@ùI@ùHòÿµzÿÿa
RTÿÿÁ
RRÿÿÁ è =@ù @ùÁ °!T"ö¿ ãÿÿÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýôªó ªè y@ù@ù¨øÿ© °! Áè'©%è©ù 9s@ùùC ùã ´ ñh Tõª< °¡
it8)
ÖûªxAø ñè# ù T Ò °Å@ùºb H{vø ë TÖ ëaÿÿT ÒA{vøàªB R½c ` 5Ö ë!ÿÿT³¿ ´¡
R
ñ@ T ña T"@ùH H RÉ Ð)y Ê ÐJU
ñI±µê JA@ù@@ùÊ ÐJ© êÓ©é£ ©¨ è ùÁ Ð!¸ ¿ ¡"
Rf 7 @ù÷; ùûªvAøös©ß ñ
TJ ü' ù7h@©÷k©ûª|Aø ñ
Tè# ùv@ùß ñK T Ò °uEù¹b ({{ø ë T{ ßëaÿÿT Ò!{{øàªB Rvc ` 5{ ßë!ÿÿT^ ü' ù:@©ú©7 @ù÷; ù¼
@ù] â Bp@ù7h@©tv@ù@¹ 1 T\ õÿ7{vø÷; ù×ôÿ´ü' ùv@ùß ñ T Ò ° Aù¼b {zø ë@ TZ ßëaÿÿT ҁ{zøàªB RKc 5Z ßë!ÿÿTA¿ @ µè A@ù @ù* RÈ Ð© K Rè«©È ÐU © ) è¯ ©é ùÁ Ð!¸ &¿ á
RÀ Ð | °c 8RòØÿ ÒD üÿ7è'@ùyzøú? ùüÿ´è#@ù ш ñJóÿTâ Bp@ùtv@ù@¹ 1£ T à ø7è'@ùy{ø ´âC ùü#@ù ¿ µâ Bp@ùù 9s@ù ñ* Ttv@ù@¹ 1B T ¹ °ÕGùa" °)a& @ù*u@ù+áEù)@ùù ùÿ+ ¹ë§©I Ré ¹ú+ © p ãªD RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàªý¿ ¨Zøé )y@ù)@ù?ë¡ Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ ùa Tàªè¿ À Ð | °c )
Râ=Rÿÿ¥ ¥ âCãÃàªá'@ùäªéa ø7÷kG©âC@ùtv@ù@¹ 1ÃöÿT¶ÿÿ¡
RÿÿÁ
Rÿÿa
RÿÿͿ ÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýCôªó ªè y@ù@ù¨ø !) è'©ÿ3 ùmAùÙ ð9s@ùõç©£ ´öª( ô ´ ñÀ T
ñ Tè' ù5@©õ©Ú
@ù Â ðBp@ùT ´ ñ T
ñ T"@ù5 @ùtv@ù@¹ 1 T| þ~Óè(*É °)y Ê °JU ñI±Ê ðJA@ù@@ùÊ °J© ðk+ë' ©êÓ©è ùÁ °!¸ _¾ ¡8
RÀ ° c >R+Øÿ Òz ûªzAøI ñ Té#© Ò %Eù×b èz|ø ë T _ ëaÿÿT Òáz|øàªB RPb ` 5 _ ë!ÿÿT è' ù5 @ùõ7 ùûªzAø ø7è'@ùy|ø¨ ´è7 ùõªú#@ù 7¾ µH ñ+ Tè# ùw@ùÿ ñk T Ò uEùÜb {{ø ëÀ T{ ÿëaÿÿT ҁ{{øàªB R&b 5{ ÿë!ÿÿT  ðBp@ùtv@ù@¹ 1c T à ø7è'@ùy{ø ´â; ùú#@ù
¾ @
µÂ ðBp@ù_ ñê Ttv@ù@¹ 1B T ¹ ÕGùa" )a&}Dù*áEù)@ùù ùÿ+ ¹ê§©ÿ ¹ê' ©` ð `ãª$ Råª' R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tઠ¿ ¨ZøÉ ð)y@ù)@ù?ë Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_ÖÈ ø7 ñ ùa Tàªë¾ À ° c ?
RbGRiÿÿ
ð¥+âCã£àªá'@ùäªì` ø7õF©tv@ù@¹ 1#÷ÿT¹ÿÿá5
RSÿÿ6
RQÿÿ5
ROÿÿѾ ÿÑüo©úg©ø_©öW ©ôO
©ý{ ©ýÃõªô ªÈ ðy@ù@ù )¡+è/ ùé©Ó ðsr@ùó+ ùC ´öª7 5 ´¿ ñÁ T" @ùâ+ ùÙ
@ùS 5 ´¿ ñá T" @ùv@ù¨@¹ 1#
TQ è5ªýÓÉ °)y Ê °JU ¿ ñI±Ê ðJA@ù@@ù JË °k© j±ê×©é£ ©¨ è ùÁ °!¸ l½ áL
RÀ ° À c "HR8×ÿ ÒI Ù
@ù: ñ« T Ò uEùÜb {{ø ëÀ T{ ?ëaÿÿT ҁ{{øàªB R_a 5{ ?ë!ÿÿT  ðBp@ùv@ù¨@¹ 1C T À ø7âz{ø ´â+ ùùª G½
µÂ ðBp@ù? ñj Tv@ù¨@¹ 1B T¨ ¹ ÕGù"ó ùÿ+ ¹óÏ©ÿ ¹óO ©` Р㪠Råªæª R ?֨@ùà ´ó ªÈ ø7 ñ¨ ùa Tàª>¾ è/@ùÉ ð)y@ù)@ù?ëA Tàªý{K©ôOJ©öWI©ø_H©úgG©üoF©ÿÀ_ÖÈ ø7 ñ¨ ùa Tàª)¾ À ° À c ÁS
RâLRÿÿ¥ ¥âãCàªáªäª*` à ø7â+@ùv@ù¨@¹ 1£÷ÿT½ÿÿ!K
RÿÿJ
Rÿÿ¾ ÿCÑüo©úg©ø_ ©öW
©ôO ©ý{ ©ýôªó ªÈ ðy@ù@ù )¡+¨øéÿ©Ü ðs@ùü+ ùC ´õª6 t ´ ñ T7 @ù÷+ ù¸
@ùP ñ T4 ´è4ªýÓÉ °)y Ê °JU ñI±Ê ðJA@ù@@ù JË °k© j±êÓ©é£ ©È °1 è ùÁ °!¸ ²¼ !a
RÀ ° c ¢MR~Öÿ Ұ ¸
@ù ñ T Ò uEùºb H{yø ë T9 ëaÿÿT ÒA{yøàªB R¥` à 59 ë!ÿÿT ÿ©ÿ ùÐ 7 @ù÷+ ùÿ©ÿ ùÿ ëA TÉ À ø7×zyø ´÷+ ù Ñ ¼ `m µ× ð÷r@ù ñê5 Tÿ©ÿ ùÿ ë 7 Tö ðÖ"9ÕÒDùÀ@ù¢@ù᪽ À] ´ô ª @¹ 1B T ¹ô ù åAù@ùI@ù¨] ´àª ?Öø ªà# ù ] ´@ùÈ ø7 ñ ùa Tàª|½ R,½ à ù@] ´ù ªè@¹ 1B Tè ¹7 ù9¼ à' ùà\ ´÷ ªÔÒDùÀ@ù@ùáªT½ À\ ´ö ª @¹ 1B TÈ ¹ ¡BùÈ@ùI@ùh\ ´àª ?Öõ ª`\ ´È@ù ø7 ñÈ ù T áAùàªâª ¼ à ø7¨@ùÈ ø7 ñ¨ ùa TàªH½ @ùA@ù\ ´À Ø!'½ \ 5àªáªâª?Öô ª#½ [ ´@ùÈ ø7 ñ ùa Tàª3½ ÿ# ù(@ùÈ ø7 ñ( ùa Tàª+½ ÿ ùè@ùÈ ø7 ñè ùa Tàª#½ @¹ 1B T ¹@ùÈ ø7 ñ ùa Tઽ ÿ' ùéª
@ù ÙGùyBù @ùé ù!@¹ ?Ö ñ« Tö ªèc! w " Ö ñ Tuv@ù ýAù»@ùàªá ª÷¼ ´ú ª@ù@ù ´àªáªâª ?Öú ªÀ µã H@¹ 1B TH ¹{v@ù ñAù|@ùà ªáªà¼ õ ª ´¨@ù @ù) ´àªáªâ ª ?Öõ ª ´¨@ù ©@¹) 1B T© ¹É ð)U@ù ëÁ T»@ùû ù ´¹
@ùh@¹ 1ã T(@¹ 1 T¨@ù(ø6
h ¹(@¹ 1BÿÿT( ¹¨@ùÈ ø7 ñ¨ ùa Tસ¼ õª" Rûÿ©ËàªNîÿü ªà' ù ´h@ùÈ ø7 ñh ùa Tન¼ ÿ ù¼ ´¨@ù ø7 ñ¨ ù Tà'@ù @ùhø7 ñ ù T¼ ઼ à'@ù @ùèþÿ6ÿ' ù» õ ªàª¨ ù઻ åFùH@ùA@ùù ´À Ø!i¼ ` 5àªáª Ò ?Öõ ªe¼ U ´H@ùÈ ø7 ñH ùa Tàªu¼ õ ´¨@ùíÿ7 ñ¨ ù!íÿTàªm¼ fÿÿ Ò Ҵÿÿàªáª Ò̻ õ ªèÿÿH» ` ´ ÒäÿÿÈ ð=@ù @ùÁ !T"E» øÿÿô@ù@¹ 1B T ¹÷ª. àªO¼ áAùàªâª» `ßÿ6 ÒØSR³
Rè@ùÈ ø7 ñè ùa Tàª?¼ Òà#@ùà ´ @ù¨ ø7 ñ ùA T6¼ à @ùà ´ @ù¨ ø7 ñ ùA T.¼ ´È@ùÈ ø7 ñÈ ùa Tàª&¼ ´¨@ùÈ ø7 ñ¨ ùa Tઠ¼ À ° c áªâªÇÔÿ ÒT µø È ð@ù @ùá ªøº Ò ÒxTR
Rô@ùÌÿÿÈ ð@ù @ùáªíº S
R Ӊ
RH@ùô@ùÈ ø7 ñH ùa Tàªù» ÒxTR¹ÿÿ ÒxTR
Rô@ù´ÿÿÅ °¥0 âcãCàªáªäªù] `2ø7÷+@ùÿ©ÿ ùÿ ë!ÉÿTtv@ù ýAù@ùàªáªֻ õ ª ´¨@ù@ù ´àªáªâª ?Öõ ªÀ µÔ ¨@¹ 1B T¨ ¹vv@ù ñAù×@ùàªáª¿» ´ô ª@ù @ùi ´àªáªâª ?Öà# ù ´ô ª@ùÉ Ð)U@ù ë T@ùö ùö ´
@ùÈ@¹ 1 Tè@¹ 1# T÷# ù@ùHø6 È ¹è@¹ 1"ÿÿTè ¹÷# ù@ùÈ ø7 ñ ùa T઻ " Rôªèc! öÿ©
Ëàª-íÿ÷ ªà' ù ´È@ùÈ ø7 ñÈ ùa T઻ ÿ ù× ´@ùÈ ø7 ñ ùa Tàª~» ÿ# ùè@ùÈ ø7 ñè ùa Tàªv» l» ø ª4@ù@ù? ñ$\úá T@ùhÿÿµ Ò Ò Ò
(@¹ 1B T( ¹6@ùÈ@¹ 1B TÈ ¹àªYº ô ª` O§ º ÿ' ù ´÷ ª7@ù @ù ùà ´ @ù¨ ø7 ñ ùA TM» ´È@ùÈ ø7 ñÈ ùa TàªE» ´@ùÈ ø7 ñ ùa Tàª=» ´è ðåFù¨@ùA@ùt ´ ð Ø!» 5àªáª Ҁ?Öô ª» t ´¨@ùÈ ø7 ñ¨ ùa Tàª%» Ô ´@ùÈ ø7 ñ ùa Tઠ» ¨ZøÉ Ð)y@ù)@ù?ë¡ Tàªý{L©ôOK©öWJ©ø_I©úgH©üoG©ÿCÀ_։@¹) 1B T ¹ô# ùÉ Ð)U@ù ë@êÿT Ò ÒlÿÿÈ Ð@ù @ùáªæ¹ Ò ÒxSRSj
R»þÿÈ Ð@ù @ùáªܹ ÿ# ùj
R m
R¨@ùÈ ø7 ñ¨ ùa Tàªèº Ò Ò ÒxSR¦þÿ ÒKÿÿÿÿ©À c ðc áo
RSRÓÿá#âãã àª` ÷'@ù`ø7è§C©é£©é£ ©÷ ù` Rº À ´è ªàªûªáª Ҟçÿú ª¨@ùÈ ø7 ñ¨ ùa Tઽº h@ùÈ ø7 ñh ùa Tશº Z ´õªÈ Ðu@ù_ë TÉ Ð)m@ù¿ ë T¿ ëà
Tàª0º ú ªU ¹ ` µàª´äÿô ªà ù`¢ÿµ Ò Òw ઺ ø ªà# ù ¢ÿµ Ò Ò ÒÓ~
RØSRà @ù Ëÿµbþÿ Ò Ò ÒØSR3
RLþÿ Ò Ò ÒØSRÓ
RFþÿh¹ à µàªäÿö ª`£ÿµ[ àªð¹ õ ªà£ÿµØSRS
R0þÿàªáª Òع ô ªDÿÿ Ò ÒxSRsz
R-þÿO¹ à ´ Ò;ÿÿàªáªâªɹ ô ªà¤ÿµ D¹ ` ´ Ò ÒØSRó
Rþÿsr
R! a_
Rüÿ¿ëú¨@ùÈ ø7 ñ¨ ùa TàªKº ø7Ú 4àª+Íÿÿ' ùà@ù(Íÿÿ# ùà@ù%Íÿ 7@ùáªâªãªò_ × Ð÷r@ùüÿÁ^
Rdüÿt
R 7@ùáªâªãªç_ Ò Ò ÒxSR÷¼ÿµîýÿ-º Ò Ò Òÿ ùØSR~
Ræýÿ Ò ÒØSR
RÙýÿór
Rçÿÿs
RåÿÿÈ Ð=@ù @ù¡ ð!T" ¹ ¬ÿÿÈ Ð=@ù @ù¡ ð!T"ù¸ °ÿÿ·¹ áªâB©¶äÿ 7@ùáªâªãª¹_ À c ðc u
RbSR.üÿÿÑüo
©úg ©ø_ ©öW
©ôO©ý{©ýÃôªø ªÈ Ðy@ù@ù¨øè ð a
¡é«© ¡ é£©Û Ð{s@ùÿÿ©ûï©ÍDùúG ù ´ ñh Tõª( è ùh ð±
it8)
ÖöªûªxAø ñ T Òè ðMCù¹b ({wø ëÀ T÷ ëaÿÿT Ò!{wøàªB R¬\ 5÷ ë!ÿÿT¢¸ ´!
R/ Ñ
ñh TÜ Мs@ùi ð)Ū +ih8J ö ª@ Ö: @ùúG ù<@ùüC ù6@ùö? ù9 @ùù; ùà È y É )U R ñ(±I¥Ê ÐJA@ù@@ùÊ J© k ðkj±êÓ©è§ © ð)<é ùÁ !¸ i¸ !¦
RÀ 8 c ðc âTR5Òÿ Ò÷ (hA©èk©÷ª9X@©ù[©¼
@ù ú# ù9X@©ù[©ûª|Aø ñ Töã©z@ù_ ñK T Òè ðuEù¶b Èzsø ë Ts _ëaÿÿT ÒÁzsøàªB RM\ @ 5s _ë!ÿÿT6 6 @©÷ªö£©9 @ùù; ùûª|Aø ñª TÛ Ð{s@ùüª ú# ù9 @ùù; ùûª|Aø ñË
Tè ù÷ªz@ù_ ñ T Òè ðuBù¶b Èzxø ëà T _ëaÿÿT ÒÁzxøàªB R \ 5 _ë!ÿÿT` ø7è @ùysø¨ ´üª÷ªèC ù
¸ Ë µ× Ð÷r@ùöãB©ú#@ù ñ«ùÿTèã©ú# ùøªz@ù_ ñ T Òè ðáAù¶b Èzsø ëà Ts _ëaÿÿT ÒÁzsøàªB Rö[ 5s _ë!ÿÿT `ø7è @ùysø ´èG ùúªöªÛ Ð{s@ùüãB© à· öªú#@ùÛ Ð{s@ùø@ù> µ ñüª« T
ð¥ <â#ãÃàªá @ùäªùZ Äø7ù[G©ükH©! åÿ7è @ùywøù; ùäÿ´ú# ùøª ñòÿTÜ Мs@ùö ª à ø7è @ùyxø ´ö? ùü@ù ¶· à µÖ ÐÖr@ùøª ñÊêÿTÜ Мs@ùú#@ùÛ Ð{s@ù(@¹ 1 TÈ@¹ 1# Tßë@ Tóª# ( ¹È@¹ 1"ÿÿTÈ ¹ßëÿÿT(@¹ 1B T( ¹h@ùè ø7 ñh ù TÀ Ð p@ù¨¸ è ðFùi@¹) 1b Ti ¹Fù(@ùÈ ø7 ñ( ùa Tસ öªè Ð IGùè#! ÿë©âA².êÿk ´õ ªú# ùè ð¹Bù@ùI@ùÈk ´àª ?Öú ªÀk ´Ô Дv@ù_ë× Ð÷n@ùDWúD[ú T_ëù સ ù ªsø7H@ù ø7 ñH ù@ Tè Ð!9Y 59Gù @ù"@ùáªU¸ ´ú ª @¹ 1B TH ¹è ðUFùH@ùI@ùȚ ´àª ?Öù ª ´ôªøªH@ùÈ ø7 ñH ùa TàªR¸ è ðéFù(@ùA@ù ´ ð Ø!/¸ 5àªáª Ò`?Öú ª+¸ Z ´(@ùÈ ø7 ñ( ùa Tàª;¸ H@ùóªÈ ø7 ñH ùa Tàª3¸ è ð¹Cù¨@ùI@ùH ´àª ?Öù ª@ ´(@ùÉ Ð)U@ù ëX T:@ùZ ´3 @ùH@¹ 1£ Th@¹ 1à T(@ùèø6 સ è Ð!9ù 5¥ÿÿH ¹h@¹ 1þÿTh ¹(@ù ø7 ñ( ù T÷ª" Rùªóªè#! úÿ©
Ëàªéÿû ªøª ´H@ùÈ ø7 ñH ùa Tàªõ· Ô Дv@ùû ´(@ùÈ ø7 ñ( ùa Tàªë· ¨@ùÈ ø7 ñ¨ ùa Tàªä· õªûª× Ð÷n@ùè Ð!9ÑDù @ù"@ùáªķ V ´ú ª @¹ 1B TH ¹è ðBùH@ùI@ùV ´àª ?Öù ªV ´H@ùÈ ø7 ñH ùa Tàª÷ àªáªB RM· U ´ú ª(@ù ø7 ñ( ùÀ T_ë T_ëÀ T_ë Tàª8· ù ª [ø7H@ùHø6 ઩· _ëAþÿT_ëùH@ù ø7 ñH ùà T9 4w@ùH@¹ 1B TH ¹è ÐÝGù àªáªâ ª# R Ræª ?Ö÷ ª [ µ ҔaR{
R ષ 9ýÿ5è °!9ÑDù @ùB@ùáªk· @
´ù ª @¹ 1B T( ¹è СBù(@ùI@ùH
´àª ?Öú ª@
´(@ùÈ ø7 ñ( ùa Tàªj· àªáªB Rô¶ ù ª ´H@ùÈ ø7 ñH ùa Tàª]· ?ë T?ë@ T?ë Tàªݶ ú ª ø7(@ùÈ ø6 ?ëú(@ù ø7 ñ( ù Tú 4w@ùH@¹ 1B TH ¹è ÐáGù àªáªâ ª# R Ræª ?Ö÷ ª P µÛDžRÔaRùªH@ù¨©ø6Q ÷ªàª.· &ÿÿàª+· züÿ5è °!9ÑDù @ù"@ù᪷ ` ´ú ª @¹ 1B TH ¹è ÐBùH@ùI@ù¨ ´àª ?Öù ª ´H@ùÈ ø7 ñH ùa Tàª
· àªáªB R¶ ´ú ª(@ùÈ ø7 ñ( ùa Tઠ· _ë T_ë@ T_ë Tશ ù ªàø7H@ùÈ ø6
_ëùH@ùÈ ø7 ñH ùa Tàªê¶ Ù 4w@ùH@¹ 1B TH ¹è ÐåGù àªáªâ ª# R Ræª ?Ö÷ ª@D µ ÒbR;ͅRå è °!9ÑDù @ùB@ù᪸¶ ´ù ª @¹ 1B T( ¹è Ð¥Bù(@ùI@ùè ´àª ?Öú ªà ´(@ùÈ ø7 ñ( ùa Tષ¶ àªáªB RA¶ ù ª ´H@ùÈ ø7 ñH ùa Tપ¶ ?ëÀ T?ë T?ë@ Tàª*¶ ú ª ø6 Ò4bRûЅR¹ µ» ?ëú(@ùÈ ø7 ñ( ùa Tશ 4w@ùH@¹ 1B TH ¹è ÐéGù àªáªâ ª# R Ræª ?Ö÷ ª@9 µ҅RTbRùªH@ùȒø6 è Ð õCù Ïÿ ´ú ªè Ð!Fù@ùI@ùè~ ´àª ?Öù ªà~ ´H@ùÈ ø7 ñH ùa Tàªe¶ àªáªB Rïµ à} ´ú ª(@ùÈ ø7 ñ( ùa TàªX¶ _ëÀ T_ë T_ë@ Tàªص ù ª ø6 Ò ÒtbR[օRZ _ëùH@ùÈ ø7 ñH ùa Tàª@¶ Ù 4w@ùH@¹ 1B TH ¹è ÐíGù àªáªâ ª# R Ræª ?Ö÷ ª / µ ҔbRûׅR; è Ð õCù¼Îÿ`w ´ù ªè Ð Fù@ùI@ù(w ´àª ?Öú ª w ´(@ùÈ ø7 ñ( ùa Tશ àªáªB Rµ ù ª@v ´H@ùÈ ø7 ñH ùa Tશ ?ëÀ T?ë T?ë@ Tવ ú ª ø6 ҴbR»ۅRy µ ?ëú(@ùÈ ø7 ñ( ùa Tàªðµ 4w@ùH@¹ 1B TH ¹è ÐñGù àªáªâ ª# R Ræª ?Ö÷ ª % µ[݅RÔbRùªH@ù~ø6ø è Ð õCùjÎÿ`o ´ú ªè ÐFù@ùI@ù(o ´àª ?Öù ª o ´H@ùÈ ø7 ñH ùa Tàªõ àªáªB RMµ n ´ú ª(@ùÈ ø7 ñ( ùa Tશµ _ëÀ T_ë T_ë@ Tàª6µ ù ª ø6 Ò ÒôbRá
R¸ _ëùH@ùÈ ø7 ñH ùa Tવ Ù 4w@ùH@¹ 1B TH ¹è ÐõGù àªáªâ ª# R Ræª ?Ö÷ ªÀ µ ÒcR»â
R è Ð õCùÎÿÀg ´ù ªè Ð%Fù@ùI@ùg ´àª ?Öú ªg ´(@ùÈ ø7 ñ( ùa Tàªsµ àªáªB Rý´ ù ª f ´H@ùÈ ø7 ñH ùa Tàªfµ ?ëÀ T?ë T?ë@ Tàªæ´ ú ª ø6 Ò4cR{æ
R9n µw ?ëú(@ùÈ ø7 ñ( ùa TàªNµ : 4w@ùH@¹ 1B TH ¹è ÐùGù àªáªâ ª# R Ræª ?Ö÷ ªÀ µè
RTcRùªH@ùHjø6V ð 8 c Ðc ᱅R"_RßÍÿ Ғ ડ´ ú ªÿµ Òb_Ra³
R¸
´ µàª3ßÿú ª ©ÿµ ÒbaRR® ઴ ù ª)ÿµ ÒtaR;R$ қRtaR(@ù(eø6- è Ð õCùÍÿ Z ´ú ªè ÐIAù@ùI@ùhZ ´àª ?Öù ª`Z ´H@ùÈ ø7 ñH ùa Tàªø´ àªáªB R´ `Y ´ú ª(@ùÈ ø7 ñ( ùa Tàªë´ _ë T_ëÀ T_ë Tàªk´ ù ª@ø6 Ò ÒtcRÛë
Rí Ò Òt_R»³
Rè Ò ÒtaRÛRã _ëùH@ùÈ ø7 ñH ùa Tàªɴ ÙT 4w@ùH@¹ 1B TH ¹è ÐýGù àªáªâ ª# R Ræª ?Ö÷ ª X ´H@ù ø7 ñH ù Tëà Tè@¹ 1B Tè ¹øª¨@ùÈ ø7 ñ¨ ùa Tત´ ´è@ùÈ ø7 ñè ùa T઴ ´h@ùÈ ø7 ñh ùa T઴ È@ùÈ ø7 ñÈ ùa T઴ ¨ZøÉ °)y@ù)@ù?ëH Tàªý{O©ôON©öWM©ø_L©úgK©üoJ©ÿÀ_Öàª|´ ëaùÿTú#@ùH@¹ 1B TH ¹Á °!@ùàªB Rþ³ ù ª& ´?ëÀ TÈ °m@ù?ë@ T?ë Tàªì³ ø ª ,ø7(@ùÈ ø6 ?ëø(@ù ø7 ñ( ù T 5Á °!P@ùàªB Rà³ ù ª`0 ´?ë@ TÈ °m@ù?ëÀ T?ë Tàªγ ø ª@5ø7(@ùHø6 àª?´ x 5çÿÿ?ëø(@ùÈ ø7 ñ( ùa Tàª4´ H@ùÈ ø7 ñH ùa Tàª-´ ¸ïÿ4è °!9ÑDù @ù@ù᪴ ´ù ª @¹ 1B T( ¹è ÐAù(@ùI@ù ´àª ?Öü ª ´(@ùÈ ø7 ñ( ùa T઴ @ùÉ °)U@ù ë T Ò Ré#)! øß©!M(Ë à ªåÿú ª ´@ùÈ ø7 ñ ùa Tàªø³ ú ´@ùÈ ø7 ñ ùa Tà ªð³ è ÐQEùH@ùI@ù( ´àª ?Öù ª ´H@ùÈ ø7 ñH ùa Tàªà³ è °1GùàªB Ri³ à ´ú ª(@ùÈ ø7 ñ( ùa Tàªҳ _ëÀ TÈ °m@ù_ë@ T_ë TàªP³ ø ª "ø7H@ùÈ ø6
_ëøH@ùÈ ø7 ñH ùa T઺³ Xáÿ4ú#@ùH@¹ 1B TH ¹H@ùÉ )U@ù ë` T Ò Ré#)! ùß©!M(Ë àªBåÿø ª ´(@ùÈ ø7 ñ( ùa Tળ ø ´H@ùÞÿ7 ñH ù¡ÝÿTળ êþÿy² µàª¢Ýÿú ª`eÿµ Ң_R!µ
R àªþ² ù ªeÿµ Ҵ_R{µ
R àªáª Òå² ú ª`gÿµ Ò۶
R´_Róª(@ù(2ø6 àªé² ù ª iÿµ ÒB`RA¸
R Ð 8 c °c N² óªà1 ´ Ò۶
R´_R(@ù/ø6 ÷ª Ò ÒXûÿ Òۺ
RT`R(@ùH.ø6v ;² µàªdÝÿù ªàzÿµ ҢaRAŅRßÿÿàª2 ú ª {ÿµ қŅR´aR(@ùÈ+ø6b ÷ª Ò;ûÿ ҴaRûŅRL dR»ó
RI ² µàªFÝÿù ªâÿµ"dRáö
RÂÿÿણ² ü ªÀâÿµ;÷
R4dR(@ùH(ø6F ùª@ùx* ´ @ù@¹ 1# Th@¹ 1C T@ùh ø6_ 4dRÛù
Rù ª@ùè%ø63 લ ù ª åÿµ4dR[ú
R 4dR»ú
R(@ùh$ø6' ҴaR;ƅR# µ" dRÛó
R b
RsùÿôªY@ù% ´è#@ù @ù(@¹ 1£ TH@¹ 1Ã Tè#@ù@ùèø6L TdRÛþ
RùªH@ù ø6 ͱ à µàªöÜÿú ª× ÷n@ùxÿµ ÒâaR¡ʅRoÿÿàªP² ù ª xÿµ ÒôaRûʅRå Ò[˅RôaR(@ùH ø6î dR»ô
RÜ ᡅR?ùÿa£
R=ùÿ ¹h@¹ 1õÿTh ¹@ùÈ ø7 ñ ùa Tà ª»² ( Rüªóª°þÿ Ò4dRûú
RÄ ¡
R'ùÿ( ¹H@¹ 1÷ÿTH ¹è#@ù@ùè ø7 ñé#@ù( ùa Tà#@ù£² ( Róªôþÿ Ò ÒôaR˅R¬ dRÛô
R© }± à µàª¦Üÿù ª× ÷n@ù@yÿµ Ò"bRЅR ÿÿઠ² ú ª`yÿµ Ò[ЅR4bR(@ùÈø6¢ Ò4bR»ЅR ÒbbRaՅR
ÿÿàªî± ù ª`ÿµ ÒtbR»ՅR ÒօRtbR(@ùø6 ҢbRÁڅRûþÿàªܱ ú ª ÿµ ÒۅR´bR(@ùHø6~ ҴbR{ۅRk ÒâbR!à
Réþÿàªʱ ù ª ÿµ ÒôbR{à
R_ ÒÛà
RôbR(@ù ø6h J² Ò"cRå
RÖþÿષ± ú ªÿµ ÒÛå
R4cR(@ù¨
ø6Y Ò4cR;æ
RF ÒbcRáê
RÄþÿથ± ù ªà¥ÿµ ÒtcR;ë
R: қë
RtcR(@ùèø6C øªóªè ° ¡@ù ë`
T¨@ù B9© 6É )a@ù ë Táªá± ù ª ´è ° ©Gùè#! ÿç©âA²§ãÿ ´ö ª(@ùÈ ø7 ñ( ùa Tલ àªßÿÈ@ùÈ ø7 ñÈ ùa Tàªù± ÒÂcRAñ
Röªóªþÿ ҔcR{í
RH@ùÈ ø7 ñH ùa Tàªé± ´(@ùÈ ø7 ñ( ùa Tàªá± Ð 8 c °c áªâªÊÿ Ò.ýÿÈ =@ù @ù¡ °!T"¾° lþÿ Rÿÿ Róªú#@ù þÿáª'± ù ªÀöÿµ ÒÂcRað
RÎÿÿ һð
RÔcRöªóª(@ùèúÿ6ÛÿÿÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýôªó ªÈ y@ù@ùè' ùè °aèÿ©C ´õª6 ´ ñ T @ùà ù¸
@ù: ñA T @ùà ùvW ô ª ± T º
@ùX ñ T Òè °
Cù»b h{yø ë T9 _ëaÿÿT Òa{yøàªB RpT @ 59 _ë!ÿÿTf° ` ´AR È A@ù @ùh °* RèÓ©¨ Ð Ð)ù)è« ©é ù¡ Ð!¸ J° ARr @ýÿ7Àzyøà ùàüÿ´ ñj+ T?W ô ª ± , T щ
ñ5±è °¡Dùh@ùI@ùH& ´àª ?Öö ª@& ´° ó ª@& ´¨þB ° ÷ ª & ´è °uEùàªâª° à
ø7è@ùÈ ø7 ñè ùa Tàª?± è !9ÑDù @ù¢@ùáª#± à# ´÷ ª @¹ 1B Tè ¹è ° Fùè@ùI@ù# ´àª ?Öõ ª# ´è@ù ø7 ñè ù Tè °áAùàªâªí¯ àø7¨@ùÈ ø7 ñ¨ ùa T઱ è °íFùÈ@ùA@ù÷% ´ ° Ø!ô° À& 5àªáªâªà?Öõ ªð° µ% ´È@ùÈ ø7 ñÈ ùa Tઠ± h@ùÈ ø7 ñh ùa Tàªù° è °Aù¨@ùI@ù$ ´àª ?Öó ª $ ´¨@ùÈ ø7 ñ¨ ùa Tàªé° h@ù× ÷V@ù ë!# Tv@ù¶# ´u
@ùÈ@¹ 1C T¨@¹ 1c Th@ùø6 ҔR È ¹¨@¹ 1âþÿT¨ ¹h@ùÈ ø7 ñh ùa Tàªɰ ( Róªéã )! ê °JFùö«©!M(Ë àªZâÿõ ª ´È@ùÈ ø7 ñÈ ùa Tવ° ´h@ùÈ ø7 ñh ùa Tર è °ùEù¨@ùI@ù¨ ´àª ?Öó ª¨@ù ´È ø7 ñ¨ ùa Tર h@ù ëa Tv@ùV ´u
@ùÈ@¹ 1ã T¨@¹ 1 Th@ù(ø6
È ¹¨@¹ 1BÿÿT¨ ¹h@ùÈ ø7 ñh ùa Tર " Róªèã ! öÿ©
Ëàªâÿõ ª ´È@ùÈ ø7 ñÈ ùa Tàªq° ´h@ùÈ ø7 ñh ùa Tàªi° àªáª Ò Ò R% R|V ¨@ù ´ó ª
ø7 ñ¨ ù!
TàªY° f àªV° è °áAùàªâª ¯ `æÿ6 Òt RØhRÈ@ùÈ ø7 ñÈ ùa TàªF° ´h@ùÈ ø7 ñh ùa Tàª>° ´è@ùÈ ø7 ñè ùa Tàª6° ´¨@ùÈ ø7 ñ¨ ùa Tàª.° Ð Ø c °c áªâª3 ય ö ª ÚÿµÔRØhRóÿÿ Ò ÒRÏÿÿ ÒTRÌÿÿþ® @ µàª'Úÿ÷ ª@Üÿµn ય õ ªÀÜÿµ RøhR¿ÿÿ
Хø)âã ãà àªáªäªR @ ø7à@ùÛU ô ª ±¡ÓÿTâ® `Óÿ´ÁR Ð Ø c °c ¢dR¤Èÿ Òè'@ùÉ )y@ù)@ù?ëá Tàªý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_ÖàªáªâªG¯ õ ª Ûÿµ Ҵ Rÿÿ. ´ Ò Ҵ RÿÿàªI¯ ó ª@Üÿµ4 RøhR¨@ùhóÿ6ÿÿ Ò Rÿÿ ÒÔ!R Rþþÿàª8¯ ó ª¨@ù ãÿµT"Rhø7øhR ñ¨ ùñÿTÿÿ Ò Ò6ÿÿ Òô$RøhRh@ùÈíÿ6rÿÿ Ò.ÿÿt%Rèýÿ6øhR|ÿÿáR®ÿÿ©¯ Ò ÒÔRøhRUÿÿ¨ ð=@ù @ù¡ !T"® ÂÿÿÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýôªó ª¨ ðy@ù@ù¨øè ! %è'© á!é#©ÿ3 ù¨ ðq@ùÿ£©© ð)u@ù飩㠴 ñ Tõª( è ùh Õ
it8)
ÖúªVAøÛ ñ T Òè Å@ù¹b ({xø ë T ßëaÿÿT Ò!{xøàªB RJR à
5 ßë!ÿÿT@® À ´a3R- Ñ
ñ( T¹ ð9w@ù¤ ðp@ùi )éª +ih8J øª@ Ö$ @ù9@ù8@ù7 @ùÀ ¨ °y © °)U R ñ(±I¥ª ðJA@ù@@ùª °J© k kj±êÓ©è§ © °)4é ù¡ °!¸ ® a9R ° ì c c "iRÕÇÿ Ҥ 7 @ù÷7 ùúª[Aø 7`@©÷ã©úª[AøB 8ä@©øg©7 @ù÷7 ùúª[Aøh ñê T¤ ðp@ù 9A©ù©7`@©÷ã©»
@ù õÿ7è @ùyxø÷7 ù7õÿ´h ñ+ Tè ùV@ùß ñK T Òè uEù¹b ({|ø ë T ß ëaÿÿT Ò!{|øàªB RÙQ ` 5 ß ë!ÿÿT ¹ ð9w@ù¤ ðp@ùøª_ à ø7è @ùy|ø ´ø; ùû@ù m ` µ¸ ðs@ùh ñ+ TèÏ©\@ù ñ+ T Òè Eù³b hzvø ë TÖ ëaÿÿT ÒazvøàªB R®Q @ 5Ö ë!ÿÿT
¹ ð9w@ù¤ ðp@ù5 à ø7è @ùyvø ´ù? ùû@ù µ¹ ð9w@ùó@ùh ñkóÿTèÏ©\@ù ñ T Òè %Dù³b hzvø ëà TÖ ëaÿÿT ÒazvøàªB RQ 5Ö ë!ÿÿT à ø7è @ùyvø ´äC ùû@ù q µ¤ ðp@ùó@ù ñ TàªáªâªãªU ¨Zø© ð)y@ù)@ù?ë¡ Tý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_օ °¥4âã£àªá @ùäªzP ø7÷ãF©ùG©âÿÿ6R:ÿÿ!5R8ÿÿ¡6R6ÿÿA4R4ÿÿ`® ÿÑë+
mé# müo ©úg
©ø_©öW©ôO©ý{©ýCóªõ ª¨ ðy@ù@ù¨øè ¡ Á飩 éÿ©Dù DùøÛ©· ð÷r@ù÷G ù_ ñ ´h Tôª( è+ ùh ù
is8)
ÖûªzAø\ ñ Tõ' ù Òè MCùb ({uø ë Tµ _ëaÿÿT Ò!{uøàªB R Q ` 5µ _ë!ÿÿTJ T» ð{s@ùh
is8)
Ö;@ùûG ù6@ùöC ù8 @ùø? ù h R ñ賈© °)y ª °JU I±ª ðJA@ù@@ùª °J© êÏ©é£ © Ðá+è ù¡ °!¸ Ԭ ZR ° °!c c BR Æÿ ҋ 8 @ùø? ùûªzAø 8X@©øÛ©ûªzAø@ 6ì@©öo©8 @ùø? ù
@ùf `ø7è+@ùyuø ´è? ùøªú ªõ'@ù· ð÷r@ù ¸¬ õ'@ù· ð÷r@ù µH ñk TèW©y@ù? ñë T Òè uBùb {uø ëà Tµ ?ëaÿÿT ҁ{uøàªB R¤P 5µ ?ë!ÿÿT @ø7è+@ùyuøè ´èC ùöªúWD©· ð÷r@ù ¬ õ'@ù· ð÷r@ù@{ µH ñK Tè' ùüªy@ù? ñë T Òè uEùb h{uø ë@ Tµ ?ëaÿÿT Òa{uøàªB RzP 5µ ?ë!ÿÿT » ð{s@ù à ø7è+@ùyuø ´ûG ùú'@ù e¬ àu µ» ð{s@ùõ ª· ð÷r@ù_ ñÊa Tü ÛGùAùµ@ùR ?Öá ªàª R R R Ò`?ÖàB ´ó ª @¹ 1B Th ¹h@ùÈ ø7 ñh ùa Tàª] ÛGùAùµ@ùR ?Öá ªàª R R R Ҁ?Öô ª@ ´@¹ 1B T ¹@ù ø7 ñ ù@" T@¹i@¹(*" 4û+ ùÛ ð{#9vÓDù`@ùÂ@ùáª% `> ´ú ª @¹ 1B TH ¹è ÝEùH@ùI@ù> ´àª ?Öù ª> ´H@ùÈ ø7 ñH ùa Tàª$ (@ù· ð÷V@ù ëÀ= T R Òéc)! øÓ©ó7 ù!M(Ë 2઱Þÿö ª ´@ùÈ ø7 ñ ùa Tઠö< ´(@ùÈ ø7 ñ( ùa TઠÈ@¹ 1B TÈ ¹ÛGùAùઠ?Öø ª`; ´@¹ 1B T ¹@ùÈ ø7 ñ ùa Tàªï¬ zÓDù`@ùB@ùáªլ 9 ´ù ª @¹ 1B T( ¹è å@ù(@ùI@ù9 ´àª ?Öú ª(@ù9 ´È ø7 ñ( ùa TàªԬ yÓDù`@ù"@ù᪺¬ 9 ´ü ª @¹ 1B T ¹è ±Bù@ùI@ù¨9 ´à ª ?Öû ª 9 ´@ùÈ ø7 ñ ùa Tà ª¹¬ h@ù ëà8 T R Òéc)! ùã©!M(Ë àªIÞÿü ª ´(@ùÈ ø7 ñ( ùa Tત¬ <8 ´h@ùÈ ø7 ñh ùa Tબ H@ù ë@7 T R Òéc)! ûó©!M(Ë àª,Þÿù ª· ð÷r@ù ´h@ùÈ ø7 ñh ùa Tàª
¬ @ùÈ ø7 ñ ùa Tà ª~¬ û+@ùY5 ´H@ùÈ ø7 ñH ùa Tàªu¬ ¨ ðu@ù?ëÀ T© ð)m@ù? ë@ T?ë Tàªñ« ú ª@Eø7(@ùÈ ø6
?ëú(@ùÈ ø7 ñ( ùa Tàª[¬ 1 4¹v@ù(@¹ 1B T( ¹è ÕGù¡ é )a&@ù)áEù÷ ùÿ+ ¹é©ÿ ¹ø © ð âªãªD Råª R ?Ö 0 ´õ ª(@ùhø7 ñ( ù Tàª8¬ h@ùÈø6º àª3¬ @¹i@¹(*ÈÝÿ5àª.« @`
~ j a T« @ µàª&« @` j a T« à? µ)9h È ð!9ÑDù @ùÂ@ù᪬ `+ ´ú ª @¹ 1B TH ¹è ±BùH@ùI@ù+ ´àª ?Öù ª+ ´H@ùÈ ø7 ñH ùa Tબ A` « ö ªà* ´(@ù© ð)U@ù ëà* T Ò Réc)! øÛ©!M(Ë àªÝÿü ª ´@ùÈ ø7 ñ ùa Tàªç« È@ùÈ ø7 ñÈ ùa Tàªà« |) ´(@ùÈ ø7 ñ( ùa Tàªث ¨ ðu@ùëÀ T© ð)m@ù ë@ Të Tà ªT« ö ªÀ5ø7@ùÈ ø6
ëö@ùÈ ø7 ñ ùa Tà ª¾« ö% 4¼v@ù@¹ 1B T ¹ A` ºª ù ª`' ´ A` ¶ª ú ª ' ´È ðÕGù¡ É ð)a&@ù)áEù÷ ùÿ+ ¹é©ÿ ¹ú © Ð âªã ªD Råª R ?֠% ´õ ª@ùÈ ø7 ñ ùa Tà ª« (@ùÈ ø7 ñ( ùa Tફ H@ùÈ ø7 ñH ùa Tàª
« Ò Òh@ùÈ ø7 ñh ùa Tàª|« ´@ùÈ ø7 ñ ùa Tàªt« ´@ùÈ ø7 ñ ùa Tàªl« ´È@ùÈ ø7 ñÈ ùa Tàªd« ¨Xø© Ð)y@ù)@ù?ëá2 Tàªý{Q©ôOP©öWO©ø_N©úgM©üoL©é#Kmë+JmÿÀ_֠ °!C ðc !cRR\ýÿ Ò ÒeR·Rm ,ª µàªUÕÿú ªÀÁÿµ Ò ÒU{RRb રª ù ªÀÁÿµ Ò Ò җ{RR% öª8@ù8- ´5 @ù@¹ 1à T¨@¹ 1ã T(@ùø6Ô Ò ҕR7~R RRC ª µàª+Õÿù ªÆÿµõR7R: પ ú ª(@ùÀÆÿµÈ ø7 ñ( ùa Tઠ« °!C ðc !R"R. ç© µàªÕÿü ªÆÿµ Ò җR( à ªlª û ª Æÿµ Ò5R׃RÚ üªy@ù9% ´u @ù(@¹ 1 T¨@¹ 1£ Th@ùÈø6¢ ÒwR ÷ª[@ù{# ´U @ùh@¹ 1 T¨@¹ 1# TH@ùHø6¦ ÒWR5RÂ È ð ¹GùÈ ð%Gù Ң×ÿ ! ´ù ªÔ×ÿ(@ùhø7ՋRWRB ÒuRwR¸ ¢© µàªËÔÿú ªÀÔÿµ Ò ÒUlRwRØ àª&ª ù ªÀÔÿµ Ò Ò җlRuR Ò ÒuR÷lR úª÷ª8@ùX ´5 @ù@¹ 1 T¨@¹ 1£ T(@ùÈø6² Ò Ò ÒuRoR È ð ¹GùÈ ð%Gù Òb×ÿ ´ù ª×ÿ(@ùÈø7 Ò ÒrRR ñ( ùa Tàª{ª Ò Ò ÒõR·uR^ Ò ÒR÷vRY Ò ÒՐR7xRT
°¥à+âcããàªá+@ùäªrL ø7øÛG©ûG@ùèüÿ ¹¨@¹ 1bæÿT¨ ¹(@ùÈ ø7 ñ( ùa TàªRª ( Rùªõª2ýÿ( ¹¨@¹ 1¢ìÿT¨ ¹h@ùÈ ø7 ñh ùa TàªBª ( Rûªõ ªýÿ ÒR5R4 h ¹¨@¹ 1"ìÿT¨ ¹H@ùÈ ø7 ñH ùa Tàª.ª ( RúªõªýÿՋRWRM Ò ҵhRRH Ò ÒõiR7RC Ò Ò Ò ÒuRpR@ùÈ ø7 ñ ùa Tà ªª Ò ´H@ùÈ ø7 ñH ùa Tપ ´(@ùÈ ø7 ñ( ùa Tàªÿ© ´h@ùÈ ø7 ñh ùa Tàª÷© °!C ðc áªâª ¹¨@¹ 1¢êÿT¨ ¹(@ùÈ ø7 ñ( ùa Tàªä© ( Rùªõª÷ªéýÿ Ò ÒrRR °!C ðc áªâªÂÿ Òh@ù(Êÿ6UþÿaWRÙûÿXR×ûÿVRÕûÿ¡URÓûÿʩ Rvÿÿ Rÿÿ RÿÿURWRäÿÿ RÛÿÿ Ò ҕqRÝÿÿÿÑø_©öW©ôO©ý{©ýCóªô ª¨ Ðy@ù@ùè ù µh@¹ 1B Th ¹h
@ù¨ ´ ±@ TÈ ðÍDù@ùI@ù ´àª ?Öõ ª ´a¨ ô ªà ´È ðuEùàªâª`¨ À ø7È Ð1Gù¨@ùA@ù ´ ð Ø!n© 5àªáªâªà?Öö ªj© ´¨@ùèø7 ñ¨ ù Tàªz© 9 È ðÍDù@ùI@ù¨ ´àª ?Öô ª ´@ù© Ð)U@ù ë¡ T@ùu ´
@ù¨@¹ 1ã TÈ@¹ 1 T@ù(ø6
¨ ¹È@¹ 1BÿÿTÈ ¹@ùÈ ø7 ñ ùa TàªS© " Rôªè# ! õÿ ©
ËàªçÚÿö ª ´¨@ùÈ ø7 ñ¨ ùa TàªB© Ö ´@ùÈ ø7 ñ ùa Tàª:© h@ùø7 ñh ù¡ Tàª3© è@ù© Ð)y@ù)@ù?ë` T: v¢R¨@ùÈ ø7 ñ¨ ùa Tàª$© uR ´@ùÈ ø7 ñ ùa T઩ P"C ðc áªâªÄÁÿ Òh@ùHûÿ6è@ù© Ð)y@ù)@ù?ë! Tàªý{E©ôOD©öWC©ø_B©ÿÀ_Öõªàªէ Àêÿ´ Ð!|$ઠRÖJ êÿ5 Òè@ù© Ð)y@ù)@ù?ë ýÿTõ¨ ¶RRÕÿÿàªc¨ õ ª@êÿµö¡RuRÎÿÿàª\¨ ô ª îÿµ6R5RÇÿÿ6¢Rµÿÿ Ò Ҍÿÿ¶R5R@ù(÷ÿ6½ÿÿ ҅ÿÿàªáªâª8¨ ö ªàéÿµ ³§ ` ´¢R ÿÿ¨ Ð=@ù @ù ð!T"°§ øÿÿÿÑø_©öW©ôO©ý{©ýCóªô ª¨ Ðy@ù@ùè ù µh@¹ 1B Th ¹h
@ù¨ ´ ±@ TÈ ðEù@ùI@ù ´àª ?Öõ ª ´l§ ô ªà ´È ðuEùàªâªk§ À ø7È Ð1Gù¨@ùA@ù ´ ð Ø!y¨ 5àªáªâªà?Öö ªu¨ ´¨@ùèø7 ñ¨ ù Tàª
¨ 9 È ðEù@ùI@ù¨ ´àª ?Öô ª ´@ù© Ð)U@ù ë¡ T@ùu ´
@ù¨@¹ 1ã TÈ@¹ 1 T@ù(ø6
¨ ¹È@¹ 1BÿÿTÈ ¹@ùÈ ø7 ñ ùa Tàª^¨ " Rôªè# ! õÿ ©
ËàªòÙÿö ª ´¨@ùÈ ø7 ñ¨ ùa TàªM¨ Ö ´@ùÈ ø7 ñ ùa TàªE¨ h@ùø7 ñh ù¡ Tàª>¨ è@ù© Ð)y@ù)@ù?ë` T: µR¨@ùÈ ø7 ñ¨ ùa Tàª/¨ õ R ´@ùÈ ø7 ñ ùa Tàª&¨ ä"C ðc áªâªÏÀÿ Òh@ùHûÿ6è@ù© Ð)y@ù)@ù?ë! Tàªý{E©ôOD©öWC©ø_B©ÿÀ_Öõªàªà¦ Àêÿ´ Ð!T6ઠRáI êÿ5 Òè@ù© Ð)y@ù)@ù?ë ýÿT ¨ VR RÕÿÿàªn§ õ ª@êÿµ´Rõ RÎÿÿàªg§ ô ª îÿµ֮Rµ RÇÿÿִRµÿÿ Ò ҌÿÿV±Rµ R@ù(÷ÿ6½ÿÿ ҅ÿÿàªáªâªC§ ö ªàéÿµ ¾¦ ` ´6µR ÿÿ¨ Ð=@ù @ù ð!T"»¦ øÿÿÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýC÷ªü ª¨ Ðy@ù@ùÉ ð)¡¨ø(Áè'©(詺 °Zs@ùÿk©ú; ùã ´ÿ ñH Tøª( è ùH Ð
iw8)
ÖöªÕAø» ñ T ÒÈ ÐMCùc ({tø ëà T ¿ëaÿÿT Ò!{tøàªB RJ 5 ¿ë!ÿÿTx¦ ´GR' ¶ °Ör@ùÿ ñ
Tÿ
ñ Tÿ ñÁ T6@ùö; ù3@ùó7 ùL ðy ð)U j Rÿ ñ(±I¥ª °JA@ù@@ù ðJ© K Ðkj±êß©è§ © Ð)
é ù ð!¸ G¦ AƇR ð |#C Ðc "¡RÀÿ Òj 4 @ùô3 ùöªÛAøH 4L@©ôO©öªÛAøh ñË
Tèó©Ù@ù? ñË T ÒÈ ÐuEù c {uø ë Tµ ?ëaÿÿT ҁ{uøàªB R.J à 5µ ?ë!ÿÿT 3Ø@©óÛ©4 @ùô3 ù @ù óª4 @ùô3 ùN à ø7è @ùyuø ´ö; ùû@ù ¦ À^ µ¶ °Ör@ùü@ù ñ T
Х âãàªá @ùäª.I `^ø7ôOF©ö;@ù4 àðÿ7è @ùytøô3 ùtðÿ´h ñ+ Tèó©Ù@ù? ñ T ÒÈ ÐuBù c {uø ë` Tµ ?ëaÿÿT ҁ{uøàªB RëI 5µ ?ë!ÿÿT ¶ °Ör@ùóª à ø7è @ùyuø ´ó7 ùû@ù ե Z µ³ °sr@ùü@ùh ñòÿT¶ °Ör@ù@¹ 1B T ¹h@¹ 1B Th ¹È °!99Gù @ùâ@ùáªæ ø ªë` T> ´@¹ 1B T ¹È ÐUFù@ùI@ù> ´àª ?Ö÷ ª > ´@ùÈ ø7 ñ ùa Tàª& È ÐÁ @ùAù@ùI@ùè< ´ ?Öù ªà< ´}¥ ú ªà< ´È ÐMCùàªâª|¥ ø7È ÐuBùàªâªv¥ ø7È °1Gù(@ùA@ùÕD ´ Ð Ø!¦ `E 5àªáªâª ?Öø ª¦ XD ´(@ùÈ ø7 ñ( ùa Tદ H@ùÈ ø7 ñH ùa Tદ è@ù© °)U@ù ëB T Ò Ré)! ùc©Ê ÐJµGùê+ ù!M(Ë 2àªØÿú ª ´(@ùÈ ø7 ñ( ùa Tàªo¦ @ùÈ ø7 ñ ùa Tàªh¦ z@ ´è@ù ø7 ñè ù TH@ùhø7ûª ñH ù T 85 ´@¹ 1B T ¹È ÐUFù@ùI@ùè5 ´àª ?Öù ªà5 ´@ùÈ ø7 ñ ùa TàªF¦ È Ð¡ @ùAù@ùI@ù5 ´ ?Öø ª 5 ´¥ ú ª5 ´È ÐMCùàªâª¥ ³ °sr@ù@ø7È °1Gù@ùA@ùu9 ´ Ð Ø!¦ : 5àªáªâª ?Ö÷ ª
¦ ÷8 ´@ùÈ ø7 ñ ùa Tદ H@ùÈ ø7 ñH ùa Tદ (@ù© °)U@ù ë7 T Ò Ré)! ø_©Ê ÐJµGùê+ ù!M(Ë 2àª×ÿú ª ´@ùÈ ø7 ñ ùa Tàªù¥ è@ùÈ ø7 ñè ùa Tàªò¥ z5 ´(@ùÈ ø7 ñ( ùa Tàªê¥ H@ùÈ ø7 ñH ùa Tàªã¥ @¹ 1B T ¹h@ùè ø7 ñh ù T ° p@ùץ È Ð¡Fùi@¹) 1b Ti ¹¡Fù@ùhø7úªóª ñ ù¡ Tàªǥ v¬RµۇR v¬RÕۇR ÒЇRv«R óª સ¥ H@ùèêÿ6ûªÈ СDù@ùI@ùè ´à ª ?Öô ªà ´h@ùµ °µR@ù ë Tàªý¤ ÷ ª# ´è@ùÉ Ð8¡Fù ëA# Tè
@ùÈ
7 = ñ Té@¹@(¥ Ƥ ø ª ´è@ùÈ ø7 ñè ùa Tથ @ R<¥ ÷ ª ´h@¹ 1B Th ¹ûâ©J¤ ø ª ´È ÐuEùàªâªI¤ ø7È Ð@ùý@ùàªB¤ ø7@ùA@ù& ´ Ð Ø!R¥ & 5àªáªâª ?Öõ ªN¥ % ´@ùÈ ø7 ñ ùa Tàª^¥ è@ùÈ ø7 ñè ùa TàªW¥ @ù ø7 ñ ù@
TôªK h@¹ 1B Th ¹È СFù÷ªh
@ùõ6@¹ 1BöÿT ¹°ÿÿõãR äR@ùÈ ø7 ñ ùa Tàª8¥ ֬R ´ Ò Òôª@ùÈ ø7 ñ ùa Tàª,¥ ´(@ùÈ ø7 ñ( ùa Tàª$¥ Z ´H@ùø7 ñH ù¡ Tઠ¥ ôªûª7 ´è@ùÈ ø7 ñè ùa Tથ ûª ð |#C Ðc áªâª¹½ÿ Òôª ´@ùÈ ø7 ñ ùa Tàªÿ¤ h@ùÈ ø7 ñh ùa Tàªø¤ ¨Zø© °)y@ù)@ù?ë Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_Öàªç¤ ôªàÿÿʣ µàªóÎÿø ª Âÿµ"¬RهR3 àªP¤ ÷ ª@Âÿµ Ò6¬RÕهRùª©ÿÿH¤ ù ª`Ãÿµv¬R5ۇR¶ÿÿv¬RuۇR ÿÿà ª>¤ ô ª`ãÿµ֬RÕáR´ÿÿUâRÿÿµâRÿÿ @ýCÓ¡ ñà T ± Té"C)(yªèË ÿÿµãRtÿÿ£ µàªÀÎÿø ªàÊÿµB«Rá͇R ð |#C Ðc U½ÿ Ҟÿÿત ù ª`Êÿµ Ò ҳ °sr@ù5·RV«Rfÿÿ
¤ ø ª@Ëÿµ Ò Òv«RχR³ °sr@ùdÿÿ ҳ °sr@ùÕχRv«RVÿÿ ÒâRGÿÿ© °)I@ù ë Tàªáªʣ éþÿàªáªâªà£ ø ª ¼ÿµ [£ ` ´v¬RõۇRGÿÿù@ù¹½ÿ´õ
@ù(@¹ 1c T¨@¹ 1 Tè@ù¨ø6I 6¬RÕ߇RKÿÿàªáªâªţ ÷ ªÇÿµ @£ à ´ ҳ °sr@ù5ЇRv«R!ÿÿ8@ù¸Èÿ´5 @ù@¹ 1à T¨@¹ 1ã T(@ùø6< ÒV«RԇR³ °sr@ùÿÿàªáªâª¤£ õ ªàÚÿµ £ ´5äRøþÿAÇRÌüÿé"C)(yªþÿ¨2@ù@ùàªáª ?֗þÿáÇRÁüÿ( ¹¨@¹ 1Â÷ÿT¨ ¹è@ùÈ ø7 ñè ùa Tઠ¤ ( R÷ªýÿaR°üÿ ¹¨@¹ 1bùÿT¨ ¹(@ùÈ ø7 ñ( ùa Tઠ¤ ( Rùªþýÿà
@ý( Rb (a £ oþÿ¤ ¨ °=@ù @ù Ð!T"è¢ ÿÿ¨ °=@ù @ù Ð!T"ᢠÿÿ¨ °=@ù @ù Ð!T"ڢ ¶ÿÿÿÑüo©úg©ø_©öW ©ôO
©ý{ ©ýÃõªô ª¨ °y@ù@ùÉ Ð)¡+è/ ù驳 °sr@ùó+ ùC ´öª7 5 ´¿ ñÁ T" @ùâ+ ùÙ
@ùS 5 ´¿ ñá T" @ùv@ù¨@¹ 1#
TQ è5ªýӉ ð)y ðJU ¿ ñI±ª °JA@ù@@ùJ °J Ðk© j±ê×©é£ © Ðè ù Ð!¸ ¢ aòR Ð <$C °c "RW¼ÿ ÒI Ù
@ù: ñ« T ÒÈ °uEùÜb {{ø ëÀ T{ ?ëaÿÿT ҁ{{øàªB R~F 5{ ?ë!ÿÿT ¢ Bp@ùv@ù¨@¹ 1C T À ø7âz{ø ´â+ ùùª f¢
µ¢ Bp@ù? ñj Tv@ù¨@¹ 1B T¨ ¹È °ÕGù"ó ùÿ+ ¹óÏ©ÿ ¹óO © ð @㪠Råªæª R ?֨@ùà ´ó ªÈ ø7 ñ¨ ùa Tàª]£ è/@ù© )y@ù)@ù?ëA Tàªý{K©ôOJ©öWI©ø_H©úgG©üoF©ÿÀ_ÖÈ ø7 ñ¨ ùa TàªH£ Ð <$C °c AùRµRÿÿ
ХâãCàªáªäªIE à ø7â+@ùv@ù¨@¹ 1£÷ÿT½ÿÿ¡ðRÿÿðRÿÿ0£ ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýõªó ª¨ y@ù@ù¨øÈ °Á aè'© áé©uCùyCùôk©· ÷r@ù÷C ù_ ñ ´ Töª( è' ùH °)
iu8)
ÖüªAøi ñ«
T ÒÈ °CùÙb é# ù({wø ë
T÷ ëaÿÿT Ò!{wøàªB RÞE ` 5÷ ë!ÿÿTO ( T¢ Bp@ùH °9
iu8)
Ö"@ù:@ù4 @ùuv@ù¨@¹ 1à T h R¿ ñ賈 Ð)y ÐJU I±ª JA@ù@@ù ÐJ© ê×©é£ © ÐÁ)è ù Ð!¸ ¥¡ !
R Ð ü$C °c µRq»ÿ Ҟ 4 @ùô; ùüªAø 4h@©ôk©üªAø= :@©ú©4 @ùô; ùÛ
@ùi ¢ Bp@ùuv@ù¨@¹ 1#
Ti ø7è'@ùywø¨ ´è; ùôªû#@ù
¡ à µh ñë TèÏ©@ù? ñ« T ÒÈ °%EùÓb hzwø ëà T÷ ?ëaÿÿT ÒazwøàªB RtE 5÷ ?ë!ÿÿT ø7è'@ùywø¨ ´è? ùúªûÏC© a¡ ó#@ù µh ñK Tè# ù÷ª@ù? ñ« T ÒÈ °uEùÓb hz|ø ë T ? ëaÿÿT Òaz|øàªB RNE À 5 ? ë!ÿÿT ¢ Bp@ù· ÷r@ùuv@ù¨@¹ 1à T à ø7è'@ùy|ø ´âC ùû#@ù 3¡ à
µ¢ Bp@ùóª· ÷r@ù ñ
Tuv@ù¨@¹ 1B T¨ ¹È °ÕGùa"É °)a&@ù*}Dù)áEù÷ ùÿ+ ¹é©) Ré ¹ú+ © ð /ãªD Råª R ?֨@ùà ´ó ªÈ ø7 ñ¨ ùa Tàª"¢ ¨Zø© )y@ù)@ù?ëá Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ¨ ùa Tàª
¢ Ð ü$C °c R¢REÿÿ
ХÀ)âCãÃàªá'@ùäªD @ø7ôkG©âC@ùuv@ù¨@¹ 1ãöÿT·ÿÿR.ÿÿ¡R,ÿÿ!R*ÿÿAR(ÿÿð¡ ÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýCôªó ª¨ y@ù@ù¨øÈ °* !è'©ÿ3 ù¹ 9s@ùÿç©Ã ´õª( 4 ´ ñ T
ñ! T7@©÷©º
@ù_ ñë TÄ ñ T
ñá T"@ùF è' ùøª Aø ñ T ÒÈ °QEù¶b Èz{ø ë T{ ëaÿÿT ÒÁz{øàªB RD à 5{ ë!ÿÿT ` ´ R Ðy Ð)U * R ñ(±Iµª JA@ù@@ù ÐJ© K °kj±êÓ©è§ © ð)%)é ù Ð!¸ l R Ð %C °c bÀR8ºÿ Òe è' ù7 @ù÷7 ùøªAø ¢ Bp@ù7 @ùtv@ù@¹ 1C T: ùÿ7è'@ùy{ø÷7 ù7ùÿ´H ñ+ Tè# ù@ù ñk T ÒÈ °uEù¶b Èz|ø ëÀ T ëaÿÿT ÒÁz|øàªB RID 5 ë!ÿÿT ¢ Bp@ùtv@ù@¹ 1 T à ø7è'@ùy|ø ´â; ùú#@ù 0
µ¢ Bp@ùè'@ù_ ñê Ttv@ù@¹ 1B T ¹È °ÕGùa"É °)a&©Dù*áEù)@ùù ùÿ+ ¹ê§©ÿ ¹ê' © ð `ãª$ Råª' R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàª"¡ ¨Zø© )y@ù)@ù?ëA Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_ÖÈ ø7 ñ ùa Tàª
¡ Ð %C °c á&RầR~ÿÿ
ð¥$)âCã£àªáªäªC à ø7÷F©tv@ù@¹ 1#÷ÿT¹ÿÿ Rhÿÿa Rfÿÿõ ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýôªó ª¨ y@ù@ù¨øÈ °!) aé#© é©mAùÿk©» {s@ùûC ù ´ ñÈ Tõª( è' ùH °I
it8)
ÖüªAø ñè# ù T ÒÈ °QEù¹b ({vø ë
TÖ ëaÿÿT Ò!{vøàªB R¤C ` 5Ö ë!ÿÿT ` ´á2R* ¢ Bp@ù ñà T
ñ T ñ! T"@ù:@ù7 @ùtv@ù@¹ 1C T Ðy Ð)U j R ñ(±I¥ª JA@ù@@ù ÐJ© K °kj±êÓ©è§ ©© )Ýé ù Ð!¸ f ¡7R Ð T&C °c ¢̀R2¹ÿ Ҙ 7 @ù÷; ùüªAø ñª TV 7h@©÷k©üªAø6 :@©ú©7 @ù÷; ù¨
@ù` ÷ÿ7è'@ùyvø÷; ù·öÿ´è#@ù ñk T飩@ù? ñë T ÒÈ °%Eù»b h{vø ëà TÖ ?ëaÿÿT Òa{vøàªB R>C 5Ö ?ë!ÿÿT @ø7è'@ùyvøè ´è? ùúªè @ù» {s@ù ) » {s@ùè#@ùà µ ñK T飩öª@ù? ñ T ÒÈ °uEù»b h{|ø ëÀ T ? ëaÿÿT Òa{|øàªB RC 5 ? ë!ÿÿT ¢ Bp@ùtv@ù@¹ 1à T ø7è'@ùy|ø¢ ´âC ùè @ùûª ú à
µ¢ Bp@ùûªè#@ù ñ* Ttv@ù@¹ 1B T ¹È °ÕGùa"É °)a&©Dù*}Dù+áEù)@ùû ùÿ+ ¹ë§©) Ré ¹ú+ © ð ãªD Råª' R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàªé ¨Zø© )y@ù)@ù?ë¡ Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ ùa Tàªԟ Ð T&C °c >R׀RKÿÿ¥ ¥ÜâCãÃàªá'@ùäªÕA @ø7÷kG©âC@ùtv@ù@¹ 1ÃöÿT¶ÿÿ¡4R4ÿÿA5R2ÿÿÁ3R0ÿÿ¹ ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýôªó ª ðy@ù@ù¨øÿ©È Á
A é#©á è© ð9s@ùùC ùã ´ ñh Tõª< H Y
it8)
ÖûªxAø ñè# ù T ÒÈ ÁAùºb H{vø ë TÖ ëaÿÿT ÒA{vøàªB RjB ` 5Ö ë!ÿÿT` ´aJR
ñ@ T ña T"@ùH H R °)y °JU
ñI±µ ðJA@ù@@ù °J© êÓ©é£ ©¨ 1è ù °!¸ 9 aORf 7 @ù÷; ùûªvAøös©ß ñ
TJ ü' ù7h@©÷k©ûª|Aø ñ
Tè# ùv@ùß ñK T ÒÈ uEù¹b ({{ø ë T{ ßëaÿÿT Ò!{{øàªB R#B ` 5{ ßë!ÿÿT^ ü' ù:@©ú©7 @ù÷; ù¼
@ù] ðBp@ù7h@©tv@ù@¹ 1 T\ õÿ7{vø÷; ù×ôÿ´ü' ùv@ùß ñ T ÒÈ ¹Aù¼b {zø ë@ TZ ßëaÿÿT ҁ{zøàªB RøA 5Z ßë!ÿÿTî @ µ ðA@ù @ù* R °© K Rè«© °U © )1è¯ ©é ù °!¸ ӝ ¡KR ° ì&C c "R·ÿ ÒD üÿ7è'@ùyzøú? ùüÿ´è#@ù ш ñJóÿT ðBp@ùtv@ù@¹ 1£ T à ø7è'@ùy{ø ´âC ùü#@ù » µ ðBp@ù ð9s@ù ñ* Ttv@ù@¹ 1B T ¹È ÕGùa"É )a&Aù*Aù+áEù)@ùù ùÿ+ ¹ë§©I Ré ¹ú+ © ð àãªD RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tપ ¨Zø ð)y@ù)@ù?ë¡ Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ ùa Tઠ° ì&C c AVRBãRÿÿ¥ ¥0âCãÃàªá'@ùäª@ ø7÷kG©âC@ùtv@ù@¹ 1ÃöÿT¶ÿÿaKRÿÿLRÿÿ!MRÿÿz ÿCÑüo ©úg ©ø_
©öW©ôO©ý{©ýôªó ª ðy@ù@ù¨øÿ©È Á
A 飩 á 飩ÿ? ù ðs@ùÿc ©ã ´ ñh Tõª( è+ ùH i
it8)
ÖûªxAø ñ T ÒÈ ÁAù¹b ({vø ëÀ
TÖ ëaÿÿT Ò!{vøàªB R)A 5Ö ë!ÿÿT ´bR® ñ T ña T" @ù h R °)y °JU ñI±µ ðJA@ù@@ù °J© êÓ©é£ ©¨ ©>è ù °!¸ ø iR ðBp@ù:ð@©7 @ùtv@ù@¹ 1 T¸ 7 @ù÷C ùûªvAøüªß ñ
TJ 7h@©÷k©ûª|Aøü' ù ñJ
Td :ð@©úó©7 @ù÷C ùûªvAøÈ ñ TèO©y@ù? ñË T ÒÈ uEù³b hz{ø ë T{ ?ëaÿÿT Òaz{øàªB RÐ@ à 5{ ?ë!ÿÿTz <A©ü ©7h@©÷k©¶
@ù{ ôÿ7è+@ùyvø÷C ùóÿ´v@ùß ñ T ÒÈ ¹Aù¹b ({zø ë` TZ ßëaÿÿT Ò!{zøàªB R®@ 5Z ßë!ÿÿT¤ @ µÓcR( R" `ÿÿ7è+@ùyzøúG ùúþÿ´ Ñè' ù|@ù ñ T ÒÈ ÉCù¹b ({vø ë` TÖ ëaÿÿT Ò!{vøàªB R@ 5Ö ë!ÿÿT À µeRH R ð)A@ù @ùè ù °© i Ré#© °U © )©>é# © °!¸ f ° t'C c áªâãR2¶ÿ ÒG `üÿ7è+@ù yvøüK ùüûÿ´è'@ù ј ðs@ùÈ ñÊïÿT ðBp@ùtv@ù@¹ 1à T à ø7è+@ùy{ø ´âO ùö#@ù L µ ðBp@ùó'@ù ðs@ùß ñ* Ttv@ù@¹ 1B T ¹È ÕGùa"É )á
& @ù*@ù)Bùø ù+ Rë+ ¹ü§©I Ré ¹ú+ © Ð )ãªd RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàª: ¨Zø ð)y@ù)@ù?ëá Tàªý{P©ôOO©öWN©ø_M©úgL©üoK©ÿCÀ_ÖÈ ø7 ñ ùa Tàª% ° t'C c áoR"îRÿÿ¥ ¥¨>âcãàªá+@ùäª&? Àø7÷kH©ü I©tv@ù@¹ 1ÃöÿT¶ÿÿÓdRÿÿcRÿÿóeRÿÿfR~ÿÿ ÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýCôªó ª ðy@ù@ù¨øÈ
! è'©ÿ3 ù ð9s@ùÿç©Ã ´õª( 4 ´ ñ T
ñ! T7@©÷©º
@ù_ ñë TÄ ñ T
ñá T"@ùF è' ùøª Aø ñ T ÒÈ ±Aù¶b Èz{ø ë T{ ëaÿÿT ÒÁz{øàªB R²? à 5{ ë!ÿÿT¨ ` ´a{R °y °)U * R ñ(±Iµ ðJA@ù@@ù °J© K kj±êÓ©è§ ©© °)4é ù °!¸ á~R ° ((C c ÂîRPµÿ Òe è' ù7 @ù÷7 ùøªAø ðBp@ù7 @ùtv@ù@¹ 1C T: ùÿ7è'@ùy{ø÷7 ù7ùÿ´H ñ+ Tè# ù@ù ñk T ÒÈ uEù¶b Èz|ø ëÀ T ëaÿÿT ÒÁz|øàªB Ra? 5 ë!ÿÿT ðBp@ùtv@ù@¹ 1 T à ø7è'@ùy|ø ´â; ùú#@ù H
µ ðBp@ùè'@ù_ ñê Ttv@ù@¹ 1B T ¹È ÕGùa"É )a& Aù*áEù)@ùù ùÿ+ ¹ê§©ÿ ¹ê' © Ð !ãª$ RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàª: ¨Zø ð)y@ù)@ù?ëA Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_ÖÈ ø7 ñ ùa Tàª% ° ((C c ER¢÷R~ÿÿ¥ °¥4âCã£àªáªäª&> à ø7÷F©tv@ù@¹ 1#÷ÿT¹ÿÿá|RhÿÿA|Rfÿÿ
ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýôªó ª ðy@ù@ù¨øÿ©È
Áè'©! è© ð9s@ùùC ùã ´ ñh Tõª< H }
it8)
ÖûªxAø ñè# ù T ÒÈ ±Aùºb H{vø ë TÖ ëaÿÿT ÒA{vøàªB R¾> ` 5Ö ë!ÿÿT´ ´¡R
ñ@ T ña T"@ùH H R °)y °JU
ñI±µ ÐJA@ù@@ù J© êÓ©é£ ©¨ °è ù !¸ ¡Rf 7 @ù÷; ùûªvAøös©ß ñ
TJ ü' ù7h@©÷k©ûª|Aø ñ
Tè# ùv@ùß ñK T Ҩ ðuEù¹b ({{ø ë T{ ßëaÿÿT Ò!{{øàªB Rw> ` 5{ ßë!ÿÿT^ ü' ù:@©ú©7 @ù÷; ù¼
@ù] ÐBp@ù7h@©tv@ù@¹ 1 T\ õÿ7{vø÷; ù×ôÿ´ü' ùv@ùß ñ T Ҩ ðÉCù¼b {zø ë@ TZ ßëaÿÿT ҁ{zøàªB RL> 5Z ßë!ÿÿTB @ µ ÐA@ù @ù* R © K Rè«© U © °)è¯ ©é ù !¸ ' ᒈR Ð(# ðc BøRó³ÿ ÒD üÿ7è'@ùyzøú? ùüÿ´è#@ù ш ñJóÿT ÐBp@ùtv@ù@¹ 1£ T à ø7è'@ùy{ø ´âC ùü#@ù µ ÐBp@ù Ð9s@ù ñ* Ttv@ù@¹ 1B T ¹¨ ðÕGùa"© ð)a& Aù*!Cù+áEù)@ùù ùÿ+ ¹ë§©) Ré ¹ú+ © ° @#ãªD RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàªþ ¨Zø Ð)y@ù)@ù?ë¡ Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ ùa Tàªé Ð(# ðc RÂRÿÿ¥ °¥âCãÃàªá'@ùäªê< ø7÷kG©âC@ùtv@ù@¹ 1ÃöÿT¶ÿÿ¡RÿÿSRÿÿaRÿÿΚ ÿÑüo©úg©ø_©öW ©ôO
©ý{ ©ýÃôªó ª Ðy@ù@ù© ð)¡+è/ ùé© Ðs@ùø+ ùC ´õª6 4 ´ ñÁ T" @ùâ+ ù¹
@ùS 4 ´ ñá T" @ùtv@ù@¹ 1#
TQ è4ªýӉ )y JU ñI± ÐJA@ù@@ù* ðJ k© j±êÓ©é£ ©¨ Ðõ è ù !¸ i ᪈R ¤)# ðc bR5³ÿ ÒK ¹
@ù: ñ« T Ҩ ðuEù¼b {{ø ëÀ T{ ?ëaÿÿT ҁ{{øàªB R\= 5{ ?ë!ÿÿT ÐBp@ùtv@ù@¹ 1C T À ø7Âz{ø ´â+ ùùª D @
µ ÐBp@ù? ñª Ttv@ù@¹ 1B T ¹¨ ðÕGùa"© ð)a%áEù&@ùø ùÿ+ ¹å©ÿ ¹å © ° `;㪠R R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàª9 è/@ù Ð)y@ù)@ù?ëA Tàªý{K©ôOJ©öWI©ø_H©úgG©üoF©ÿÀ_ÖÈ ø7 ñ ùa Tàª$ ¤)# ðc qRb Rÿÿ¥ Хô âãCàªáªäª%< à ø7â+@ùtv@ù@¹ 1c÷ÿT»ÿÿ!©Rÿÿ¨Rÿÿ ÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýCôªó ª Ðy@ù@ù¨ø¨ ð
! è'©ÿ3 ù Ð9s@ùÿç©Ã ´õª( 4 ´ ñ T
ñ! T7@©÷©º
@ù_ ñë TÄ ñ T
ñá T"@ùF è' ùøª Aø ñ T Ҩ ð±Aù¶b Èz{ø ë T{ ëaÿÿT ÒÁz{øàªB R¶< à 5{ ë!ÿÿT¬ ` ´A½R y )U * R ñ(±Iµ ÐJA@ù@@ù J© + ðkj±êÓ©è§ ©© Ð)93é ù !¸ ÁR d*# ðc  RT²ÿ Òe è' ù7 @ù÷7 ùøªAø ÐBp@ù7 @ùtv@ù@¹ 1C T: ùÿ7è'@ùy{ø÷7 ù7ùÿ´H ñ+ Tè# ù@ù ñk T Ҩ ðuEù¶b Èz|ø ëÀ T ëaÿÿT ÒÁz|øàªB Re< 5 ë!ÿÿT ÐBp@ùtv@ù@¹ 1 T à ø7è'@ùy|ø ´â; ùú#@ù L
µ ÐBp@ùè'@ù_ ñê Ttv@ù@¹ 1B T ¹¨ ðÕGùa"© ð)a& Aù*ñEù)@ùù ùÿ+ ¹ê§©ÿ ¹ê' © ° p6ãª$ RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàª> ¨Zø Ð)y@ù)@ù?ëA Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_ÖÈ ø7 ñ ùa Tàª) d*# ðc ¡LjRbR~ÿÿ¥ Х83âCã£àªáªäª*; à ø7÷F©tv@ù@¹ 1#÷ÿT¹ÿÿ~Rhÿÿ!¾Rfÿÿ ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýôªó ª Ðy@ù@ù¨øÿ©¨ ða Aé#©Aè© Ð9s@ùùC ùã ´ ñh Tõª< ( ð
it8)
ÖûªxAø ñè# ù T Ҩ ðuCùºb H{vø ë TÖ ëaÿÿT ÒA{vøàªB RÂ; ` 5Ö ë!ÿÿT¸ ´ӈR
ñ@ T ña T"@ùH H R )y JU
ñI±µ ÐJA@ù@@ù J© êÓ©é£ ©¨ ðm9è ù !¸ ؈Rf 7 @ù÷; ùûªvAøös©ß ñ
TJ ü' ù7h@©÷k©ûª|Aø ñ
Tè# ùv@ùß ñK T Ҩ ðuEù¹b ({{ø ë T{ ßëaÿÿT Ò!{{øàªB R{; ` 5{ ßë!ÿÿT^ ü' ù:@©ú©7 @ù÷; ù¼
@ù] ÐBp@ù7h@©tv@ù@¹ 1 T\ õÿ7{vø÷; ù×ôÿ´ü' ùv@ùß ñ T Ҩ ðÍBù¼b {zø ë@ TZ ßëaÿÿT ҁ{zøàªB RP; 5Z ßë!ÿÿTF @ µ ÐA@ù @ù* R © K Rè«© U © ð)m9è¯ ©é ù !¸ + ÁԈR +# ðc "R÷°ÿ ÒD üÿ7è'@ùyzøú? ùüÿ´è#@ù ш ñJóÿT ÐBp@ùtv@ù@¹ 1£ T à ø7è'@ùy{ø ´âC ùü#@ù µ ÐBp@ù Ð9s@ù ñ* Ttv@ù@¹ 1B T ¹¨ ðÕGùa © ð)a&ÍBù*%Bù+áEù)@ùù ùÿ+ ¹ë§©) Ré ¹ú+ © Ð ãªD Råª R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tઠ¨Zø Ð)y@ù)@ù?ë¡ Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ ùa Tàªí +# ðc a߈R¢%Rÿÿ¥ ð¥l9âCãÃàªá'@ùäªî9 ø7÷kG©âC@ùtv@ù@¹ 1ÃöÿT¶ÿÿԈRÿÿ¡ՈRÿÿAֈRÿÿҗ ÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýCôªó ª Ðy@ù@ù¨ø¨ ð! %è'©ÿ3 ù °9s@ùÿç©Ã ´õª( 4 ´ ñ T
ñ! T7@©÷©º
@ù_ ñë TÄ ñ T
ñá T"@ùF è' ùøª Aø ñ T Ҩ ÐÅ@ù¶b Èz{ø ë T{ ëaÿÿT ÒÁz{øàªB R|: à 5{ ë!ÿÿTr ` ´áêR h ðy i ð)U * R ñ(±Iµ °JA@ù@@ùj ðJ© + Ðkj±êÓ©è§ ©© ð)-é ùa ð!¸ N aîR` ð ´+# Ðc B&R°ÿ Òe è' ù7 @ù÷7 ùøªAø °Bp@ù7 @ùtv@ù@¹ 1C T: ùÿ7è'@ùy{ø÷7 ù7ùÿ´H ñ+ Tè# ù@ù ñk T Ҩ ÐuEù¶b Èz|ø ëÀ T ëaÿÿT ÒÁz|øàªB R+: 5 ë!ÿÿT °Bp@ùtv@ù@¹ 1 T à ø7è'@ùy|ø ´â; ùú#@ù
µ °Bp@ùè'@ù_ ñê Ttv@ù@¹ 1B T ¹¨ ÐÕGùa"© Ð)a& @ù*áEù)@ùù ùÿ+ ¹ê§©ÿ ¹ê' © ãª$ RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tઠ¨Zø °)y@ù)@ù?ëA Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_ÖÈ ø7 ñ ùa Tàªï ` ð ´+# Ðc AõR2R~ÿÿ¥ ð¥-âCã£àªáªäªð8 à ø7÷F©tv@ù@¹ 1#÷ÿT¹ÿÿaìRhÿÿÁëRfÿÿז ÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýCôªó ª °y@ù@ù¨ø¨ Ð! %è'©ÿ3 ù °9s@ùÿç©Ã ´õª( 4 ´ ñ T
ñ! T7@©÷©º
@ù_ ñë TÄ ñ T
ñá T"@ùF è' ùøª Aø ñ T Ҩ ÐÅ@ù¶b Èz{ø ë T{ ëaÿÿT ÒÁz{øàªB R9 à 5{ ë!ÿÿTw ` ´Á R h ðy i ð)U * R ñ(±Iµ °JA@ù@@ùj ðJ© + Ðkj±êÓ©è§ ©É )-é ùa ð!¸ S AR` ð P,# Ðc "3R ¯ÿ Òe è' ù7 @ù÷7 ùøªAø °Bp@ù7 @ùtv@ù@¹ 1C T: ùÿ7è'@ùy{ø÷7 ù7ùÿ´H ñ+ Tè# ù@ù ñk T Ҩ ÐuEù¶b Èz|ø ëÀ T ëaÿÿT ÒÁz|øàªB R09 5 ë!ÿÿT °Bp@ùtv@ù@¹ 1 T à ø7è'@ùy|ø ´â; ùú#@ù
µ °Bp@ùè'@ù_ ñê Ttv@ù@¹ 1B T ¹¨ ÐÕGùa"© Ð)a& @ù*áEù)@ùù ùÿ+ ¹ê§©ÿ ¹ê' © à ãª$ Råª' R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tઠ¨Zø °)y@ù)@ù?ëA Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_ÖÈ ø7 ñ ùa Tàªô ` ð P,# Ðc ! R?R~ÿÿÅ ¥-âCã£àªáªäªõ7 à ø7÷F©tv@ù@¹ 1#÷ÿT¹ÿÿARhÿÿ¡Rfÿÿܕ ÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýCôªó ª °y@ù@ù¨ø¨ Ð! %è'©ÿ3 ù °9s@ùÿç©Ã ´õª( 4 ´ ñ T
ñ! T7@©÷©º
@ù_ ñë TÄ ñ T
ñá T"@ùF è' ùøª Aø ñ T Ҩ ÐÅ@ù¶b Èz{ø ë T{ ëaÿÿT ÒÁz{øàªB R8 à 5{ ë!ÿÿT| ` ´¡R h ðy i ð)U * R ñ(±Iµ °JA@ù@@ùj ðJ© + Ðkj±êÓ©è§ ©É °)m%é ùa ð!¸ X !R` ð ð,# Ðc "@R$®ÿ Òe è' ù7 @ù÷7 ùøªAø °Bp@ù7 @ùtv@ù@¹ 1C T: ùÿ7è'@ùy{ø÷7 ù7ùÿ´H ñ+ Tè# ù@ù ñk T Ҩ ÐuEù¶b Èz|ø ëÀ T ëaÿÿT ÒÁz|øàªB R58 5 ë!ÿÿT °Bp@ùtv@ù@¹ 1 T à ø7è'@ùy|ø ´â; ùú#@ù
µ °Bp@ùè'@ù_ ñê Ttv@ù@¹ 1B T ¹¨ ÐÕGùa"© Ð)a& @ù*áEù)@ùù ùÿ+ ¹ê§©ÿ ¹ê' © 0 ãª$ RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tઠ¨Zø °)y@ù)@ù?ëA Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_ÖÈ ø7 ñ ùa Tàªù ` ð ð,# Ðc !R"MR~ÿÿÅ °¥l%âCã£àªáªäªú6 à ø7÷F©tv@ù@¹ 1#÷ÿT¹ÿÿ!RhÿÿRfÿÿá ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýõªó ª °y@ù@ù¨ø¨ ÐÁ aè'© áé©uCùyCùôk© °÷r@ù÷C ù_ ñ ´ Töª( è' ù( Ð
iu8)
ÖüªAøi ñ«
T Ҩ ÐCùÙb é# ù({wø ë
T÷ ëaÿÿT Ò!{wøàªB R7 ` 5÷ ë!ÿÿTO ( T °Bp@ù( Ð
iu8)
Ö"@ù:@ù4 @ùuv@ù¨@¹ 1à T h R¿ ñ賈i ð)y j ðJU I± °JA@ù@@ùj ðJ© ê×©é£ ©È ÐE è ùa ð!¸ V á1R` ð -# Ðc ÂMR"ÿ ҟ 4 @ùô; ùüªAø 4h@©ôk©üªAø= :@©ú©4 @ùô; ùÛ
@ùi °Bp@ùuv@ù¨@¹ 1#
Ti ø7è'@ùywø¨ ´è; ùôªû#@ù 6 µh ñë TèÏ©@ù? ñ« T Ҩ Ð%EùÓb hzwø ëà T÷ ?ëaÿÿT ÒazwøàªB R%7 5÷ ?ë!ÿÿT ø7è'@ùywø¨ ´è? ùúªûÏC© ó#@ù µh ñK Tè# ù÷ª@ù? ñ« T Ҩ ÐuEùÓb hz|ø ë T ? ëaÿÿT Òaz|øàªB Rÿ6 À 5 ? ë!ÿÿT °Bp@ù °÷r@ùuv@ù¨@¹ 1à T à ø7è'@ùy|ø ´âC ùû#@ù ä µ °Bp@ùóª °÷r@ù ñ* Tuv@ù¨@¹ 1B T¨ ¹¨ ÐÕGùa © Ð)a&qBù*}Dù+áEù)@ù÷ ùÿ+ ¹ë§©) Ré ¹ú+ © ° ãªD Råª R ?֨@ùà ´ó ªÈ ø7 ñ¨ ùa Tàªғ ¨Zø °)y@ù)@ù?ëá Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ¨ ùa Tઽ ` Ð -# °c Á8RâXRDÿÿÅ °¥D âCãÃàªá'@ù䪾5 @ø7ôkG©âC@ùuv@ù¨@¹ 1ÃöÿT¶ÿÿÁ.R-ÿÿa/R+ÿÿá-R)ÿÿ-R'ÿÿ ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýõªó ª y@ù@ù¨ø¨ °Á aè'© áé©uCùyCùôk© ÷r@ù÷C ù_ ñ ´ Töª( è' ù( °½
iu8)
ÖüªAøi ñ«
T Ҩ °CùÙb é# ù({wø ë
T÷ ëaÿÿT Ò!{wøàªB RN6 ` 5÷ ë!ÿÿTO ( T Bp@ù( °Í
iu8)
Ö"@ù:@ù4 @ùuv@ù¨@¹ 1à T h R¿ ñ賈i Ð)y j ÐJU I± JA@ù@@ùj ÐJ© ê×©é£ ©È Ðè ùa Ð!¸ ¡IR` Ð (.# °c YRá«ÿ ҟ 4 @ùô; ùüªAø 4h@©ôk©üªAø= :@©ú©4 @ùô; ùÛ
@ùi Bp@ùuv@ù¨@¹ 1#
Ti ø7è'@ùywø¨ ´è; ùôªû#@ù õ µh ñë TèÏ©@ù? ñ« T Ҩ °%EùÓb hzwø ëà T÷ ?ëaÿÿT ÒazwøàªB Rä5 5÷ ?ë!ÿÿT ø7è'@ùywø¨ ´è? ùúªûÏC© ё ó#@ù µh ñK Tè# ù÷ª@ù? ñ« T Ҩ °uEùÓb hz|ø ë T ? ëaÿÿT Òaz|øàªB R¾5 À 5 ? ë!ÿÿT Bp@ù ÷r@ùuv@ù¨@¹ 1à T à ø7è'@ùy|ø ´âC ùû#@ù £ µ Bp@ùóª ÷r@ù ñ* Tuv@ù¨@¹ 1B T¨ ¹¨ °ÕGùa © °)a&qBù*}Dù+áEù)@ù÷ ùÿ+ ¹ë§©) Ré ¹ú+ © "ãªD Råª R ?֨@ùà ´ó ªÈ ø7 ñ¨ ùa Tઠ¨Zø )y@ù)@ù?ëá Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ¨ ùa Tàª| ` Ð (.# °c PRbhRDÿÿÅ Х¬âCãÃàªá'@ùäª}4 @ø7ôkG©âC@ùuv@ù¨@¹ 1ÃöÿT¶ÿÿFR-ÿÿ!GR+ÿÿ¡ER)ÿÿÁDR'ÿÿ_ ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýõªó ª y@ù@ù¨ø¨ °Á aè'© áé©uCùyCùôk© ÷r@ù÷C ù_ ñ ´ Töª( è' ù( °Ý
iu8)
ÖüªAøi ñ«
T Ҩ °CùÙb é# ù({wø ë
T÷ ëaÿÿT Ò!{wøàªB R
5 ` 5÷ ë!ÿÿTO ( T Bp@ù( °í
iu8)
Ö"@ù:@ù4 @ùuv@ù¨@¹ 1à T h R¿ ñ賈i Ð)y j ÐJU I± JA@ù@@ùj ÐJ© ê×©é£ ©È ðM!è ùa Ð!¸ Ԑ aaR` Ð Ä.# °c iR ªÿ ҟ 4 @ùô; ùüªAø 4h@©ôk©üªAø= :@©ú©4 @ùô; ùÛ
@ùi Bp@ùuv@ù¨@¹ 1#
Ti ø7è'@ùywø¨ ´è; ùôªû#@ù ´ µh ñë TèÏ©@ù? ñ« T Ҩ °%EùÓb hzwø ëà T÷ ?ëaÿÿT ÒazwøàªB R£4 5÷ ?ë!ÿÿT ø7è'@ùywø¨ ´è? ùúªûÏC© ó#@ù µh ñK Tè# ù÷ª@ù? ñ« T Ҩ °uEùÓb hz|ø ë T ? ëaÿÿT Òaz|øàªB R}4 À 5 ? ë!ÿÿT Bp@ù ÷r@ùuv@ù¨@¹ 1à T à ø7è'@ùy|ø ´âC ùû#@ù b µ Bp@ùóª ÷r@ù ñ* Tuv@ù¨@¹ 1B T¨ ¹¨ °ÕGùa © °)a&qBù*}Dù+áEù)@ù÷ ùÿ+ ¹ë§©) Ré ¹ú+ © #ãªD Råª R ?֨@ùà ´ó ªÈ ø7 ñ¨ ùa TàªP ¨Zø )y@ù)@ù?ëá Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ¨ ùa Tàª; ` Ð Ä.# °c AhR"sRDÿÿÅ ð¥L!âCãÃàªá'@ùäª<3 @ø7ôkG©âC@ùuv@ù¨@¹ 1ÃöÿT¶ÿÿA^R-ÿÿá^R+ÿÿa]R)ÿÿ\R'ÿÿ ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýõªó ª y@ù@ù¨ø¨ °Á è'© áé©5Cù9Cùôk© ÷r@ù÷C ù_ ñ ´ Töª( è' ù( °ý
iu8)
ÖüªAøi ñ«
T Ҩ °YCùÙb é# ù({wø ë
T÷ ëaÿÿT Ò!{wøàªB RÌ3 ` 5÷ ë!ÿÿTO ( T Bp@ù( °
iu8)
Ö"@ù:@ù4 @ùuv@ù¨@¹ 1à T h R¿ ñ賈i Ð)y j ÐJU I± JA@ù@@ùj ÐJ© ê×©é£ ©è 1è ùa Ð!¸ !yR` Ð h/# °c ÂsR_©ÿ ҟ 4 @ùô; ùüªAø 4h@©ôk©üªAø= :@©ú©4 @ùô; ùÛ
@ùi Bp@ùuv@ù¨@¹ 1#
Ti ø7è'@ùywø¨ ´è; ùôªû#@ù s µh ñë TèÏ©@ù? ñ« T Ҩ °iEùÓb hzwø ëà T÷ ?ëaÿÿT ÒazwøàªB Rb3 5÷ ?ë!ÿÿT ø7è'@ùywø¨ ´è? ùúªûÏC© O ó#@ù µh ñK Tè# ù÷ª@ù? ñ« T Ҩ °uEùÓb hz|ø ë T ? ëaÿÿT Òaz|øàªB R<3 À 5 ? ë!ÿÿT Bp@ù ÷r@ùuv@ù¨@¹ 1à T à ø7è'@ùy|ø ´âC ùû#@ù ! µ Bp@ùóª ÷r@ù ñ* Tuv@ù¨@¹ 1B T¨ ¹¨ °ÕGùa"© °)a&±Bù*ÁDù+áEù)@ù÷ ùÿ+ ¹ë§©) Ré ¹ú+ © ð 3ãªD Råª R ?֨@ùà ´ó ªÈ ø7 ñ¨ ùa Tઠ¨Zø )y@ù)@ù?ëá Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ¨ ùa Tàªú ` Ð h/# °c R¢RDÿÿå ¥0âCãÃàªá'@ùäªû1 @ø7ôkG©âC@ùuv@ù¨@¹ 1ÃöÿT¶ÿÿvR-ÿÿ¡vR+ÿÿ!uR)ÿÿAtR'ÿÿݏ ÿÑüo©úg ©ø_
©öW ©ôO ©ý{
©ýCôªó ª y@ù@ù¨ø¨ °!) è'©ÿ3 ùmAù 9s@ùõç©£ ´öª( ô ´ ñÀ T
ñ Tè' ù5@©õ©Ú
@ù b ðBp@ùT ´ ñ T
ñ T"@ù5 @ùtv@ù@¹ 1 T| þ~Óè(*i °)y j °JU ñI±j ðJA@ù@@ùj °J© ë kë' ©êÓ©è ùa °!¸ o !R` ° 0# c BR;¨ÿ Òz ûªzAøI ñ Té#© Ҩ %Eù×b èz|ø ë T _ ëaÿÿT Òáz|øàªB R`2 ` 5 _ ë!ÿÿT è' ù5 @ùõ7 ùûªzAø ø7è'@ùy|ø¨ ´è7 ùõªú#@ù G µH ñ+ Tè# ùw@ùÿ ñk T Ҩ uEùÜb {{ø ëÀ T{ ÿëaÿÿT ҁ{{øàªB R62 5{ ÿë!ÿÿT b ðBp@ùtv@ù@¹ 1c T à ø7è'@ùy{ø ´â; ùú#@ù @
µb ðBp@ù_ ñê Ttv@ù@¹ 1B T ¹¨ ÕGùa © )a&}Dù*áEù)@ùù ùÿ+ ¹ê§©ÿ ¹ê' © Ð 0"ãª$ Råª' R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tઠ¨Zøi ð)y@ù)@ù?ë Tàªý{M©ôOL©öWK©ø_J©úgI©üoH©ÿÀ_ÖÈ ø7 ñ ùa Tàªû ` ° 0# c RBRiÿÿå ¥âCã£àªá'@ùäªü0 ø7õF©tv@ù@¹ 1#÷ÿT¹ÿÿaRSÿÿRQÿÿROÿÿá ÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýôªó ªh ðy@ù@ù¨øÿ©¨ Á aè'©áè©y ð9s@ùùC ùã ´ ñh Tõª< (
it8)
ÖûªxAø ñè# ù T Ҩ YCùºb H{vø ë TÖ ëaÿÿT ÒA{vøàªB R1 ` 5Ö ë!ÿÿT ´ᡉR
ñ@ T ña T"@ùH H Ri °)y j °JU
ñI±µj ðJA@ù@@ùj °J© êÓ©é£ ©è °5è ùa °!¸ a ᦉRf 7 @ù÷; ùûªvAøös©ß ñ
TJ ü' ù7h@©÷k©ûª|Aø ñ
Tè# ùv@ùß ñK T Ҩ uEù¹b ({{ø ë T{ ßëaÿÿT Ò!{{øàªB RK1 ` 5{ ßë!ÿÿT^ ü' ù:@©ú©7 @ù÷; ù¼
@ù] b ðBp@ù7h@©tv@ù@¹ 1 T\ õÿ7{vø÷; ù×ôÿ´ü' ùv@ùß ñ T Ҩ %Eù¼b {zø ë@ TZ ßëaÿÿT ҁ{zøàªB R 1 5Z ßë!ÿÿT @ µh ðA@ù @ù* Rh °© K Rè«©h °U é °)5è¯ ©é ùa °!¸ û !£R` ° ´0# c ⋁RǦÿ ÒD üÿ7è'@ùyzøú? ùüÿ´è#@ù ш ñJóÿTb ðBp@ùtv@ù@¹ 1£ T à ø7è'@ùy{ø ´âC ùü#@ù ã µb ðBp@ùy ð9s@ù ñ* Ttv@ù@¹ 1B T ¹¨ ÕGùa"© )a&±Bù*}Dù+áEù)@ùù ùÿ+ ¹ë§©I Ré ¹ú+ © Ð p*ãªD RåªG R ?ֈ@ùà ´ó ªÈ ø7 ñ ùa Tàªҍ ¨Zøi ð)y@ù)@ù?ë¡ Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ ùa Tઽ ` ° ´0# c mR━Rÿÿå °¥4âCãÃàªá'@ù䪾/ ø7÷kG©âC@ùtv@ù@¹ 1ÃöÿT¶ÿÿᢉRÿÿ¤Rÿÿ¡¤Rÿÿ¢ ÿÃÑë+ mé# müo
©úg©ø_©öW©ôO©ý{©ýóªü ªh ðy@ù@ù¨øÿ©¨ ¡ ¡è§© á飩ÿ? ùh ðq@ùÿ# ©ã ´ ñ Tôª( è' ù( -
is8)
ÖöªÙAø: ñ T Ҩ õBùb ¨zxø ëà
T ?ëaÿÿT ҡzxøàªB RO0 5 ?ë!ÿÿTE @ ´ºR¯ ñ T ñ T6 @ùöO ù h Ri °)y j °JU ñI±µj ðJA@ù@@ùj °J© êÏ©é£ ©è °õ0è ùa °!¸ R v ðÖr@ù9è@©ùë©8 @ùøC ù 8 @ùøC ùöªÙAøúª? ñJ TL ü+ ù8d@©øg©öªÚAøûª_ ñj
Te 9è@©ùë©8 @ùøC ùöªÛAøh ñk Tè# ùü+ ùÕ@ù¿ ñ T Ҩ uEùb {vø ë` TÖ ¿ëaÿÿT ҁ{vøàªB Rõ/ 5Ö ¿ë!ÿÿTt :XA©ú[ ©8d@©øg©
@ùs àóÿ7è'@ùyxøøC ùxóÿ´Ù@ù? ñ T Ҩ iCùb ¨z{ø ë` T{ ?ëaÿÿT ҡz{øàªB RÓ/ 5{ ?ë!ÿÿTɋ @¡ µS»R( R" `ÿÿ7è'@ùy{øùG ùùþÿ´ü+ ù[ ÑÚ@ù_ ñ T Ҩ Eùb ¨z|ø ë` T _ ëaÿÿT ҡz|øàªB R±/ 5 _ ë!ÿÿT§ ` µ¼RH Ri ð)A@ù @ùè ùh °© i Ré#©h °U é °)õ0é# ©a °!¸ ` ° H1# c áªRW¥ÿ ÒÇ `üÿ7è'@ùy|øúK ùúûÿ´{ Ñü+@ùh ñêïÿTv ðÖr@ù à ø7è'@ùyvø ´öO ùû#@ù w @ µv ðÖr@ùü+@ù ñJ Tµ ¨ÚGùAùµ@ùR ?Öá ªàª R R R Ò`?Ö V ´ó ª @¹ 1B Th ¹h@ùÈ ø7 ñh ùa Tàªq ¨ÚGùAùµ@ùR ?Öá ªàª R R R Ҁ?Öô ª S ´@¹ 1B T ¹@ùÈ ø7 ñ ùa TàªX ¨ÚGùAùµ@ùR ?Öá ªàª R R R Ҡ?Öõ ª Q ´¨@¹ 1B T¨ ¹¨@ù ø7 ñ¨ ù@ T@¹i@¹?k T©@¹(*( 5àª9 @`
~ j a T 慦1 @` j a T 慦*
@` ~ @!` a T
à µ!j ́ TP!i L T !i Tw@ùH@¹ 1B TH ¹ A`
´û ª@A` ù ª ´ A` ø ª ´¨ ÕGù © &@ùi ð)q@ùé ùÿ+ ¹ø©ÿ ¹ù © ° pâªãªd Råª R ?ր ´ö ªH@ùÈ ø7 ñH ùa Tàªï h@ùÈ ø7 ñh ùa Tàªè (@ùH=ø7 ñ( ùá< Tàªá ä àªދ @¹i@¹?kÀóÿT ð÷"9ùÒDùà@ù"@ù᪾ `B ´ø ª @¹ 1B T ¹¨ ù@ù@ùI@ùHB ´àª ?Öù ª@B ´@ùÈ ø7 ñ ùa Tઽ øÒDùà@ù@ù᪣ ö' ùà@ ´û ª @¹ 1B Th ¹ ðÁbBùh@ùI@ù(A ´àª ?Öú ª A ´ü+ ùh@ùÈ ø7 ñh ùa TઠH@ù| МW@ù ë @ T R Òéc)! øÏ©ô7 ù!M(Ë 2àª-½ÿû ª ´@ùÈ ø7 ñ ùa Tઠ? ´H@ùÈ ø7 ñH ùa Tઠ(@ù ë> T R Òéc)! úï©!M(Ë àª½ÿø ª ´H@ùÈ ø7 ñH ùa Tàªk h@ùÈ ø7 ñh ùa Tàªd Ø< ´(@ùÈ ø7 ñ( ùa Tàª\ i Ð)u@ùh Ðm@ù ëÀ T ë Th Ðq@ù ë Tàª֊ ù ª`Xø7@ùÈ ø6
ëù@ùÈ ø7 ñ ùa Tàª@ ù8 5øÒDùà@ù@ùáª% à9 ´ù ª @¹ 1B T( ¹ ðù@ù(@ùI@ùÈ9 ´àª ?Öø ªÀ9 ´(@ùÈ ø7 ñ( ùa Tàª$ ùÒDùà@ù"@ùáª
À8 ´ú ª @¹ 1B TH ¹ÁbBùH@ùI@ùÈ8 ´àª ?Öû ªÀ8 ´H@ùÈ ø7 ñH ùa Tàª
h@ù ë@8 T R Òéc)! úÓ©õ7 ù!M(Ë 2઼ÿù ª ´H@ùÈ ø7 ñH ùa Tàªô Y7 ´h@ùÈ ø7 ñh ùa Tàªì @ù ë6 T R Òéc)! ûç©!M(Ë àª|¼ÿú ª ´h@ùÈ ø7 ñh ùa Tઠ(@ùÈ ø7 ñ( ùa TàªЊ v ÐÖv@ù4 ´@ùÈ ø7 ñ ùa TàªƊ _ë Th Ðm@ù_ë Th Ðq@ù_ë TàªB ø ª`Jø7H@ùÈ ø6
_ëøH@ùÈ ø7 ñH ùa Tબ ¸0 5ùÒDùà@ù"@ù᪠1 ´ø ª @¹ 1B T ¹ ðù@ù@ùI@ù1 ´àª ?Öù ª1 ´@ùÈ ø7 ñ ùa TઠøÒDùà@ù@ùáªv @0 ´û ª @¹ 1B Th ¹ ðùAùh@ùI@ù0 ´àª ?Öú ª0 ´h@ùÈ ø7 ñh ùa Tàªu H@ù ëÀ0 T R Òéc)! øÏ©õ7 ù!M(Ë 2઼ÿû ª ´@ùÈ ø7 ñ ùa Tàª_ Û/ ´H@ùÈ ø7 ñH ùa TàªW (@ù ëà0 T R Òö+@ùéc)! úï©!M(Ë àªæ»ÿø ª ´H@ùÈ ø7 ñH ùa TàªA h@ùÈ ø7 ñh ùa Tàª: / ´(@ùÈ ø7 ñ( ùa Tàª2 i Ð)u@ù ë Th Ðm@ù ë Th Ðq@ù ë Tબ ù ª@<ø7@ùÈ ø6
ëù@ùÈ ø7 ñ ùa Tઠù, 5Øv@ù@¹ 1B T ¹¨ @ùB ð%@ùÿ# ¹õ©ÿ ¹å ù pâ'@ùãªäª Rçª ?Ö`, ´ö ª@ùÈ ø7 ñ ùa Tàªö h@ùÈ ø7 ñh ùa Tàªï ´@ùÈ ø7 ñ ùa Tàªç ´¨@ùÈ ø7 ñ¨ ùa Tàª߉ ¨Xøi Ð)y@ù)@ù?ë!C Tàªý{R©ôOQ©öWP©ø_O©úgN©üoM©é#Lmë+KmÿÃÀ_Ö` H1 ðc ɉRR ýÿ Ò6R÷ʉR VR×̉R ¥ µàªγÿø ª=ÿµ¡RéR àª+ ù ª ¾ÿµVéR¡Rô µàª¾³ÿû ª@¿ÿµ җ¡R¶éR(@ùHø6ç ઠú ª ¿ÿµ ÒöéR¡R§ X@ùx; ´[ @ù@¹ 1à Th@¹ 1ã TH@ù ø6 ҖìR¡RH@ùø6´ :@ùz9 ´8 @ùH@¹ 1à T@¹ 1ã T(@ù ø6 ¡RvïR(@ùèø6¼ ð ¥Gù ð)Gù ÒL¶ÿà6 ´ø ª~¶ÿ@ùè ø7¶¡R×ñRÊ P µàªy³ÿù ª@Æÿµ֡RôR6 àªֈ ø ªÆÿµסRVôR(@ùèø6 > µàªg³ÿú ª`Çÿµ¶ôRסR àªĈ û ªÇÿµ ÒöôRסRH@ù
ø6p z@ù1 ´v @ùH@¹ 1 TÈ@¹ 1£ Th@ùÈø6Ò Җ÷RסRA @ùÛ/ ´ @ùh@¹ 1ã TÈ@¹ 1 T@ù(ø6Õ vúRסRk ð ¥Gù ð-Gù Òúµÿ- ´ø ª,¶ÿ@ùHø7ö¡R×üRx þ µàª'³ÿø ªÎÿµ¢RÿRä ઠù ªÀÎÿµVÿR¢RM î µàª³ÿû ªàÏÿµ Ò¢R¶ÿR(@ùhø6@ àªq ú ªÀÏÿµ ÒöÿR¢Rh@ùÈ ø7 ñh ùa Tàªï : µ X@ùX' ´V @ù@¹ 1 TÈ@¹ 1# TH@ùHø6 ҖR¢RH@ùÈ ø7 ñH ùa Tઠ9 ´(@ùèø7 ñ( ù Tàªψ :@ùº# ´6 @ùH@¹ 1c TÈ@¹ 1 T(@ù¨ø6 ¢RvR(@ùhýÿ6 ´@ùÈ ø7 ñ ùa Tશ ` H1 ðc áªâª ð ¥Gù ð1Gù ҂µÿ` ´ø ª´µÿ@ùÈø76¢R×R ñ ùa Tઠp v Rw¢RÝÿÿ ¹h@¹ 1bàÿTh ¹H@ùÈ ø7 ñH ùa Tઠ( RúªòüÿöïR¡RËÿÿH ¹@¹ 1bàÿT ¹(@ùÈ ø7 ñ( ùa Tàª{ ( Rùªþüÿ¶¡R×ñRI H ¹È@¹ 1¢æÿTÈ ¹h@ùÈ ø7 ñh ùa Tàªi ( RûªbýÿöúRסRøª¦ÿÿh ¹È@¹ 1BæÿTÈ ¹@ùÈ ø7 ñ ùa TàªV ( Røªmýÿö¡R×üR$ ¹È@¹ 1"íÿTÈ ¹H@ùÈ ø7 ñH ùa TàªD ( RúªÒýÿöR¢RÿÿH ¹È@¹ 1ÂîÿTÈ ¹(@ùÈ ø7 ñ( ùa Tàª2 ( RùªÞýÿ6¢R×R` H1 ðc áªâª֠ÿ Òh@ùÆÿ64þÿå ¥ô0âcãàªá'@ùäª** ø7øgH©ú[I©ûÿS¼Rgûÿ ð ¥Gù ð)Gù Òç´ÿ` ´ø ªµÿ@ùø7V Rw։Reÿÿ ð ¥Gù ð-Gù Òٴÿ ´ø ª µÿ@ù¨ø7 RwډRWÿÿ ð ¥Gù ð1Gù Ò˴ÿ ´ø ªý´ÿ@ùHø7֠RwމRIÿÿ Ò ÒâR¡RH@ù(áÿ6
ÿÿ ÒVãR7¡RêþÿäRW¡RçþÿÖåR÷ Räþÿ»R*ûÿs½R(ûÿ¾R&ûÿ¶R÷ЉR¤ÿÿ֟R7҉R¡ÿÿöRwӉRÿÿV Rw։Rÿÿ RwډRÿÿ֠RwމRÿÿÇ R&üÿ RBüÿ¶¡RWñRÿÿ R³üÿ RÏüÿö¡RWüRÿÿ RAýÿ R]ýÿ6¢RWRÿÿV R÷ՉR|ÿÿ R÷ىRyÿÿ֠R÷݉RvÿÿÿÃÑé# müo
©úg©ø_©öW©ôO©ý{©ýóªü ªh °y@ù@ù¨ø¿ÿ7© С 觩èÿ©y °9s@ù¹øà ´ ñh Tôª7 ÐA
is8)
ÖõªºAøY ñ T ҈ ÐCùb h{xø ë` T _ëaÿÿT Òa{xøàªB RV* 5 _ë!ÿÿTL @ ´R
ñ` T ñ T5@ùµøH H RI ð)y J ðJU
ñI±µj °JA@ù@@ùJ ðJ© êÏ©é£ ©è Qè ùA ð!¸ $ Rc ü/ ù6 @ù¶øõªºAøùª_ ñ TF 6`@©¶ã7©õªºAøH ñË Tès©ûª¼@ù ñK
T ҈ ÐuEùb èzuø ëÀ Tµ ëaÿÿT ÒázuøàªB R
*
5µ ë!ÿÿTV 8Ô@©¸W8©6 @ù¶ø
@ùX u °µr@ù6`@©¶ã7©U `õÿ7özxø¶øõÿ´ü/ ùº@ù_ ñ T ҈ Ð%Dùb {{ø ë@ T{ _ëaÿÿT ҁ{{øàªB Ræ) 5{ _ë!ÿÿT܅ Àx µh °A@ù @ù* RH ð© K Rè«©H ðU é )Qè¯ ©é ùA ð!¸ E AR@ ð ô1 Ðc "£Rÿ Ò üÿ7øz{ø¸ø8üÿ´: Ñü/@ùy °9s@ùH ñóÿTu °µr@ù À ø7u{uø ´µøú+@ù
t µu °µr@ùü/@ùy °9s@ù÷ª_ ñ*l Tÿ© ÐHÛGùAùµ@ùR ?Öá ªàª R R R Ò`?Öó ªà; ù` ´h@¹ 1B Th ¹h@ùÈ ø7 ñh ùa Tઢ ÿ; ùt@¹HÛGùAùµ@ùà R ?Öá ªàª R R R Òà?Öû ªà7 ùÀ] ´h@¹ 1B Th ¹h@ù ø7 ñh ù Tÿÿ©ô 5h@¹¨ 5àª
@` ~ !` a Tc
- µàªUN ÷ ª ±a T\
`Á µ ð@ù Ð )Dù A` R ?Ö 1 T@ùàb Ð Cù! R ?Ö 1 T¿ëû/ ù`* T °!9ÑDù @ù@ùáªE ´ö ª @¹ 1B TÈ ¹ö7 ù ÐåAùÈ@ùI@ù ´àª ?Öø ªà3 ù ´È@ùÈ ø7 ñÈ ùa TàªB @ùi °)U@ù 렜 T Ò Réã)! ùשj °JQ@ùêG ù!M(Ë 2àªͷÿö ªà; ù ´(@ùÈ ø7 ñ( ùa Tàª' ÿ7 ùv ´@ùÈ ø7 ñ ùa TઠÈ@¹ 1B TÈ ¹È@ùÈ ø7 ñÈ ùa Tઠÿ; ùÿ3 ùHÛGùyBùÀ@ùÁ@¹ ?Öù ªØ
@ùw@ù ÐýAù[@ùàªáªý
´ô ª@ù@ùó+ ù ´àªáªâª ?Öô ª@ µ Òõ~RÍ àªò
ÿÿ©tíÿ4 ð
@ù Ð!)DùઠR ?Ö 1 I T
@ù Ð!Cùàª" R ?Ö 1ÀH Tt °V@ù¿ë T °!9ÑDù @ùâ@ùᪿ
@I ´ö ª @¹ 1B TÈ ¹ö7 ù ÐåAùÈ@ùI@ù(I ´àª ?Ö÷ ªà3 ù I ´È@ùÈ ø7 ñÈ ùa T઼
è@ù ë@H T Ò Réã)! øשj °JQ@ùêG ù!M(Ë 2àªI·ÿö ªà; ù ´@ùÈ ø7 ñ ùa Tણ
ÿ7 ù6G ´è@ùÈ ø7 ñè ùa Tàª
È@¹ 1B TÈ ¹È@ùÈ ø7 ñÈ ùa Tàª
õª Òÿ; ùÿ3 ùHÛGùyBùÀ@ùÁ@¹ ?Öù ªHÛGùAùóï ©ö ù` R ?Ö@= ´ø ªà7 ù ëK T °QGùhB ´ @ù?ëÀJ T+@ùE ´j @ù_ ñ Tka l@ùë I Tk! J ñaÿÿT)
@ù
@ùj °JA@ù@@ùé# ©A ð!Ø < õDRٱR* HÛGùAùóo ©@ R ?Ö÷ ª@ ´÷3 ùÿ렉 T °QGùHD ´é@ù?ëà T+@ù+{ ´j @ù_ ñ Tka l@ùë Tk! J ñaÿÿT)
@ù
@ùj °JA@ù@@ùé# ©A ð!Ø Ò ҕ<R9±Rà;@ùà ´ @ù¨ ø7 ñ ùA T+
à7@ùà ´ @ù¨ ø7 ñ ùA T#
à3@ùà ´ @ù¨ ø7 ñ ùA T
@ ð ô1 Ðc áªâªĝÿ ÒÖe ´È@ùeø7& w@ù ÐýAù@ùàªáª
ö ª ´È@ù@ù¨ ´àªáªâª ?Öö ª` µ Ò5bR³ @¹ 1B T ¹ó ªw@ù ÐñAù|@ùà ªáªè ô' ù v ´ú ª@ù @ùI ´àªáªâ ª ?Öà; ùu ´ú ª@ù I@¹) 1B TI ¹ú; ùi °)U@ù ëAt T[@ùû7 ùûu ´T @ùh@¹ 1 T@¹ 1# Tô; ùH@ùHø6 h ¹@¹ 1"ÿÿT ¹ô; ùH@ùÈ ø7 ñH ùa T઻ " Rúªèã! ûÿ©
ËàªO¶ÿü ªà3 ùô'@ù ´h@ùÈ ø7 ñh ùa Tન ÿ7 ù¼n ´H@ùÈ ø7 ñH ùa Tઠÿ; ù@ùÈ ø7 ñ ùa Tà ª ÿ3 ù ú ª? ñk T{ uઠA` áªâªU ø9 ñ!ÿÿTàª{ ÐåFù@ùA@ùôk ´@ Ð Ø!c óoE©Àl 5÷'@ùàªáª Ҁ?Öõ ª] l ´è@ùÈ ø7 ñè ùa Tàªm Uj ´¨@ùÈ ø7 ñ¨ ùa Tàªe È@¹ Ò 1¢N TÈ ¹s È@¹ 1B TÈ ¹w@ù ÐñAù:@ùàªáªN à~ ´ø ª@ù @ùI ´àªáªâª ?Öà7 ù`~ ´ø ª@ù @¹) 1B T ¹ø7 ùi °)U@ù ë!} T@ùù; ùÙ~ ´ @ù(@¹ 1 T@¹ 1# Tô7 ù@ùHø6 ( ¹@¹ 1"ÿÿT ¹ô7 ù@ùÈ ø7 ñ ùa Tàª" " Røªèã! ùÿ©
Ëશµÿú ªà3 ù ´(@ùÈ ø7 ñ( ùa Tઠÿ; ùºw ´@ùt °r@ùÈ ø7 ñ ùa Tઠÿ7 ùH@ùÈ ø7 ñH ùa Tàªý ó ú ª4@ù@ù ñdTú T@ùhÿÿµôª Ò Ò Ò h@¹ 1B Th ¹y@ù(@¹ 1B T( ¹ôªàªނ ø ª A` ᪧ
s ´ü ªÿ3 ùH7@ù @ù ùà ´ @ù¨ ø7 ñ ùA Tσ û/@ùóª ´(@ùÈ ø7 ñ( ùa TàªŃ ´@ùÈ ø7 ñ ùa Tઽ < ´ °åFùઠҐ°ÿ÷ ªÈ@ùÈ ø7 ñÈ ùa Tય w9 µ ÒusRY´Rxþÿ Ò Ò ÒٯR5)Rzþÿ Ò Ò5-R°Rmþÿ Ò Òu2R°Rhþÿ Ò ҕ3R¹°Rcþÿ@ Ð 3C °cD A>RaR>ÿÿ7 ùµDRٱRXþÿo Ày µàªÿö ªà7 ùà¶ÿµ Òõ5R àªô ÷ ªà3 ù ·ÿµ Ò56R öªø@ùø7 ùøw ´ô
@ù@¹ 1 T@¹ 1# Tô3 ùè@ùHø66 ÒÕ8Rù°R3þÿh =@ù @ùA Ð! K þÿÅ ð¥Pâã£#Ñàªáªäªf% ø7¶ãw©µXøüÿ@ Ð 2C °cD 8R"aRûÿ Òÿ3 ùU<Rþÿê ªj ´J@ù_ë¡ÿÿT# ¹@¹ 1"úÿT ¹ô3 ùè@ùÈ ø7 ñè ùa Tàª4 ( R÷ªôªzýÿRLüÿh =@ù @ùA Ð! ñýÿ!RCüÿÁRAüÿj J@ù
ë·ÿT ´è@ùÈ ø7 ñè ùa Tઠ°QEù@ùI@ù, ´àª ?Ö÷ ªà7 ù , ´ Ð
@ùàªáª ?Öà3 ù`+ ´ú ªè@ùÈ ø7 ñè ùa Tàªþ óo©ÿ7 ùH@ùÈ ø7 ñH ùa Tàªõ ÿ3 ùó ªw@ù ° ýAù[@ùàªá ªæ ( ´÷ ª@ù@ù( ´àªáªâª ?Ö÷ ªéªà µ= è@¹ 1éªB Tè ¹;u@ù °ñAù|@ùà ªáª͂ & ´ú ª@ù @ùI" ´àªáªâ ª ?Öà7 ù & ´ú ª@ù ëá! T[@ùû; ù»& ´T @ùh@¹ 1 T@¹ 1# Tô7 ùH@ùHø6 h ¹@¹ 1"ÿÿT ¹ô7 ùH@ùÈ ø7 ñH ùa T઩ " Rúªèã! ûÿ©
Ëàª=´ÿü ªà3 ù ´h@ùÈ ø7 ñh ùa Tઠÿ; ùü ´H@ùÈ ø7 ñH ùa Tઠÿ7 ù@ùÈ ø7 ñ ùa Tà ª ÿ3 ù| ú ª? ñË
T Ò{ uà ëÀ T§S©Bù @ý(Bù@ùàªâª; @ùBù ù@ù ù@¹ q«ýÿT Ò
IAùKBùi Iùzhø*@ùJ * ù ¹ ëêûÿT ñ}Ӊjkø*
@ùJ *
ùjkøI@¹©ýÿ4LáT9 4IBù) @ù)!¹KBùi Iùìÿÿ? qA TI@ùL@ù? ëJ T) I ùzhø*Aù' üÿ7zhø*}}Ók
l@ùm@ù
ëK T ùzhøj
JAùlBù
Ëjù* Q? qé
ªìýÿTÍÿÿ_ ùjkø*@ùJ * ùjkø*Aù+Aù,BùJ ˊ
*ùÀÿÿ i ùzhø*
JAù+Bùj
*ù·ÿÿઠ°åFùè@ùA@ùt ´@ ° Ø!ï óoE©` 5àªáª Ҁ?Öõ ªê U ´è@ùÈ ø7 ñè ùa Tàªú Õ ´¨@ùÈ ø7 ñ¨ ùa Tàªò È@¹ 1B TÈ ¹÷ªüªÈ@ùÈ ø7 ñÈ ùa Tàªå ´è@ùÈ ø7 ñè ùa Tàª݁ ´h@ùÈ ø7 ñh ùa TàªՁ ´h@ùÈ ø7 ñh ùa Tàª́ ¨Yøi )y@ù)@ù?ë¡@ Tà ªý{R©ôOQ©öWP©ø_O©úgN©üoM©é#LmÿÃÀ_ÖI@¹) 1B TI ¹ú7 ù ë`ÞÿT Ò Ò
ÿÿàª' ÷ ªà7 ù@ÔÿµUFR FRù±R÷ªvüÿh @ù @ùá ª 5HR²R÷ªy h @ù @ù᪠ÿ7 ùuHR õJRóoE©è@ù(ø7 ñè ùÁ TઠÒåþÿàªáª Òî õ ªóoE©ÿÿµVR²R÷ªNüÿe 7 ´ Ò|ÿÿ Ò ҕ^RٳREüÿ Ò ҵ_Rù³R@üÿê ªê ´J@ù_ë¡ÿÿTg Q 7 µàªz«ÿö ªà7 ù`bÿµ Ҹ àª׀ ø ªà3 ùÀbÿµ Ò ÒÕwRٴR'üÿ@ùù7 ùycÿ´ @ù(@¹ 1C* T@¹ 1c* Tô3 ù@ù*ø6X ÒuzRٴRüÿh @ù @ùáª+ Òõ~RYµRû/@ù üÿh @ù @ùáª! ÿ; ù5R Ò ÒzüÿµR@ùè ø7 ñé'@ù( ùa Tà'@ù) ÒYµRóoE©óûÿ Òküÿ÷'@ùàªáª ҅ õ ªóoE©¨üÿ ÒRYµRåûÿ Ò ú `- ´ Òû/@ù÷'@ùüÿ Ò Ò\R³RØûÿj J@ù
ëáxÿTÿ3 ù !9ÑDù @ù@ùáªé ´ö ª @¹ 1B TÈ ¹ö; ù °åAùÈ@ùI@ùÈ
´àª ?Öø ªà7 ùÀ
´È@ùÈ ø7 ñÈ ùa Tàªæ õª °QEùè@ùI@ù¨ ´àª ?Öù ªà; ù ´@ù ëÀ T Ò Réã)! úç©j JQ@ùêG ù!M(Ë 2àªh²ÿö ªà3 ù ´H@ùÈ ø7 ñH ùa Tઠ(@ùÈ ø7 ñ( ùa T઻ ÿ; ù °v ´@ùÈ ø7 ñ ùa T઱ È@¹ 1B TÈ ¹È@ùdÿ7 ñÈ ù¡cÿTદ ûÿ µàª³ªÿö ªà; ù õÿµì ઠø ªà7 ùõÿµ Ò5>RY±Rbûÿઠù ªà; ù öÿµ ÒY±R>Raûÿ@ùzöÿ´ @ùH@¹ 1c TÈ@¹ 1 Tö7 ù@ù¨ø6 Y±R5ARQûÿH ¹È@¹ 1ÂþÿTÈ ¹ö7 ù@ùÈ ø7 ñ ùa Tàªn ( Røªÿÿ Ò ÒU]R¹³R4ûÿh @ù @ùáªJ Ò5bRY´R+ûÿh @ù @ùáªA ÿ7 ùubR Ò Ò3üÿõdRÈ@ùÈ ø7 ñÈ ùa TàªJ Ò ÒY´Rû/@ùûÿ Ò$üÿó ªÿÿ©ÿ3 ù@ Ð ô1 °c ÁhRb´Réÿáâ£ãÃàªp% `ø7ê'F©è;@ùé£©é£ ©ê ùê ù` Rà ´ü ªàªá ª Òþ¬ÿà' ùÈ@ùÈ ø7 ñÈ ùa Tઠ@ùÈ ø7 ñ ùa Tà ª è'@ù¨ ´h u@ùé'@ù?ë Ti )m@ùê'@ù_ ë Ti )q@ùê'@ù_ ëà Tà'@ù ö ª ( ¹@¹ 1âÕÿT ¹ô3 ù@ùÈ ø7 ñ ùa Tàªô ( Røª·ùÿukR" é'@ù?ëöè'@ù@ùè ø7 ñé'@ù( ùa Tà'@ùã ø7 4à@ùÒÿÿ3 ùà @ùÿà#@ù¾ÿÿ; ù@7@ùáªâªãª% û/@ùüªóª °oùÿmR@7@ùáªâªãª% Ò ÒY´Rû/@ùóªúÿÅ h =@ù @ùA °!T"¨~ >þÿ Ò Òÿ7 ùõ5RPüÿ Rüÿ Òÿ; ùY±Rõ=R
úÿ Ò Òÿ7 ùwRٴRwúÿH ð=@ù @ùA !T"~ þÿõkRÓÿÿlRÑÿÿI á C©ã#@ùHªÿÿ©nRÿ; ùÉÿÿÿÃÑüo ©úg
©ø_ ©öW ©ôO
©ý{©ýôªó ªH ðy@ù@ù¨øÿ© ¡ è'©è©H ðq@ùèC ùÃ ´ ñH Tõª< Q
it8)
ÖúªYAø; ñ T ҈ Cù¶b Èzxø ë T ?ëaÿÿT ÒÁzxøàªB RK" @ 5 ?ë!ÿÿTA~ ´!R
ñ T ña T"@ùG H RI °)y J °JU
ñI±µJ ðJA@ù@@ùJ °J© êÓ©é£ ©È ðè ùA °!¸ ~ !Re ü' ù7 @ù÷; ùúªYAøûª? ñÊ TH 7d@©÷g©úª[Aøh ñë Tès©V@ùß ñ+ T ҈ uEù¼b {zø ë TZ ßëaÿÿT ҁ{zøàªB R" @ 5Z ßë!ÿÿT] 9@©ù©7 @ù÷; ù»
@ù\ B ðBp@ù7d@©tv@ù@¹ 1c T[ @õÿ7{xø÷; ù÷ôÿ´ü' ùY@ù? ñ T ҈ %Dù¶b Èz|ø ë@ T ? ëaÿÿT ÒÁz|øàªB RÚ! 5 ? ë!ÿÿTÐ} à µH ðA@ù @ù* RH °© K Rè«©H °U É ð)è¯ ©é ùA °!¸ µ} aR@ ° x3 c "¶Rÿ ÒO üÿ7è'@ùy|øù? ùüÿ´{ Ñü'@ùh ñjóÿTB ðBp@ùtv@ù@¹ 1 T à ø7è'@ùyzø ´âC ùû#@ù } À
µB ðBp@ùü'@ù ñê
Ttv@ù@¹ 1B T ¹ °@ùa" )a'íBù*}Cù+áEù)@ùÿ3 ¹ë'© Ré ¹ù« ©I Ré ¹à Ð `:ãªD R Ræª ?ֈ@ù@ ´ó ªÈ ø7 ñ ùa Tàª~ તF ô ª ´h@ùÈ ø7 ñh ùa Tàª~ ¨ZøI ð)y@ù)@ù?ëá Tàªý{N©ôOM©öWL©ø_K©úgJ©üoI©ÿÃÀ_ÖÈ ø7 ñ ùa Tàªl~ @ ° x3 c ¥RBRÿÿ@ ° x3 c fRâRÿh@ùèúÿ6ÛÿÿÅ ð¥âCãÃàªá ªäªc ø7÷gG©âC@ùtv@ù@¹ 1ôÿT ÿÿ!RsÿÿARqÿÿᛊRoÿÿG~ ÿCÑüo©úg©ø_ ©öW
©ôO ©ý{ ©ýõªó ªH ðy@ù@ù¨ø ¡è'©ÿ+ ù±CùH ðq@ùô£© ´öª7 Õ ´¿ ñ T¿
ña T4@©ô©Ù
@ù B ðBp@ù5 ´¿ ñ T¿
ñ T"@ù4 @ùuv@ù¨@¹ 1c T{ ¨þ~Óè(*I °)y J °JU ¿ ñI±J ðJA@ù@@ùJ °J© ë kÉ
ë' ©êשè ùA °!¸ Ú| ᵊR@ ° È4 c "AR¦ÿ ҅ úªYAø) ñë T ҈ áBùÛb é ùh{|ø ë T ? ëaÿÿT Òa{|øàªB RË @ 5 ? ë!ÿÿT
4 @ùô/ ùúªYAø
à ø7èz|ø¨ ´è/ ùôªù @ù ´| à µ( ñK Tè ùûª\@ù ñK T ҈ uEù×b èzzø ëÀ TZ ëaÿÿT ÒázzøàªB R¢ 5Z ë!ÿÿT B ðBp@ùuv@ù¨@¹ 1c T À ø7b{zø ´â3 ùù @ù |
µB ðBp@ù÷ª? ñª
Tuv@ù¨@¹ 1B T¨ ¹ °@ùa )a'9Bù*áEù)@ùÿ3 ¹ê'©ÿ ¹ê§ ©IRé ¹à ð ãª$ R Ræª ?֨@ù@ ´ó ªÈ ø7 ñ¨ ùa Tàª{} àªE ô ª ´h@ùÈ ø7 ñh ùa Tàªp} ¨ZøI ð)y@ù)@ù?ëÁ Tàªý{L©ôOK©öWJ©ø_I©úgH©üoG©ÿCÀ_ÖÈ ø7 ñ¨ ùa Tàª[} @ ° È4 c |R¢ʁR^ÿÿ@ ° È4 c ¾RBˁRýÿh@ùèúÿ6Ûÿÿå ¥È
âãcàªáªäªR ø7ôE©uv@ù¨@¹ 1côÿT£ÿÿ!³R>ÿÿsR<ÿÿA²R:ÿÿ7} ÿCÑüo©úg©ø_ ©öW
©ôO ©ý{ ©ýôªó ªH ðy@ù@ù¨ø ! %è'©ÿ+ ùH ðq@ùÿ£© ´õª6 ô ´ ñ T
ñÁ T7@©÷©¹
@ù ñÀ T
ñÁ T"@ùD øªAøy ñ T ҈ Å@ù¼b {zø ë TZ ëaÿÿT ҁ{zøàªB Rä À 5Z ë!ÿÿTÚ{ ` ´ʊR H °y I °)U * R ñ(±IµJ ðJA@ù@@ùJ °J© kj±êÓ©è§ ©é )å5é ùA °!¸ ¶{ ͊R@ ° h5 c ˁRÿ Òm 7 @ù÷/ ùøªAø
B ðBp@ù7 @ùtv@ù@¹ 1ã T7 Àùÿ7×zzø÷/ ùwùÿ´( ñ+ Tè ù @ù ñK T ҈ uEùºb H{{ø ëÀ T{ ëaÿÿT ÒA{{øàªB R 5{ ë!ÿÿT B ðBp@ùtv@ù@¹ 1C T À ø7Âz{ø ´â3 ùù @ù }{ @
µB ðBp@ù? ñª
Ttv@ù@¹ 1B T ¹ °@ùa )a' @ù*áEù)@ùÿ3 ¹ê'©ÿ ¹ê§ ©é Ré ¹à ð ãª$ R Ræª ?ֈ@ù@ ´ó ªÈ ø7 ñ ùa Tàªo| àªD ô ª ´h@ùÈ ø7 ñh ùa Tàªd| ¨ZøI ð)y@ù)@ù?ë Tàªý{L©ôOK©öWJ©ø_I©úgH©üoG©ÿCÀ_ÖÈ ø7 ñ ùa TàªO| @ ° h5 c aԊR¢ցRvÿÿ@ ° h5 c !֊RBׁRñÿh@ùèúÿ6Ûÿÿå ¥ä5âãcàªáªäªF à ø7÷E©tv@ù@¹ 1côÿT£ÿÿˊRVÿÿáʊRTÿÿ-| ÿCÑüo©úg©ø_ ©öW
©ôO ©ý{ ©ýôªó ªH ðy@ù@ù¨ø !!
è'©ÿ+ ùH ðq@ùÿ£© ´õª6 ô ´ ñ T
ñÁ T7@©÷©¹
@ù ñÀ T
ñÁ T"@ùD øªAøy ñ T ҈ %Dù¼b {zø ë TZ ëaÿÿT ҁ{zøàªB RÚ À 5Z ë!ÿÿTÐz ` ´¡áR H °y I °)U * R ñ(±IµJ ðJA@ù@@ùJ °J© kj±êÓ©è§ ©é °) %é ùA °!¸ ¬z !åR@ ° ü5 c ׁRxÿ Òm 7 @ù÷/ ùøªAø
B ðBp@ù7 @ùtv@ù@¹ 1ã T7 Àùÿ7×zzø÷/ ùwùÿ´( ñ+ Tè ù @ù ñK T Òh ðuEùºb H{{ø ëÀ T{ ëaÿÿT ÒA{{øàªB R 5{ ë!ÿÿT B ÐBp@ùtv@ù@¹ 1C T À ø7Âz{ø ´â3 ùù @ù sz @
µB ÐBp@ù? ñª
Ttv@ù@¹ 1B T ¹ @ùa i ð)a'}Cù*áEù)@ùÿ3 ¹ê'©ÿ ¹ê§ ©© Ré ¹à Ð °ãª$ R Ræª ?ֈ@ù@ ´ó ªÈ ø7 ñ ùa Tàªe{ àª}C ô ª ´h@ùÈ ø7 ñh ùa TàªZ{ ¨ZøI Ð)y@ù)@ù?ë Tàªý{L©ôOK©öWJ©ø_I©úgH©üoG©ÿCÀ_ÖÈ ø7 ñ ùa TàªE{ @ ü5ã ðc ìRbށRvÿÿ@ ü5ã ðc ÁíR߁Rçÿh@ùèúÿ6Ûÿÿå ¥ %âãcàªáªäª< à ø7÷E©tv@ù@¹ 1côÿT£ÿÿ!ãRVÿÿâRTÿÿ#{ ÿCÑüo ©úg ©ø_
©öW©ôO©ý{©ýóªö ªH Ðy@ù@ù¨øÿ©h ð á 飩 Á¡é£©ÿ? ùH Ðq@ùÿ# ©ã ´ ñ Tôª< è ða
is8)
Öö+ ùöªÚAøY ñ T Òh ð½Cùb ¨zxø ë T _ëaÿÿT ҡzxøàªB RÒ à 5 _ë!ÿÿTÈy @ ´úR° ñ T ñ T: @ùúO ù h RI )y J JU ñI±µJ ÐJA@ù@@ùJ J© êÏ©é£ ©è °1è ùA !¸ y R Z ÐZs@ù8ä@©øç©7 @ù÷C ù¯ ö+ ù7 @ù÷C ùöªÚAøùª_ ñJ TL ú ªö+ ù7`@©÷c©öªÛAøû' ù ñJ
Td ö+ ù8ä@©øç©7 @ù÷C ùöªÛAøh ñ+ Tès©Õ@ù¿ ñ T Òh ðuEùb {vø ë` TÖ ¿ëaÿÿT ҁ{vøàªB Rv 5Ö ¿ë!ÿÿTt 9hA©ùk ©7`@©÷c©
@ùs óÿ7{xø÷C ùWóÿ´Ú@ù_ ñ T Òh ð¡Cùb ¨z{ø ë` T{ _ëaÿÿT ҡz{øàªB RU 5{ _ë!ÿÿTKy à® µSûR( R" `ÿÿ7{{øøG ùÿÿ´ú ª( Ñè' ùÛ@ù ñ T Òh ðùCùb ¨z|ø ë` T ëaÿÿT ҡz|øàªB R3 5 ë!ÿÿT)y µüRH RI Ð)A@ù @ùè ùH © i Ré#©H U é °)1é# ©A !¸
y @ ¤6ã ðc áªB߁Rْÿ ҫ `üÿ7Y{|øùK ùüÿ´è'@ù Ñüªh ñ*ðÿTZ ÐZs@ùö+@ù à ø7è'@ùyvø ´úO ùû#@ù øx ¦ µZ ÐZs@ùüÛD© ñ* Ts ðhÚGùAùµ@ùà R ?Öá ªàª R R R Ҁ?Öõ ª h ´¨@¹ 1B T¨ ¹¨@ùÈ ø7 ñ¨ ùa Tàªòy hÚGùAùµ@ùà R ?Öá ªàª R R R Ҁ?Öô ª e ´@¹ 1B T ¹@ùÈ ø7 ñ ùa TàªÙy hÚGùAùµ@ùà R ?Öá ªàª R R R Ò`?Öó ª c ´h@¹ 1B Th ¹h@ù ø7 ñh ùÀ
T@¹©@¹?k Ti@¹(*¨
5ó+ ùàªöB ÷ ª ±a Tx ª µóªàªîB ø ª ±a Tx © µàªçB ú ª ±a Tx `© µ ëˋ TÜv@ù@¹ 1B T ¹àªËx ´ù ªàªÇx ø ª ´àªÃx û ª ´ @ùB i ð)! ' @ù*@ù)Y@ù Rë3 ¹û'©) Ré ¹ø« ©é ¹à Ð Ð
âªã ª Re Ræª ?Ö ´÷ ª@ùó+@ùÈ ø7 ñ ùa Tà ªoy (@ùÈ ø7 ñ( ùa Tàªhy @ùÈ ø7 ñ ùa Tàªay h@ùÈ ø7 ñh ùa TàªZy àªrA à ´ö ªº àªSy @¹©@¹?k@òÿTö+ ùv ÐÖ"9×ÒDùÀ@ùâ@ùáª2y S ´û ª @¹ 1B Th ¹h ðù@ùh@ùI@ùS ´àª ?Öø ª S ´h@ùÈ ø7 ñh ùa Tàª1y ×ÒDùÀ@ùâ@ùáªy R ´ù ª @¹ 1B T( ¹h ðCù(@ùI@ù¨R ´àª ?Öü ª R ´(@ùÈ ø7 ñ( ùa Tàªy ÙÒDùÀ@ù"@ùáªüx Q ´÷ ª @¹ 1B Tè ¹ú' ùh ðá@ùè@ùI@ùHQ ´àª ?Öú ª@Q ´è@ùÈ ø7 ñè ùa Tàªúx H@ù[ Ð{W@ù ë P T R Òéc)! ÷שô7 ù!M(Ë 2પÿù ª ´è@ùÈ ø7 ñè ùa Tàªâx 9O ´H@ùÈ ø7 ñH ùa TàªÚx @ù ë`N T R Òéc)! úç©ó7 ù!M(Ë 2à ªiªÿ÷ ª ´H@ùÈ ø7 ñH ùa TàªÄx (@ùÈ ø7 ñ( ùa Tઽx L ´@ùÈ ø7 ñ ùa Tà ªµx @ù ë L T R Òéc)! ùß©!M(Ë àªEªÿú ª ´(@ùÈ ø7 ñ( ùa Tઠx è@ùÈ ø7 ñè ùa Tàªx ZJ ´@ùÈ ø7 ñ ùa Tàªx H Ðu@ù_ë TI Ð)m@ù_ ë TI Ð)q@ù_ ë Tઠx ÷ ª `ø7H@ùÈ ø6
_ë÷H@ùÈ ø7 ñH ùa Tàªux ×F 5| ðAù¨@ùI@ùHH ´àª ?Öø ª@H ´×ÒDùÀ@ùâ@ùáªQx H ´û ª @¹ 1B Th ¹h ð¡Bùh@ùI@ù¨G ´àª ?Ö÷ ª G ´h@ùÈ ø7 ñh ùa TàªPx @ù[ Ð{W@ù ëG T@ùZH ´ @ùH@¹ 1ã T(@¹ 1 T@ù(ø6
H ¹(@¹ 1BÿÿT( ¹@ùÈ ø7 ñ ùa Tàª3x ( Røªéc)! úß©!M(Ë àªƩÿù ª ´H@ùÈ ø7 ñH ùa Tàª!x è@ùÈ ø7 ñè ùa Tàªx 9A ´@ù ø7 ñ ù Tz ÐH Ðq@ù?ëÀ THWGù(G ´)@ù?ë T+@ù V ´j @ù_ ñ Tka l@ùë Tk! J ñaÿÿT)
@ù
@ùJ ÐJA@ù@@ùé# ©A !Ø Òv 65RøîRúª! àªïw z ÐH Ðq@ù?ëûÿT¨@ùÈ ø7 ñ¨ ùa Tàªãw Aù@ùI@ùH; ´àª ?Öø ª@; ´ÕÒDùÀ@ù¢@ùáªÁw ; ´ü ª @¹ 1B T ¹h ð¡Bù@ùI@ù; ´à ª ?Öõ ª; ´@ùÈ ø7 ñ ùa Tà ªÀw @ù ëA; T@ù·< ´ @ùè@¹ 1ã Th@¹ 1 T@ù(ø6
è ¹h@¹ 1BÿÿTh ¹@ùÈ ø7 ñ ùa Tથw ( Røªéc)! ÷ש!M(Ë àª8©ÿü ª ´è@ùÈ ø7 ñè ùa Tàªw ¨@ùÈ ø7 ñ¨ ùa Tàªw |5 ´@ù ø7 ñ ù` TH °q@ùë THWGù(D ´@ù?ë T+@ù F ´j @ù_ ñ Tka l@ùëà Tk! J ñaÿÿT)
@ù
@ùJ °JA@ù@@ùé# ©! ð!Ø Ev V:RïRú ª àªbw H °q@ùë¡ûÿT@ùÈ ø7 ñ ùa TàªWw h ÐAùh@ùI@ù¨0 ´àª ?Öø ª 0 ´ÔÒDùÀ@ù@ùáª4w 0 ´û ª @¹ 1B Th ¹h СBùh@ùI@ùH0 ´àª ?Öô ª@0 ´h@ùÈ ø7 ñh ùa Tàª3w @ùI °)U@ù ë0 T@ùu1 ´ @ù¨@¹ 1ã TÈ@¹ 1 T@ù(ø6
¨ ¹È@¹ 1BÿÿTÈ ¹@ùÈ ø7 ñ ùa Tàªw ( Røªö+@ùéc)! õÓ©!M(Ë àª¨¨ÿû ª ´¨@ùÈ ø7 ñ¨ ùa Tàªw @ùÈ ø7 ñ ùa Tàªüv * ´@ùÈ ø7 ñ ùa Tàªôv H °q@ùë@D THWGù3 ´i@ù?ë C T+@ùË? ´j @ù_ ñ Tka l@ùëB Tk! J ñaÿÿT)
@ù
@ùJ °JA@ù@@ùé# ©! ð!Ø ³u v?R8ïRúªô ªõªH@ùÈ ø7 ñH ùa TàªÊv Ò ð ¤6ã Ðc áªâªrÿ ÒùªD µ* Ò Ò Ò8ìRv Rðÿÿ Ò ÒXìRV Rëÿÿ ÒxìR6
Rçÿÿu µàª½ ÿû ª ÿµ ҘîRö"RÝÿÿàªv ø ª@ÿµ Ò Ò6#RîR u µàªª ÿù ª ®ÿµ Ò Ò ҈îRèK ¹#R@ùÈ0ø6 àªv ü ª ÿµ ÒÖ#RîRèK ¹h iu @F µàª ÿ÷ ª®ÿµ Ò. àªðu ú ª ¯ÿµ Òv$R W@ùE ´Y @ùè@¹ 1 T(@¹ 1# TH@ùHø6Ö Ò Ò'R @ùZC ´ @ùH@¹ 1ã Tè@¹ 1 T@ù(ø6Õ Ò Òö)RîRèK ¹A @ùYA ´ @ù(@¹ 1ã TH@¹ 1 T@ù(ø6Õ Ò ҈îRèK ¹Ö,R@ù'ø6< h Ð ¥Gùh Ð5Gù Ò£ÿ`> ´ú ªD£ÿH@ù¨ø7¸îR6/R ñH ùÁìÿTcÿÿઢu ø ª ¸ÿµ ÒøîRv1R^ÿÿ u `< µàª4 ÿû ª ¸ÿµß àªu ÷ ª ¸ÿµ ÒèîRèK ¹ö1R@ù¨!ø6 R Òáýÿ Ò Ò ÒèîRèK ¹¶4R@ù( ø6 RÖýÿàªzu ø ª Åÿµ ÒïR6Rõª5ÿÿât µàª ÿü ª Åÿµ Ò Ò ÒïRèK ¹Ö6R à ªdu õ ªÀÄÿµ Ò Ò Ò7RïRèK ¹õªÒ R Ò?þÿ Ò Ò ÒïRèK ¹Ö9Rõª@ùø6Ô R3þÿH °=@ù @ù! ð! »t ÚýÿàªBu ø ª Ïÿµ Ò8ïR¶;Rõªô ªüþÿ©t @1 µàªҟÿû ªÏÿµ àª1u ô ª Ðÿµ Ò Ò(ïRèK ¹6<Rõªô ª@ùø6¬ R ҙþÿ Ò Ò(ïRèK ¹ö>Rõªô ª@ùhø6 Rþÿè ¹(@¹ 1"æÿT( ¹H@ùÈ ø7 ñH ùa Tàªu ( RúªüÿH ¹è@¹ 1BæÿTè ¹@ùÈ ø7 ñ ùa Tà ª
u ( Rüª®üÿV-RîR¯þÿ( ¹H@¹ 1BæÿTH ¹@ùÈ ø7 ñ ùa Tàªsu ( RøªÁüÿ ҸîR6/R¤þÿå ¥0âcãàªá ªäªt ø7÷cH©ùkI©UûÿH °=@ù @ù! ð! Ft òýÿê ªJ ´J@ù_ë¡ÿÿTjýÿH °=@ù @ù! ð! 9t wþÿê ªÊ
´J@ù_ë¡ÿÿTéýÿSüRûÿh Ð ¥Gùh Ð5Gù Ò¢ÿ " ´ú ªI¢ÿH@ùH ø7ÖR ñH ù T Òó+@ùíRiþÿ Ò Ò Ò ÒVRÈíRèK ¹ó+@ù ҖRèíR Ö RîR R¨íRèK ¹ó+@ù(@ùÈ ø7 ñ( ùa Tàªu Ò Ò ´@ùÈ ø7 ñ ùa Tà ª u ´@ùÈ ø7 ñ ùa Tàªu øK@¹ ´h@ùÈ ø7 ñh ùa Tàªût ´è@ùÈ ø7 ñè ùa Tàªót ZÄÿµ(þÿXîR6 R&þÿûR½úÿê ª
´J@ù_ë¡ÿÿT J °J@ù
ë ÿTäüÿsýR°úÿþR®úÿJ °J@ù
뀯ÿThýÿ ҘíRÖRó+@ù þÿJ °J@ù
ë!¾ÿTh@ùÈ ø7 ñh ùa TàªÈt Úv@ùH@¹ 1B TH ¹h ð@ùB i Ð)! % @ù*@ù)Y@ù Rë# ¹û'©) Ré ¹ê ùà ° Ð
â'@ùãªäª& Rç ª ?Öà ´÷ ªH@ùÈ ø7 ñH ùa Tતt ઼< ´ö ªõªô ªóª ´¨@ùÈ ø7 ñ¨ ùa Tàªt ´@ùÈ ø7 ñ ùa Tàªt ´h@ùÈ ø7 ñh ùa Tàª
t ´è@ùÈ ø7 ñè ùa Tàª}t ¨ZøI °)y@ù)@ù?ëÁ Tàªý{P©ôOO©öWN©ø_M©úgL©üoK©ÿCÀ_ÖBRXïRóªýÿøïRÖCRõªô ªóªýÿ ÒøìRVRó+@ùýÿ ÒíRRó+@ùýÿ Ò8íRÖRó+@ùýÿó+@ùíRýÿTt Ò Ò Ò6$R÷ýÿ RXûÿ Rtûÿ Rûÿ ҸîR¶.Rzýÿ Ò Ò ÒèîRèK ¹¶1R@ùHæÿ66ÿÿ Ò Ò Ò(ïRèK ¹ö;Rõªô ª@ùèäÿ6+ÿÿ ҘíRVRó+@ùaýÿÿCÑüo©úg©ø_ ©öW
©ôO ©ý{ ©ýôªó ªH °y@ù@ù¨øh Ð!!
è'©ÿ+ ùH °q@ùÿ£© ´õª6 ô ´ ñ T
ñÁ T7@©÷©¹
@ù ñÀ T
ñÁ T"@ùD øªAøy ñ T Òh Ð%Dù¼b {zø ë TZ ëaÿÿT ҁ{zøàªB RÙ À 5Z ë!ÿÿTÏr ` ´APR ( ðy ) ð)U * R ñ(±IµJ °JA@ù@@ù* ðJ© ë Ðkj±êÓ©è§ ©é °)%é ù! ð!¸ «r ÁSR ð `7ã Ðc "ðRwÿ Òm 7 @ù÷/ ùøªAø
B °Bp@ù7 @ùtv@ù@¹ 1ã T7 Àùÿ7×zzø÷/ ùwùÿ´( ñ+ Tè ù @ù ñK T Òh °uEùºb H{{ø ëÀ T{ ëaÿÿT ÒA{{øàªB R 5{ ë!ÿÿT B Bp@ùtv@ù@¹ 1C T À ø7Âz{ø ´â3 ùù @ù rr @
µB Bp@ù? ñª
Ttv@ù@¹ 1B T ¹h Ð@ùa i °)a'}Cù*áEù)@ùÿ3 ¹ê'©ÿ ¹ê§ ©É Ré ¹à P"ãª$ R Ræª ?ֈ@ù@ ´ó ªÈ ø7 ñ ùa Tàªds àª|; ô ª ´h@ùÈ ø7 ñh ùa TàªYs ¨ZøI )y@ù)@ù?ë Tàªý{L©ôOK©öWJ©ø_I©úgH©üoG©ÿCÀ_ÖÈ ø7 ñ ùa TàªDs Ð `7ã °c ¡ZRBúRvÿÿ Ð `7ã °c a\RâúRæÿh@ùèúÿ6Ûÿÿå ¥$âãcàªáªäª; à ø7÷E©tv@ù@¹ 1côÿT£ÿÿÁQRVÿÿ!QRTÿÿ"s ÿÑüo ©úg
©ø_©öW©ôO©ý{©ýCöªú ªH y@ù@ù¨øh °A ÿÿ©
Áé«© a 飩 ¡$J Jq@ùéÿ©ñDùê× ©-EùôW ù ´ß ñÈ T÷ª( è+ ùè °u
iv8)
Öú ùøªAøs ñ T Òh °YCùüb {zø ë` TZ ëaÿÿT ҁ{zøàªB RÌ 5Z ë!ÿÿTÂq ` ´AiR È
Ñ
ñÈ T[ {s@ùé °) +ih8J @ Ö4@ù5 @ù;@ù!@©ü ¨ RI Rß
ñ(±) Ð)y * ÐJU I±J JA@ù@@ù* ÐJ© ê󩎣 ©è %5è ù! Ð!¸ q ÁpRr ú ù( @ùè' ùèG ùøªAøóª ñJ TT ($@©é#©è§©øªAø ñk Té#©@ù ñ+ T Òh °uEùùb ({|ø ë
T ëaÿÿT Ò!{|øàªB Rx @ 5 ë!ÿÿTe )ì@©éo ©( @ùé#©èG ùøªAøb ;TA©û× ©($@©é#©è§©øªAø 5ÐA©õS
©"ì@©âo ©! @ùáG ùè
@ù¡ `òÿ7è+@ùyzøèG ùè' ùÈñÿ´@ù ñ T Òh °¡Aùùb ({|ø ë@ T ëaÿÿT Ò!{|øàªB RC 5 ë!ÿÿT9q µH A@ù @ù* R( Щ K Rè«©( ÐU é )%5è¯ ©é ù! Ð!¸ q jR Ð 8ã °c BûRêÿ Òp üÿ7è+@ùy|øèK ùè# ùèûÿ´h Ñú@ù ñêñÿT[ {s@ùM à ø7è+@ùy|ø ´ûO ùè@ù q µ[ {s@ùè @ù ñë Téë©è ù@ù? ñ« T Òh ° iAùúb H{sø ëà Ts ?ëaÿÿT ÒA{søà ªB Rô 5s ?ë!ÿÿT ø7è+@ùysø¨ ´èS ùõªèëB© áp ú#C©À µ ñ+ Té#©@ù ñ T Òh ° ýEùùb ({sø ë Ts ëaÿÿT Ò!{søà ªB RÏ à 5s ë!ÿÿT âD© ø7è+@ùysøÈ ´èW ùôªè@ùâD© ¹p âD©è @ù` µ ñ TàªãªäªåªF; ¨ZøI )y@ù)@ù?ë Tý{Q©ôOP©öWO©ø_N©úgM©üoL©ÿÀ_Öå ¥$5âcã#àªá+@ùäªÃ `ø7áH©û×I©ôW@ùáÿÿ!mRmÿÿAlRkÿÿAjRiÿÿÁmRgÿÿakReÿÿ¦q ÿCÑüo ©úg ©ø_
©öW©ôO©ý{©ýóªà' ùH y@ù@ù¨ø¿ÿ8©h °¡ A觩èÿ©Z Zs@ùºøà ´ ñH Tôª5 è °
is8)
ÖøªAøy ñ T Òh °Cùb {wø ë T÷ ëaÿÿT ҁ{wøàªB RX @ 5÷ ë!ÿÿTNp ´ðRj
ñ T ña T(@ù¨ø6 @©¶£8©àª69 ÷ ª ±! T H R) Ð)y * ÐJU
ñI±µJ JA@ù@@ù* ÐJ© êÏ©é£ ©è ÐE
è ù! Ð!¸ p õRE 6 @©¶£8©øªAø( ñê Ts )@ù6 @©¨'9©¶ø
@ùk 6 @ù¶øøªAøû# ù ñJ T @øÿ7¶zwø¶øö÷ÿ´ù# ù@ù ñ T Òh °}Dùb ({|ø ë@ T ëaÿÿT Ò!{|øàªB Rÿ 5 ë!ÿÿTõo º µH A@ù @ù* R( Щ K Rè«©( ÐU é Ð)E
è¯ ©é ù! Ð!¸ Úo AñR Ð Ø8ã °c "R¦ÿ Òð üÿ7¨z|ø¨ø(üÿ´è#@ù Ñ( ñË Tè# ùûª @ù ñ T Òh °uEùb ¨zxø ëà T ëaÿÿT ҡzxøàªB Rà 5 ë!ÿÿT à ø7h{xø¨ ´¨øù#@ùõª ±o õª ¹ µ? ñJ¤ Tઠ8 ÷ ª ±a T§o @« µ´[y©ÿ©h °ÙGùAùµ@ùR ?Öá ªàª R# R$ R Ò`?Öó ªà3 ù w ´h@¹ 1B Th ¹h@ùÈ ø7 ñh ùa Tણp ÿÿ©a@¹ó# ùav 4| °Ã>@ùyBù`@ù ?Öø ªy
@ù3@ùi °!DùઠR ?Ö 1Àw T8 ´h Ð@ù Ñઠ?Ö(BҨ%°ò(óÒò(®çògn A(a a m T@ùh UGù?ëà: T*@ù
: ´I @ù? ñ«] TJa K@ùëÀ9 TJ! ) ñaÿÿTå ßëÀ Tbp 4@ùà ù@ù¿ ñ¤Zú T@ùhÿÿµ Ò Òÿ ù àªo à/ ù ´ó ª R
p ô ªà+ ù ´ ùÿ/ ùr ¨@¹ 1B T¨ ¹º@ùH@¹ 1B TH ¹àªBo à ùh !9ýDù @ùb@ùáª*p t ´ü ª @¹ 1B T ¹ü/ ùh °Bù@ùI@ùÈs ´à ª ?Öû ªà3 ùÀs ´@ùÈ ø7 ñ ùa Tà ª'p h@ùI )U@ù ëÀr T Ò Ré£)! ôÛ©!M(Ë àªµ¡ÿü ªà+ ù ´@ùÈ ø7 ñ ùa Tàªp ÿ/ ùüq ´h@ùÈ ø7 ñh ùa Tàªp àª5o àp ´û ª@ R²o r ´ô ª ì©ÿ©ÿ3 ù ´H@ùÈ ø7 ñH ùa Tàªóo | °Ã> ´¨@ùÈ ø7 ñ¨ ùa Tàªéo à @ùà ´ @ù¨ ø7 ñ ùA Táo h !9ÑDù @ùb@ùáªÅo b ´ö ª @¹ 1B TÈ ¹ö+ ùó#@ùh °}FùÈ@ùI@ùb ´àª ?Öõ ªà3 ùb ´È@ùÈ ø7 ñÈ ùa TàªÁo Rqo û ªà+ ù b ´@¹ 1B T ¹t ù~n ö ªà/ ùÀa ´h áAù" ðBP@ùàª{n Àø7¨@ùA@ùs{ ´ Ø!o `} 5àªáªâª`?Öú ªo Z| ´¨@ùÈ ø7 ñ¨ ùa Tàªo ÿ3 ùh@ùÈ ø7 ñh ùa Tàªo ÿ+ ùÈ@ùÈ ø7 ñÈ ùa Tàªo ÿ/ ùH@¹ 1B TH ¹V @ù@ùyBù@@ùA@¹ ?Öó ª;@ùàbi Cù! R ?Ö 1 v Tú ùx ´zؚ
Ò Ò Ò Ò ҙ8RX#R Òè'@ùu@ùh ýAù{@ùàªá ªXo `u ´õ ª@ù@ù ´àªáªâª ?Öõ ªÀ µ¥ ¨@¹ 1B T¨ ¹ô ùè'@ùu@ùh ñAù|@ùà ªáª?o àu ´û ª@ù @ù ´àªáªâ ª ?Öà/ ù`u ´û ª@ù) ð)U@ù ë¡ T|@ùü+ ùv ´s @ù@¹ 1 Th@¹ 1# Tó/ ùh@ùHø6 ¹h@¹ 1"ÿÿTh ¹ó/ ùh@ùÈ ø7 ñh ùa Tàªo " Rûªè£! üÿ©
Ëઠÿó ª ´@ùÈ ø7 ñ ùa Tà ªo ÿ+ ù3o ´h@ùÈ ø7 ñh ùa Tàªÿn ÿ/ ùh@ùÈ ø7 ñh ùa Tàª÷n îm ó ª_ ñë Tè'@ù ó}Óàªáªâªãªäªå ªÅl ÖZ ñáþÿTàªØm h åFù¨@ùA@ùtl ´ Ø!Àn ú @ùm 5àªáª Ҁ?Öó ª»n ô@ùól ´¨@ùÈ ø7 ñ¨ ùa TàªÊn ³j ´h@ùÈ ø7 ñh ùa TàªÂn H@¹ Ò 1B TH ¹õªó#@ùó1 µ i@¹) 1B Ti ¹û/ ù) ð)U@ù ë ïÿT Ò җÿÿ)@ù?ëÀ T©ÿÿµ) ð)@ù ë# TH ð!9ÑDù @ùb@ùáªn @l ´ö ª @¹ 1B TÈ ¹ö3 ùh ÁBùÈ@ùI@ùl ´àª ?Öõ ªà+ ùl ´È@ùÈ ø7 ñÈ ùa Tàªn | ãAù@ùI@ùl ´àª ?Öö ªà3 ù l ´¨@ù; ð{W@ù ë@l T Ò Ré£)! øÛ©J ðJqGùê? ù!M(Ë 2ઠÿ÷ ªà/ ù ´@ùÈ ø7 ñ ùa Tàªan È@ùÈ ø7 ñÈ ùa TàªZn ÿ3 ùj ´¨@ùÈ ø7 ñ¨ ùa TàªQn 8 ðw@ùÿ+ ùÿë9 ð9o@ùäYúäZú Tÿëó àªËm ó ªàkø7è@ùÈ ø7 ñè ùa Tàª:n 4ãAù@ùI@ù¨g ´àª ?Öó ªà/ ù g ´! ð!H@ùàªb R¹m à+ ùÀg ´õ ªh@ùÈ ø7 ñh ùa Tàª!n ÿ/ ù¿ë T¿ëà T¿ë Tઠm ó ª`ø6 Ò Ò Ò Ò Ò ÒyR* ¿ëó¨@ùÈ ø7 ñ¨ ùa Tàªn ÿ+ ùS 4h áEù@ùI@ù¨f ´àª ?Öô ªà/ ù f ´@ù ë!g T@ùõ3 ùh ´
@ù¨@¹ 1 Th@¹ 1# Tó/ ù@ùHø6 ¨ ¹h@¹ 1"ÿÿTh ¹ó/ ù@ùÈ ø7 ñ ùa TàªÛm " Rôªè£! õÿ©
Ëàªoÿö ªà+ ù ´¨@ùÈ ø7 ñ¨ ùa TàªÉm ÿ3 ù¶a ´@ùÈ ø7 ñ ùa TàªÀm h FùઠRIm ô ªà/ ùà` ´È@ùÈ ø7 ñÈ ùa T઱m ÿ+ ùë Tëà Të Tàª0m ó ª`ø6 Ò Ò Ò Ò Ò ҙRó ëó@ùÈ ø7 ñ ùa Tàªm s 4h A/ @ù*@¹J 1 T* ¹h A/
h !/ @ù*@¹J 1 T* ¹h !/@ùh ¥Gùè£! ÿß©âA²ÿà/ ù`B ´ó ªÿh@ùÈ ø7 ñh ùa Tàªnm Ò Ò Ò Ò Òÿ/ ùÙ RX"Ró#@ùà3@ùà ´ @ù¨ ø7 ñ ùA T]m à/@ùà ´ @ù¨ ø7 ñ ùA TUm à+@ùà ´ @ù¨ ø7 ñ ùA TMm ´È@ùÈ ø7 ñÈ ùa TàªEm ´@ùÈ ø7 ñ ùa Tà ª=m ´h@ùÈ ø7 ñh ùa Tàª5m ° Ø8ã c áªâªޅÿ Ò ´h@ùÈ ø7 ñh ùa Tàª%m ´H@ùÈ ø7 ñH ùa Tઠm ´è@ùÈ ø7 ñè ùa Tàªm ´@ùÈ ø7 ñ ùa Tàª
m ´H@ùÈ ø7 ñH ùa Tàªm ¨Zø) ð)y@ù)@ù?ëÁJ Tàªý{P©ôOO©öWN©ø_M©úgL©üoK©ÿCÀ_Ö Ò Ò Ò Ò Ò ÒþR Rÿÿh ©Gùh UGù Òÿà/ ù J ´ó ªñÿh@ùÈ ø7 ñh ùa TàªÜl Ò Ò Ò Ò Ò Òÿ/ ù¹Rø Rmÿÿ Ò Ò Ò Ò Ò Ò9RX Reÿÿ®k `G µàªזÿö ªà+ ùó#@ù ÿµ Ò Ò Ò Ò7RX#RVÿÿàª.l õ ªà3 ù ÿµ Ò Ò Ò Ò ÒY7RX#RIÿÿ Ò Ò Ò ҹ7RX#RBÿÿ Ò Ò Ò ÒY8RX#R;ÿÿk À µàªÿü ªà/ ù ÿµÔ&R/ à ª
l û ªà3 ùÿµÿ3 ù'Ró@ù t@ùô/ ùTÿ´s @ù@¹ 1#' Th@¹ 1C' Tó3 ùh@ùh'ø6? ´)R ü/@ùÿ3 ù4*Ró@ù| ´@ù(ø7 ñ ùÁ Tà ªql t*Rh@ùÈ ø7 ñh ùa Tàªhl ó@ùÿ3 ùÿ/ ùà+@ùà ´ @ù¨ ø7 ñ ùA T]l ÿ+ ù ° Ø8ã c áªâ"R
ÿácâãCઠø7È@ù) ð)]@ù ëA4 TÈ@¹ 1B TÈ ¹àªuk ü ª`4 ´ Ròk û ª`4 ´| ùàªáªk 4 ´ô ªÈ@ùÈ ø7 ñÈ ùa Tàª1l h@ùÈ ø7 ñh ùa Tàª*l à/@ùà ´ @ù¨ ø7 ñ ùA T"l ÿ/ ùà3@ùà ´ @ù¨ ø7 ñ ùA Tl ÿ3 ùà+@ùà ´ @ù¨ ø7 ñ ùA Tl ÿ+ ùh6@ù @ù ùà ´ @ù¨ ø7 ñ ùA Tl ó @ù ´H@ùÈ ø7 ñH ùa Tàªük Ó ´h@ù ø7 ñh ù T| Ã>üÿ Ò Ò Ò9/R#Rh6@ù @ù ùà ´ @ù¨ ø7 ñ ùA Täk ó @ù ´H@ùÈ ø7 ñH ùa TàªÛk ´h@ùÈ ø7 ñh ùa Tà @ùÓk Ò Ò Òjþÿàªáªâª2k ú ª
ÿµ Ò Ò Ò Ò Ò Ò Ò Òy?Rø#RXþÿ¢j à& ´ Ò Ò Ò Ò ҹ8RX#RNþÿ( Ð@ù @ùá ªj Ò Ò Ò ҹCRx$RúÏC©Bþÿå ¥D
⣣ãÑàªáªäª®
Àø7¶Xøàªu3 ÷ ª ±[ÿTÕúÿ( Ð@ù @ùáªzj ÿ/ ùùCR yFRúÏC©ô@ù¨@ùÈ ø7 ñ¨ ùa Tàªk Ò Ò Ò Òx$Rþÿ Òfüÿàªáª Òßj ó ªôkC©¥üÿ Ò Ò Ò ÒùORx$R þÿ Òô@ùüÿPj ´ җüÿAôRjúÿ Ò Ò Ò Ò ÒY Røýÿ Ò Ò Ò Ò Ò ÒY!R Ò Ò Ò Ò ҙ!R"Réýÿ ¹h@¹ 1ÙÿTh ¹ó3 ùh@ùÈ ø7 ñh ùa TàªAk ( Rûª ûÿñRAúÿ!j µàªJÿö ªà3 ùàÿµ Ò Ò Ò Ò ÒÀ ણj õ ªà+ ùÿµ Ò Ò Ò Ò Ò ҙ RG àªj ö ªà3 ù@ÿµ Ò Ò Ò Ò Òù R; ¸@ùøÿ´³
@ù@¹ 1ã Th@¹ 1 Tó+ ù¨@ù(ø6= Ò Ò Ò Ò ҙR' !òRúÿÁòRúÿàªüj \ ðÃ>ûÿàªmj ó ªà/ ù ÿµ Ò Ò Ò Ò Ò ÒùR Ò Ò Ò Ò Ò Ò9R8!R~ýÿ Ò Ò Ò Ò Ò ÒR!Ruýÿ ¹h@¹ 1BùÿTh ¹ó+ ù¨@ùÈ ø7 ñ¨ ùa TàªÍj ( RõªVüÿàª>j ô ªà/ ù ÿµ Ò Ò Ò Ò ÒYR Ò Òãüÿ Ò Ò Ò Ò ÒÙR ÒÚüÿ Ò Ò Ò Ò ÒYRX!REýÿ¬j àªMj ö ª Ìÿµ Ò ҹ0R8#R³þÿ Òù0R8#R¯þÿ91R8#R¬þÿ ÒÙ1R8#R¨þÿ Ò Ò Ò Ò Ò Ò9Rºýÿ Ò Ò Ò Ò Òÿ+ ù7RÑþÿ( Ð=@ù @ù ð!T"ki Äþÿ( Ð=@ù @ù ð!T"di ÿÿ Ò Ò Ò Ò Ò Òÿ3 ùY RÿÿÿCÑé#
müo ©úg ©ø_
©öW©ôO©ý{©ýóª( Ðy@ù@ù¨øH ð !$觩ÿG ù7 Ð÷r@ùÿß©£ ´õª6 ´ ñ T
ñ Tà# ù8P@©øÓ©¹
@ù ñ@ T
ñá Tà# ù4@ùô; ùG à# ù8 @ùø7 ùúªYAøN à# ùúª[Aøy ñ T ÒH ðñ@ù¼b {xø ëà T ëaÿÿT ҁ{xøàªB R
5 ë!ÿÿT
i ` ´_R ( y ) )U * R ñ(±Iµ* ÐJA@ù@@ù* J© Ë ðkj±êÏ©è§ ©é )¹>é ù! !¸ æh bR 9à ðc B%R²ÿ Òú à# ù4 Дr@ù8 @ùø7 ùÿÿ©ÿ+ ùàªi ±a TK àùÿ7Øzxøø7 ùùÿ´( ñ+ Tè' ù\@ù ñ T ÒH ðuEù»b h{zø ë TZ ëaÿÿT Òa{zøàªB RÆ À 5Z ë!ÿÿT 4 Дr@ùÿÿ©ÿ+ ùàªji ± T$ À ø7Ôzzø ´ô; ùù'@ù ¬h ਠµ4 Дr@ù? ñ
¡ Tÿÿ©ÿ+ ùàªWi ±@¢ Tõ ª\ ðÛGùAùµ@ùR ?Öá ªàª" R# R$ R Ò`?Öó ªà3 ùV ´h@¹ 1B Th ¹ô' ùh@ùÈ ø7 ñh ùa Tàªi ÿ/ ùX Ð#9ÓDù @ù@ùáªi àT ´ö ª @¹ 1B TÈ ¹ö3 ùH ðù@ùÈ@ùI@ù(U ´àª ?Öà+ ù U ´È@ùÈ ø7 ñÈ ùa Tàªi ÿ3 ùÓDù @ù@ùáªdi @T ´ú ª @¹ 1B TH ¹H ðCùH@ùI@ù(T ´àª ?Öû ª T ´H@ùÈ ø7 ñH ùa Tàªci h@ù: ÐZW@ù ë@S T R Òéã)! öÏ©J ðJFùêG ù!M(Ë 2àªîÿô ªà3 ù ´È@ùÈ ø7 ñÈ ùa TàªHi R ´h@ùÈ ø7 ñh ùa Tàª@i ö+@ùÈ@ù ë`Q T R Òéã)! ô3@ùùÓ©!M(Ë àªΚÿø ªà/ ù ´(@ùÈ ø7 ñ( ùa Tàª(i @ùÈ ø7 ñ ùa Tàª!i ÿ3 ùO ´È@ùÈ ø7 ñÈ ùa Tàªi ÿ+ ù( Ðu@ù ëÀ T) Ð)m@ù ë@ T ë Tàªh ô ª }ø7@ùÈ ø6
ëô@ùÈ ø7 ñ ùa Tàªýh L 5ó ùs
@ùè'@ù ëÀ Tíh ù ª4@ù @ù ñWúÁ T@ùhÿÿµ Ò Ò Ò àªh à/ ù ´ô ª Rh ö ªà+ ùY Ð9#9 ´Ô ùÿ©v @¹ 1B T ¹@ùh@¹ 1B Th ¹à ªËg ø ªH Ð!9ýDù @ù@ù᪳h X ´ö ª @¹ 1B TÈ ¹ö/ ùô'@ù÷ªH ðBùÈ@ùI@ùHX ´àª ?Öú ªà3 ù@X ´È@ùÈ ø7 ñÈ ùa Tમh H@ù ë`W T Ò Réã)! öÓ©!M(Ë àª>ÿô ªà+ ù ´È@ùÈ ø7 ñÈ ùa Tàªh ÿ/ ùV ´H@ùÈ ø7 ñH ùa Tàªh ાg U ´ú ª@ R;h @W ´ö ªè©ÿ©ÿ3 ù ´h@ùÈ ø7 ñh ùa Tàª|h úªY Ð9#9 ´@ùÈ ø7 ñ ùa Tà ªqh X ´@ù\ ðø7 ñ ù¡ Tàªhh \ ð4ÓDù @ù@ùáªLh À; ´ø ª @¹ 1B T ¹ø3 ùH ð}Fù@ùI@ùè; ´àª ?Ö÷ ªà/ ùà; ´@ùÈ ø7 ñ ùa TàªIh 4ÓDù @ù@ùáª/h à: ´ø ª @¹ 1B T ¹ø3 ùH ð!Bù@ùI@ù(; ´àª ?Öù ª ; ´@ùÈ ø7 ñ ùa Tàª-h è@ù ë : T Ò Rø#@ùéã)! úÛ©ùG ù!M(Ë 2઻ÿô ªà+ ù ´H@ùÈ ø7 ñH ùa Tàªh ÿ3 ù(@ùÈ ø7 ñ( ùa Tàª
h Ô8 ´è@ùÈ ø7 ñè ùa Tàªh ö# ùÿ/ ù@¹ 1B T ¹ôÿ©
@ùÛGùyBù@ù@¹ ?Öù ªw@ùH ðýAù@ùàªáªêg ÷ ª 6 ´è@ù@ù ´àªáªâª ?Ö÷ ªÀ µ« è@¹ 1B Tè ¹w@ùH ð ñAù@ùàªá ªÓg 4 ´ú ª@ù @ù©
´àªáªâª ?Öà/ ù 4 ´ú ª@ù) Ð)U@ù ëA
T[@ù;5 ´T @ùh@¹ 1 T@¹ 1# Tô/ ùH@ùHø6 h ¹@¹ 1"ÿÿT ¹ô/ ùH@ùÈ ø7 ñH ùa Tમg " Rúªèã! ûÿ©
ËàªBÿô ªà+ ù ´h@ùÈ ø7 ñh ùa Tàªg . ´H@ùÈ ø7 ñH ùa Tàªg ÿ/ ù@ùÈ ø7 ñ ùa Tàªg ÿ+ ùf à ù? ñk T¿ ñM T Ò#¼ò}Ón Ò ä /ó}Ó`jzüàªõ` Àj:ü))` ¿ëÿÿT Ò i ñ}ÓÁjiü!` Áj)ü ¿ëAÿÿTÖ {ë+ýÿT I@¹) 1B TI ¹ú/ ù) °)U@ù ë óÿT Ò ұÿÿ Ò ä /n ë"` «ÿÿTà@ùHf H ÐåFùè@ùA@ùs& ´ Ð Ø!0g öWD©' 5àªáª Ò`?Öô ª+g ó @ùô& ´è@ùÈ ø7 ñè ùa Tàª:g Ô$ ´@ù ø7 ñ ùà T¨@¹ 1# TôªS µ àª,g ¨@¹ 1"ÿÿT¨ ¹ôª ´h@ùÈ ø7 ñh ùa Tઠg ´¨@ùÈ ø7 ñ¨ ùa Tàªg ´È@ùÈ ø7 ñÈ ùa Tàªg ´¨@ùÈ ø7 ñ¨ ùa Tàªg ¨Yø) °)y@ù)@ù?ë¡P Tàªý{P©ôOO©öWN©ø_M©úgL©üoK©é#JmÿCÀ_Ö Ò Ò Òÿ' ù ҔlRu3RÚ Ôe Q µàªýÿö ªà3 ù@«ÿµ Ò Ò Òÿ' ùtnRÌ àªVf à+ ù «ÿµ Ò Ò Òÿ' ù ҴnRÁ ¼e O µàªåÿú ªà«ÿµ Ò Òx àªBf û ª ¬ÿµ Òÿ' ù ÒToR¯ ôªv@ùN ´s @ùÈ@¹ 1C2 Th@¹ 1c2 Th@ù2ø6 Ò Òÿ' ù ÒôqR ôªÙ@ùùK ´Ó
@ù(@¹ 1#: Th@¹ 1C: Tó+ ùÈ@ùh:ø6× Ò Ò Òÿ' ù ÒÔtR H Ð ¥GùH ÐYGù Òpÿà/ ùàH ´ô ª¡ÿ@ùÈ ø7 ñ ùa Tàªf Ò Ò Òÿ' ù Òÿ/ ù4wRõ3Rn he `G µàªÿø ªà3 ù`Äÿµ Ò Ò Òÿ' ù6 àªëe ÷ ªà/ ù`Äÿµ Ò Òÿ' ùôR, Re E µàª{ÿø ªà3 ù@Åÿµ Ò Ò Òÿ' ùTR àªÔe ù ª Åÿµ Ò Ò Òÿ' ùR ú@ùú3 ùø#@ùZC ´ô
@ùH@¹ 1£0 T@¹ 1Ã0 Tô/ ùè@ùè0ø6 Ò Ò Òÿ' ùTRU5Ró @ù* ( °@ù @ùáª#e Ò ÒR6RóÛC© ( °@ù @ùá ªe ÿ/ ùTR ԞRè@ùóÛC©È ø7 ñè ùa Tàª#f Ò Ò Ò6R Òqþÿàªáª Òe ô ªóÛC©õ'@ùÔþÿ Ò Ò Òô¯R6Rù Òó @ùËþÿðd `: ´ ÒÇþÿìd À: µàªÿö ªà/ ùô'@ù ¨ÿµ÷ªARÿÿ©à+@ù` µB àªme ú ªà3 ù ¨ÿµÿ3 ùR V@ùö/ ù¶8 ´T @ùÈ@¹ 1#+ T@¹ 1C+ Tô3 ùH@ùh+ø6_ !R ö/@ùÿ3 ù¡Rô'@ùV ´È@ùø7 ñÈ ù¡ TàªöªÔe áªÿ/ ùà+@ù µ ᄌRH@ùô'@ùø7 ñH ù¡ TàªöªÅe áªÿ3 ùÿ/ ùà+@ù ´ @ùè ø7 ñ ù Töª¹e áªÿ+ ù ð 9à Ðc Â4Ra~ÿácâãCàªè
` ø7@ù) °)]@ù ëa% T@¹ 1B T ¹àªÑd ú ª % ´ RNe à% ´á ª ùàªá' ùâd À% ´ö ª@ùúªÈ ø7 ñ ùa Tàªe à'@ù @ù¨ ø7 ñ ùA T
e à/@ùà ´ @ù¨ ø7 ñ ùA T}e ÿ/ ùà3@ùà ´ @ù¨ ø7 ñ ùA Tte ÿ3 ùà+@ùà ´ @ù¨ ø7 ñ ùA Tke ÿ+ ù(7@ù @ù ùà ´ @ù¨ ø7 ñ ùA T`e \ ÐY °9#9 ´h@ùÈ ø7 ñh ùa TàªUe øÿ´@ùȜÿ6ìüÿ Ò Ò ÒԉRõ4R(7@ù @ù ùà ´ @ù¨ ø7 ñ ùA TBe ´h@ùÈ ø7 ñh ùa Tàª:e ´@ùÈ ø7 ñ ùa Tàª2e ÿ' ù Òûªó @ù È ¹h@¹ 1âÍÿTh ¹h@ùÈ ø7 ñh ùa Tàª!e ( RûªóªÂûÿ Ò Ò Òÿ' ù ÒTuRÕ3Rà3@ùà ´ @ù¨ ø7 ñ ùA Te à/@ùà ´ @ù¨ ø7 ñ ùA Te à+@ùà ´ @ù¨ ø7 ñ ùA Tþd ´H@ùÈ ø7 ñH ùa Tàªöd ´h@ùÈ ø7 ñh ùa Tàªîd ´è@ùÈ ø7 ñè ùa Tàªæd ð 9à Ðc áªâª}ÿ Òõ'@ùó¶ÿµ½ýÿ( ¹h@¹ 1ÆÿTh ¹ó+ ùÈ@ùÈ ø7 ñÈ ùa TàªÎd ( RöªóªûÿH ¹@¹ 1ÏÿT ¹ô/ ùè@ùÈ ø7 ñè ùa Tઽd ( R÷ªüÿÅ ð¥¸>âãã£àªáªäªÂ ø7øÓF©ÿÿ©ÿ+ ùàªFd ±^ÿT Ò Ò Òÿ' ù Ò ÒTkRU3Rÿÿ Ò Ò Òÿ' ù ÒÔ{R Ò Ò Òÿ' ù|Ru4Ró @ù}ÿÿÈ ¹@¹ 1ÕÿT ¹ô3 ùH@ùÈ ø7 ñH ùa Tàª
d ( Rúªô'@ùÙûÿ`Rxúÿá_Rvúÿd ઠd ô ªàÚÿµ Ò Ò ÒTR5R'ÿÿóª ҔR5R"ÿÿóª ÒԋR5R ÿÿóª ÒtR5R÷'@ùÿÿ Ò Ò Òÿ' ù Òÿ3 ùtnRDÿÿ Ò Ò Òÿ' ù ÒoR=ÿÿ R3ÿÿ Rÿÿ Ò Ò Òÿ' ù ҴvRõ3R2ÿÿ Ò Ò Òÿ' ùÿ3 ù´Rÿýÿ Ò Ò Òÿ' ùÿ3 ùTRøýÿ Rüÿ( °=@ù @ù Ð!T" c (þÿ÷ªARôD©ÿÿ©Íÿµsþÿ R¦ÿÿÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýôªó ª( °y@ù@ùè' ùH Ð3è©C ´õª6 t ´ ña T! @ùá# ù¸
@ù< ñ¡ T! @ù: º
@ùX ñ T ÒH ÐqFù»b h{yø ë` T9 _ëaÿÿT Òa{yøàªB Râ 59 _ë!ÿÿTØb ` ´a¾R ( °A@ù @ùÈ Ð* RèÓ© ð é )e0è« ©é ù ð!¸ ¼b a R ð 0:à Ðc â7R|ÿ Ò `üÿ7Ázyøá# ùüÿ´ ñ* Tàª|8 è'@ù) °)y@ù)@ù?ëÁ Tý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_Öå ¥d0âà ãàªáªäªÈ ` ø7á#@ùæÿÿ¿RÖÿÿµc ÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýóªô ª( y@ù@ùè' ùH °3è©C ´õª6 ó ´ ñá T8 @ùø ù¹
@ù@ ñ! T8 @ùø ù @ù(B9È 6á º
@ùY ñ T ÒH °qFù»b h{xø ë` T _ëaÿÿT Òa{xøàªB Rh 5 _ë!ÿÿT^b ` ´A[R ( A@ù @ùÈ °* RèÏ© Ð é )Eè« ©é ù Ð!¸ Bb A]R Ð ;à °c GR|ÿ ÒN `üÿ7Øzxøø ùüÿ´? ñjS T @ù(B9¨T 7H aGù?ë T T*@ùQ ´I @ù? ñ TJa K@ùë S TJ! ) ñaÿÿTY 9#93ÓDù @ùb@ùáª'c @p ´õ ª @¹ 1B T¨ ¹H °
Aù¨@ùI@ù¨p ´àª ?Öö ª p ´¨@ùÈ ø7 ñ¨ ùa Tàª&c È@ù) )U@ù ëào T R Òéà )! õc©!M(Ë àª´ÿó ª ´¨@ùÈ ø7 ñ¨ ùa Tàªc o ´È@ùÈ ø7 ñÈ ùa Tàªc \ °«Cùh@ùI@ùHn ´àª ?Öö ª@n ´Z °A£FùઠRb ÷ ªÀm ´È@ùÈ ø7 ñÈ ùa Tàªðb ; {w@ùÿë( m@ùäHú( q@ùäHú Tÿëõ àªib õ ªzø7è@ùÈ ø7 ñè ùa TàªØb j 5«Cùh@ùI@ùl ´àª ?Öö ªl ´A£Fùßë TÈ@ù) )Q@ù ë: ZW@ùák TÈ
@ù© ! ñ! TÈ@¹ qõ 5 R: ZW@ù RÈ@ùÈ ø7 ñÈ ùa Tરb 7ÓDù @ùâ@ùáªb ö ªµ 4j ´È@¹ 1B TÈ ¹H °UCùÈ@ùI@ùj ´àª ?Öõ ªj ´È@ùÈ ø7 ñÈ ùa Tàªb ¨@ù ë j T R Òéà )! öO©ø# ù!M(Ë 2àª#ÿ÷ ª ´È@ùÈ ø7 ñÈ ùa Tàª~b i ´¨@ùÈ ø7 ñ¨ ùa Tàªvb ÿëà T( m@ùÿë` T( q@ùÿëà Tàªòa õ ª yø7è@ù¨ø6¡ öp ´È@¹ 1B TÈ ¹H °ý@ùÈ@ùI@ùèp ´àª ?Öû ªàp ´È@ùÈ ø7 ñÈ ùa TàªPb H °QEùh@ùI@ù(p ´àª ?Ö÷ ª p ´àª Ò R R
õ ª p ´è@ùÈ ø7 ñè ùa Tàª9b Réa ÷ ª@o ´õ ùû` õ ª`o ´6ÓDù @ùÂ@ùáªb @o ´ù ª @¹ 1B T( ¹H °©Bù(@ùI@ùHo ´àª ?Öø ª@o ´(@ùÈ ø7 ñ( ùa Tàªb H °áAùàªâªß` ø7@ùÈ ø7 ñ ùa Tઠb h@ùA@ù¶p ´ ° Ø!èa @q 5àªáªâªÀ?Öö ªäa 6p ´h@ùÈ ø7 ñh ùa Tàªôa è@ùÈ ø7 ñè ùa Tàªía ¨@ùÈ ø7 ñ¨ ùa Tàªæa H °YEù@ùI@ùÈm ´àª ?Öõ ªÀm ´¨@ù ëÁm T´@ùn ´·
@ù@¹ 1c Tè@¹ 1 T¨@ù¨ø6á ÿëõè@ùÈ ø7 ñè ùa TàªÅa 5 46ÓDù @ùÂ@ù᪪a W ´õ ª @¹ 1B T¨ ¹H °Aù¨@ùI@ùhW ´àª ?Öö ª`W ´¨@ùÈ ø7 ñ¨ ùa T઩a È@ù ëÀV T R Òéà )! õO©!M(Ë àª9ÿû ª ´¨@ùÈ ø7 ñ¨ ùa Tàªa ûU ´È@ùÈ ø7 ñÈ ùa Tàªa h@ùø7 ñh ù¡ Tàª
a ûªH °YEù@ùI@ùèI ´àª ?Öö ªàI ´È@ù ëJ TÓ@ù3K ´Ô
@ùh@¹ 1ã T@¹ 1 TÈ@ù(ø6
h ¹@¹ 1BÿÿT ¹È@ùÈ ø7 ñÈ ùa Tàª_a ( Röªéà )! óo©!M(Ë àªòÿô ª ´h@ùÈ ø7 ñh ùa TàªMa E ´È@ùÈ ø7 ñÈ ùa TàªEa @ùÈ ø7 ñ ùa Tàª>a h@¹ Ò 1£ Tóªh@ù#ø6 h ¹óªh@ùè"ø6 ҴORZRöªÈ@ùÈ ø7 ñÈ ùa Tàª&a öª ´È@ùÈ ø7 ñÈ ùa Tઠa Ò ´¨@ùÈ ø7 ñ¨ ùa Tàªa ´(@ùÈ ø7 ñ( ùa Tઠa ´@ùÈ ø7 ñ ùa Tàªa Ð ;à °c áªâªyÿ ÒS µä ¹è@¹ 1ÂäÿTè ¹¨@ùÈ ø7 ñ¨ ùa Tàªî` ( Rõªéà )! ô[©!M(Ë àªÿ÷ ª ´@ùÈ ø7 ñ ùa TàªÜ` WN ´¨@ùÈ ø7 ñ¨ ùa TàªÔ` è@ùÈ ø7 ñè ùa TàªÍ` àªáªÐ' àL ´û ªh@ùhø6¯ )@ù?ë T©ÿÿµ) )@ù ëa¯ÿT å ¥Dâà 㣠àªáªäªÄ `)ø7ø@ù @ù(B9¨«6H !9ÑDù @ùb@ùáª` ´ö ª @¹ 1B TÈ ¹H °ý@ùÈ@ùI@ùè ´àª ?Öõ ªà ´È@ùÈ ø7 ñÈ ùa Tàª` ¨@ù7 ÷V@ù ë T R Òéà )! öc©!M(Ë àª ÿó ª ´È@ùÈ ø7 ñÈ ùa Tàª{` S ´¨@ùÈ ø7 ñ¨ ùa Tàªs` H °YEù@ùI@ù ´àª ?Öõ ª ´¨@ù ë¡ T´@ùt ´¶
@ù@¹ 1ã TÈ@¹ 1 T¨@ù(ø6
¹È@¹ 1BÿÿTÈ ¹¨@ùÈ ø7 ñ¨ ùa TàªO` ( Rõªéà )! ôO©!M(Ë àªâÿö ª ´@ùÈ ø7 ñ ùa Tàª=` ¶
´¨@ù ø7 ñ¨ ù TÈ@ùhø7 ñÈ ù Tàª0` h@¹ Ò 1 Th ¹ûªh@ùHø7 àª%` È@ùèýÿ6h@¹ Ò 1þÿTûªh@ùÈ ø7 ñh ùa Tàª` ´È@ùÈ ø7 ñÈ ùa Tàª` è'@ù) )y@ù)@ù?ëa8 Tàªý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_Öå^ µàªÿö ª ëÿµfRMRF àªk_ õ ª`ëÿµ Ò Ò ҔMRZfRÊþÿ¶@ùÖ4 ´³
@ùÈ@¹ 1ã Th@¹ 1 T¨@ù(ø6% Ò Ò ÒúhRMRÁþÿàªO_ õ ªÀíÿµ ҡjR¢MRs R ҄ÿÿ Ò Ò:mR´MR±þÿ R}ÿÿÈ ¹h@¹ 1BüÿTh ¹¨@ùÈ ø7 ñ¨ ùa Tઽ_ ( Rõª0ÿÿ^ µàªȉÿõ ªàÿµaqRNR ° ;à c Oüÿàª!_ ö ª ÿµ Ò Ò ҺqRNRþÿÕ@ùÕ+ ´Ó
@ù¨@¹ 1c Th@¹ 1 TÈ@ù¨ø6 Ò Ò ÒNRZtRnþÿàª_ ö ª ÿµvR"NR* Ò Ò Ò4NRZvRXþÿH ÅGùH iGù ÒWÿ' ´ô ªÿ@ùÈ ø7 ñ ùa Tàªt_ ÒaxRBNR àªä^ ö ªÿµ¡zR¢NR á[Rüÿ ð)I@ù ë@ TàªB Rî^ p& õ ª ðZW@ù ÿ6 Ò Ò ҴNRúzR2þÿ:^ À" µàªcÿö ª ðZW@ù@ÿµ àªÀ^ õ ªÿµ Ò Ò ÒôNR|Rþÿ¶@ùö ´·
@ùÈ@¹ 1C Tè@¹ 1c T¨@ùø6¨ Ò Ò Ò:RôNRþÿત^ ö ª`¶ÿµFR"ORóªÈ R ÒÉýÿ Ò Ò Ò Ò4ORZRóªñýÿ R¿ýÿ¨ ¹h@¹ 1ÂïÿTh ¹È@ùÈ ø7 ñÈ ùa Tàª_ ( Röªîûÿ Ò Ò ҚvR4NRáýÿë] à µàªÿõ ª ðZW@ù(ÿµ ÒROR àªn^ ö ªà¨ÿµ Ò ÒZROR×ýÿÕ@ù ´×
@ù¨@¹ 1 Tè@¹ 1£ TÈ@ùÈø6 Ò Ò Ò ÒORúR²ýÿÃ] à µàªìÿö ª ðZW@ùàÿµ¡ àªI^ û ª`ÿµ Ò Ò ҴORڍR¨ýÿàª?^ ÷ ª ÿµ Ò Ò ҴOR:Rýÿ Ò ҴORzRýÿ Ò ҴORڎRýÿ Ò ҴORzR
ýÿ] à µàªÿù ª ðZW@ù ÿµ Òy ઠ^ ø ª ÿµ´ORúRtýÿ Ò Ò ҺRôNRvýÿÈ ¹è@¹ 1âëÿTè ¹¨@ùÈ ø7 ñ¨ ùa Tàª^ ( Rõª ðZW@ùüûÿÀ
@ý( Rb a õ ðZW@ùÌûÿàªáªâªå] ö ª@ÿµ `] ´ Ò ҴORRGýÿàªè] õ ªÿµaRÂOR
R Òýÿ Ò ÒúRÔORKýÿ Rxýÿ¡RâOR ° ;à c wÿ Òh@ùÈÇÿ6Bþÿ¨ ¹è@¹ 1¢íÿTè ¹È@ùÈ ø7 ñÈ ùa TàªL^ ( Röª ðZW@ù¤üÿI^ Rºýÿ R$ûÿ ÒáwRBNRÞÿÿ ÒA|RâNRÚÿÿ R¬ÿÿ Ríÿÿ ҁR¢ORÒÿÿ Ò ҴORºR ýÿ ð=@ù @ù !T"] ®ÿÿÿCÑöW©ôO©ý{©ýõªóªô ªÿ©@ùB96 Rµ 5
@ùh ´@ùè ù ð)A@ù @ùó# © °!8
ê\ Rý{D©ôOC©öWB©ÿCÀ_Öè@ù@ùB9 6áC âc ઠÒÉ\ àþÿ5 Rþÿ5è@ùÈýÿ´åÿÿ ðA@ù @ùó ù °!° äÿÿÿCÑüo©úg©ø_©öW©ôO©ý{©ýóªõªöªôª÷ªø ªÿ©ÿ ùY @ùU@ùà@ùà ´ @ù¨ ø7 ñ ùA TÖ] ÿ ùà@ùÀ ´ @ù ø7 ñ ù Tÿ ùÚÐ7ác ⣠ã àª\ À 4*@ùè@ùj µ Á] ÿ ùþ×6 @ùè@ù ëj T ñ}Ó
J
@ùéjiøé+© è ù*@ùè@ùê ´éªJ@ù_ë T*@øÿÿµ Òè@ù)ËÈj)øÿ© ùÿµÎÿÿ @¹) 1C Tè@ù @¹) 1c Tè@ù@ùB9 7{ ¹è@ù @¹) 1âþÿT ¹è@ù@ùB9( 6(@ù¨ ´ûª n\ à µh@øè ´ @ù@ùá@ù)@ù ë!ÿÿTB] þÿ7Àþÿ5è@ùiËÈj)øh@ùHóÿµ?ë Tµò}Ó X\ µ" µ" ñÀ T@ù @ùá@ù ë T@ù)@ù ë¡þÿT(] þÿ7@þÿ5à@ù ðA@ù@ùó © °!TઠðA@ù @ùè@ùó# © °!8
.\ à@ùÀ ´ @ù ø7 ñ ù Tà@ùÀ ´ @ùø7 ) ñ ù T@] èª =] à@ùþÿµ àªý{H©ôOG©öWF©ø_E©úgD©üoC©ÿCÀ_Öà@ùà ´ @ù¨ ø7 ñ ùA T)] à@ù ´ @ùé ø7 R R) ñ ùáüÿTßÿÿ Räÿÿ ðA@ù @ùó ù °!° ÅÿÿöW½©ôO©ý{©ý óª ë`
T @ù ða@ù*@ù?ë@Hú@ T ðµr@ù? ë Húé_ë Uú` TI 7âª\ ´ô ª ðu@ù ë@ T ð)m@ù ëÀ Të Tàªw\ ó ª@ùhø6àªý{B©ôOA©öWèÀ_Ö@ù)@ù ëÁ T @ù* @ù_ ±$Aº$Jú T @¹iBÓ* @¹LS? kA Të(7 @ù àªý{B©ôOA©öWèÀ_֟ëó@ùèûÿ7 ñ ùûÿTàªÅ\ àªý{B©ôOA©öWèÀ_Ö
à r j (7! @ù + ,à _r? qÀ T? qá T
@9+ @9
@y+ @y
@¹+ @¹_ kA T ñá T
qóàªý{B©ôOA©öWèÀ_Ö qóàªý{B©ôOA©öWèÀ_Ö} ¿\ qèé
qàªý{B©ôOA©öWèÀ_Öÿà ÑôO©ý{©ý ` µ|\ 0@ùÈ ´ó ª @ù µý{B©ôOA©ÿà À_Ö @ùè ø7 ñ ù Tóªu\ ᪠ðE@ù @ùá ù °!ÌJ[ ý{B©ôOA©ÿà À_Ö ð9@ù@ùՇÿ` 4àª Ò Ò Ò ÿ Rý{B©ôOA©ÿà À_Ö ý{B©ôOA©ÿà À_ÖôO¾©ý{©ýC G\ 0@ù( ´ó ª @ù µý{A©ôO¨À_Ö ð9@ù@ùµÿ@ 4àª Ò Ò Òìÿ Rý{A©ôO¨À_Ö ý{A©ôO¨À_ÖÿÑöW©ôO©ý{©ýà ó ª@ù ð)M@ù ë@ T ð)]@ù ë@ TÕF© ´¨@ùH ´àªU[ ` ´ô ª¨@ùàªáª ?Öó ª@ùHø7 ñ ùá Tàª\ , 誡 ø¶èªb 4h
@ù 4i
@ù ëâ Ti@ù3yhøh@¹ 1¢ T" ´@ùÈ ´A ø¶â 5@ùàªý{C©ôOB©öWA©ÿ@ Ö誡 ø¶èªb 4h
@ù 4i
@ù ëb Th
@ùh@¹ 1ã Tàªý{C©ôOB©öWA©ÿÀ_Öh ¹àªý{C©ôOB©öWA©ÿÀ_Öઠ[ @ ´ô ªàªáªO[ ó ª@ù(÷ÿ6éÿÿá ù@ù¨ ´àª ?ր ø·á@ù Êÿÿ ð1@ù @ùZ 4Z á@ùÂÿÿ Òàªý{C©ôOB©öWA©ÿÀ_Öÿà ÑôO©ý{©ý ôªvZ ó ª@ ´h@¹ 1B Th ¹àªý{B©ôOA©ÿà À_Z @ÿÿµ@ùB9h7 Ð)@ù @ùáª
Z àªý{B©ôOA©ÿà À_Öô ù RI[ ýÿ´ô ª Ð)@ù @ùáªvZ @ù(üÿ7 ñ ùÁûÿTàª[ àªý{B©ôOA©ÿà À_Öÿà ÑôO©ý{©ý @ùB9H 6@ù = ñI T @ýCÓ¡ ñ` T ±! T C)(yªé2 ë" TàKý{B©ôOA©ÿà À_Ö @¹@ ¥ À ë ÿÿT C)(yª ý_ÓàªIþÿ´ Ð1@ù @ù !ðAZ ý{B©ôOA©ÿà À_ÖzZ À ëaþÿTý{B©ôOA©ÿà À_Ö `þÿ´ó ªÅÿÿh@ùHûÿ7 ñh ùáúÿTà ùàª=[ à@ùý{B©ôOA©ÿà À_Öý{¿©ý @ù B9) 6 @¹ 1c Tý{hÀ_Ö ¹ý{hÀ_Ö1@ùÈ ´A@ù ´ ?Ö@ ´@ù Ð)Q@ù ë þÿT !xý{h Z à µ ÐA@ù @ù ! Z Òý{hÀ_ÖÿÑôO©ý{©ýÃ ó ª @ù(
@ù)B9I 7 Ð)A@ù @ùᣠ©á ù !ÝY
Ð)@ù @ùè ù Bä! RéY 4h@ùÈ ø7 ñh ùa TàªïZ Òàªý{C©ôOB©ÿÀ_ÖôO¾©ý{©ýC óªè ª Ð)q@ù @ù ñIúA T@ùhÿÿµ Ò_ ù? ù` ùý{A©ôO¨À_Ö@ ù @¹ 1B T ¹@ù( ù @¹) 1B T ¹ÄY ` ùý{A©ôO¨À_ÖÿCÑöW©ôO©ý{©ýóªôªöªõ ªÿ ù 0@ùà©¿2 ù@ ´@ùè ù @¹) 1b T ¹à @ùªY à ùàc áC â# Y ¨2@ùè µá@ùA ´à @ù¢Y @ ø7è@ù¨ ´ @¹) 1B T ¹è@ù¨ ´ @¹) 1B T ¹è @ùÈ ´ @¹) 1b T ¹è @ùé@ùÉ ù ùé@ùi ù©6@ù3@ù( ùà@ùÀ ´ @ù ø7 ñ ù Tà@ùÀ ´ @ù ø7 ñ ù TS ´h@ù ø7 ñh ù` T Rý{D©ôOC©öWB©ÿCÀ_ÖmZ à@ù ýÿµñÿÿiZ þÿµ Rý{D©ôOC©öWB©ÿCÀ_Öàª`Z Rý{D©ôOC©öWB©ÿCÀ_Öß ù ù ùà@ù9mÿà @ù7mÿà@ù5mÿ ý{D©ôOC©öWB©ÿCÀ_ÖôO¾©ý{©ýC óªôªè ª @ù ùà ´ @ù¨ ø7 ñ ùA T<Z Ô ´@ù ø7 ñ ù` T³ ´h@ùhø7 ñh ù Tàªý{A©ôO¨,Z àª*Z ³þÿµý{A©ôO¨À_Öÿà ÑôO©ý{©ý @ùB9h 6@ù = ñé T @ýCÓ¡ ñ T ±¡ T C)(yªàËý{B©ôOA©ÿà À_Ö @¹@ ¥ý{B©ôOA©ÿà À_Ö C) yªý{B©ôOA©ÿà À_Öý{B©ôOA©ÿà (Y Åþÿ ´ó ªÔÿÿh@ùÈüÿ7 ñh ùaüÿTà ùàªñY à@ùý{B©ôOA©ÿà À_Ö ý{B©ôOA©ÿà À_ÖÿÑúg©ø_©öW©ôO©ý{©ýC@ù9@ù ´øª"@ù¢
´ó ªC ´a @ùàªý{E©ôOD©öWC©ø_B©úgA©ÿ@ Öõª÷ª 4 ÒþX ö ªô ª@ ´Ø ´ Ò@ù ÐBp@ùàªiY ö ªT µ" Ò ÐÖr@ùþÿµ 4àªêX á ªõ ªà ´ ÐBp@ùàªXY ö ªT ´@ùø7 ñ ù¡ TદY
Ò Ð!p@ù ÐBp@ùàªGY ö ªþÿµ ´¨@ùÈ ø7 ñ¨ ùa TàªY Ö ´(@ùàªáª ?Öó ªÈ@ùø7 ñÈ ù¡ TàªY
@ù Ð)A@ù @ùè ù !p [X Òàªý{E©ôOD©öWC©ø_B©úgA©ÿÀ_ÖàªWlÿõÿÿÿÑé#
müo©úg©ø_©öW©ôO©ý{©ýÃôªóªöª Ðy@ù@ù¨ø¢øÿ ©ÿ©( @¹ 1 TH @¹ 1# Tà# ù@¹ 1B T ¹( Ð!9ÑDù @ùâ@ùáª8Y @û´õ ª @¹ 1B T¨ ¹õK ù( ðAù¨@ùI@ùü´àª ?Öø ªü´¨@ùÈ ø7 ñ¨ ùa Tàª6Y RæX àK ù ý´È@¹ 1B TÈ ¹ ùôW àG ùàý´õ ª( ðAù ÐBl@ùòW
ø7÷K@ù@ùA@ùyþ´à ð Ø!Y 5àªáªâª ?Öõ ªýX ´õC ù@ùÈ ø7 ñ ùa TઠY àK@ù @ù¨ ø7 ñ ùA TY ÿK ùàG@ù @ù¨ ø7 ñ ùA TýX ÿG ùûC@ùÈ@ùÈ ø7 ñÈ ùa TàªôX ÿC ù( ð©Cùh@ùI@ùú´àª ?Öõ ªàC ùú´8 ðFù Ð÷R@ù¿ë T¨@ù ëT¨@¹ È ¹H @¹ 1"ðÿTH ¹à# ù@¹ 1ðÿTÿÿ Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿ+ ù5uRËERá 6 R¨@ùÈ ø7 ñ¨ ùa T઼X еr@ùÿC ù Мw@ùû ùÖ 4«X ú ª4@ù@ù ñUú! T@ùhÿÿµ Ò Ò Ò' ( ð©Cùh@ùI@ù´àª ?Öö ªàG ù ´( ð¡Fùßë`+ TÈ@ù ëáTÈ
@ù© ! ñ¡* TÈ@¹ q÷R @¹ 1B T ¹@ùè@¹ 1B Tè ¹àª~W ö ª( Ð!9ýDù @ùb@ùáªfX ´ù ª @¹ 1B T( ¹ùG ùû @ù( ðBù(@ùI@ù(´àª ?ÖàK ù ´(@ùÈ ø7 ñ( ùa TàªcX ÿG ù( ðÅBùh@ùI@ùè
´àª ?Öù ªà
´(@ù Ð)U@ù ëÁ
T;@ù{´< @ùh@¹ 1ã T@¹ 1 T(@ù(ø6
h ¹@¹ 1BÿÿT ¹(@ùÈ ø7 ñ( ùa Tàª<X " Rù ª Мw@ù¨#Ñ! »ÿ7©
ËàªΉÿàG ù; ´h@ùÈ ø7 ñh ùa Tàª)X àG@ùû @ù`´(@ùÈ ø7 ñ( ùa TઠX èK@ù @ù
ÐJU@ù?
ëT R ҩ#Ñ)! êH©¹«7©!M(Ë ¬ÿàC ù ´(@ùÈ ø7 ñ( ùa TàªX àG@ù @ù¨ ø7 ñ ùA T X ÿG ùèC@ùÈ´àK@ù @ù¨ ø7 ñ ùA TöW ÿK ùúC@ùÿC ù ´è@ùÈ ø7 ñè ùa TàªëW ´@ùÈ ø7 ñ ùa TàªãW ´È@ùÈ ø7 ñÈ ùa TàªÛW 8 ðFùàª" RdW àG ù@
´ ëÀ T Ðm@ù ë@ T ë TSW @ú7ö ªàG@ù @ùÈ ø6 ëö @ù ø7 ñ ù@ TÿG ù¶ 4( °!9ÑDù @ùÂ@ù᪠W e´ @¹ 1B T ¹àK ù( ÐyDù@ùI@ùg´ ?ÖàC ù g´àK@ù @ù¨ ø7 ñ ùA T W ÿK ùèC@ù @ù
°JU@ù?
ë`gT RéK@ùª#ÑJ! «Wø©¯7©àC@ùAM(Ë +ÿè ªàG ùàK@ù ´ @ù¨ ø7 ñ ùA T
W èG@ùÿK ùhf´àC@ù @ù¨ ø7 ñ ùA T{W ÿC ùàG@ùFù ë T@ù °)Q@ù ë!ºT@¹) R6(
@ù¨ ø6 R @ù¨ ø7 ñ ùA TdW ÿG ùv 4ú+ ù( Ð ¥Gù( ÐõFù Ò4ÿàG ù ´fÿàG@ù @ù¨ ø7 ñ ùA TQW Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿG ù5vRËaRö @ù] R 7 RÈ@ùÈ ø7 ñÈ ùa Tàª6W ÿG ù÷m5( ÐQEùh@ùI@ùÈq´àª ?Öö ªàG ùÀq´àª Ò R RðúÿàC ù s´È@ùÈ ø7 ñÈ ùa TઠW úC@ùÿ©Fù_ë T( °!9ÑDù @ùâ@ùáªûV àú´ö ª @¹ 1B TÈ ¹öG ù( ÐyDùÈ@ùI@ù(ý´àª ?ÖàK ù ý´È@ùÈ ø7 ñÈ ùa TàªùV ÿG ùèK@ù @ù
°JU@ù?
ëýT RéH©ª#ÑJ! «Wø©¯7©AM(Ë
ÿè ªàC ùàG@ù ´ @ù¨ ø7 ñ ùA TßV èC@ùÿG ù¨ü´àK@ù @ù¨ ø7 ñ ùA TÕV ÿK ùàC@ùFù ë T@ù °)Q@ù ëABT@¹) R6(
@ù(ø6 ÄV ÿG ùöàÿ5
R @ù¨ ø7 ñ ùA TºV ÿC ùVú5ëú+ ù TàªMV ± èT÷ ª( °!9ÑDù @ùÂ@ùáªV àè´ @¹ 1B T ¹àK ù< ЁEù@ùI@ù(ê´ ?ÖàG ù ê´àK@ù @ù¨ ø7 ñ ùA TV ÿK ù( °!9ÑDù @ùÂ@ùáªwV ê´ø ª @¹ 1B T ¹9 Ð!Bù@ùI@ùê´àª ?Öú ª ê´@ùÈ ø7 ñ ùa TàªvV ( °!9ÑDù @ùÂ@ùáªZV àé´ø ª @¹ 1B T ¹( Ð!Bù@ùI@ù¨é´àª ?Öö ª é´@ùÈ ø7 ñ ùa TàªYV H@ù °)U@ù ëàéT R ҩ#Ñ)! ¸Û7©!M(Ë àªçÿàK ù ´@ùÈ ø7 ñ ùa TàªBV È@ùÈ ø7 ñÈ ùa Tàª;V èK@ùè´H@ùÈ ø7 ñH ùa Tàª2V àK@ù8 Ð÷Aù@ùI@ùHè´ ?Öö ªú+@ù@è´àK@ù @ù¨ ø7 ñ ùA T!V ÿK ùèG@ù @ù
°JU@ù?
ëèT Rà§H©ª#ÑJ! ©Û7©AM(Ë ®ÿàC ùàK@ùà ´ @ù¨ ø7 ñ ùA T V ÿK ùÈ@ùÈ ø7 ñÈ ùa TàªV èC@ùç´ó? ùàG@ù @ù¨ ø7 ñ ùA T÷U èC@ùè3 ùÿ©@ù( °UGù3 Ð?ëÀ T*@ùê ´I @ù? ñË4 TJa K@ùë TJ! ) ñaÿÿT ÿ3 ùôª¹Wø?ëah T@¹ 1C TÿG ù( °1Gùé@¹) 1c T) Ð(¡Fù
@¹J 1£ T Wø¨ø @ùù ùèø6 ¹ÿG ù( °1Gùé@¹) 1âýÿTé ¹1Gù) Ð(¡Fù
@¹J 1¢ýÿT
¹(¡Fù Wø¨ø @ùù ù¨ ø7 ñ ùA T¯U °u@ùè? ù ëAv TÙ )@ù?ëÀ T©ÿÿµ °)@ù ëÁ+ T( °!9ÑDù @ùÂ@ùáª
U F´ @¹ 1B T ¹àG ù( ÐÁBù@ùI@ùÈG´ ?Öú ªÀG´àG@ù @ù¨ ø7 ñ ùA T
U ÿG ù; ÐaãAù@ùI@ùH´àª ?ÖàG ù H´ÿK ùH@ù °)U@ù ë IT Rë§H©ª#ÑJ! ©¯7©) °)qGù©øAM(Ë 2àªÿàC ùàK@ùà ´ @ù¨ ø7 ñ ùA T`U ÿK ùàG@ù @ù¨ ø7 ñ ùA TXU ÿG ùèC@ùèF´H@ùÈ ø7 ñH ùa TàªNU àC@ù °u@ù ëÀ T °m@ù ë@ T ë TÊT ú7ö ªàC@ù @ùø6 °u@ù ëö @ù¨ ø7 ñ ùA T2U ÿC ù6 4öª`öCùÂmÿú ªàv´EùH@ùI@ùHx´àª ?ÖàG ù@x´H@ùÈ ø7 ñH ùa TઠU ÀöCù¯mÿàK ùÀx´!Bù@ùI@ùHz´ ?Öü ª@z´àK@ù @ù¨ ø7 ñ ùA T
U ÿK ùaãAù@ùI@ù¨z´àª ?Öû @ùàK ù z´@ù °)U@ù ëà{T R ҩ#Ñ)! êK@ù¶«7©!M(Ë à ªÿú ªàªÒgÿàK@ù @ù¨ ø7 ñ ùA TçT ÿK ùÚz´@ùÈ ø7 ñ ùa Tà ªÞT ÷AùH@ùI@ù({´àª ?Öö ª °9w@ù {´H@ùÈ ø7 ñH ùa TàªÍT èG@ù @ù
°JU@ù?
ë`{T R ҩ#Ñ)! ¸Û7©àG@ù!M(Ë ZÿàC ùàªgÿÈ@ùÈ ø7 ñÈ ùa T઴T èC@ùz´àG@ù @ù¨ ø7 ñ ùA T«T ÿG ùá3@ù( @¹ 1B T( ¹áG ùàC@ù R/T ú ª z´_ë T °m@ù_ë T_ë` TઠT ö ª Ãú7H@ù(ø6
û @ùú+@ùJ _ëöH@ùÈ ø7 ñH ùa TàªT 4èC@ù @¹) 1ú+@ùc Tè@ùàG@ù @ùø6 èG@ù @¹) 1ú+@ùB T ¹è#@ùàG@ù @ùø6 ¹è@ùàG@ù @ù¨ ø7 ñ ùA TbT ÿG ùàC@ù @ù¨ ø7 ñ ùA TZT öC ùÈ@¹ 1B TÈ ¹È@ùÈ ø7 ñÈ ùa TàªNT öC@ùà3@ù @ù¨ ø7 ñ ùA TFT ÿC ùö3 ù( ÐÙGùAùµ@ùR ?Öá ªàª R R$ R ÒÀ?ÖàC ù/´ö ª @¹ 1b TÈ ¹àC@ù @ù ø7 ñ ù TÿC ù@ù¨ø7 ñ ùA Tàª"T ßë T T ÿC ù@ù¨þÿ6ßëÀ T( °UGùઠÀú4( ЩCùÈÒ@©I@ù´àª ?Öü ª ´( СFùëà T@ù °)Q@ù ëúT @ù© ! ñá T@¹ qø R 8 R@ùÈ ø7 ñ ùa Tà ªïS X«5( ÐuEùÈ@ùI@ù¨®´àª ?Öü ª ®´à ªáªb RoS àC ù/´@ùÈ ø7 ñ ùa Tà ªØS àC@ù °)u@ù ëÀ T °m@ù ë@ T ë TTS ` ú7ø ªàC@ù @ùÈ ø6 ëø @ù¨ ø7 ñ ùA T¾S ÿC ùX5( Ð@ùàªáª ?Ö@` ( !9ÑDù @ù@ùáªS `¯´ü ª @¹ 18 °B T ¹( °µBù@ùI@ù¯´à ª ?ÖàG ù ¯´@ùÈ ø7 ñ ùa Tà ªS A` R ¯´ô ªèG@ù @ù
JU@ù?
뀵T R Ò 9w@ù©#Ñ)! ·Ó7©àG@ù!M(Ë
ÿàC ù ´è@ùÈ ø7 ñè ùa TàªzS @ùÈ ø7 ñ ùa TàªsS èC@ùè³´àG@ù @ù¨ ø7 ñ ùA TjS ÿG ùàC@ù ëÀ T m@ù ë@ T ë TçR Àú7ô ªàC@ù @ùÈ ø6 ëô @ù¨ ø7 ñ ùA TQS ÿC ù´³5`öCùâkÿàG ù ¹´( °%Cù@ùI@ù¨½´ ?Öü ªó?@ù ½´àG@ù @ù¨ ø7 ñ ùA T;S ÿG ù( °ýDù@ùI@ùè½´à ª ?ÖàG ùུ@ùÈ ø7 ñ ùa Tà ª*S FùઠR´R @¾´ô ªèG@ù @ù
JU@ù?
ëa¿T
@ù w@ùÁ´ @ùé@¹) 1# T @¹) 1C TàG@ùèG ù @ùhø6 é ¹ @¹) 1ÿÿT ¹àG@ùèG ù @ù¨ ø7 ñ ùA TS ( R©#Ñ)! ·Ó7©àG@ù!M(Ë ÿàC ùàªÚeÿ@ùÈ ø7 ñ ùa TàªïR èC@ùè¹´àG@ù @ù¨ ø7 ñ ùA TæR ÿG ùàC@ù ëÀ T m@ù ë@ T ë TcR ú7ô ªàC@ù @ùÈ ø6 ëô @ù¨ ø7 ñ ùA TÍR ÿC ùô·5 n 9` À` ËQ àC ù »´á3@ù RPR àG ù@¼´àC@ù @ù¨ ø7 ñ ùA T¹R ÿC ùàG@ù ëÀ T m@ù ë@ T ë T6R ú7ô ªàG@ù @ùÈ ø6 ëô @ù¨ ø7 ñ ùA T R ÿG ùô¹5ôª¹Wø?ëàÿT m@ù@¹ 1 T )m@ù( ¹ÿG ù(@¹ 1c T÷ª ( ¹·Wø( !9ÑDù @ùÂ@ùáªnR @´ @¹ 1B T ¹àG ù( °yDù@ùI@ùH´ ?ÖàC ù@´àG@ù @ù¨ ø7 ñ ùA TnR ÿG ù R R àG ù´è@¹ 1b Tè ¹àG@ù ù*Q ü ª ´( !9ÑDù @ùÂ@ùáªDR ´ú ª @¹ 1B TH ¹( °©BùH@ùI@ùH´àª ?ÖàK ù@´H@ù ø7 ñH ù Z T( °áAùâK@ùà ªQ @Zø7ù ùùªàK@ù @ù¨ ø7 ñ ùA T6R ÿK ùö_H©È@ùA@ùú+@ùxÃ´à ° Ø!R Æ5àªáªâ ª ?Öö ªR Å´öK ùû @ù8 °àC@ù @ù÷ª¨ ø7 ñ ùA TR ÿC ùàG@ù @ù¨ ø7 ñ ùA TR ÿG ù@ùÈ ø7 ñ ùa Tà ª
R WøèK@ù¨ø @ù¨ ø7 ñ ùA TR ÿK ù m@ùè? ù w@ù ë T m@ùë Të` TàªyQ àÀù7@ 4ë T( °Aù@ùI@ù(í´àª ?Öü ª í´ÿG ù@ù )U@ù ë!¦T@ùèG ùȥ´ @ù @¹) 1c
Th@¹ 1
T@ù¨
ø6q ëà üÿ5 Wø᪠RXQ àK ù`÷´ ë 7 T m@ù ë6 T ë@6 TGQ @Mú7ó ªàK@ù @ù6ø6³ ( °¡Dùà#@ù@ùI@ùÈ+´ ?ÖàG ùÀ+´@ R`Q àC ù@-´Fù @¹) 1cN T ùH@¹ 1ÃN TèC@ù ùiP ü ªàN ´( °uEùà ªâªhP Àhø7áH©â ªo~ÿàK ù e´àG@ù @ù¨ ø7 ñ ùA TQ ÿG ùàC@ù @ù¨ ø7 ñ ùA T
Q ÿC ù@ùÈ ø7 ñ ùa Tà ª}Q ÿÿ© Ò Òÿ/ ùÿ ùÿ ù ÒèK@ùè# ùÿK ù r@ùè@ù ëè Tí ¹h@¹ 1ÂòÿTh ¹@ùÈ ø7 ñ ùa Tà ªaQ " RüªèG@ù©#Ñ)! ¨ÿ7©!
Ëà ªôÿè ªàK ùàG@ù ´ @ù¨ ø7 ñ ùA TNQ èK@ùÿG ù¨Û´@ùÈ ø7 ñ ùa Tà ªDQ ûK@ùÿK ùઠ" R RõÿàK ù@Û´á ªàªP Ü´ö ªàK@ù @ù¨ ø7 ñ ùA T/Q ÿK ùh@ùÈ ø7 ñh ùa Tàª'Q ( °ÍDùà#@ù@ùI@ùÛ´ ?ÖàK ù Û´ÿG ù@ù )U@ù 롍T @ùéG ùI´@ù*@¹J 1# T @¹) 1C TàK@ùèK ù @ùhø6 * ¹ @¹) 1ÿÿT ¹àK@ùèK ù @ù¨ ø7 ñ ùA TüP ( RéH©ª#ÑJ! ©ß7©AM(Ë ÿó ªàG@ùÕcÿÿG ùÖ´àK@ù @ù¨ ø7 ñ ùA TèP ÿK ù( °-EùÈ@ùI@ùHִઠ?Öü ªó ù@Ö´ RP àK ù ×´h@¹ 1b Th ¹àK@ù ùO àG ù ×´( °¡(Q@ù@ùO -ø7âH©à ª }ÿàC ù ´@ùÈ ø7 ñ ùa Tà ª¾P àK@ù @ù¨ ø7 ñ ùA T·P ÿK ùàG@ù @ù¨ ø7 ñ ùA T¯P øC@ùÿ©( ° õCù?iÿàC ùø# ù ´( °Aù@ùI@ùÈ´ ?ÖàG ùÀ´àC@ù @ù¨ ø7 ñ ùA TP ÿC ù RGP àC ù´@¹ 1b T ¹àC@ù ùTO àK ù ´( °Aù Bl@ùSO àDø7áH©âK@ùZ}ÿü ª7´àG@ù @ù¨ ø7 ñ ùA TxP ÿG ùàC@ù @ù¨ ø7 ñ ùA TpP ÿC ùàK@ù @ù¨ ø7 ñ ùA ThP ÿK ù( °Aù@ùI@ù5´à ª ?ÖàK ù 5´@ùÈ ø7 ñ ùa Tà ªWP RP ü ªÀ4´ )Q@ù(@¹ 1B T( ¹ ùO àC ù 4´( °! @ùÕDùO `±ø7àK@ùâC@ùá ª}ÿàG ù r´àK@ù @ùû @ù¨ ø7 ñ ùA T5P ÿK ù@ùÈ ø7 ñ ùa Tà ª-P øªàC@ù @ù¨ ø7 ñ ùA T%P ÿC ù÷G@ùà#@ù @ù¨ ø7 ñ ùA T P ÿÿ© Ò Òÿ/ ùÿ ùÿG ù÷# ù÷ª8 °è@ù ë| T ëó @ù¨ ø7 ñ ùA TP ÿK ùÓÀ5 WøFù RO àK ùàô ëÀ T m@ù ë@ T ë T~O àú7ó ªàK@ù @ùÈ ø6 ëó @ù¨ ø7 ñ ùA TèO ÿK ùÂ5ë T( !9ÑDù @ùb@ùáªÈO @õ´ü ª @¹ 1: °B T ¹( °Aù@ùI@ù¨ö´à ª ?ÖàC ù ö´@ùÈ ø7 ñ ùa Tà ªÆO FùઠRPO ó ª ö´ÿG ùèC@ù @ùê ðJU@ù?
ëö ðÖv@ù ÷T Rà'H©ª#ÑJ! ©Ï7©AM(Ë KÿàK ùàG@ùà ´ @ù¨ ø7 ñ ùA T¦O ÿG ùh@ùÈ ø7 ñh ùa TàªO èK@ù¨õ´àC@ù @ù¨ ø7 ñ ùA TO ÿC ùàK@ù¡Wø R O àC ù õ´àK@ù @ù¨ ø7 ñ ùA TO ÿK ùàC@ù ë@
Tè ðm@ù ëÀ T ë TO àUú7ó ªàC@ù @ùH ø6e àªtO ( áAùâK@ùà ª=N ¦ÿ6 Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òè ðm@ùè? ù+½RÕzR{ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùkцR5|R¥ ( =Dùà#@ù@ùI@ùè$´ ?ÖàK ùà$´ÿG ù@ùé ð)U@ù ëÑT @ùéG ù©Ð´@ù*@¹J 1# T @¹) 1C TàK@ùèK ù @ùhø6> ¹àC@ùFù ùH@¹ 1±ÿTH ¹èC@ù ùóM ü ª`±ÿµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òô ðr@ùۆRÕ|R7 ëó @ù¨ ø7 ñ ùA TO ÿC ù³ç5Fù @¹) 1b T ¹FùèO ùAAù@ùI@ù(ê´àª ?ÖàK ù ê´@ùé ð)U@ù ëAëT @ù3í´@ùi@¹) 1# T @¹) 1C TàK@ùèK ù @ùhø6 i ¹ @¹) 1ÿÿT ¹àK@ùèK ù @ù¨ ø7 ñ ùA TáN " R¨#Ñ! ³ÿ7©àK@ù
ËvÿàC ù઻aÿèC@ùÈæ´àK@ù @ù¨ ø7 ñ ùA TÎN ÿK ùèC@ùè ù@ùÈ ø7 ñ ùa TàªÄN ÿC ù( õCùUgÿàC ùàå´( }Fù@ùI@ùèæ´ ?ÖàK ùàæ´àC@ù @ù¨ ø7 ñ ùA T¯N ÿC ù R^N àC ù ç´è@¹ 1b Tè ¹àC@ù ùkM ü ªç´( áAùâ ðBP@ùà ªiM À
ø7àK@ùáC@ùâ ªo{ÿàG ùà´àK@ù @ù¨ ø7 ñ ùA TN ÿK ùàC@ù @ù¨ ø7 ñ ùA T
N ÿC ù@ùÈ ø7 ñ ùa Tà ª}N óG@ùÿG ù( éDùh@ùI@ù¨´àª ?Öü ªó ù ´ÿC ù@ùé ð)U@ù 끵T@ùèC ù(µ´ @ù @¹) 1à Th@¹ 1ã T@ùø64 Ò Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ùëԆR¤ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òô ðr@ùËۆRÕ|Rb Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò+øRu~Rô@ùT ¹h@¹ 1búÿTh ¹@ùÈ ø7 ñ ùa Tà ª+N " RüªèC@ù©#Ñ)! ¨ÿ7©!
Ëà ª¾ÿàG ùàC@ùaÿÿC ùèG@ù¨û´@ùÈ ø7 ñ ùa Tà ªN ÷ ùèG@ùè/ ùÿG ùàO@ù¡Wø RM àG ù û´ Ò Ò Ò Ò Ҩ#Ñ! ( Rè ù9 8 £( ÿC ùàO@ù¡Wø RM àG ùþR º ´öß©é ð)u@ù ëè ðm@ùHúUúü' ù T ëô÷ @ù6 @ùHø6
lM ÷ @ù6 )ù7ô ªàG@ù @ù¨ ø7 ñ ùA TÙM ÿG ùte 4( Dùà#@ù@ùI@ùHJ ´ ?Öü ª` ´ WøáO@ù,M àC ù ´ÿK ù@ùé ð)U@ù ëI T@ùèK ù( ´ @ù @¹) 1ã T@¹ 1 T@ù(ø6
¹@¹ 1BÿÿT ¹@ùÈ ø7 ñ ùa Tà ªªM üª( RéK@ùêC@ù©«7©AË à ª=ÿàG ùàK@ù`ÿÿK ùàC@ù @ù¨ ø7 ñ ùA TM ÿC ùèG@ù¨ ´@ùÈ ø7 ñ ùa Tà ªM ÷G@ùà;@ùm`ÿÿG ùàO@ù( Fù RM àG ù ´é ð)u@ù ëÀ Tè ðm@ù ë@ T ë TþL À ù7ô ªàG@ù @ùÈ ø6 ëô @ù ø7 ñ ù@< TÿG ù 4âcà/@ù Ò Ò$ R RzóÿàG ù ´á ª( Fùà@ùðL àù7àG@ù @ù¨ ø7 ñ ùA TQM ÿG ùÀöCùãeÿü ªà ´( Aù@ùI@ùÈ9 ´à ª ?ÖàC ù ´@ùÈ ø7 ñ ùa Tà ª<M èC@ù @ùê ðJU@ù?
ë@8 T Ò Òé@ù´§7©AË àC@ùÊ~ÿàG ùàª`ÿèG@ùH ´àC@ù @ù¨ ø7 ñ ùA T"M ÿC ùôG@ùàª`ÿÿG ùઠ" R RãðÿàG ùà ´á ªàªeL àC ù ´àG@ù @ù¨ ø7 ñ ùA T
M ÿG ùûC@ù@ùÈ ø7 ñ ùa TàªM ÿC ù( -Eùh@ùI@ù¨2 ´àª ?ÖàC ù ´ R§L àG ù ´è@¹ 1b Tè ¹àG@ù ù´K ü ª ´S@ù@ùà ª´K àGø7àH©â ª»yÿàK ù ´àC@ù @ù¨ ø7 ñ ùA TÙL ÿC ùàG@ù @ù¨ ø7 ñ ùA TÑL ÿG ù@ùÈ ø7 ñ ùa Tà ªÉL ôK@ùપ_ÿÿK ùÀöCùXeÿàK ù ´( 5Fù@ùI@ùh+ ´ ?Öü ª ´àK@ù @ù¨ ø7 ñ ùA T²L ÿK ù RaL àK ù@
´@¹ 1b T ¹àK@ù ùnK àG ùà ´( Eùâ ðBt@ùmK à?ø7âH©à ªtyÿàC ù@ ´@ùÈ ø7 ñ ùa Tà ªL àK@ù @ù¨ ø7 ñ ùA TL ÿK ùàG@ù @ù¨ ø7 ñ ùA TL ÿG ùàC@ù@ùé ð)]@ù ëá# T@ù ñ T @ùèG ù )@ùéK ù
@¹J 1b T
¹éK@ù(@¹ 1£ TàC@ù @ùÈ ø6 ( ¹àC@ù @ù¨ ø7 ñ ùA T`L ÿC ùüG@ùà'@ù@_ÿÿG ùöK@ùà7@ù<_ÿÿK ù( yEùÈ@ùI@ù# ´àª ?ÖàK ùà| ´ÿG ù@ùé ð)U@ù ë¡ T @ùéG ùI ´@ù*@¹J 1# T @¹) 1C TàK@ùèK ù @ùhø6 * ¹ @¹) 1ÿÿT ¹àK@ùèK ù @ù¨ ø7 ñ ùA T,L " RèH©¨ÿ7©AËÃ}ÿàC ùàG@ù_ÿÿG ùèC@ùhx ´àK@ù @ù¨ ø7 ñ ùA TL ÿK ùàC@ù @ù¨ ø7 ñ ùA TL ÿC ù( ñEù@ùI@ùh ´àª ?ÖàK ù`v ´ÿG ù@ùé ð)U@ù ë! T @ùéG ùÉ ´@ù*@¹J 1# T @¹) 1C TàK@ùèK ù @ùhø6 * ¹ @¹) 1ÿÿT ¹àK@ùèK ù @ù¨ ø7 ñ ùA TæK ( RéH©©Û7©AË |}ÿàC ùàG@ùÁ^ÿÿG ùèC@ùÈq ´àK@ù @ù¨ ø7 ñ ùA TÓK ÿK ùóC@ù@ùÈ ø7 ñ ùa TàªÊK ÿC ù!wEùh@ùI@ù( ´àª ?Öá ªàC ù o ´àO@ù
K àK ù p ´àC@ù @ù¨ ø7 ñ ùA TµK ÿC ùâcãCà/@ùáªh à"ø7àK@ù @ù¨ ø7 ñ ùA T§K ÿK ù!wEùh@ùI@ù ´àª ?Öá ªàK ù m ´àO@ùêJ àC ù`m ´àK@ù @ù¨ ø7 ñ ùA TK àO@ùèC@ùÿ# © @ù²ÿ7 ñ ù¡±ÿTK ýÿK ÿG ùôÃÿ55þÿ ÒXÿÿ ҜÿÿõJ ü ª ¶ÿµ ÒÓýÿà ªîJ àC ùÆÿµ§
@ùôÇÿ´ @ù@¹) 1ã T @¹) 1
TàC@ùèC ù @ù(
ø6T àªÛJ àC ù Íÿµ´ ×J ü ªàÔÿµÕ é Ð)M@ù ë TØJ ü ª@´àC@ù @ù¨ ø7 ñ ùA TPK ÿC ù@ùq@ùà ªÀ?Öó ªàG ù ´à ªÀ?ÖàK ù ´à ªÀ?ÖA R¶îÿÀåù7@ùèÛÿ7 ñ ùÛÿTà ª8K ÙþÿફJ àK ùÀÜÿµË દJ àK ùàäÿµØ ડJ á ªàC ù íÿµä àªJ á ªàK ùÀðÿµì ¹ @¹) 1BöÿT ¹àC@ùèC ù @ù¨ ø7 ñ ùA TK ( Rßýÿ@ù ñÁS T @ù(
@øèG ù)@ùéK ù
@¹J 1ãÒÿTþÿ* ¹ @¹) 1yÿT ¹àK@ùèK ù @ù¨ ø7 ñ ùA TùJ ( RéH©ª#ÑJ! ©ë7©AM(Ë |ÿàC ùàG@ùÒ]ÿÿG ùèC@ùè´àK@ù @ù¨ ø7 ñ ùA TäJ ÿK ùàC@ù¢CÑ Ò Ò R RöðÿàK ù´àC@ù @ù¨ ø7 ñ ùA TÓJ ÿC ùàK@ùÿK ù ðQEù@ùM@ùà# ù⪨´ ?Ö Òô Дr@ù ù7üó©è ªó ªü/ ùü ùü ùö ªè@ù ë T9 Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ùëֆR|Rûªö @ùÊ é@ù(@¹ 1à Tÿ ù Ò Òÿ©ÿ# ùkRuR Ò Òÿ©ÿ# ùëRRóª ÿs© Ò Ò Òÿ©ë$RõRö7 ù÷; ù÷SA©ö @ù© ÿ ù( ¹é# ùöªô@ùû @ùú+@ù ðè@ù ëá
Tè#@ù@ù ÐUGùàªRvÿà 4 ðÅBùK@ù¨¼´à#@ù ?ÖàC ù ð ¼´ÿG ù@ùé Ð)U@ù ëÁtT @ùéG ùit´@ù*@¹J 1# T @¹) 1C TàC@ùèC ù @ùhø6 * ¹ @¹) 1ÿÿT ¹àC@ùèC ù @ù¨ ø7 ñ ùA TOJ ( Rà'H©ª#ÑJ! Fù©¯7©AM(Ë â{ÿàK ùàG@ù']ÿÿG ùèK@ù·´øªàC@ù @ù¨ ø7 ñ ùA T8J ÿC ù÷K@ùà#@ù @ù¨ ø7 ñ ùA T/J ÿK ù÷# ù÷ª ð ð©Cùh@ùI@ùh´àª ?ÖàK ù`´Fù Òw Àù7ø ªàK@ù @ù¨ ø7 ñ ùA TJ ÿK ùø 4ø#@ù@¹ 1C Tÿ ù è@ù ëõ3@ù T ð©Cùà#@ù@ùI@ùh±´ ?Ö ðàK ù`±´Fù ÒU ²ù7ø ªàK@ù @ù¨ ø7 ñ ùA TôI ÿK ù8
4 ð õCùbÿàK ù@²´ ðåAù@ùI@ù¨²´ ?ÖàC ù ²´àK@ù @ù¨ ø7 ñ ùA TÞI ÿK ù¤H àK ù@²´ ð¡âAùh@ùI@ù²´àª ?Öâ ªàG ù²´àK@ù¡âAùH à ø7àG@ù @ùõ3@ù¨ ø7 ñ ùA TÄI ÿG ùàC@ù ð!GùâK@ùvÿàG ù`²´àC@ù @ù¨ ø7 ñ ùA TµI ÿC ùàK@ù @ù¨ ø7 ñ ùA TI øG@ùÿÿ©àªá#@ù® àG ùø ù°´â ª Ð1Gùàª7I 0ù7àG@ù @ù¨ ø7 ñ ùA TI ÿG ùø@ù@¹ 1B T ¹ûªö @ùÿ ÿ ù ¹ûªö @ùù àªá#@ù ø ªàG ùèª ¤´ÿ ùÿG ùûªöªî ü' ù Ò Ò Òÿ ùË@RRèªûªöª XH @µàªsÿõ ªàK ùàþµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿ+ ùe
àªÒH ø ªÀþµ Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿ+ ù5uRDRh Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿ+ ù5uRëDRY Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿ+ ù5uRERJ àªáªâªH àC ù þµ Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ù$ àªH õ ªàC ùÀþµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÿ+ ùUuRËGR" êG £´ Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿÿ©ÿ+ ù5uRëER Ò Òÿ©ÿ# ù R Ò Òÿ©ÿ# ùK RÕ~RU Ò Òÿ©ÿ# ùëRÕ~Rô@ùö @ùû
Ò Ò Òÿ©ÿ# ù«Rõ~RGþÿ Ò Òÿ©ÿ# ùËR5R@þÿ Ò Òÿ©ÿ# ù R5R9þÿ Ò Ò Òÿ©ÿ# ù« R5R1þÿ Ò Ò Òÿ©ÿ# ùk
R Ò Ò Òÿ©ÿ# ù«
RUR÷; ùûª!þÿ Ò Ò Òÿ©ÿ# ùKRuRþÿ Ò Ò Òÿ©ÿ# ùRuRþÿ Ò Òÿ©ÿ# ù+RuR þÿ Ò Òÿ©ÿ# ùRuRþÿ Ò Ò Òÿ©ÿ# ùkRðýÿ Ò Òÿ©ÿ# ù«Rêýÿ Ò Òÿ©ÿ# ù Räýÿ Ò Òÿ©ÿ# ù«RÞýÿ Ò Òÿ©ÿ# ù RØýÿ
ñ˞ Tè ÐE@ù @ùH Rè ùá !Ìû ÿs© Ò Ò Òÿ©ëRµRö7 ùÆýÿÿs© Ò Ò Òÿ©k RµRö7 ù½ýÿÿs© Ò Ò Òÿ© RÕRö7 ù´ýÿÿs© Ò Ò Òÿ©"RÕRö7 ù«ýÿÿs© Ò Ò Òÿ©K$R¬ýÿÿs© Ò Ò Òÿ©$R¥ýÿÿs© Ò Ò Òÿ©+&R ÿs© Ò Ò Òÿ©k&RRýÿÿs© Ò Ò Òÿ©öß©÷SA©ö @ùµ~R:
é Ð)I@ù ë Ð TàªB R¤G & ö ª êý6 Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÿ+ ùUuR HR
çF µàªrÿù ªàG ùû @ù ñýµkKRàK@ù µ3 àªjG àK ù ñýµÿK ù«KR7 àªcG ù ª`òýµ LRàK@ù µ$ Ò ҭïÿNRàK@ùÀ µ ҧïÿ
@ù´ @ù)@¹) 1# T @¹) 1C TàK@ùèK ù @ùhø6Î ÒkQRàK@ù ´ @ùè ø7 ñ ù Tó ªÅG ëªÿK ùY ´(@ùø7 ñ( ù¡ Tàªó ªºG ëªàG@ù ´ @ùè ø7 ñ ù Tó ª°G ëªÿG ùàC@ù ´ @ùè ø7 ñ ù Tó ª¥G ëªÿC ùH3@ù¨ ´ Ð!©Gù @ù ëàwT(@ùU@ùhtÑ7 @ù)B9iq96 ¬B9)q16qù6(¬B9Èp16 ¬@ùs´( @ù ñ T)a *@ù_ë`uT)! ñaÿÿTµuRÓ ÿë© Ò Ò Òÿÿ©ÿÿ© Òÿÿ©ÿ# ùÿ ùöª Ò Òÿ? ùvRK[R Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùUwR«uR GF µàªpqÿàK ù@þµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ù ÃF àG ù þµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùwR+wRX F ~µàªIqÿø ª þµ Ò Òì દF ú ª@þµ Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùwRËwR= F |µàª.qÿø ª@þµ Òá àªF ö ª þµ Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùwRkxR# X@ùX{´[ @ù@¹ 1# Th@¹ 1C TH@ùhø6 Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùwR+{R `F ö ªú+@ù þµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùwR«{Rô
@ùéK ùiþ´ @ù*@¹J 1#~ T @¹) 1C~ TàG@ùèG ù @ùh~ø6ö Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùwRk~RÕ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ù5xR˓RŠઠF ü ª@Sþµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùµxR떆R Ð ¥Gù ÐGù Òhsÿó ª l´àªsÿh@ùÈ ø7 ñh ùa TàªF Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùÕxR RÅ àªéE ü ª Qþµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùõxRKRà Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùõxRRÑ Ð ¥Gù ÐGù Ò&sÿàC ù@f´XsÿàC@ù @ù¨ ø7 ñ ùA TCF Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿÿ©yR«R E Ð eµàªApÿü ªÀPþµ$ à ª E àG ù@Qþµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùUyRK¡R Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùUyR«¡R îD ÀaµàªpÿàG ùàpþµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò
lE àC ù pþµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òè °m@ùè? ùK»RÕzR
@ùù °9w@ù_´ @ùé@¹) 1ce T @¹) 1e TàG@ùèG ù @ù¨eø60 Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùK¤R Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òè °m@ùè? ù«»RÕzRÐ Ð ¥Gù Ð Gù ҆rÿàC ùÀX´¸rÿàC@ù @ù¨ ø7 ñ ùA T£E Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿÿ©uyR«¦Rä Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òè °m@ùè? ùK¼RÕzR¡ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù먆RyRò YD Sµàªoÿú ªcþµ
àªáD àK ù dþµ Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò˼Rè °m@ùè? ùÕzRw ÏD ü ªó?@ù Bþµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù+©RyRÅ à ª»D àG ù`Bþµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù©RyR² Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù멆RyR¢ R Òü °w@ù òÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùk¬RyR Ròÿ Ð ¥Gù Ð
Gù ÒàqÿàC ù H´rÿàC@ù @ù¨ ø7 ñ ùA TýD Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿÿ©µyRˮR> Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù ±R\ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùK±RM Ð ¥Gù ÐGù ңqÿàG ù`B´ÕqÿàG@ù @ù¨ ø7 ñ ùA TÀD Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùÿG ùõyRk³Rôªö @ùË ÒNóÿ R°óÿ Ò Ò Òÿ©ÿ# ù+RRúÿ Ò Ò Òÿ©ÿ# ùkRR úÿ Ò Ò Òÿ©ÿ# ù«þRµ~Rô@ùö @ù Ò Ò Òÿ©ÿ# ùËRõ~RùùÿmC @AµàªnÿàK ùýµÿë© Ò Ò Òÿÿ©ÿÿ© Òÿÿ©ÿ# ùÿ ùöª Ò Òÿ? ù
èC àC ù@ýµÿë© Ò Ò Òÿÿ©ÿÿ© Òÿÿ©ÿ# ùÿ ùöª Ò Òÿ? ùvR\R|
@ùéK ùI>´ @ù*@¹J 1£s T @¹) 1Ãs TàC@ùèC ù @ùèsø6¢ ÿë© Ò Ò Òÿÿ©ÿÿ© Òÿÿ©ÿ# ùÿ ùöª Ò Òÿ? ùvR+_R\ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùuxR«R é °)I@ù ë@ Tà ªb R¶C 8 ø ª þ6 Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùµxR+R àªáªâ ªyC àK ù ÐÀ=þµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òè °m@ùè? ùk½RÕzR÷ª ãB 4´ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù ÒÿK ùè °m@ùè? ùÕzRk½Rö @ù÷ª Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒkÆR{Rù àªPC ö ªàG ù@gýµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÿ+ ùUvRKeRã Ð ¥Gù ÐùFù ҙpÿó ªàG ù-´àªÉpÿh@ùÈ ø7 ñh ùa T઴C Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿ+ ùÿG ùuvRkgRö @ù¿ àªC ö ªàG ùýµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÿ+ ùµvRËiR© Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÿ+ ùµvR jR Èø·é )E@ù @ùÉ Ð)© °J ñIè' ©Á Ð!pJB Ò Ò Òÿ©ÿ# ùkRÌøÿKB `$µàªtmÿàG ù ¹ýµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ù ÇB ú ª¸ýµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ùÕwR«R] ઴B àG ù@¸ýµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùÕwR Rö @ùJ H@ùèK ùè¶ý´àªZ @ù @¹) 1CX TH@¹ 1cX T @ùXø6È Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùÕwR«Rö @ù- ) ¹ @¹) 1gÿT ¹àK@ùèK ù @ù¨ ø7 ñ ùA TC ( Rëêÿÿë© Ò Ò Òÿÿ©ÿÿ© Òÿÿ©ÿ# ùÿ ùöª Ò Òÿ? ùvRk[R
¹h@¹ 1~ÿTh ¹H@ùÈ ø7 ñH ùa TàªäB ( Rúªû @ùìÿ* ¹ @¹) 1ÿT ¹àG@ùèG ù @ù¨ ø7 ñ ùA TÓB ( R¹ìÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùõxR˛R? Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùˤRUyR/ é ¹ @¹) 1ÿT ¹àG@ùèG ù @ù¨ ø7 ñ ùA T¤B ( Rïÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù묆RyR Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù±RÕyRôªöª àªôA ü ª þµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒëņRÕ{R Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒkȆRÕ{R Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù+ʆR Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùkʆRõ{Rö @ùg ¿A àK ù@%þµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù ̆R
Ò Ò Òÿÿ©ÿÿ©ÿ©ÿ/ ùÿ ùΆR|R÷ÿથA ü ªó ù *þµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùKІR5|Rs÷ÿ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùІR5|Ri÷ÿ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ù+цR5|R_÷ÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òk߆R}R ° ¥Gù °Gù ÒÓnÿàK ù ù ´oÿàK@ù @ù¨ ø7 ñ ùA TðA Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù ÒÿK ù5}RkáRö @ùþ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ҫãRu}Rð ° ¥Gù °Gù ҦnÿàK ù õ ´ØnÿàK@ù @ù¨ ø7 ñ ùA TÃA Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù ÒÿK ù}R«åRö @ùÑ àª(A àK ùàñþµü' ù Ò Ò Òÿ ù«8R ü' ù Ò Ò Òÿ ùë8RuR+øÿú+ ùé )I@ù ë Tb R(A ª Àôø7ö ªàG@ù®
@ýáb a öÎèÿé )I@ù ë Tàªb RA ÷ ª@Iý6 Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÿ+ ùUvReR Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùõwRRö @ù àªÚ@ àG ù ýµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùõwRˆRö @ùp Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùõwR+Rö @ù` ¸@ ü ª ýµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùõwRkRö @ùN થ@ û @ùàK ù
ýµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ùõwRˇR: @ùöà ´à ª @ùÈ@¹ 1cO T@¹ 1O T @ù¨Oø6 Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ùõwRkR àªv@ ö ªù 9w@ù
ýµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ùõwR늆R
@ù8Û ´ @ù @¹) 1CK T @¹) 1cK TàG@ùèG ù @ùKø6_ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ùõwR«Rì Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ùõwRkRÝ Җòÿ RÅõÿ* ¹ @¹) 1ÿT ¹àC@ùèC ù @ù¨ ø7 ñ ùA T¯@ ( Rû @ù °ü w@ùéÿ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùцR5|Rðõÿ Ò Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ùkӆRåõÿ
@ àG ùþýµ Ò Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ù«ӆRØõÿ Ò Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ù ԆRÎõÿ Ò Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ù«ԆRÄõÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò Òÿ? ùÕwR+
Rö @ù ¹H@¹ 1â§ÿTH ¹ @ùÈ ø7é ª ñ ùA TX@ ( RãêÿË? àG ùÔýµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òô r@ùKچRÕ|R` Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òô r@ùچRÕ|RP ? Ä µàªAjÿü ªû @ù ° °
þµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò+éRõ}R: à ª? àC ù þµ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒkéRõ}R) Ò Ò Òÿÿ©ÿÿ©ÿ©ÿ/ ùÿ ùöª ÒËéRõ}R
@ùéG ùI¿ ´ @ù*@¹J 1#c T @¹) 1Cc TàC@ùèC ù @ùhcø6 Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒKìRõ}Rÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒËìRõ}Rñ ° ¥Gù ° Gù ҧlÿàC ù¹ ´ÙlÿàC@ù @ù¨ ø7 ñ ùA TÄ? Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù ÒÿC ù~RëîRö @ùÒ àª)? àK ù þµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒkòRU~RÀ Ò ÒÁðÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒëôRU~R¯ ұðÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ҫöRJñÿø> àK ù`þµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒëöR:ñÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒK÷R-ñÿ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Òë÷R!ñÿ @ý( Rb a [ëÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ҋ߆R}Rd Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒËãRu}RV ú+ ù > ª µàªFiÿö ªàG ùû @ùú+@ù Ü ðw@ùýµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÕvRklR9 àª> àK ù ýµÿë© Ò Ò Òÿÿ©ÿÿ© Òÿÿ©ÿ# ùÿ ùöª Ò Òÿ? ùÕvR«lR$
@ùéG ùi¦ ´ @ù*@¹J 1K T @¹) 1£K TàK@ùèK ù @ùÈKø6a ÿë© Ò Ò Òÿÿ©ÿÿ© Òÿÿ©ÿ# ùÿ ùöª Ò Òÿ? ùÕvRKoR ú+ ù ¥Gù ýFù ҹkÿàC ùà¡ ´ëkÿàC@ù @ù¨ ø7 ñ ùA TÖ> Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿÿ©õvRëqRö @ùã Rwôÿ Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ù ՆR ôÿà ª/> àK ù@Ëýµ Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ù«ՆRþóÿ Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ù ֆRõóÿ Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ù«ֆRìóÿÈ ¹@¹ 1°ÿT ¹ @ù¨ ø7 ñ ùA T> ( Rû @ùéÿ ¹ @¹) 1â´ÿT ¹àG@ùèG ù @ù¨ ø7 ñ ùA T> ( Rû @ùÙ ð9w@ù¸éÿ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ùõwRR Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒÔ ðr@ùëۆRÕ|R{ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒKøRðÿàªÆ= ü ªó ù ûýµ Ò Òÿ©ÿÿ©ÿ© Òÿ/ ùöª Ò+úR~Rô@ù] Ò Òÿ©ÿÿ©ÿ© Òÿ/ ùöª ҫüR~Rô@ùP Ò Ò Òÿ©ÿÿ©ÿ© Ò ҋþRµ~Róÿ= àK ù`Ûýµ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒÔ ðr@ùË*RuR2 Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒÔ ðr@ùK-RuR" Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒÔ ðr@ùË-RuR
= ÒÔ ðr@ù eþ6k/RRú ªø ªüó©üó©ü' ùó ªü/ ùü ùöªû ªàK@ùÀ ´ @ùø7 ñ ù! Tü ùüªøªúªõªûªôªù ªÔ= ëªôªûªõªúªø ªü @ùX ´@ùø7 ñ ù¡ Tàªø ªÄ= ëªàG@ù ´ @ùè ø7 ñ ù Tø ªº= ëªàC@ù ´ @ùè ø7 ñ ù Tø ª°= ëªZ ´H@ùø7 ñH ù¡ Tàªø ª¦= ëª\ ´@ùø7 ñ ù¡ Tà ªø ª= ëªÀ ° ì c á ªâªDVÿ ÒüëD©õ3@ù ´H@ùÈ ø7 ñH ùa Tàª= ´¨@ùÈ ø7 ñ¨ ùa Tàª= õ@ùè?@ùH ´è?@ù@ùè ø7 ñé?@ù( ùa Tà?@ùu= ´è@ùÈ ø7 ñè ùa Tàªm= ´h@ùÈ ø7 ñh ùa Tàªe= à@ù÷;@ùà ´ @ù¨ ø7 ñ ùA T\= à#@ùà ´ @ù¨ ø7 ñ ùA TT= àO@ùà ´ @ù¨ ø7 ñ ùA TL= ´¨@ùÈ ø7 ñ¨ ùa TàªD= à/@ùà ´ @ù¨ ø7 ñ ùA T<= ´è@ùÈ ø7 ñè ùa Tàª4= ´h@ùÈ ø7 ñh ùa Tàª,= ´@ùÈ ø7 ñ ùa Tà ª$= à7@ùà ´ @ù¨ ø7 ñ ùA T = à@ùà ´ @ù¨ ø7 ñ ùA T= ´È@ùÈ ø7 ñÈ ùa Tઠ= Wøà ´ @ù¨ ø7 ñ ùA T= ´@ùÈ ø7 ñ ùa Tàªü< ¨YøÉ ð)y@ù)@ù?ëÁ Tàªý{S©ôOR©öWQ©ø_P©úgO©üoN©é#MmÿÀ_Ö @ýáb a öû @ùú+@ù Ü ðw@ù @ùH¯ü6}åÿ* ¹ @¹) 1ÿT ¹àC@ùèC ù @ù¨ ø7 ñ ùA TÓ< ( Rû @ù Ö ðÖv@ùíÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò íRõ}RÜþÿÀ
@ý( Rb a +äÿú+ ùÉ ð)I@ù ë Tb RA< à @^ø7ö ªàC@ù} Ò Òÿÿ©ÿÿ©ÿ' ù Òÿ/ ù ׆Rõñÿ* ¹ @¹) 1¢´ÿT ¹àK@ùèK ù @ù¨ ø7 ñ ùA T< ( Rû @ù Ü ðw@ù¢åÿà#@ù< àC ù Cþµü' ù Ò Ò Òÿ ùK3RRóÿü' ù Ò Ò Òÿ ùË5RRèªûªöªþÿï; àK ùàNþµõ3 ùü' ù Ò Ò Òÿ ùË=RՁR÷òÿõ3 ùü' ù Ò Ò Òÿ ù >RՁRîòÿõ3 ùü' ù Ò Òÿ ù GRRçòÿõ3 ùü' ù Ò Ò Òÿ ù«?RÝòÿÉ; àC ù Mþµõ3 ùü' ù Ò Ò Òÿ ùë?RÒòÿü' ù Ò Ò Òÿ ùK@RËòÿશ; â ªàG ùÀMþµü' ù Ò Ò Òÿ ù@R¿òÿ @ýáb a öû @ùú+@ù Ü ðw@ù @ùȭü6qåÿõ3 ùü' ù Ò Ò Òÿ ù AR«òÿõ3 ùü' ù Ò Ò ÒËBRµR¤òÿõ3 ùü' ù Ò Ò Ò CRµRòÿ Ò Òÿ©ÿ# ù Rrñÿó ªê: ) < Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿ+ ùÿK ù5uRKDRþÿó ªØfÿ û @ùó ª ´ @ù ëëªaÿÿT È ð=@ù @ùÁ !T"Ò: ãòÿÈ ð@ù? ëàû @ùëª@þ4À ° ì c á ª¢uRTÿáâCã#àªáÿàø7 ¥Gù ñFùh@ùA@ù ´À Ø!¬; @ 5àªáª Ò ?Öó ª¨; Ó
´àªËhÿh@ùÈ ø7 ñh ùa Tશ; õuRëWR ÕuRëURH7@ù @ù ù ´ @ùè ø7 ñ ù Tó ª¦; ëªW ´è@ùø7 ñè ù¡ Tàªó ª; ëª6 ´È@ùèø7 ñÈ ù¡ Tàªó ª; ëª Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿ+ ùö @ùýÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÿ+ ùýÿàªáª ÒÖ: ó ªàõÿµõuRkWRºÿÿO: 7 ´õuRkWRû @ù´ÿÿ ÒÿG ùkKRû @ùàK@ù`rþµóÿ REãÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùÿK ùwRëvRgýÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùwRwRWýÿ Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ùöª Ò Òÿ? ùwR+xRHýÿ RHøÿ Ò Ò Òÿÿ©ÿÿ©ÿ©ÿ/ ùÿ ùèª Ò Òÿ? ùÕxRRøÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùyR+Røÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùUyR ¡Rxøÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒÿG ùÈ Ðm@ùè? ù »RÕzRýÿ R]çÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù+¦RuyRTøÿ Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª ÒÈ Ðm@ùè? ù¼RÕzRãüÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ùK®RµyR4øÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùèª Ò Òÿ? ù벆RõyR$øÿ Ò Òÿ©ÿ# ù Rðÿù?@ùÿ ù ù?@ù@ùÈ ø7 ñ ùa Tà ª: AÞÿù? ùà 5È ÐE@ù @ùh ðÉ )© ñ*è@ùè+ ©Á !pa9 Ò Ò Òÿ©ÿ# ù Rãïÿÿë© Ò Ò Òÿÿ©ÿÿ© Òÿÿ©ÿ# ùÿ ùöª Ò Òÿ? ùÿK ùvRK\Rüÿ R¼ùÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ù5vRKaRö @ùvüÿÈ Ð=@ù @ù¡ ð!T"?9 Wöÿ Ò Ò Òÿÿ©ÿÿ©ÿ©ÿÿ©ÿ ù Ò Òÿ? ùÿ+ ùuvRëfRö @ù_üÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ùöª Ò Òÿ? ùÿG ùÕwRkRNüÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù ÒëàR5}Rö @ù@üÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò+åR}Rö @ù2üÿ Rûÿ Rûÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù Ò+éRõ}Rö @ù üÿ R0ýÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿ/ ùÿ ù ÒkîR~Rö @ùüÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùvR«_Rö @ù üÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÿG ùÕvRklRö @ùïûÿ R:ýÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùõvRkqRö @ùÝûÿ Ò Ò Òÿÿ©ÿÿ©ÿ© Òÿÿ©ÿ ù Ò Òÿ? ùÕvRËoRö @ùÍûÿÈ Ð=@ù @ù¡ ð!T"8 Bþÿý{¿©ý ë T@ùÉ Ð)Q@ù ë¡ T@ù¢ ´© ! ñ T@¹ qàý{hÀ_Ö Rý{hÀ_Ö ý{hÀ_Ö Rý{hÀ_ÖÉ Ð)I@ù ë TB R9 ý{h @ýA b a àý{hÀ_Öÿ Ñý{©ýC ¡ ´@ù ë T
@ùê ´I @ù? ñ TJa K@ùë` TJ! ) ñaÿÿT
@ù) @ùÊ ÐJA@ù@@ùè' ©Á !Ø ?8 Rý{A©ÿ À_ÖÈ Ð=@ù @ùÁ ! D8 öÿÿéª R© ´)@ù?ë¡ÿÿTðÿÿÉ Ð)@ù? ëAüÿT Rý{A©ÿ À_ÖÿÑöW©ôO©ý{©ýà óª@ù9@ù ´É
@ùÉ ´ô ª" ´@ @ùC ´a @ù ÐBp@ùÞ8 ` µ2 À Ð p@ùÿÿµÁ Ð!p@ù ÐBp@ùÔ8 ´õ ªÈ
@ùàªáªâª ?Öó ª¨@ù ø7 ñ¨ ùà Tàªý{C©ôOB©öWA©ÿÀ_Öàª9 àªý{C©ôOB©öWA©ÿÀ_Ö
@ùÉ Ð)A@ù @ùÉ )
Ê J9 ñIè' ©Á !X ß7 àªý{C©ôOB©öWA©ÿÀ_Ö@ù¥F© ´"@ùB ´@ ֈ ´
@ùH ´, ôO¾©ý{©ýC @ ´ó ªÈ Ðu@ù ëÉ Ð)m@ùIúÉ Ð)q@ùIú! Tëôh@ùHø6àªý{A©ôO¨À_Öàª_8 ô ªh@ùÿÿ7 ñh ù¡þÿTàªÏ8 àªý{A©ôO¨À_Ö àªý{A©ôO¨À_ÖÿÑöW©ôO©ý{©ýà óªô ª(@ùÉ Ð)Q@ù ë Th
@ù = ñ( Ti@¹@!¥? ± T7 µ àª" R# Rý{C©ôOB©öWA©ÿrÜÿàªú7 `þÿ´õ ªÐ7 á ª¨@ùýÿ7 ñ¨ ù!ýÿTàªõª8 áªäÿÿ @ýCÓ¡ ±` T ñ¡ Ti"C)!yªßÿÿÈ Ð1@ù@ùi7 ` 4h@ù
@ù\7 È Ð%@ù @ùó ùÁ !\ [7 Òý{C©ôOB©öWA©ÿÀ_Öi"C)(yªáËÁÿÿઠ7 á ª½ÿÿÿCÑöW©ôO©ý{©ýÈ Ðy@ù@ùè ù@ù B9©86ôªó ªé ð!AùI@ùÉ Ð)Y@ù ë¡ T Ò# RI8 õ ª ´è# ! ÿÓ ©àªâA²ìiÿó ª¨@ùèø7 ñ¨ ù TàªH8 ¨ ´ ?Öõ ªÀýÿµbÿ7 h@ù
@ùÉ Ð)A@ù @ùè ùÁ ! !7 Òè@ùÉ Ð)y@ù)@ù?ëá Tàªý{D©ôOC©öWB©ÿCÀ_Ö-8 7 õ ª@úÿµäÿÿÿà ÑôO©ý{©ý @ùB9h 6@ù = ñé T @ýCÓ¡ ñ T ±¡ T C)(yªàËý{B©ôOA©ÿà À_Ö @¹@ ¥ý{B©ôOA©ÿà À_Ö C) yªý{B©ôOA©ÿà À_Öý{B©ôOA©ÿà (7 ÅÜÿ ´ó ªÔÿÿh@ùÈüÿ7 ñh ùaüÿTà ùàªñ7 à@ùý{B©ôOA©ÿà À_Ö ý{B©ôOA©ÿà À_ÖÿCÑöW©ôO©ý{©ýô ªÈ Ðy@ù@ùè ùè Ð!9ÑDù @ùb@ùáªÁ7 @ ´õ ª @¹ 1B T¨ ¹è ð½Bù¨@ùI@ù( ´àª ?Öó ª¨@ù ´È ø7 ñ¨ ùa TàªÀ7 h@ùÉ Ð)U@ù ëà T R Òé# )! öÓ ©!M(Ë àªNiÿõ ª ´È@ùÈ ø7 ñÈ ùa T઩7 ´h@ùÈ ø7 ñh ùa Tડ7 È °u@ù¿ëÉ °)m@ù¤IúÉ °)q@ù¤Iú T¿ëó àª7 ó ª ø7¨@ù ø7 ñ¨ ù Ts 4àªÆ ó ª ±a Tj6 µàª²6 ô ª ´è@ùÉ °)y@ù)@ù?ë¡ Tàªý{D©ôOC©öWB©ÿCÀ_Öàªq7 óüÿ5è ÐAù@ùI@ùÈ ´àª ?Öõ ªÀ ´.6 ó ªÀ ´è Ð! @ùÕDùàª,6 ø7è йFù¨@ùA@ù ´ Ð Ø!:7 5àªáªâªÀ?Öô ª67 ´¨@ùÈ ø7 ñ¨ ùa TàªF7 h@ùÈøÿ7 ñh ùaøÿTàª?7 Àÿÿ´Rv˃R¨@ùÈ ø7 ñ¨ ùa Tàª57 ´h@ùÈ ø7 ñh ùa Tàª-7 ð @4c Ðc áªâªÖOÿ Ҧÿÿ 6 µàª2aÿõ ªàéÿµTRöCRïÿÿàª6 ó ª¨@ù êÿµÈ ø7 ñ¨ ùa Tàª7 TR6Ráÿÿv@ù ´u
@ùÈ@¹ 1c T¨@¹ 1 Th@ù¨ø6 TRÖăRh@ùùÿ6ÐÿÿRȃRÍÿÿ ÒTRVŃRºÿÿÈ ¹¨@¹ 1ÂýÿT¨ ¹h@ùÈ ø7 ñh ùa Tàªé6 ( Róª.ÿÿàªZ6 õ ªïÿµ´RöʃR³ÿÿ´R6˃R¡ÿÿtR¶ƃRÿÿàªáªâª<6 ô ªàðÿµ ·5 à ´´R˃RÿÿÏ6 RÿÿÈ °=@ù @ù¡ Ð!T"°5 ôÿÿÿà ÑôO©ý{©ý @ùB9h 6@ù = ñé T @ýCÓ¡ ñ T ±¡ T C)(yªàËý{B©ôOA©ÿà À_Ö @¹@ ¥ý{B©ôOA©ÿà À_Ö C) yªý{B©ôOA©ÿà À_Öý{B©ôOA©ÿà Å5 bÛÿ ´ó ªÔÿÿh@ùÈüÿ7 ñh ùaüÿTà ùàª6 à@ùý{B©ôOA©ÿà À_Ö ý{B©ôOA©ÿà À_ÖÿCÑüo©úg©ø_ ©öW
©ôO ©ý{ ©ýôªóªúªüªõªö ªÈ °y@ù@ù¨ø( @¹ 1ã T@¹ 1 T R5 ´ø ª÷ ÐèîEù @¹) 1ó ùô ùb T ¹èîEù @ù( ùè Ð
Dù"5 `· ´ó ªö ùè °%Gùàªâªãª Rl5 ö ªh@ùÈ ø7 ñh ùa TàªH6 ¶ ´@ùÈ ø7 ñ ùa Tàª@6 áîEùàªfMÿó ª ¶ ´h@¹ 1B Th ¹h@ù ø7 ñh ù` Tó ùÈ@ù¨ø7 ñÈ ùA Tàª*6 ¨ ¹@¹ 1B÷ÿT ¹ RJ5 ÷ÿµ ð 8c Ðc ¡xR" RÊNÿ ÒE àª6 ó ùÈ@ù¨üÿ6÷ °÷"9óÒDùà@ùb@ùáª÷5 @± ´ø ª @¹ 1B T ¹ù Ð!Aù@ùI@ùh± ´àª ?Öó ª`± ´@ùÈ ø7 ñ ùa Tàªö5 h@ùÉ °)U@ù 렱 T R ÒéC)! öW©!M(Ë àªgÿô ª ´È@ùÈ ø7 ñÈ ùa Tàªß5 ´h@ù ø7 ñh ù T¨@ùhø7 ñ¨ ù TàªÒ5 àªÏ5 ¨@ùèþÿ6õÒDùà@ù¢@ù᪳5 ô' ù ¯ ´ó ª @¹ 1B Th ¹!Aùh@ùI@ù° ´àª ?Öø ª ° ´h@ùÈ ø7 ñh ùa Tલ5 @ùÉ °)U@ù ë ° T R ÒéC)! ós©!M(Ë àª@gÿù ª ´h@ùÈ ø7 ñh ùa Tàª5 9¯ ´@ù ø7 ñ ù T@ùhø7 ñ ù Tà ª5 àª5 @ùèþÿ6Õ °µr@ù_ë TI@ù(B9¨ 7è °aGù?ë T*@ùJ ´I @ù? ñ TJa K@ùë TJ! ) ñaÿÿTH@¹ 1¢ TH ¹# ғ4 ú ªà µÿ# ùÿ ù Ò Ò Ò Òó
Rö Rüª Òy )@ù?ëÀ T©ÿÿµÉ °)@ù ë¡üÿT R|4 ÀÞ ´é ªH@¹ 1B TH ¹(
@ù ùú ªü ЁSEù@ùI@ù(¦ ´àª ?Öö ª ¦ ´àªÚ4 ±& Tó ªÈ@ùÈ ø7 ñÈ ùa Tàª65 ñᦠTSEù(@ùI@ù¨© ´àª ?Öö ª © ´àªÄ4 ± ª Tó ªÈ@ù ø7 ñÈ ùÀe T
ñf TSEù(@ùI@ù² ´àª ?Öö ª ² ´àª Ò R RÞØÿø ªú ù ² ´È@ùÈ ø7 ñÈ ùa Tઠ5 SEù(@ùI@ùè± ´àª ?Öö ªà± ´àª! R R RÇØÿû ª@² ´È@ùÈ ø7 ñÈ ùa Tàªó4 àªáªb R}4 ö ª ± ´@ùÈ ø7 ñ ùa Tàªæ4 h@ùÈ ø7 ñh ùa Tàªß4 Û °{w@ùÈ °m@ùßë Tßë@ Tßë Tàª[4 ó ªù7È@ùÈ ø6
ßëóÈ@ùÈ ø7 ñÈ ùa TàªÅ4 Z 5SEù@ùI@ù( ´àª ?Öö ª ´àª Ò R RØÿó ª` ´È@ùÈ ø7 ñÈ ùa Tમ4 SEù(@ùI@ù( ´àª ?Öö ª ´àª Ò R RlØÿø ª ´È@ùÈ ø7 ñÈ ùa Tàª4 àªáªb R"4 ö ª ´h@ùÈ ø7 ñh ùa Tàª4 @ùÈ ø7 ñ ùa Tàª4 ßëÀ TÈ °m@ùßë@ Tßë Tàª4 ó ªÀùø7È@ùÈ ø6
ßëóÈ@ùÈ ø7 ñÈ ùa Tàªl4 S© 5H@ù 9@ùi ´)@ù) ´è ÐÉFùઠ?Öö ª « ´È@ùÛ °{O@ù ë! TÈ@ù ñR T È ¹ö# ùÈ@ùÈ ø7 ñÈ ùa TàªN4 SEù@ùI@ù© ´àª ?Öø ª© ´àª Ò R R Øÿö ª © ´@ùÈ ø7 ñ ùa Tàª84 é#@ù( @ù)@ù?ëÍ T)ýA ëm TÉ@¹) 1B TÉ ¹ê#@ùI
@ù6y(ø H ù à#@ùáªE3 1@ð TÈ@ùÈ ø7 ñÈ ùa Tàª4 è ÐEùà@ù@ùI@ùh¥ ´ ?Öó ª`¥ ´h@ùÉ °)U@ù ëᥠTu@ù5§ ´v
@ù¨@¹ 1ã TÈ@¹ 1 Th@ù(ø6
¨ ¹È@¹ 1BÿÿTÈ ¹h@ùÈ ø7 ñh ùa Tàªô3 ( RóªéC)! ê#@ùõ+©!M(Ë àªeÿø ª ´¨@ùÈ ø7 ñ¨ ùa Tàªá3 ؠ ´h@ùÈ ø7 ñh ùa TàªÙ3 è ÐEù@ùI@ù¨ ´àª ?Öó ª ´@ùÈ ø7 ñ ùa TàªÉ3 SEù@ùI@ùè ´àª ?Öø ªà ´àª Ò R R×ÿ@¡ ´õ ª@ùÈ ø7 ñ ùa Tળ3 h@ùÉ )U@ù ë!¡ Tv@ù֢ ´x
@ùÈ@¹ 1ã T@¹ 1 Th@ù(ø6
È ¹@¹ 1BÿÿT ¹h@ùÈ ø7 ñh ùa Tàª3 ( RóªéC)! ê °J©Fùö+©õ3 ù!M(Ë 2àª&eÿà ù ´È@ùÈ ø7 ñÈ ùa Tàª3 ¨@ùÈ ø7 ñ¨ ùa Tàªz3 ö@ù֚ ´h@ùÈ ø7 ñh ùa Tàªq3 è °Aù(@ùI@ù ´àª ?Öó ª ´õÒDùà@ù¢@ùáªN3 ` ´ú ª @¹ 1B TH ¹÷ @ùè °ÝAùH@ùI@ùè ´àª ?Öõ ªà ´H@ùÈ ø7 ñH ùa TàªL3 h@ùÉ )U@ù ëa Tv@ùú@ùV ´w
@ùÈ@¹ 1ã Tè@¹ 1 Th@ù(ø6
È ¹è@¹ 1BÿÿTè ¹h@ùÈ ø7 ñh ùa Tàª.3 ( Róª÷ @ùéC)! öW©!M(Ë àªÀdÿü ª ´È@ùÈ ø7 ñÈ ùa Tàª3 ¨@ùÈ ø7 ñ¨ ùa Tàª3 ö@ù\ ´h@ùÈ ø7 ñh ùa Tઠ3 (@ùÈ ø7 ñ( ùa Tàª3 è@¹ 1B Tè ¹è@ùÉ )U@ù ë` T R ÒóªéC)! õs©!M(Ë àªdÿö ª ´¨@ùÈ ø7 ñ¨ ùa Tàªè2 v ´h@ùÈ ø7 ñh ùa Tàªà2 È@ùÉ )]@ù ëA TÈ
@ù
ñaÎ TÈb ʂ ɢ X@ù@ù9@ùh@¹ 1ó@ùC T@¹ 1c T(@¹ 1 TÈ@ù¨ø6 h ¹@¹ 1âþÿT ¹(@¹ 1ÂþÿT( ¹È@ùÈ ø7 ñÈ ùa Tવ2 è °Bùàªb RÕÿø7÷ °õ °À 4è °YFùàªb RÕÿ ø7 4è °Dùàªb RÕÿ`Ãø7Àà 5àöCù1Kÿ@ ´ö ªè °í@ù@ùI@ù ´àª ?Öú ªô'@ù ´È@ùÈ ø7 ñÈ ùa Tàª2 àöCù Kÿ ´õ ªè °ÙAù@ùI@ùö@ùȑ ´ ?Öó ª ´¨@ùÈ ø7 ñ¨ ùa Tàªu2 è °@ù(@ùI@ùȑ ´ôªàª ?Öù ª ´àªáªÃ1 ´õ ª(@ùÈ ø7 ñ( ùa Tàª_2 h@ùÉ )U@ù ë T R ÒéC)! ùW©ô3 ù!M(Ë 2àªìcÿö ªàª1Eÿ¨@ùÈ ø7 ñ¨ ùa TàªF2 ö ´h@ùÈ ø7 ñh ùa Tàª>2 @ Rî1 ó ªùªà ´v ù@¹ 1B T ¹| ùú0 ô@ù` ´ö ªè °Eùâªù0 ø7è °Aùàªâªó0 õ'@ù ø7àªáªâªø^ÿ@Á ´ô ªH@ùÈ ø7 ñH ùa Tàª2 h@ùÈ ø7 ñh ùa Tàª2 È@ùú@ùÈ ø7 ñÈ ùa Tàª2 È u@ùë $ TÈ m@ùë # TÈ q@ùë # Tàª1 @¿ø7@# 4õ ° àªó1
ñ@ÿTè ° ¥Gùè °=Gù ÒÄ^ÿJ ´ó ªö^ÿh@ù÷ @ùÈ ø7 ñh ùa Tàªà1 ÿ# ù Ò Ò Ò Òÿ ù!RR¸ ÒàöCùiJÿ ´ö ªô ù¡ÚAù@ùI@ùH ´àª ?Öó ªô'@ù@ ´È@ùÈ ø7 ñÈ ùa TàªÁ1 àöCùTJÿú ª ´è °EùH@ùI@ùö_C©àªȃ ´ ?Öõ ª ´H@ùÈ ø7 ñH ùa Tબ1 ôª¨@ùÉ )U@ù ëà T Ò Rú@ùéC)! ùc©!M(Ë àª8cÿö ªàª}Dÿւ ´¨@ùÈ ø7 ñ¨ ùa Tàª1 è °QGùàªøÿ@ ´ù ªÈ@ùÈ ø7 ñÈ ùa Tàª1 àªáªÜ0 ´õ ª(@ùÈ ø7 ñ( ùa Tàªx1 h@ùÉ )U@ù ëà T R ÒéC)! ê@ùö+©õ3 ù!M(Ë 2àªcÿù ªàªIDÿ¨@ùÈ ø7 ñ¨ ùa Tàª^1 ¹ ´h@ùõ@ùÈ ø7 ñh ùa TàªU1 ¨@ùÈ ø7 ñ¨ ùa TàªN1 àªá'@ù0 ´ö ª(@ùÈ ø7 ñ( ùa TàªB1 à#@ùe0 @ ´ó ªè °QEùÈ@ùM@ùùªàªâªè ´ ?Öàø7h@ù ø7 ñh ù TÈ@¹ 1ô@ùã Tóªè@ùȂø6 ÿ ùÿ ùbRɋRàªõ'@ù ÿ ùÿ ùbR¡ɋRàªÈ@ùø7 ñÈ ù! T÷ ªàªôªöª1 àªâªáªûª÷ªôªõªôªóªû ªøªö_C© ´h@ùHø7 ñh ùá Tàªóªùªû0 âªáªõ' ùó@ùÚ ´H@ùø7 ñH ù! Tàªùªóªõªì0 âªáªóªù ªú@ùóx ´h@ùxø7º È u@ùëà Ýÿ5è °YFùà@ùB RÄÓÿ ø7à 4è ° ]FùiIÿ ´ó ªè °UFù@ùI@ù¨ ´àª ?Öö ª ´h@ùÈ ø7 ñh ùa TàªÂ0 è °IGùઠҖ]ÿó ªà ´È@ùÈ ø7 ñÈ ùa T઴0 h@ùõ °Ûÿ7 ñh ù!ÛÿTબ0 Öþÿ઩0 È@¹ 1ô@ùbïÿTÈ ¹óªè@ùèqø6õ'@ù ÿÿ©ÿ©ÿ ù Ò Ò Ò ÿÿ©ÿ©ÿ ù Ò Ò Ò Ò Òÿ ùAyR" Rôª$ ÿÿ© Òÿÿ© Ò Òÿÿ©" R¡yRhÿÿg/ µàªZÿø ªàNÿµ Òÿ# ùÿ ù Һ àªë/ ó ªàNÿµÿ©ÿ# ùÿ ù Ò Ò Ò Ò Ò Òÿ ù¡{R Rôªþ v@ù ´t
@ùÈ@¹ 1c T@¹ 1 Th@ù¨ø6± ÿ©ÿ# ù Ò Ò Ò Òÿ ùA~R R÷ @ùKÿÿ3/ µàª\Zÿó ª Qÿµ Òÿ# ùÿ ù Ò Ò Ò ÒR¶ RY લ/ ø ª@Pÿµÿ©ÿ# ù Ò Òõª Ò Òÿ ùAR¢ R÷ @ù+ÿÿ@ùó ´ @ùh@¹ 1c T¨@¹ 1 T@ù¨ø6 ÿ©ÿ# ùÿ ù Ò Ò Ò Ò Òÿ ùႋR¢ R¯ àª/ ö ª Zÿµÿ# ù Ò Ò Òÿ ù¡R¢
R÷ @ùê ÿë© Ò Òÿÿ© Ò Ò Òÿ# ù¢
RᏋRh è ° ¥Gùè °9Gù ÒÑ\ÿ ´ó ª]ÿh@ù÷ @ùÈ ø7 ñh ùa Tàªí/ ÿ# ù Ò Ò Ò Òÿ ùᑋRÂ
RÅ àªX/ ö ª Vÿµÿ# ù Ò Ò Òÿ ù!RW ÿë© Ò Òÿÿ© Ò Ò Òÿ# ùâ
RaR8
@ùÉ )A@ù @ùè ù¡ Ð!p £. ÿ# ù ҽ àªd/ à# ù`mÿµÿ ù Ò Òÿÿ© Ò Òÿ# ùRa¡R È ¹@¹ 1ÂêÿT ¹h@ùÈ ø7 ñh ùa T઩/ ( Róª¸ùÿh ¹¨@¹ 1ÂïÿT¨ ¹@ùÈ ø7 ñ ùa Tàª/ ( Røªíùÿÿ# ù Ò Ò Ò Òÿ ù¡RR÷ @ùn àª/ ö ª@Nÿµÿ# ù Ò Ò Òÿ ùaRâ
R÷ @ùa ÿ ù Ò Òÿÿ© Òÿ# ùâ
R¡Rá àªë. ö ª`Nÿµÿ# ùÿÿ© Ò Ò Ò Ò Òÿ ùR ÿ# ùÿÿ© Ò Ò Òÿ ùAR ÿ# ùÿÿ© Ò Ò Òÿ ù¡Râ
R àªÌ. ö ª Sÿµÿ# ù Ò Ò Òÿ ùaR"R÷ @ù, ÿ ù Òÿÿ© Ò Òÿ# ù"R¡R¬ શ. ö ª Sÿµÿ# ù Ò Òõª Òÿ ù Òÿ ùR"R ÿ ù Òÿÿ© Òÿ# ù"RAR ÿ# ùÿÿ© Ò Ò Òÿ ù¡R"Ry è ¥Gùè AGù Òõ[ÿ@n ´ó ª'\ÿh@ù÷ @ùÈ ø7 ñh ùa Tàª/ ÿ# ù Ò Ò Ò Òÿ ùឋRBRé ÿ# ù Ò Ò Òÿ ù!¡RR÷ @ùà àªs. ø ªÀVÿµ Ò Ò Òÿ ù£R"R÷ @ùÔ ÿÿ© Ò Ò Ò Òÿ ùA£R"R) _. ó ªàZÿµ Ò Ò Ò Òÿ ùᤋRBR÷ @ù¿ Ò Rêúÿ Ò Òõª Òÿ ù Òÿ ùa§R8 RßúÿàªD. ó ª _ÿµÿÿ© Ò Ò Ò Ò Ò Òÿ ùRBRüª ÒX àª3. ø ª`_ÿµ Ò Òõª Òÿ ù Òÿ ùA¨R ÿÿ© Ò Ò Ò Òÿ ù¨RBRüª Òûª? R Òûÿ Ò Òõª Òÿ ù Òÿ ùA«RBRüª÷ @ùýÿ Rûÿઠ. ó ª@eÿµ Ò Ò Òÿ ùRbR÷ @ùú@ùi m- à\ µàªXÿú ª÷ @ùÀdÿµ Ò Òõª Òÿ ùÿ ùAR àªí- õ ª`dÿµ Ò Òõª Òÿ ùÿ ùR
Ò Rú@ù?ûÿ Ò Òõª Òÿ ù Òÿ ùA°RbRüª[ýÿ Òÿ# ù Ò Ò Ò Òÿ ùኋR"
R÷ @ù4 R'ûÿõ@ùUW ´ó
@ù¨@¹ 1#7 Th@¹ 1C7 Tè@ùh7ø6¿ Ò Òõª Òÿ ù Òÿ ùa´RRö@ù7ýÿ ë9 Tવ- @T ´õ ªÈ@ùÈ ø7 ñÈ ùa Tàª-. ¨@ùq@ùàª`?Öû ªÀS ´àª`?Öø ª T ´àª`?Ö@T ´ù ªàª`?Öa RÑÿ`Aø7¨@ùHBø7öª ñ¨ ùó@ùákÿT\ûÿ ÒS½RÖR* ғ¾RöR% ғËRvR! àªz- ú ªô'@ù@nÿµÿ ù Òÿ ùbRÁËRY ôª Òÿ ùbR!ċRö_C©H@ù ÿ6
ýÿg- ó ªnÿµÿ ù Òÿ ùaċRbRàª÷ªãªøªùª Ò| ôªàªV- ù ªnÿµÿ ùÿ ùÁċRbRõ'@ù÷ @ùÔüÿÿ ù Òÿ ùŋRbRàª÷ªãªøªûªùªc y@ùyM ´v
@ù(@¹ 1c0 TÈ@¹ 10 Th@ù¨0ø6 ÿ ùÿ ùÁNjR
ÿ ùÿ ùbRAȋRüÿôªÿ ùÿ ùAɋRbRõ'@ù óRRÇ àª - ó ªô'@ù |ÿµÿ ù ҂R!Ràªõªüÿõªôªÿ ùRRö_C©üÿ- õ ª|ÿµõªôªÿ ùÁRRüÿ¹@ùú@ù9F ´¶
@ù(@¹ 1Ã* TÈ@¹ 1ã* T¨@ù+ø6\ ÿ ùaڋRRàª÷ªãªøª ÿ ù ҂RáڋRàªõ'@ùùªYüÿ Òÿ ùAۋRRàª÷ªãªøªûª Òô'@ù@ùø7úª ñ ù¡ Tù ªàªóªõªøª\- ãªàªâªáª úªù ªóªèªøªüªùªõªÿµCüÿv@ù6> ´w
@ùÈ@¹ 1c$ Tè@¹ 1$ Th@ù¨$ø6) Òÿ ùދRRõ'@ùö@ù7üÿÓߋR¶Rù ù ö ùSáRÖRùªô@ùL À, `ÿ6áRÂRh@ùHø7 ñh ùá Tàªóªõª#- âªáªù ª ° 8c c ËEÿ Òüªõ'@ùùªô@ù7 ´è@ùhÿ7 ñè ùõ'@ùa Tàª
- ´H@ùÈ ø7 ñH ùa Tàª- à#@ùà ´ @ù¨ ø7 ñ ùA Tý, ´È@ùÈ ø7 ñÈ ùa Tàªõ, ´h@ùÈ ø7 ñh ùa Tàªí, ´@ùÈ ø7 ñ ùa Tàªå, ´(@ùÈ ø7 ñ( ùa TàªÝ, ´@ùÈ ø7 ñ ùa TàªÕ, ´¨@ùÈ ø7 ñ¨ ùa TàªÍ, ´@ùÈ ø7 ñ ùa Tà ªÅ, ¨Zø© ð)y@ù)@ù?ë Tàªý{L©ôOK©öWJ©ø_I©úgH©üoG©ÿCÀ_Öÿ# ùÿÿ© Ò Ò Ò Ò Òÿ ùRâ
RWÿÿÿ# ùÿÿ© Ò Ò Ò Ò Òÿ ùR"RLÿÿÿ ù Ò Òÿÿ© Ò Ò Ò"R¡£Rüª Òõªyûÿ¨ ¹h@¹ 1ÉÿTh ¹è@ùÈ ø7 ñè ùa Tàª, ( Rùÿ ÒS¿RöR è ¥Gùè EGù ÒTYÿ@$ ´õ ªYÿ¨@ùHø7 ÒSKRR ñ¨ ùá
Tàªn, l È
@ù
ñ¡ TÈ@ù
! A ùÿ ñ+ T¨ ðE@ù @ùh Rè ù¡ °!Ì Èø·© ð)E@ù @ù© °)© j J ñIè' ©¡ °!p++ ÿ ù Ò Òÿ ù Ò Ò ҂R¡µRõª)ûÿ( ¹È@¹ 1ÂÏÿTÈ ¹h@ùÈ ø7 ñh ùa Tàª7, ( RóªÝùÿ( ¹È@¹ 1bÕÿTÈ ¹¨@ùÈ ø7 ñ¨ ùa Tàª(, ( RõªúÿÈ ¹è@¹ 1ÂÛÿTè ¹h@ùÈ ø7 ñh ùa Tàª, ( Róª÷ @ù¥úÿÿ ùÿ ùbRÁɋRõúÿõ ù Ò Ò Òÿ ù Ò!ºRR þÿó@ùQùÿ ÒSKRR÷ @ùú@ù ³ˋRR ͋R¶R è ¥Gùè MGù ÒÌXÿ ´õ ªþXÿ¨@ùø7SӋR6R ñ¨ ùýÿTyÿÿSRÖR÷ @ù ° 8c c áªâªDÿ Òö@ùè@ùÙÿ69ûÿàªM+ ö ª aÿµô ùôªRÂRö_C©h@ù¨Ôÿ6þÿô ùÿ ù ÒÂRáϋR¬úÿSӋR6RÃÿÿÆ+ Òÿ# ùÿ ù Ò Ò Ò Òs{R Rõ' ùÓÿÿ RÈõÿ R
öÿÿ# ù Ò Ò Ò Òÿ ùaRÂ
R÷ @ùþÿÿ# ù Ò Ò Ò Òÿ ùaRBR÷ @ùþÿ Ò Òõª Òÿ ù Òÿ ùARbRýüÿ Røÿÿ ù Ò Òÿ ù Ò ҂RḋRõªpúÿàª Ò ҳ sª
àªS ðs®5 R ળ sª U R @ù¨ ø7 ñ ùA Tu+ !Ïÿ 5¨ ÐE@ù @ùõO ©¡ !pI* Ò Ò Òÿ ù Ò Òÿ ù ҂R!»Rô'@ù8¿ÿµUúÿ Rùÿ R¹ùÿ RCÿÿ ÒÓ RTÿÿÓҋR6RRÿÿÿCÑüo ©úg ©ø_
©öW©ôO©ý{©ýöªù ª¨ Ðy@ù@ù¨ø¿øÿÿ©ÿÿ©ÿÿ©àªÙ* ±À Tú ªÈ@ùØ Ð WGù¼ Мs@ù ë T @ù+ ´j @ù_ ñ« Tka l@ù ë Tk! J ñaÿÿTE Ò ÒÓȌR´=Rb ꪪ ´J@ù_ ë¡ÿÿT ª ÐJ@ù?
ëÁ TÉ ð! BùI@ù( ´àª ?Öõ ª ø ´È ðmFù¨@ùI@ù( ´àª ?Öô ªàC ù ´¨@ùÈ ø7 ñ¨ ùa Tàªÿ* ¨ Ðu@ù¿øë© Ð)m@ùIú\ú Tëó àªy* ó ªø7@ùÈ ø7 ñ ùa Tàªè* ÿC ùӑ 4È@ù WGù ëÀ TÈ@ù WGù 뀞 T @ùk ´j @ù_ ñ Tka l@ù ë` Tk! J ñaÿÿTÕ е"9´fAù @ù@ù᪶* ´ó ª @¹ 1B Th ¹ó; ùàªáªF* 1` Tô ªh@ù ø7 ñh ù` Tÿ; ùô2 5³:Gù @ùb@ùáª* ´ô ª @¹ 1B T ¹ô; ùÈ ðUFù@ùI@ùè´àª ?Ö÷ ªàC ùà´@ùÈ ø7 ñ ùa Tàª* ` RJ* à; ù ´ø ªÉ ð(yFù
@¹J 1b T
¹(yFù ùÀ@ùÈ ðCù@ùI@ùÈ´ ?Öô ªà? ùÀ´@ù© Ð)a@ù ëÁT@¹ 1B T ¹´øõª@ùÈ ø7 ñ ùa Tàªq* ÿ? ù¨"@¹¨07Séý¿êÿR qIê R qSu È ð©Cù(I@ù( ´àª ?Öô ªàC ù ´È ð¡Fùëà T@ù© Ð)Q@ù ëî T
@ù© ! ñá T@¹ qó 3 R R@ùÈ ø7 ñ ùa Tàª@* ÿC ù³ëÿ4È ðuEùÈ@ùI@ù(í ´àª ?Öô ªàC ù í ´¨ Ðu@ùëÀ T© Ð)m@ù ë@ T ë Tર) ó ªàýø7@ùÈ ø6
ëó@ùÈ ø7 ñ ùa Tàª* ÿC ùóæÿ4ß ë`? TWGù¨
´É@ù?ëà> T+@ùë´j @ù_ ñ Tka l@ùë Tk! J ñaÿÿT)
@ù
@ùª ÐJA@ù@@ùé# ©¡ !Ø Ù( Ò ҳӌR?R6 àªõ) ÿ; ùt 5<ÿÿóR¨
@ù ùÊ ðI Dù+@¹k 1ù' ùb T+ ¹I Dù Y ùᪿ) v ´ù ª RI RB@q(1q%h Q q3èª @¹÷+ ùi (75 @ù *£ +ã ?ru÷ª ð<%Ț@ùT@ù ´ëdq TI @¹(SI(7A @ù k Tàª Ò Ò䪸)
J Kà ?ra k¡þÿT"ӚàªÞ) @ùZ@ùz ´Ë ë n TI @¹(SI(7A @ù k Tàªáª Òäª) J Kà ?ra k¡þÿT"Ӛ B#ӚÂ) T@ùD@ùúªä ´Ë ëKj TI @¹(S©(7A @ù kúª Tàªáª Ò) ¹ø@ùø6 J Kà ?ra kúªAþÿT"Ӛ Ӛ ) ¹ø@ùÈ ø7 ñ ùa Tàªk) @ R) à; ù¼ Мs@ù÷+@ù`ä ´ô ª ùÈ ð½Gù @¹) 1B T ¹ ù"( øù'@ù`ã ´õ ªÈ ð!,@ù Aù ( `Eø7è@ùA@ùSö ´ ð Ø!/) @÷ 5àªáªâª`?Öø ª+) 8ö ´ø? ùè@ùÈ ø7 ñè ùa Tàª:) ÿC ù@ùÈ ø7 ñ ùa Tàª2) ÿ; ù¨@ùÈ ø7 ñ¨ ùa Tàª*) ¿ø@ùÈ ø7 ñ ùa Tàª") ÿ? ù3w@ùÈ ðýAùt@ùàªáª) ÷ ª a ´è@ù@ù ´àªáªâª ?Ö÷ ªÀ µ è@¹ 1B Tè ¹3w@ùÈ ðñAùu@ùàªáªý( _ ´ô ª@ù @ùé ´àªáªâª ?֠ø _ ´ô ª@ù© Ð)U@ù ë T@ùõ; ùU_ ´
@ù¨@¹ 1 Th@¹ 1# T³ø@ùHø6 ¨ ¹h@¹ 1"ÿÿTh ¹³ø@ùÈ ø7 ñ ùa Tàª×( " Rôª¨ÃÑ! µ9©
ËàªkZÿø ªà? ù ´¨@ùÈ ø7 ñ¨ ùa TàªÅ( ÿ; ù¸X ´@ùÈ ø7 ñ ùa T઼( ¿ø@ùÈ ø7 ñ ùa T઴( ª( à# ù4@ù@ù ñ\ú T@ùhÿÿµ Ò Ò Òÿ©à©S Ñ ñj T? ø3 ù@¹ 1B T ¹@ùû7 ùh@¹ 1B Th ¹àª' à©S Ñ ñË Tèªùª à ªáª; ú ªàªáª R RPÌÿô ª`3 ´àªáª R RIÌÿõ ªà2 ´àªáªâª2 2ø7@ùÈ ø7 ñ ùa Tàªp( àªáªâª& @1ø7¨@ù ø7 ñ¨ ù`) T: ñ!* Tÿ? ù¿ø ´h@ùÈ ø7 ñh ùa TàªZ( ÿ7 ù ´@ùÈ ø7 ñ ùa TàªQ( ÿ3 ù¼ Мs@ùà+@ùà ´ @ù¨ ø7 ñ ùA TF( ÿ/ ùW ´È ðåFùઠÒUÿó ªà/ ùè@ùÈ ø7 ñè ùa Tàª6( ó ´h@ùÈ ø7 ñh ùa Tàª.( Òÿ/ ù@¹ 1 Ta @¹) 1B T ¹´ø© Ð)U@ù ëÀåÿT Ò ÒHÿÿÈ@ùÉ
@ùé+ ùÉ ð!ÙEùI@ùÝ ´àª ?Öô ªàC ùÝ ´àª Ò R RÖËÿ ø@ ´ó ª@ùÈ ø7 ñ ùa Tàª( ÿC ùàªÙÍÿà# ù ±a Tà& `× µh@ùÈ ø7 ñh ùa Tàªò' × ðáâAùÈ@ùI@ùh¿ ´àª ?Öô ª ø`¿ ´È ðÉBù@ùI@ùh¿ ´àª ?Öõ ªàC ù`¿ ´ù' ù@ùÈ ø7 ñ ùa TàªÖ' ¿øમÍÿù ª ±a Tµ& Ò µ¨@ùÈ ø7 ñ¨ ùa TàªÇ' Õ е"9³ÒDù @ùb@ù᪫' ¼ ´ô ª @¹ 1B T ¹ôC ùú ùÈ ÐåAù@ùI@ùè» ´àª ?Öú ª øà» ´@ùÈ ø7 ñ ùa Tધ' àªÖ& àC ù » ´ó ª RR' à? ù » ´ü ª ùc& àC ù » ´û ª³ÒDù @ùb@ùáª~' ຠ´ö ª @¹ 1B TÈ ¹È Ð¥BùÈ@ùI@ùº ´àª ?Öó ªà; ùº ´È@ùÈ ø7 ñÈ ùa Tàª|' áâAùàªâªF& à
ø7h@ùÈ ø7 ñh ùa Tàªp' H@ùA@ù¾ ´ Ð Ø!O' `¿ 5àªá ªâª`?Ö÷ ªK' W¾ ´÷; ùH@ùÈ ø7 ñH ùa TàªZ' ¿ø@ùÈ ø7 ñ ùa Tà ªR' ÿ? ùh@ùÈ ø7 ñh ùa TàªJ' ÿC ùÿ; ù¼ °s@ùÿ ë È TWGù¨¿ ´é@ù?ë`Ç T+@ùëÅ ´j @ù_ ñ Tka l@ùë@Æ Tk! J ñaÿÿT)
@ù
@ùª °JA@ù@@ùé# © ð!Ø & ÒsR@Re Ò Òó.RER` Ò ÒSیRô?R[ àª' : ñ¡ T´þÿZ Ñ_ ñ-ÖÿTà ªáªÁ ó ªàªáª R RÖÊÿô ª ´àªáª R RÏÊÿõ ª ´àªáªâª¸ @ø7@ùÈ ø7 ñ ùa Tàªö& àªáªâª¬ ø7¨@ù(ûÿ7 ñ¨ ùÁúÿTàªê& Óÿÿ Òö:R 6;R v;R Ҷ;R¼ °s@ù ÒÀ9ÿÿ; ùઽ9ÿ¿øàC@ùº9ÿÿC ùષ9ÿÿ? ù ð 0:C Ðc áª"FR{?ÿ¡ãÑâããÃà#@ùÌÿ ø7¶XøôWG©õÓ ©ö ù` Rt& àC ùà ´ó ªàªáª ґSÿú ªè@ùÈ ø7 ñè ùa Tર& h@ùÈ ø7 ñh ùa T઩& ÿC ùÞ ´¨ °u@ù_ë T© °)m@ù_ ë T_ ëà Tàª#& ó ª ³>R! _ëóH@ùÈ ø7 ñH ùa Tàª& Óø7óÚ 4àªn9ÿ¿øàªk9ÿÿ? ùàªh9ÿÿ; ùè#@ù 5@ùáªâªã+@ù3Ìÿ ҈@¹ 1] T± S@Rè#@ù 5@ùáªâªã+@ù'Ìÿ Ò ÒÔER¬ àªá% õ ª ø kÿµ Ò Ò4>RÓʌRª àª×% ô ªàC ù kÿµ Ò ÒˌR4>R È Ð ¥GùÈ Ð]Gù Ò,SÿàC ùÀÖ ´ó ª]Sÿh@ùÈ ø7 ñh ùa TàªH& Ò ÒÿC ù³͌RT>R êªJ
´J@ù_ ë¡ÿÿTR ¨ °1@ù @ù ð!Ð:"% (@ùÈ ø7 ñ( ùa Tàª/& Ò ҿøôDRS+Rp àª% ô ªàC ù yÿµ Ò ҳЌR>R^ % àÐ µàª-Pÿó ªà; ù jÿµ Ò ҂ Ò Òs%RDRO ¨ °@ù @ùáªô$ Ò3RÔERF ¨ °@ù @ùáªë$ ¿øS3R Ó5Rè@ùñÿ7 ñè ù!ñÿTàª÷% ÿÿ Ò ýÿ Ò ÒsˌR4>R. ª °J@ù?
ëAcÿTÉ Ð!uEùI@ù(] ´àª ?Öô ªà? ù ] ´È ÐFùë T@ù© °)Q@ù ëa] T@¹ 3 R@ù ø7 ñ ùà T3 4@¹ 1bH T ¹A àªÈ% 3ÿÿ5È Ð©CùÈ@ùI@ù(` ´àª ?Öô ªà? ù ` ´È СFùëà T@ù© °)Q@ù ëáp T
@ù© ! ñá T@¹ qó 3 R R@ùÈ ø7 ñ ùa Tડ% ÿ? ù 4È ÐáAùÈ@ùI@ùo ´àª ?Öõ ªà? ùo ´È ÐFù¨@ùI@ùo ´àª ?Öô ªàC ùo ´¨@ùÈ ø7 ñ¨ ùa Tàª% Ø °#9ÓDù @ùb@ùáªh% @n ´õ ª @¹ 1B T¨ ¹õ? ùÈ ÐDù¨@ùI@ù(n ´àª ?Ö÷ ªà; ù n ´¨@ùÈ ø7 ñ¨ ùa Tàªe% ÿ? ù@ùÈ ø7 ñ ùa Tàª]% ÿC ùè@ùÈ ø7 ñè ùa TàªU% ë
T;Gù @ùb@ùáª9% ~ ´õ ª @¹ 1B T¨ ¹õ; ùÈ ÐUFù¨@ùI@ùè} ´àª ?Öô ªàC ùà} ´¨@ùÈ ø7 ñ¨ ùa Tàª6% ý# à; ù@} ´õ ªÈ Ð!,@ù Aùû# à,ø7È ÐaGù@ùA@ù ´ Ð Ø! % à 5àªáªâªà?Ö÷ ª% ׀ ´÷? ù@ùÈ ø7 ñ ùa Tàª% ÿC ù¨@ùÈ ø7 ñ¨ ùa Tઠ% è@ùÈ ø7 ñè ùa Tàª% ÿ? ùÈ °!9ÑDù @ùb@ùáªè$ H ´ô ª @¹ 1B T ¹ô; ùÈ ÐéAù@ùI@ù¨H ´àª ?Öø ªàC ù H ´@ùÈ ø7 ñ ùa Tàªå$ È ÐeGùÈ@ù¥F©= ´)@ùI= ´àª ?Öô ªà; ùÀF ´ûª@ùº °ZW@ù ëF T Ò R©ÃÑ)! µS9©!M(Ë àªfVÿ÷ ªà? ù ´¨@ùÈ ø7 ñ¨ ùa TàªÀ$ ¿ø@ùÈ ø7 ñ ùa Tસ$ ÿ; ù·D ´@ùÈ ø7 ñ ùa Tય$ ÿÿ©3w@ùÈ ÐýAùt@ùàªáª¡$ C ´ø ª@ù@ù ´àªáªâª ?Öø ªÀ µ @¹ 1B T ¹üª3w@ùÈ ÐñAùu@ùàªáª$ @A ´ô ª@ù @ù ´àªáªâª ?ÖàC ùÀ@ ´ô ª@ù ë! T@ùõ; ùUA ´
@ù¨@¹ 1 Th@¹ 1# TóC ù@ùHø6 ¨ ¹h@¹ 1"ÿÿTh ¹óC ù@ùÈ ø7 ñ ùa Tàªe$ " Rôª¨ÃÑ! µ9©
ËàªùUÿù ªà? ù ´¨@ùÈ ø7 ñ¨ ùa TàªS$ ÿ; ù¹: ´@ùÈ ø7 ñ ùa TàªJ$ ÿC ù(@ùÈ ø7 ñ( ùa TàªB$ 8$ ù ª 4@ùácâã£SÉÿu ѿ ñK T » °{k@ù àªáªâªê ø7µ ѿ ñÍ TàªáªÙ ¿ ë ÿÿTü ªàªá ª R RìÇÿô ª ´àªáªâª²# `ø7@ùÈ ø7 ñ ùa Tàª$ àªáª R RÙÇÿô ª ´àªá ªâªÂ Àø7@ùHúÿ7 ñ ùáùÿTઠ$ Ìÿÿÿ? ùà/@ùà6ÿÿ/ ùà3@ùÝ6ÿÿ3 ùà7@ùÚ6ÿÿ7 ù ´È ÐåFùઠÒÈPÿó ªà7 ù@ù¼ °s@ùÈ ø7 ñ ùa Tàªä# G ´h@ùÈ ø7 ñh ùa TàªÜ# ÿ7 ù@¹ 1â T @¹) 1B T ¹ôC ù ë êÿT Ò Òkÿÿ¼ °s@ù@¹ 1â T ¹5 Ò ÒÓ RôBR Xøà ´ @ù¨ ø7 ñ ùA Tº# àC@ùà ´ @ù¨ ø7 ñ ùA T²# à?@ùà ´ @ù¨ ø7 ñ ùA Tª# ´È@ùÈ ø7 ñÈ ùa Tઢ# à;@ùà ´ @ù¨ ø7 ñ ùA T# Ð 0:C °c áªâªC<ÿ Ò ´è@ùÈ ø7 ñè ùa Tàª# ¨Zø© )y@ù)@ù?ë{ Tà ªý{P©ôOO©öWN©ø_M©úgL©üoK©ÿCÀ_Ö5RöCR
uRöCR
µRDR õRDR Ò5R6DR¼ s@ù ÒL6ÿÿ; ù XøI6ÿ¿ø ÒF6ÿÿC ùàªC6ÿÿ? ù Ð 0:C °c áªâª<ÿáãâãÃàªÈÿ ø7ö×G©ô;@ùõÓ ©ö ù` R # ø s ´ó ªàªáª Ò Pÿú ª@ùÈ ø7 ñ ùa Tàª<# h@ùÈ ø7 ñh ùa Tàª5# ¿ø:q ´¨ u@ù_ë T© )m@ù_ ë T_ ëà Tય" ó ª 3R _ëóH@ùÈ ø7 ñH ùa Tàª# sø73n 4àªú5ÿÿ? ùàª÷5ÿÿC ùàªô5ÿÿ; ùáE©ã7@ù 7@ùÁÈÿ@¹ 1âîÿT@ÿÿÓ RáE©ã7@ù 7@ù¸Èÿ ÒTCR>ÿÿàªs" ô ªà? ù £ÿµ Ò ҳöRTAR4ÿÿÈj ´
@ùj ´àª+êÿþÿ© )I@ù ë TàªB Rv" øéÿó ª ¢ÿ6 Ò ÒóöRTAR ÿÿ© )I@ù ë' TàªB Rg" ééÿó ª ÿ6 Ò ÒóЌR>RÿÿàªE" ô ªàC ù ÿµ Ò ÒÓьR>Rÿÿ Ò ғDRÔERÿÿàª6" ô ªà? ù ÿµ Ò ÒÓúRÔAR÷þÿ! Àd µàªÆLÿô ªà; ù·ÿµ Ò ҳR àª!" ø ªàC ù ·ÿµ Ò ÒóR Ò ÒSR @ùµø¹ÿ´ @ù¨@¹ 1" Th@¹ 1#" TóC ù@ùH"ø6 ÒóR4CRÍþÿ¨ @ù @ùáªr! ÒÓ RTCRÄþÿ¨ @ù @ùáªi! ÿC ù
R R@ù(ïÿ7 ñ ùÁîÿTàªu" sÿÿ ÒþÿW! \ µàªLÿô ªà; ù øþµ Ò Òà àªÜ! ÷ ªàC ù`øþµ Ò3'RÔDRþÿ Ò ғ(RôDRþÿÏ! ô ªà? ùúþµ Ò ғ)RôDRþÿ© )Q@ù ëY T(-@ùઠ?Öõ ª ø úþµ Ò ÒôDRÓ)Rþÿ Ò ҳ,RÔDR|þÿ Ò ҔER³.Rþÿ Ò ÒҌR>Rrþÿ
@ýáb a óZüÿ© )I@ù ë TàªB Rµ! 7éÿó ª ÿ6 Ò ÒûRÔAR^þÿàª! õ ªà? ùÿµ Ò ÒóûRÔARTþÿàª! ô ªàC ùÿµ Ò Ò3üRÔARJþÿð R µàªLÿõ ªà? ùàÿµ Ò ҋ àªu! ÷ ªà; ù ÿµ ÒÓüRÔAR7þÿ Ò Ò4?R3ՌR:þÿàªg! ô ª øà@ÿµ Ò ÒT?RóR0þÿàª]! õ ªàC ùà@ÿµ Ò Ò3RT?R þÿÄ @M µàªíKÿô ªàC ù Dÿµ Ò Òe àªI! ú ª ø`Dÿµ Ò Òô?R3ٌRþÿ Ò ғٌRô?Rþÿ Ò ÒÓٌRô?R þÿ Ò ÒsڌRô?Rûýÿ¡ I µàªÊKÿö ª@EÿµI àª)! ó ªà; ùÀEÿµ ÒóڌRô?Rëýÿ Ò!RTCRçýÿ¨ =@ù @ù Ð! ¦÷ÿ
@ý( Rb a Q÷ÿàªáªâªÿ ø ªà? ù
ÿµ Ò Ò w E ´ Ò Òÿ? ù0RÔDRÉýÿ¨ ¹h@¹ 1"ÞÿTh ¹óC ù@ùÈ ø7 ñ ùa Tàª}! ( Røªªüÿàªá ªâªÝ ÷ ªà; ù`Bÿµ Ò V ÀA ´ Ò Òÿ; ùیRô?R¨ýÿê ªj ´J@ù_ë¡ÿÿT3
@ý( Rb a ²ûÿC A µàªlKÿõ ªà; ù ÿµ Ò Ò àªÈ ô ªàC ù`ÿµ Ò Ò3ÿRôARýÿ Ò ғ Rýÿ¨ =@ù @ù Ð! , úÿ Ò ғՌR4?Ryýÿ Ò ғRT?Rtýÿª J@ù
ë¡åþTè ªÉ
@ùé+ ùÉ °!ÙEùI@ùÈ"ÿµàª ô ªàC ùÀ"ÿµ Ò ÒóԌR4?R_ýÿàªáªâª ÷ ªà? ùàÿµ Ò ü 9 ´ Ò Òÿ? ùóRôARNýÿê ªª ´J@ù_ë¡ÿÿT ª J@ù
ëa:ÿTú
@ùè'@ùu@ùÈ °ýAùt@ùàªáªö À! ´ø ª@ù@ù ´àªáªâª ?Öø ªÀ µ @¹ 1B T ¹è'@ùu@ùÈ °ñAùu@ùàªáªÞ à ´ô ª@ù @ùI ´àªáªâª ?ÖàC ù` ´ô ª@ù @¹) 1B T ¹ôC ù© )U@ù ë! T@ùõ? ù ´
@ù¨@¹ 1 Th@¹ 1# TóC ù@ùHø6 ¨ ¹h@¹ 1"ÿÿTh ¹óC ù@ùÈ ø7 ñ ùa Tલ " Rôª¨ÃÑ! µ9©
ËàªFRÿû ªà; ù ´¨@ùÈ ø7 ñ¨ ùa Tઠÿ? ù» ´@ùÈ ø7 ñ ùa TઠÿC ùh@ùÈ ø7 ñh ùa Tઠÿ; ù 4@ùø ù@ù ñd\ú T@ùhÿÿµ Òÿ ù Òÿ© û3 ùh@¹ 1B Th ¹i@ùé7 ù(@¹ 1B T( ¹é ùàªm ÷ ùà ùà/ ùè @ù Ñ?# ñá T ñõ+@ù÷#@ù Tè'@ù öVøËàªáª |©jhøI ùÉ@ù©j(øH@ùÈ ùÖ ñþÿT ñõ+@ù÷#@ù Tè'@ù öVøËàªáªú Tàªá ªâªr à ªáªâªn àªáªâªj Ö ñÁýÿT¼ s@ù@¹ 1B T ¹@ùõßB©ôÏA©è ø7 ñ ù T p@ù* ÿ; ù ´@ùÈ ø7 ñ ùa Tàª! ÿ7 ù ´h@ùÈ ø7 ñh ùa Tઠÿ3 ù ´h@ùÈ ø7 ñh ùa Tàª È °åFù¨@ùA@ùÔ ´ ° Ø!ì 5àªáª Ҁ?Öó ªè ó ´ó/ ù¨@ùÈ ø7 ñ¨ ùa Tàª÷ ´h@ùùþ7 ñh ù¡øþTàªï Â÷ÿ¨ @ù @ùáªÒ ÒÓތR4@R$üÿ¨ @ù @ùáªÉ ÿC ùߌR Ò Ò+ÿÿáR@ùÈ ø7ઠñ ùA TÒ Ò4@Rüÿ Ò ÿÿàªáª Ò0 ó ªÉÿÿ ÒsñR4@Rüÿ ÒÃÿÿ¦ ´ Ҽ s@ù÷@ù¼ÿÿ3?RBùÿÓ?R@ùÿa áªâªãª_Jÿ¿øÿ©SAR7ùÿ³R¦üÿS R¤üÿ« S áªâªãªQJÿÿÿ©Ó Rÿ; ùüÿàª.çÿÁúÿ Ò Ò3͌RT>RÖûÿ Ò Òÿ; ù3%RDRÐûÿ Ò Òÿ; ù³Rýüÿ Ò Òÿ; ùó&RÔDRÅûÿ ð)I@ù ë&ÿT¨ ð9Gùàªë õ ª ø þµ4ýÿ Ò Òÿ? ùüRÔAR³ûÿ Ò ÒÿC ùó،Rô?Rûÿ Ò ҳڌRô?R¨ûÿ ð=@ù @ù !T"O Óýÿ ð=@ù @ù !T"H íýÿ ð=@ù @ù !T"A ÿÿ Ò Òÿ; ùóþRôARûÿ ð=@ù @ù !T"4 3þÿöW½©ôO©ý{©ý óªô ª@ù ð)M@ù ë@ TÙF©ö ´É
@ù© ´àªj ´õ ªÈ
@ùàªáªâª ?Öó ª¨@ù ø7 ñ¨ ù Tàªý{B©ôOA©öWèÀ_ÖH ´@ù ´àªâªý{B©ôOA©öWè` ֈ@ù yaøi@¹) 1b Ti ¹@ùy!ø @ù ø7 ñ ùà T3 Ràªý{B©ôOA©öWèÀ_Ö 3 Ràªý{B©ôOA©öWèÀ_Öàªÿ àªý{B©ôOA©öWèÀ_Öàª, @ ´õ ªàªáªâª ó ª¨@ùøÿ6Æÿÿ àªý{B©ôOA©öWèÀ_Öè ª @ù @¹) 1b T ¹
@ùÀ_ÖôO¾©ý{©ýC ó ª! ´ôª( @¹ 1B T ¹`@ù @ù ø7 ñ ù Tt ù Rý{A©ôO¨À_֔ ðr@ù@¹ 1þÿTðÿÿÄ t ù Rý{A©ôO¨À_ÖôO¾©ý{©ýC È Dù5 ´ô ª Òh ó ª` µ ´@ù ø7 ñ ù@ Tàªý{A©ôO¨À_Ö Òàªý{A©ôO¨À_Öડ àªý{A©ôO¨À_ֈ ð5@ù @ù Ð!Ü @ùèüÿ6éÿÿÿÃÑø_©öW©ôO©ý{©ý÷ªöªõªôª ðy@ù@ù¨ øáªý ó ªÀ ´h@ùB987 ðA@ù @ùôW © Ð!¸ h&B©Ê
@ò Rj?
ë*J? ñé)?ë T ðE@ù @ùö'©ôW © Ð!DB h@ùÈ ø7 ñh ùa Tàª^ Ҩ\ø ð)y@ù)@ù?ë! Tàªý{R©ôOQ©öWP©ø_O©ÿÃÀ_Öÿ qAþÿT ë þÿTö#©ôW © ÐBà R© á Ò Ò0 üÿ6ÛÿÿA ÿÑø_©öW©ôO©ý{©ýCõªöªôª÷ ª Ð!ð
ª ` ´ó ªáªï @ ´ø ªáªß 4àªáªØ À ù ´h@ùhø7 R R ñh ù! Tઠàªý{E©ôOD©öWC©ø_B©ÿÀ_ֈ ð!@ù@ùàªT àS © Ð!$ ઠðA@ù@ùàªJ ÷ ªàª± õ©÷S © Ð!ì àªØ h@ùø7 ñh ù ûÿTý{E©ôOD©öWC©ø_B©ÿÀ_Ö ý{E©ôOD©öWC©ø_B©ÿÀ_Ö Rý{E©ôOD©öWC©ø_B©ÿÀ_ÖÿÑø_©öW©ôO©ý{©ýCõªöªôª÷ ª Ð!ð
L ` ´ó ªáª @ ´ø ªáª 4àªáªz À ù ´h@ùhø7 R R ñh ù! T઼ àªý{E©ôOD©öWC©ø_B©ÿÀ_ֈ ð!@ù@ùàªö àS © Ð!$ઠðA@ù@ùàªì ÷ ªàªS õ©÷S © Ð!L%àªz h@ùø7 ñh ù ûÿTý{E©ôOD©öWC©ø_B©ÿÀ_Ö ý{E©ôOD©öWC©ø_B©ÿÀ_Ö Rý{E©ôOD©öWC©ø_B©ÿÀ_ÖÿÃÑüo©úg©ø_©öW©ôO ©ý{
©ýôª ðy@ù@ùÉ ))è' ùéÿ© ðsr@ùó ùC ´õª6 Ô ´ ña T8 @ùø ù¹
@ùL Ô ´ ñ T8 @ùø ùH è4ªýӉ °)y °JU ñI± ðJA@ù@@ùJ J °k© j±êÓ©é£ ©H °é8è ù °!¸ $ A±R Ð |0C c bVRð5ÿ ҿ ¹
@ù: ñ« T ÒÈ 1Eù»b h{xø ë@ T ?ëaÿÿT Òa{xøàªB RÀÿ 5 ?ë!ÿÿT
ðs@ù
À ø7Øzxø ´ø ùùª 7 µ ðs@ù? ñê% T¹ ð9#94wEù @ù@ùáªü ´÷ ª @¹ 1B Tè ¹Ú ACAùè@ùI@ù( ´àª ?Öö ª ´è@ùÈ ø7 ñè ùa Tàªû 4@ù @ù@ùáªá ´÷ ª @¹ 1B Tè ¹àªáªr 1 Tô ªÈ@ù ø7 ñÈ ù Tè@ùhø7 ñè ù TàªÞ àªÛ è@ùèþÿ65wEù @ù¢@ùᪿ ö ª´ 4Ö ´È@¹ 1B TÈ ¹È 1EùÈ@ùI@ùè ´àª ?Öõ ªà ´È@ùÈ ø7 ñÈ ùa Tઽ ¨@ù ð)U@ù ëà T Ò Réã )! ôã©!M(Ë àªKNÿó ª ´@ùÈ ø7 ñ ùa Tદ ´¨@ù$ø7 ñ¨ ù!$ Tઠö ´È@¹ 1B TÈ ¹ACAùÈ@ùI@ù( ´àª ?Öõ ª ´È@ùÈ ø7 ñÈ ùa Tઠ´@ù@¹ 1b T ¹´@ù¨@ùÈ ø7 ñ¨ ùa Tàª} èã ! ÿã©àªâA²NÿÀ ´õ ªØ ÇEù@ùI@ùh ´àª ?Ö÷ ª` ´¨@ùÈ ø7 ñ¨ ùa Tàªe 6wEù @ùÂ@ùáªK ´õ ª @¹ 1B T¨ ¹ACAù¨@ùI@ù ´àª ?Öö ª ´¨@ùÈ ø7 ñ¨ ùa TàªK ÇEùÈ@ùM@ùH ´àªâª ?Ö@ø7è@ùÈ ø7 ñè ùa Tàª< È@ùÈ ø7 ñÈ ùa Tàª5 h@¹ 1b Th ¹© µàª>Fÿ÷ ª äÿµ ҸXRS·R ઠö ª äÿµ Ò ғ·R µàª,Fÿ÷ ª åÿµ Ò Òó·R¸XRu Ò Ò3¸R¸XRè@ù(
ø6m ñ µàªFÿö ª@çÿµ ÒØXRӹRs àªv õ ª`çÿµ ÒºRØXR\ ´@ùTèÿ´³
@ù@¹ 1 Th@¹ 1£ T¨@ùÈø6 ÒØXR³¼RT E °¥è8âã ãà àªáªäªò½ÿ ø7ø@ùÈþÿÄ µàªíEÿö ª èÿµ ÒYRӿRF àªI õ ª èÿµ Ò
RYR÷ª Òè@ùÈø6* 8YRÓMR7 àª: ÷ ªàêÿµ8YRR) ¤ µàªÍEÿõ ª ìÿµ Ò] àª+ ö ª@ìÿµ³R8YRè@ùhø6 àªâª< íÿ6 ÒÍR8YRè@ùÈ ø7 ñè ùa Tઠ´È@ùÈ ø7 ñÈ ùa Tઠ´¨@ùÈ ø7 ñ¨ ùa Tઠ° |0# ðc áªâª94ÿ Ò ´@ùÈ ø7 ñ ùa Tઠè'@ù Ð)y@ù)@ù?ë¡ Tàªý{J©ôOI©öWH©ø_G©úgF©üoE©ÿÃÀ_ֈ ¹h@¹ 1¢ïÿTh ¹¨@ùÈ ø7 ñ¨ ùa Tàªe ( Rõªþÿ¯RþÿᮍRþÿ` Ò ÒsR8YRè@ùhöÿ6·ÿÿÿà ÑôO©ý{©ý ¨ Ð!9uEù @ùb@ùáª6 ´ô ª @¹ 1B T ¹¨ ðAAù@ùI@ùH ´àª ?Öó ª@ù@ ´ ø7 ñ ùÀ Tàªý{B©ôOA©ÿà À_Öàª0 àªý{B©ôOA©ÿà À_Ö µ¨ Ð )Gù@ùI@ù Ð)Y@ù᪠ëA T Ò# R ô ªàúÿµ @ ´̍R
ઠó ª@ù ûÿµÈ ø7 ñ ùa TઠA̍R ° à0# ðc b\Rµ3ÿ Òàªý{B©ôOA©ÿà À_Ö ´ ?Öô ªàöÿµNEÿß üÿµ Ð-@ù @ùó ùa ð!X Î ̍Råÿÿd ô ª õÿµñÿÿÿÑúg©ø_©öW©ôO©ý{ ©ýCóª Ðy@ù@ùè' ù¨ ð!
è©C ´õª6 s ´ ña T4 @ùô# ù·
@ù: ñ¡ T4 @ù8 ¹
@ù7 ñ T Ҩ ðEAùºb H{xø ë T ?ëaÿÿT ÒA{xøàªB R§½ÿà 5 ?ë!ÿÿT ` ´aR ÐA@ù @ù( ð* RèÏ© I Ð)]*è« ©é ù !¸ aٍR ° x1# ðc ¢\RA üÿ7Ôzxøô# ùTüÿ´ÿ ñJ
T¨ Ð!9uEù @ù¢@ùáª{ À ´ó ª @¹ 1B Th ¹ еr@ùëÀ
T¨ ÐGùÈ ´i@ù?ë
T+@ù ´j @ù_ ñ Tka l@ùëà Tk! J ñaÿÿT)
@ù
@ù ÐJA@ù@@ùé# © !Ø H ´h@ùÈ ø7 ñh ùa Tàªc ° x1# ðc !ߍRÂ_R 3ÿ ÒA ? µàªhDÿó ª`ùÿµ ° x1# ðc áލRñÿÿ Ð=@ù @ù ! 4 ÓûÿµäÿÿE Х\*âà ãàªáªäªN¼ÿ ø7ô#@ù¥ÿÿê ªª ´J@ù_ë¡ÿÿT ÐJ@ù
ëÁ÷ÿTh
@ù@ùàªáª ?Ö ´ @ù¨ ø7 ñ ùA T% ¨@¹ 1B T¨ ¹h@ùÈ ø7 ñh ùa Tઠè'@ù Ð)y@ù)@ù?ëÁ Tàªý{I©ôOH©öWG©ø_F©úgE©ÿÀ_ր ° x1# ðc àRâ_Rµ2ÿ Òh@ùüÿ6èÿÿ؍R]ÿÿ ø_¼©öW©ôO©ý{©ýÃ óª µ¾ ô ª
´h@¹ 1B Th ¹¨ Ð!9uEù @ùÂ@ùáªÔ à ´õ ª @¹ 1B T¨ ¹¨ ðÍDù¨@ùI@ù ´àª ?Öö ª ´¨@ùÈ ø7 ñ¨ ùa TàªÓ ઠõ ª` ´È@ùA@ùW ´` ð Ø!® à 5àªáªâªà?Ö÷ ªª ×
´È@ù ø7 ñÈ ù` T¨@ù¨ø7 ñ¨ ùA Tવ h@ùø6 ર ¨@ù¨þÿ6h@ùÈ ø7 ñh ùa Tધ @ù ø7 ñ ùà Tàªý{C©ôOB©öWA©ø_ĨÀ_Öઠàªý{C©ôOB©öWA©ø_ĨÀ_ÖôªA Ð!5àª" Ri»ÿ 4àªJ ô ªÀòÿµ Òàªý{C©ôOB©öWA©ø_ĨÀ_Ög à µàªCÿõ ª@óÿµ# àªï ö ªÀóÿµWìR
·ìR àªáªâªÖ ÷ ª õÿµ Q ´÷ìRàªK,ÿàªI,ÿ ° 2# ðc áªaR2ÿ Òh@ùöÿ6´ÿÿ Ò ÒìRîÿÿ Ð=@ù @ùa ð!T"< æÿÿø_¼©öW©ôO©ý{©ýÃ óª µ ô ª
´h@¹ 1B Th ¹¨ Ð!9uEù @ùÂ@ùáª% à ´õ ª @¹ 1B T¨ ¹¨ ðÍDù¨@ùI@ù ´àª ?Öö ª ´¨@ùÈ ø7 ñ¨ ùa Tàª$ àªá õ ª` ´È@ùA@ùW ´` ð Ø!ÿ à 5àªáªâªà?Ö÷ ªû ×
´È@ù ø7 ñÈ ù` T¨@ù¨ø7 ñ¨ ùA Tઠh@ùø6 ઠ¨@ù¨þÿ6h@ùÈ ø7 ñh ùa Tàªø @ù ø7 ñ ùà Tàªý{C©ôOB©öWA©ø_ĨÀ_Öàªë àªý{C©ôOB©öWA©ø_ĨÀ_ÖôªA Ð!<7àª" Rººÿ 4ઠô ªÀòÿµ Òàªý{C©ôOB©öWA©ø_ĨÀ_ָ à µàªáBÿõ ª@óÿµ# àª@ ö ªÀóÿµùR
wùR àªáªâª' ÷ ª õÿµ ¢ ´·ùRàª+ÿàª+ÿ ° |2# ðc áªâaR_1ÿ Òh@ùöÿ6´ÿÿ Ò Ò×øRîÿÿ Ð=@ù @ùa ð!T" æÿÿý{¿©ý @ù @ùઠ?Ö|S # p¦R' ! ý{hÀ_Ö @ù @ùઠÖöW½©ôO©ý{©ý ? ñK Tóªôªõ ª @ù¨@ù ?Ö` ü ñaÿÿTý{B©ôOA©öWèÀ_ÖöW½©ôO©ý{©ý ? ñë Tóªôªõ ªp¦R @ù¨
@ù ?Ö|S # Á' ! `F ¼ ñáþÿTý{B©ôOA©öWèÀ_Öë+»mé#möW©ôO©ý{©ýó ªT Д9U ðµv ÐÖ)`"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjüa ªjjø?
ëã T }ò T QÀZiüÉzhü
8i `@ùh@ù ?ÖI%@ Aa L 0!` ýÿT A` ý{D©ôOC©öWB©é#Amë+ÅlÀ_Ö`@ùh@ù ?Ö @a P hpÒÈ/¥ò(;ÙòÈèòg 8` ý{D©ôOC©öWB©é#Amë+ÅlÀ_Öë+¹mé#múg©ø_©öW©ôO©ý{©ý? ñ« Tóªôªõ ª ÒW Ð÷9X ðypÒÙ/¥ò9;ÙòÙèòz ÐZ) @ù¨@ù ?Ö @a & !g(8` hz6üÖ ßë` T "@© ?Ö üKÓ c(CÓ
ñ}Óájjüa
kjø?
ëCþÿT }ò ýÿT Q@[iüI{hü
8i @ù¨@ù ?ÖI%@ Aa ÷ 0!` ýÿTãÿÿý{F©ôOE©öWD©ø_C©úgB©é#Amë+ÇlÀ_Öë+ºmé#mø_©öW©ôO©ý{©ýCó ªT ð9u µ p¦Rw ð÷ `@ùh
@ù ?Ö | S # S
}~Ӂjj¼! ªjj¸?
kc T r` T QàZi¼ézh¼
8) `@ùh
@ù ?Ö|S # Á' ! I% A! Ä 0! eüÿT A `@ùh
@ù ?Ö|S # p¦R' ! É (ىRÈ ¨r' 8 ý{E©ôOD©öWC©ø_B©é#Amë+ÆlÀ_Öë+¸mé#müo©úg©ø_©öW©ôO©ý{©ýÃ? ñ Tóªôªõ ª ÒW Ð÷9X ð p¦R:ىRÚ ¨r{ Ð{ @ù¨
@ù ?Ö|S # !' ! A' (8 hz6¼Ö ßë T @ù¨
@ù ?Ö | S # S
}~Óájj¼!
kj¸?
k#þÿT r üÿT Q`[i¼i{h¼
8) @ù¨
@ù ?Ö|S # !' ! I% A! i 0! eüÿTÞÿÿý{G©ôOF©öWE©ø_D©úgC©üoB©é#Amë+ÈlÀ_ÖöW½©ôO©ý{©ý ? ñ« Tóªôªõ ª @ù¨@ù ?Ö @a ^ @a ` ü ñÿÿTý{B©ôOA©öWèÀ_ÖöW½©ôO©ý{©ý ? ñk Tóªôªõ ªp¦R @ù¨
@ù ?Ö|S # Á' ! À" C @a @b `F ¼ ñaþÿTý{B©ôOA©öWèÀ_Öë+ºmé#mø_©öW©ôO©ý{©ýCó ªU ðµV ðÖ9 | w ÷`"@© ?Öô ª ðIÓ c
}}ӡjjü a @a xò a Êjjø?
ëà Tè 4 QàZiüêzhü 8j `@ùh@ù ?Öj)@ h h þ P!`
üÿT 5ÒòUuÐò5ú÷ò`@ùh@ù ?Ö @a ¡g(` `@ùh@ù ?Ö @a ý @a 8` h a
þÿTh¦Ò(A°òvÇò¨èò g (h @a oò a A` ý{E©ôOD©öWC©ø_B©é#Amë+ÆlÀ_ÖöW½©ôO©ý{©ý ? ñ+ Tóªôªõ ªàª£ÿÿ` ü ñÿÿTý{B©ôOA©öWèÀ_Öë+ºmé#mø_©öW©ôO©ý{©ýCó ªu µ9v °Ö p¦R | x °`@ùh
@ù ?Ö | S #
}~ӡjj¼ ! @! r ! Êjj¸?
kã T¨ 4 Q [i¼
{h¼ 8* `@ùh
@ù ?Ö|S # á' ! `)
À" Á" ! ` ` P!` ÅûÿT" ô ªp¦RvªRѷr`@ùh
@ù ?Ö|S # ©' ) Á' ( `@ùh
@ù ?Ö|S # ) @! 8 ( ! mýÿT´R(
¨r ' (( @! r ! A ý{E©ôOD©öWC©ø_B©é#Amë+ÆlÀ_ÖöW½©ôO©ý{©ý ? ñ+ Tóªôªõ ªàªÿÿ`F ¼ ñÿÿTý{B©ôOA©öWèÀ_Öï;·mí3më+mé#múg©ø_©öW©ôO©ý{©ý@` ó ª n !` ! TT °9U еv °Ö)`"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjü a ªjjø?
ëc T }ò T QÀZiüÈzhü
8h `@ùh@ù ?ÖH!@ Aa ( !` ýÿT !` ä /a T A` É n !k TT °9U е6 RwpÒ×/¥ò7;Ùò×èòx °) Àb 8i h
@` `9h J ah / @` 9j 0!` iüÿT`@ùh@ù ?Ö @` `"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjü a ªjjø?
ëã T }ò T Q [iü
{hü
8j `@ùh@ù ?֪)@ Aa é P!` ýÿT`9h 0!` úÿT `@ùh@ù ?Ö @a ð ág,8` `9h 0!` (ùÿTah A` ý l (úÿT @` { `@ùh@ù ?Ö @a ß hpÒÈ/¥ò(;ÙòÈèòg 8` o a ``
9` (R b j Àa l` U ðµV ðÖ9·Ò×_¶òwOÞòôçò8ÒòXuÐò8ú÷òy¦Ò9A°òvÇò¹èòz Z`"@© ?Öô ª ðIÓ c
}}ӡjjü a @a xò a Êjjø?
ë TH 4 Q@[iüH{hü 8h `@ùh@ù ?Ö(!@ | o o !` eüÿT-O ` üÿT` (` `@ùh@ù ?Öá o âgBa !¬B a T @` l o m9h A` )` @ ` ÀO 0!` %ùÿT `@ùh@ù ?Ö @a g(` `@ùh@ù ?Ö @a y @a 8` h a
þÿT g (h @a oò a -O ` éõÿTÏÿÿ@ h ý{H©ôOG©öWF©ø_E©úgD©é#Cmë+Bmí3Amï;ÉlÀ_Öï;¶mí3më+mé#müo©úg©ø_©öW©ôO©ý{ ©ýC@ ó ª . ! TT Д9U ðµ p¦Rw Ð÷ `@ùh
@ù ?Ö | S # S
}~Ӂjj¼ ! ªjj¸?
kc T rà
T QàZi¼èzh¼
8( `@ùh
@ù ?Ö|S # Á' ! H! A! ! eüÿT A ã Á" ` T ä / @b Ý . !+ E TT Д9p¦RV ðÖ 7ىR× ¨rx Ð
`9) (
@ `9(
a( & @ 9* 0! üÿT`@ùh
@ù ?Ö|S # ¡' ! `@ùh
@ù ?Ö | S # S
}~Ӂjj¼ ! Êjj¸?
kc T r T Q [i¼
{h¼
8* `@ùh
@ù ?Ö|S # ¡' ! ª) A! Ø P! eüÿT`9( 0! ¨ùÿT `@ùh
@ù ?Ö|S # ¡' ! Ü á' ,8 `9( 0! è÷ÿTa( A é , ÈøÿT @ `@ùh
@ù ?Ö|S # p¦R' ! Ç (ىRÈ ¨r' 8 y ! `
9 P$ * u µ9 À! l v °Ö p¦RØ{Rø §ryªRѷr´R:
¨r{ °{`@ùh
@ù ?Ö | S #
}~ӡjj¼ ! @! r ! Êjj¸?
kà T 4 Q`[i¼h{h¼ 8( `@ùh
@ù ?Ö|S # á' ! ! À" àÁ" | !` ` w !` ¥ûÿT- IûÿT ( `@ùh
@ù ?Ö|S # á' ! á / ' B! !¬ ! Ä Tz @ , / m9( A t ) @ À 0! å÷ÿT! ô ª`@ùh
@ù ?Ö|S # é' ) b !' ( `@ùh
@ù ?Ö|S # ) Y @! 8 ( ! mýÿT@' (( @! r ! - éóÿTÅÿÿ@ ( ý{I©ôOH©öWG©ø_F©úgE©üoD©é#Cmë+Bmí3Amï;ÊlÀ_Öý{¿©ý $@©àª ?Ö üAÓý{hÀ_Öý{¿©ý @ù @ùઠ?Ö |Sý{hÀ_Öý{¿©ý $@©àª ?Ö üAÓý{hÀ_Ö@©àª Öí3»më+mé#môO©ý{©ý @` n !`
ä / T ` !`
T c 0!k Å Tè R b 8i x Ò`b()` n h ` ¨æÒ# òèìÈòÈþ÷òg!` ¨ЀÒȧòÈÒßòÈøçòg!(b !` èrÒèa¹òÈPÈòÈó÷òg!(b !` HÒ(H£ò4ÈòHïçòg!(b !` 菇Ò(3»òVÍòèë÷òg!(b !` äÒc¥òȣÒòhéçòg!(b !` hÒ(p¢ò'Ðòhè÷òg!(b !` HÒ(@£ò4ÀòHéçòg!(b !` 肍Ò(آò-ØòÈì÷òg!(b ` èó ²¨öçòg (a h ֗҈ ¹ò(þÌò¨ÿçògl J A 9b A` ´ )@
8h 0!k èW q T ñK T4 R n 9i A` § J9` ëMÿÿT@A` ý{D©ôOC©é#Bmë+Amí3ÅlÀ_Öé#¾mý{©ýC (@` @` `üÿ %@ ý{A©é#ÂlÀ_Öë+»mé#möW©ôO©ý{©ý@` ó ªT 9U °µv Ö)`"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjü a ªjjø?
ëc T }òÀ T QÀZiüÊzhü 8j `@ùh@ù ?Öj)@ Aa ^ P!` ýÿT `@ùh@ù ?Ö @a h hpÒÈ/¥ò(;ÙòÈèòg)8` i ý{D©ôOC©öWB©é#Amë+ÅlÀ_Öé#¾mý{©ýC (@` @` @ù @ùઠ?Ö %@ ý{A©é#ÂlÀ_Öé#¾mý{©ýC (@` äüÿ ` ý{A©é#ÂlÀ_Öé#¾mý{©ýC (@ áýÿ ý{A©é#ÂlÀ_Öí3»më+mé#môO©ý{©ý(@` @` ó ª n 0!` è T!` ¨ TÒȖ±ò¨ Ðò¨Tåò g0!` ¥ TÒȖ±ò¨ Ðò¨Tåò g!` Å T`@ùh@ù ?Ö!)h ` i èW b ý{D©ôOC©é#Bmë+Amí3ÅlÀ_ÖઠA` ªüÿ @` ઠA` ¦üÿ )` ` ý{D©ôOC©é#Bmë+Amí3ÅlÀ_Ö
n `@ùh@ù ?Ö
@` `@ùh@ù ?Ö @` ¡i @A` @` ¡h `A` )` m èýÿTA)k 8 ` ýÿTáb a
T` ý{D©ôOC©é#Bmë+Amí3ÅlÀ_Ö@A` Þ i `A` Û h 0!` !Í` (9a 8a A` Å
@` A` Â @)` Ï 9` ¾ ý{D©ôOC©é#Bmë+Amí3ÅlÀ_Öé#¾mý{©ýC ` h _üÿ ` ý{A©é#ÂlÀ_Öë+¼mé#môO©ý{©ýÃ (@` @` ó ª
` j Püÿ@ ` h j àªKüÿ@ ` i `` ý{C©ôOB©é#Amë+ÄlÀ_Öé#½môO©ý{©ý ó ªiûÿ@` àªfûÿ ` ý{B©ôOA©é#ÃlÀ_Öë+»mé#möW©ôO©ý{©ý@` ó ªT 9U °µv Ö)`"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjü a ªjjø?
ëc T }òÀ T QÀZiüÊzhü 8j `@ùh@ù ?Öj)@ Aa c P!` ýÿT `@ùh@ù ?Ö @a m hpÒÈ/¥ò(;ÙòÈèòg)8` h ý{D©ôOC©öWB©é#Amë+ÅlT ë+»mé#möW©ôO©ý{©ý ` T ä /ý{D©ôOC©öWB©é#Amë+ÅlÀ_Ö@` ó ªT 9U °µv Ö)`"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjü a ªjjø?
ëc T }òÀ T QÀZiüÊzhü 8j `@ùh@ù ?Öj)@ Aa P!` ýÿT `@ùh@ù ?Ö @a * hpÒÈ/¥ò(;ÙòÈèòg)8` n h A` 5 ý{D©ôOC©öWB©é#Amë+ÅlÀ_Öë+»mé#möW©ôO©ý{©ý@` ó ªT 9U °µv Ö)`"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjü a ªjjø?
ëc T }òÀ T QÀZiüÊzhü 8j `@ùh@ù ?Öj)@ Aa ã P!` ýÿT `@ùh@ù ?Ö @a í hpÒÈ/¥ò(;ÙòÈèòg)8` Aa Ù @a n !h ö ý{D©ôOC©öWB©é#Amë+ÅlÀ_Öë+¼mé#môO©ý{©ýà (@` @` ó ª
l `@ùh@ù ?Ö j j T ` MÿÿT (` Æ %@ ý{C©ôOB©é#Amë+ÄlÀ_Ö` !8` 8` ¼ ¤H ý{C©ôOB©é#Amë+ÄlÀ_Öë+¼mé#môO©ý{©ýÃ (@` @` ó ª
n `@ùh@ù ?Ö@9` j eÿÿT¦ @a ¤ ¤H ý{C©ôOB©é#Amë+ÄlÀ_Öé#½môO©ý{©ý (@` @` ó ª`@ùh@ù ?Ö ` ÿÿTn !8` a %@ ý{B©ôOA©é#ÃlÀ_Öé#¾mý{©ýC (@` @` Múÿ %@ r ý{A©é#ÂlÀ_Öë+»mé#möW©ôO©ý{©ý@` ó ªT 9U °µv Ö)`"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjü a ªjjø?
ëc T }òÀ T QÀZiüÊzhü 8j `@ùh@ù ?Öj)@ Aa J P!` ýÿT `@ùh@ù ?Ö @a T hpÒÈ/¥ò(;ÙòÈèòg)8` ` i Àa ` ý{D©ôOC©öWB©é#Amë+ÅlÀ_Öé#½môO©ý{©ý @` ó ªúÿ @` T Rb ` àªÒúÿb a !Àa !i Àa ` ý{B©ôOA©é#ÃlÀ_ÖÿCÑï;mí3më+mé#müo©úg©ø_ ©öW
©ôO ©ý{ ©ý
@` ó ªHR b P!` k THÁa @A` à ýӍÒHb°òXÙò¨ýçò g¨GÒèz´ò®Çò èòg, H -Ҩ¯òè§ÆòÈõ÷ò gh˖ÒÈú¢ò(¡Íò(óçòg- L èç ²hèò g9` HNÒȑ¼òHþÃòHþçòg ` äÒè ²òÈoßò(þçòg (` à ýU R b 9` HȇÒ=»òUßòèòg ` H.Òè!½òèöÕò¨ýçòg¶pÒ6
·ò֣Ðòvûçò=Òףò·pÝò7öçò8ÒٮòØ÷ÓòXñçò 8` à ý@Aa ê mûó ²»öçò֗Ҝ ¹ò<þÌò¼ÿçò ê@ýÀ9i ð!` T`@ùh@ù ?Öl 8h `@ùh@ù ?Ö!Á` ¢b 9a Am !h !(l !(I Âg!(b !@e 4 xág!a Tá@ý a é Tôüÿ·g!a e T h LüÿT¤ @` à@ý¡ i)` h ` (l /9` bá@ýâ @ýA b n !` ä /`ùÿT ` !` ùÿTn c !` Å Tè R b 8h x Ò b )` k ` ¨æÒ# òèìÈòÈþ÷òg!` ¨ЀÒȧòÈÒßòÈøçòg!(b !` èrÒèa¹òÈPÈòÈó÷òg!(b !` HÒ(H£ò4ÈòHïçòg!(b !` 菇Ò(3»òVÍòèë÷òg!(b !` äÒc¥òȣÒòhéçòg!(b !` hÒ(p¢ò'Ðòhè÷òg!(b !` HÒ(@£ò4ÀòHéçòg!(b !` 肍Ò(آò-ØòÈì÷òg!(b ` ag (a k gl I A j9b `A` 9 @%@ 8k c !` èW q( AúKíÿT: Rê@ýn k9h `A` + )9` Z _ëMÿÿT`ÿÿàb @!` a T Ò
@Aa @` n `@ùh@ù ?Ö) ` 0!h LÿÿTàªý{L©ôOK©öWJ©ø_I©úgH©üoG©é#Fmë+Emí3Dmï;CmÿCÀ_Öé#½môO©ý{©ý ó ª( Rb B8a Ha ùÿ ` àªý{B©ôOA©é#ÃlÏþÿÿÃÑï; mí3
më+ mé# müo
©úg©ø_©öW©ôO©ý{©ýóªô ªH @¹à' ýè 4H@ù ë TA@ý ` À/ TS ù@ ý( RH ¹n ¡8` a @` D T«8` ¬8k abK°m!,K A ý"@e U xU ùbbBk Bl BÀa èç²Hèògcl èQҨ ¥òëÑò( èògb B@e l M(c ¢b@(c Mm8m à+ ý (m Dm¢bèç²H3òÈèògb(b Ð҈èògbb ¾҈¯ò(ÝÄò(øçògh(b "8d ä? ýc
D Bc ` Dc ¤(d Dd Hm8a à/ ýl !b "c ¢(b !b `H ® ` A¸mám d Â)` a I(` â; ýB¤m`b k
l @ù@ù ?Öi @ù@ù ?Ö!A` @` ð!m Í TáC ýv · ØËyË: Rè; m c - T`b k
l @ù@ù ?ÖáC@ýa @ù@ù ?Ö @` ð!m Í Tð!n Í Tà;@ýð!` ûן A` ` Û 6á3@ý a á/@ý 8` @e xëlüÿT(!` üÿTà;@ýà9` ` á3@ý# à9m h á?@ý!(` n H ¢bB8a l B(c BÀ` Bm 8b d ¬ùÿT!@e < xëhWÚ U ñb T¡ á7@ý a á?@ý (` @e xü÷ÿ·(!` ÷ÿTà9n ` á7@ý a ëhWÚ U ñ Tb` Bb Cb B8c 0 b % Tb"j a #c l c(d èó ²¨øçòg!C !j l !(c Oa hÿbH Rb Bj *b
@` @9o 0!` ¤ T@)o 0!` LòÿT bäbbÈ Ë b#a ámd Jb H@` ` ãm@` à ýa õ à ý bl (a à ý n î á Am ` á+@ý# B `bàmÀ k î@ýÁ l a ã âAm@@ ÐÒ( èòg"o ØÒ èògb8b Bo ÐÒ èòg8b Bo Ü҈èòg¢8b Bo ×ÒHèògÂ8b ç@ýBg °É҈ èògBg (b "j b8b Bj 8b Bj ¢8b Bj Â8b Bh è@ýBg (b ð @ý"p b8b Bp 8b Bp ¢8b Bp Â8b Bn Bg (b â#@ý!b a8a !b 8a !b ¡8a !b Á8a â@ý!b î@ý!g (a 0!` ìäÿT& al Âb"b ëÍ Tn ÿ ëãÿTn èªbDd 8a cd ëMÿÿTÿÿ n ë ±Uú¬áÿTn bDd 8a cd ëMÿÿTÿÿà+@ý M (o @e xh Ë l á'@ý0 ` \ý{R©ôOQ©öWP©ø_O©úgN©üoM©é#Lmë+Kmí3Jmï;ImÿÃÀ_ÖK°AmU@ùMCmB$@ý@ EmámA0@ý@¸Fmàm@¤Gmà mÌþÿë+»mé#möW©ôO©ý{©ýõª@` óªô ªH @¹è 4¨
@ù ë T @ý h T³
ù¨ ý6 R¶ ¹ n 8h © ýjb A` < @ ` +
@` `bª ý h bbÁb . ýI #Àa d # C P c e T`b Âb I BÀa B x¶ ù@ù@ù ?Ö j Í T ÒAA` 8a i Ë"bBh Aa bBi !b ઠa m T ëmþÿT@ù@ù ?Ö ÒAA` a ìþÿTý{D©ôOC©öWB©é#Amë+ÅlÀ_֪¦Am¶@ù@ù@ù ?Ö j ûÿT Òý{D©ôOC©öWB©é#Amë+ÅlÀ_ÖôO¾©ý{©ýC ¡ ´ä /!À" a ¡ T Òý{A©ôO¨À_Öóªl a H Taba Ðg 0 b H Táªý{A©ôO¨ÿÿn 8` aba Ðg 0 b h Táª{ÿÿ` Ëý{A©ôO¨À_Öáªý{A©ôO¨ÓýÿáªÑýÿ` Ëý{A©ôO¨À_Öë+¼mé#môO©ý{©ýà a Tø¯R ' À" ý{C©ôOB©é#Amë+ÄlÀ_Ö(@` @` ó ªàb ` a T` h àªI÷ÿ ` ý{C©ôOB©é#Amë+ÄlÀ_Ö( R b i E T b 9` ` i àª9÷ÿ) ` àªböÿÁa (a $@ ý{C©ôOB©é#Amë+ÄlÀ_Ö
` j àªcüÿøÓ b )` j àª$÷ÿ@ ` ý{C©ôOB©é#Amë+ÄlÀ_Öë+¼mé#môO©ý{©ýà (@` @` ó ªA@` ³ÿÿ
h ` k àª÷ÿ` ` i @` ý{C©ôOB©é#Amë+ÄlÀ_Öë+¼mé#môO©ý{©ýà )@` @` ó ªH R b a
` &öÿ ` ` Rb !i ` !@ !Àa 8a I!@ `@ùh@ù ?Ö)i a a è T A` ý{C©ôOB©é#Amë+ÄlÀ_Ö h i ý{C©ôOB©é#Amë+ÄlÀ_Öí3ºmë+mé#möW©ôO©ý{©ýC a Tø¯R ' À" ¢ )@` @` ó ªHÒF¼òÈ1Ïò¨Èçò g0 ` TH Rb `@ùh@ù ?Ö( Rb
` £
҈ªòh?Äò(èòg ` ( Òh ±ò¨ßòÜçò g0!` ¥ T n i (i ÐÒÈ%èò g0!` ¨
T( R b Rb !i ! I !Àa (a H Rb Ca cÀa !8c Ci !c A Aa a £
Ҕªòt?Äò4èò5 RV R`@ùh@ù ?ցg ` Ø ¡b a@ `)` *` `9j , ` `@ùh@ù ?ÖÁb !8l a âb 0 b * T` Ù ¡b (a 8l áb a üÿT`@ùh@ù ?Ö @` @A` ¸ l 0!a @a L` (h áb a óG À` £
҈ªòh?Äò(èòg (h H Rb !h ´ 8h 3 7 b a % n i Àa àªyõÿ !@ £
҈ªòh?Äò(øòg a % TH Rb £
҈ªòh?Äò(èòg B £
҈ªòh?Äò(èòg a - TH Rb £
҈ªòh?Äò(èòg@A ý{E©ôOD©öWC©é#Bmë+Amí3ÆlÀ_Öí3»më+mé#môO©ý{©ý@` ó ª @a @` `@ùh@ù ?Ö h 4 Rê T
@` `@ùh@ù ?Ö
@` h ê T`@ùh@ù ?Ö ` b @a ` k P!` ( Tb @A` d @` `A` a ` )` @e x ñËüÿTH!` üÿTôª P!k 跟 q( Ràªý{D©ôOC©é#Bmë+Amí3ÅlÀ_Öé#¾mý{©ýC @` n 8h @ù @ùઠ?Ö h m T RA` i !(h a ÿÿTý{A©é#ÂlÀ_Ö Rý{A©é#ÂlÀ_Öë+»mé#möW©ôO©ý{©ý@` ó ª4 ð9U µV ðÖ)`"@© ?Ö üKÓ c(CÓ
ñ}Ӂjjü a ªjjø?
ëc T }òÀ T QÀZiüÊzhü 8j `@ùh@ù ?Öj)@ Aa ý P!` ýÿT `@ùh@ù ?Ö @a hpÒÈ/¥ò(;ÙòÈèòg)8` )Aa Aa þ ` Àd |èÒg a T ðý{D©ôOC©öWB©é#Amë+ÅlÀ_Ö xý{D©ôOC©öWB©é#Amë+ÅlÀ_Öé#¾mý{©ýC @` èó ²¨úçò g!` k T n 8h @ù @ùઠ?Ö h í T RA` i !(h a ÿÿTý{A©é#ÂlÀ_Ö A` ý{A©é#Âlÿÿ Rý{A©é#ÂlÀ_Öí3»më+mé#môO©ý{©ýó ª n 8l ` A` Ð @`
~ ð`@ùh@ù ?9` `@ùh@ù ?Ö
@` ¡h `A`  @e bp!` LþÿTp!l þÿTk )` A` ¸ A k 8l !b "9l !b i 0 ` üÿT`xý{D©ôOC©é#Bmë+Amí3ÅlÀ_Öí3¼më+mé#mý{©ýà H@` @` @8` "8i J` 9a +` @ù @ùL` ઠ?Ö l ( T j Àa )` ý{C©é#Bmë+Amí3ÄlÀ_Ön 8` k Àa 9` ý{C©é#Bmë+Amí3ÄlÀ_ÖöW½©ôO©ý{©ý ´óªô ª(Aª HªHª!HªAHªHª(ü`ӈ µ@ù
@ù ?Öè * ëHÿÿTý{B©ôOA©öWèÀ_ր"@© ?Ö ëÿÿT÷ÿÿ Òý{B©ôOA©öWèÀ_ÖöW½©ôO©ý{©ý óª¢ ´öªõªô ªHü`Ө µ ¿ë T@ù
@ù ?ÖsB àªý{B©ôOA©öWèÀ_ֿ ±@ T$ 4"@© ?Ö ëÿÿTàªý{B©ôOA©öWèÀ_֤ 4@ù
@ù ?Ö
khÿÿTsB(àªý{B©ôOA©öWèÀ_ր"@© ?Ö àªý{B©ôOA©öWèÀ_ֶ "@© ?Ö ||֛?ëèûÿTê5ªK ֚u©¿ ëIûÿT"@© ?Ö|¿ëÿÿT|֛àªý{B©ôOA©öWèÀ_ֶ @ù
@ù ?Ö|¶¿kâ TsHàªý{B©ôOA©öWèÀ_Öé5** ÖU¥¿kÉþÿT@ù
@ù ?Öè *}¿kHÿÿTîÿÿöW½©ôO©ý{©ý óª" 4õªô ª_ 1A T@ù
@ù ?Ö àªý{B©ôOA©öWèÀ_ÖÄ 4öª@ù
@ù ?Ö
khÿÿT àªý{B©ôOA©öWèÀ_ֶ @ù
@ù ?Ö|¶ k Tý`Ó àªý{B©ôOA©öWèÀ_Öé5** ÖU¥¿k©þÿT@ù
@ù ?Öè *}¿kHÿÿTíÿÿø_¼©öW©ôO©ý{©ýà óª 4ôªõª÷ªö ªèÿR_ k T¨@¹¨ 4@y ¹¨@¹ Q- ä 4øª¨@¹
@y ¹¨@¹ Q¨ ¹@¹)
?k Tèþÿ5À@ùÈ
@ù ?ր ¹( R¨ ¹@¹)
?kÈþÿT3 `> ý{C©ôOB©öWA©ø_ĨÀ_Öø ¨@¹ 4@y ¹¨@¹ Q À@ùÈ
@ù ?ր ¹( R¨ ¹@y `> ý{C©ôOB©öWA©ø_ĨÀ_ÖÀ@ùÈ
@ù ?ր ¹( R¨ ¹@¹*= ? J}K= k Tì> R Ø·±kC TsBJ `> ý{C©ôOB©öWA©ø_ĨÀ_Ö(}S ¹¨@¹ Q¨ ¹@¹*= J}ÿ"*k þÿTÈþÿ5À@ùÈ
@ù ?ր ¹( R¨ ¹@¹*= J}ÿ"*k¨þÿTãÿÿø_¼©öW©ôO©ý{©ýà óª" 4ôªõª÷ªö ª_üq! T¨@¹ 4@¹}S ¹¨@¹ Q/ 4øª¨@¹ @¹}S ¹¨@¹ Q¨ ¹@¹)
?k TÈþÿ5À@ùÈ
@ù ?ր ¹h R¨ ¹@¹)
?kÈþÿT3 ` ý{C©ôOB©öWA©ø_ĨÀ_Öø ¨@¹¨ 4@¹}S ¹¨@¹ Q À@ùÈ
@ù ?ր ¹h R¨ ¹@9 ` ý{C©ôOB©öWA©ø_ĨÀ_ÖÀ@ùÈ
@ù ?ր ¹h R¨ ¹@¹* J}K k Tì R Ø·±kC Ts"J ` ý{C©ôOB©öWA©ø_ĨÀ_Ö(}S ¹¨@¹ Q¨ ¹@¹* J}ÿ*k þÿTÈþÿ5À@ùÈ
@ù ?ր ¹h R¨ ¹@¹* J}ÿ*k¨þÿTãÿÿ" 4ôO¾©ý{©ýC óªôª¨ @¹è 4h@¹}Sh ¹@¹ Q @ù @ùઠ?Ö` ¹èR ¹h@9 ý{A©ôO¨àªÀ_Öüoº©úg©ø_©öW©ôO©ý{©ýCôªõªóªB ´÷ªö ªHü`ӈ µ ÿë T¿ ñË TÀ@ùÈ
@ù ?ÖhB øµ ñAÿÿT ¿ ñ T¿" ñ" T Ò9 ÿ ± T¿ ñ 6k T ÒèWª HªHª!HªAHªHªÀ"@© ?Ö ëÿÿTz8ø ëáþÿTi ¿ ñD 6Ë T ÒèWª HªHª!HªAHª ý`Ó9*À@ùÈ
@ù ?Ö
khÿÿThB(z8ø ëÁþÿTR ¨ò}`N êª ? ¬J! ñ¡ÿÿT ë T©ˈ
ø) ñÁÿÿTB ¿ ñ TÀ"@© ?Ö øµ ñaÿÿT9 T Òù è7ª ٚ:¡ z8ø ë TÀ"@© ?Ö ||ٛ?ëÈþÿT_ ëþÿTÀ"@© ?Ö|_ëÿÿT|ٛíÿÿ« T Òù ú7* hHz8ø ë TÀ@ùÈ
@ù ?Öè *}ÿk£þÿTI Ù;ék)þÿTÀ@ùÈ
@ù ?Öè *}kHÿÿTéÿÿý{E©ôOD©öWC©ø_B©úgA©üoƨÀ_Öüoº©úg©ø_©öW©ôO©ý{©ýCôªõªóª 4÷ªö ª_ 1À T¿ ñÄ 6K
T Òè*Hª HªHª!Hª ýPÓ9*À@ùÈ
@ù ?Ö
khÿÿT z8¸ ëÁþÿT> ¿ ñ T¿B ñb T Ò3 ¿ ñË TÀ@ùÈ
@ù ?Ö F ¸µ ñAÿÿT. « T Òù ú7* ý`Ó z8¸ ë` TÀ@ùÈ
@ù ?Öè *} kþÿTI Ù;ék þÿTÀ@ùÈ
@ù ?Öè *}kHÿÿTèÿÿ¨î|`N êª ? ¬JA ñ¡ÿÿT ëÀ T©ˈ
E ¸) ñÁÿÿTý{E©ôOD©öWC©ø_B©úgA©üoƨÀ_Öúg»©ø_©öW©ôO©ý{©ýôªõªóªÂ 4÷ªö ªèÿR_ kà T¿ ñD 6« T Ò R Ré*)Iª) Iª)Iª*ýHÓY * |S Q
ÿ")k" Thÿÿ5À@ùÈ
@ù ?Ö( R
ÿ")k#ÿÿT) z8x ëþÿT` ¿ ñË T¿ ñ¢ T ÒU ¿ ñ T R R |S Q & xµ ñà THÿÿ5À@ùÈ
@ù ?Ö( R & xµ ñÿÿTE T Ò R Ré 9= é7*)= * ÙW¥ iBI z8x ë T( 4 |S Q < )}*= _kþÿT
À@ùÈ
@ù ?Ö( R < )}*= _kBýÿT_kC TçÿÿÀ@ùÈ
@ù ?Ö( R < )}ÿ")kéûÿTÿÿ4 |S Q < )}ÿ")kHÿÿT×ÿÿ¨ê{`N êª ? ¬J ñ¡ÿÿT ëÀ T©ˈ% x) ñÁÿÿTý{D©ôOC©öWB©ø_A©úgŨÀ_Öúg»©ø_©öW©ôO©ý{©ýóªôªõª 4÷ªö ª_üq` T ñÄ 6K T Ò R Ré*)Iª) Iª*ýDÓY * |S Q
ÿ)k" Thÿÿ5À@ùÈ
@ù ?Öh R
ÿ)k#ÿÿT) ij88 ëþÿTV ñ
Tàªáªâªý{D©ôOC©öWB©ø_A©úgŨÅ ñ+ T R R |S Q i 8 ñ THÿÿ5À@ùÈ
@ù ?Öh R i 8 ñÿÿT6 « T Ò R Ré 9 é7*) * ÙW¥ ©"I ij88 ëÀ T( 4 |S Q )}* _kþÿT
À@ùÈ
@ù ?Öh R )}* _kBýÿT_k Tçÿÿ |S Q )}ÿ)k)üÿTHÿÿ5À@ùÈ
@ù ?Öh R )}ÿ)kÿÿT×ÿÿý{D©ôOC©öWB©ø_A©úgŨÀ_ÖöW½©ôO©ý{©ý ñë Tôªóª 4õ ª R R @ù¨
@ù ?ÖèR 8s ñ Tÿÿ4 |S Q 8s ñAÿÿTý{B©ôOA©öWèÀ_Öàªâªý{B©ôOA©öWèO í3¸më+mé#múg©ø_©öW©ôO©ý{©ýÃóªôªõª Ñ? ñk Töª÷ªø ªn ä /
l Ðg úª n à@ý l ´!Á" a T Ò@ ùµ ˿ ñk Tà@ü9` Z# 9 ñ!þÿT# j H T¡ba 0 k Tàªáªâª°øÿìÿÿ 9` ¡ba 0 k h Tàªáªâª¦øÿ
àªáªâª÷ÿÝÿÿàªáªâªüöÿ Ë×ÿÿ¿ ñk T øý{G©ôOF©öWE©ø_D©úgC©é#Bmë+Amí3ÈlÀ_Öí3»më+mé#môO©ý{©ýó ª@¹H 4`
@ý
¹
ùý{D©ôOC©é#Bmë+Amí3ÅlÀ_Ö ~
` n h@ù @ù
@ù ?ÖL%@ h@ù @ù
@ù ?ÖM%@ m L !k jþÿT!` þÿT A` ½ p ` h Àa l a
ý( Rh
¹ m ý{D©ôOC©é#Bmë+Amí3ÅlÀ_Öý{¿©ý @ù @ù
@ù ?Ön 8` ¥ @a ý{hÀ_ÖÿÑï;mí3më+mé#môO©ý{©ýÃó ª n i ! Th@ù @ù
@ù ?Ö 9` @a @` ` ä / T
n !j
T4 R
b 8i h @` @9h I Ah a9i a i
Th@ù @ù
@ù ?Ö @` h@ù @ù
@ù ?Ö@9` n @a @9h 0!` ÈüÿTAh A` k ¨ýÿTV a @` 9` (R b á ý a Àa L`
~ ` p ´ÒÔ_¶òtOÞòôçòh
@¹ Rk
@ý
¹
ù)K ` è T(ÿÿ5h@ù @ù
@ù ?ÖÉ5@ h@ù @ù
@ù ?ÖË5@ ` k (I !j jþÿT!` þÿT A` 8 à ` h Àa i a
ý( Rh
¹ k )K ` iüÿT` (` h@ù @ù
@ù ?Öa k gBa !¨B a $ T à ý l k à ýI9h A` )` á@ý ` á @ý K á@ý0 ` Å÷ÿTà@ý h ý{G©ôOF©é#Emë+Dmí3Cmï;BmÿÀ_Öé#¾mý{©ýC (@` aÿÿ ` ý{A©é#ÂlÀ_Öé#¾mý{©ýC @` @ù @ù
@ù ?Ön 8` ó @a h á ( Rb 8a ý{A©é#ÂlÀ_Ö ` a T ä /À_Öé#¾mý{©ýC @` @ù @ù
@ù ?Ö n 9` Û @a !h ð ý{A©é#ÂlÀ_Öë+½mé#mý{©ý @` ( R b @ù @ù
@ù ?Ö
n @9` Ç · 9` Ah Û ý{B©é#Amë+ÃlÀ_Öé#¾mý{©ýC ` h ÿÿ ` ý{A©é#ÂlÀ_Öé#¾mý{©ýC @` @ù @ùઠ?Ö @a ® p ` Àa ` ý{A©é#ÂlÀ_Öï;ºmí3më+mé#môO©ý{©ýC @` ó ªàb ` á T` h àªóþÿ ` D (@` ( R b i Å T b 9` ` k àªæþÿj ` h
@¹È 4`
@ý
¹
ù/ `@ù
` j SôÿøÓ b )` j àªÕþÿ@ ` !h Tø¯R ' À" ! ~
n h@ù @ù
@ù ?Ön1@ h@ù @ù
@ù ?Öo1@ à o ÉN 0!m jþÿT(!` þÿT A` [ p ` i Àa n a
ý( Rh
¹ o Áa (a (@ ý{E©ôOD©é#Cmë+Bmí3Amï;ÆlÀ_Öë+¼mé#môO©ý{©ýÃ (@` @` ó ªA@` ÿÿ
h ` k àªþÿ` ` i @` ý{C©ôOB©é#Amë+ÄlÀ_ÖÿÃÑï;mí3më+mé#môO©ý{©ý)@` @` ó ªH R b a ` @¹¨ 4`
@ý
¹
ù! ã ý ~
` n h@ù @ù
@ù ?֯1@ h@ù @ù
@ù ?֫1@ ` k êO P!n jþÿTH!` þÿT@A` p ` j Àa o a
ý( Rh
¹ k ã@ý ` ` Rb !i ` !@ !Àa 8a i @ h@ù @ù
@ù ?Ö)i a a h T A` h i ý{F©ôOE©é#Dmë+Cmí3Bmï;AmÿÃÀ_Öï;ºmí3më+mé#môO©ý{©ýC(@` @` ó ª@¹¨ 4`
@ý
¹
ù ~ `
n h@ù @ù
@ù ?֎-@ h@ù @ù
@ù ?֏-@ à o ÊN P!m jþÿTH!` þÿT@A` ¹ p ` j Àa n a
ý( Rh
¹ o %@ ý{E©ôOD©é#Cmë+Bmí3Amï;ÆlÀ_Öï;ºmí3më+mé#môO©ý{©ýC(@` @` ó ª@¹¨ 4`
@ý
¹
ù ~ `
n h@ù @ù
@ù ?֎-@ h@ù @ù
@ù ?֏-@ à o ÊN P!m jþÿTH!` þÿT@A` p ` j Àa n a
ý( Rh
¹ o %@ i ý{E©ôOD©é#Cmë+Bmí3Amï;ÆlÀ_Öï;ºmí3më+mé#môO©ý{©ýC@` ó ª@¹¨ 4i
@ý
¹
ù
~ ` n h@ù @ù
@ù ?Öm)@ h@ù @ù
@ù ?Ön)@ À n ©M 0!l jþÿT(!` þÿT A` M p ` i Àa m a
ý( Rh
¹ n T Rb ` àªýÿb a !Àa !i Àa ` ý{E©ôOD©é#Cmë+Bmí3Amï;ÆlÀ_Öé#½môO©ý{©ý ó ª( Rb B8a Ha ýÿ ` `@ùý{B©ôOA©é#Ãlùòÿï;ºmí3më+mé#môO©ý{©ýCó ª@¹h 4i
@ý
¹
~ ` n
ùh@ù @ù
@ù ?Öm)@ h@ù @ù
@ù ?Ön)@ À n ¨M !l jþÿT!` þÿT A` p ` h Àa m a
ý( Rh
¹ n ~
` n h@ù @ù
@ù ?ÖK%@ h@ù @ù
@ù ?ÖM%@ m hK !l jþÿT!` þÿT A` á p ` h Àa k )m
¹
ù ` ý{E©ôOD©é#Cmë+Bmí3Amï;ÆlÀ_Öí3»më+mé#môO©ý{©ý(@` @` ó ª n 0!` T!` H T
n h@ù @ù
@ù ?Ö
@` h@ù @ù
@ù ?Ö @` ¡i @A` Í @` ¡h `A` É )` 0 m ¨ýÿT)` âb 0 b
T)` ` ý{D©ôOC©é#Bmë+Amí3ÅlÀ_ÖઠA` þüÿ @` ઠA` úüÿ )` ` ý{D©ôOC©é#Bmë+Amí3ÅlÀ_Ö@A` i `A` h 0!` !Í` (9a 8a A` x
@` A` u @)` 9` q ý{D©ôOC©é#Bmë+Amí3ÅlÀ_Öë+¼mé#môO©ý{©ýÃ (@` @` ó ª
` j Îüÿ@ ` h j àªÉüÿ@ ` i `` ý{C©ôOB©é#Amë+ÄlÀ_Öé#¾mý{©ýC @` @ù @ù
@ù ?Ön 8` W @a ` ý{A©é#ÂlÀ_ÖôO¾©ý{©ýC óªl a H Taba Ðg 0 b H Táªý{A©ôO¨ëôÿn 8` aba Ðg 0 b h Táªâôÿ` Ëý{A©ôO¨À_Öáªý{A©ôO¨:óÿáª8óÿ` Ëý{A©ôO¨À_ÖÿÃÑï;mí3më+mé#müo©úg©ø_©öW©ôO ©ý{
©ýóªõªôªö ª, ñ
T뛲¨ Ë?ëé ù8±`bb a n !9` bl J @ Ë"bdbBd @` a Ñ!b a (c
Àa I#҉wºòi}Øòýçò g sÒiæ§ò©YÎòiÿçò!g âby #b+ M @c b a @e x bÊîÿ@` ( Ë bÆîÿ)` è Ë bÂîÿ)` HË b¼îÿ )` ë³ b (i R!b !(M !@e a E T b
(i " ñ« T ҿ먲bø˹ A` 8!` í TÀ@ùÈ@ù ?Ö(b!a (a @e ¸á^ Øa^)9` ÷ Ñ ë!þÿT 9i xi˿ë? b (M
@e l q ; RÀ@ùÈ@ù ?Ö@` À@ùÈ@ù ?Ö 8n ` ` h @)` ` þÿT m JþÿT @e x bvîÿ @` ( Ë brîÿ))` Ëè bmîÿ))` biîÿ )` 9` b 8h =@ i T 9i ` ab a úÿT A` w ` ` i ÈùÿTëèËê@ù_ë ± Òý{J©ôOI©öWH©ø_G©úgF©üoE©é#Dmë+Cmí3Bmï;AmÿÃÀ_Ö5ñÿöÿé#¾mý{©ýC @` èó ²¨úçò g!` « T A` ý{A©é#Âlöÿ @ù @ùઠ?Ö @a M @` ( R b 8h E ` Àd xý{A©é#ÂlÀ_Öûÿí3ºmë+mé#möW©ôO©ý{©ýC a Tø¯R ' À" x )@` @` ó ªHÒF¼òÈ1Ïò¨Èçò g0 ` TH Rb `@ùh@ù ?Ö( Rb
` £
҈ªòh?Äò(èòg ` _ ( Òh ±ò¨ßòÜçò g0!` ¥ T n i (i ( R b Rb !i ! I !Àa (a H Rb Ca cÀa !8c Ci !c A Aa a £
Ҕªòt?Äò4èò5 RV R`@ùh@ù ?ցg ` Ý ¡b a@ `)` *` `9j , ` `@ùh@ù ?ÖÁb !8l a âb 0 b * T` Þ ¡b (a 8l áb a üÿT`@ùh@ù ?Ö @` @A` ½ l 0!a @a L` (h áb a óG À` £
҈ªòh?Äò(èòg (h H Rb !h ¹ 8h 7 b a ý{E©ôOD©öWC©é#Bmë+Amí3ÆlÀ_Öï;ºmí3më+mé#môO©ý{©ýC@` ó ª
n 9` § @` `@ùh@ù ?Ö h 4 Rê T
@` `@ùh@ù ?Ö
@` h ê T`@ùh@ù ?Ö ` «9` ` k P!` ( Tb @A` @` `A` ` À)` @e x ñËüÿTH!` üÿTôª P!k 跟 q( Ràªý{E©ôOD©é#Cmë+Bmí3Amï;ÆlÀ_ @ù @ù
@ù @ù @ù @ù @ù @ù "@ù &@ù *@ù .@ù 2@ù 6@ù :@ù >@ù B@ù F@ù J@ù N@ù R@ù V@ù Z@ù ^@ù b@ù f@ù j@ù n@ù r@ù v@ù z@ù ~@ù @ù @ù @ù @ù @ù @ù @ù @ù ¢@ù ¦@ù ª@ù ®@ù ²@ù ¶@ù º@ù ¾@ù Â@ù Æ@ù Ê@ù Î@ù Ò@ù Ö@ù Ú@ù Þ@ù â@ù æ@ù ê@ù î@ù ò@ù ö@ù ú@ù þ@ù Aù Aù
Aù Aù Aù Aù Aù Aù "Aù &Aù *Aù .Aù 2Aù 6Aù :Aù >Aù BAù FAù JAù NAù RAù VAù ZAù ^Aù bAù fAù jAù nAù rAù vAù zAù ~Aù Aù Aù Aù Aù Aù Aù Aù Aù ¢Aù ¦Aù ªAù ®Aù ²Aù ¶Aù ºAù ¾Aù ÂAù ÆAù ÊAù ÎAù ÒAù ÖAù ÚAù ÞAù âAù æAù êAù îAù òAù öAù úAù þAù Bù Bù
Bù Bù Bù ֑ 1¢ðG¿©p ~@ù ÖP ùÿÿ P öÿÿ! P óÿÿ6 P ðÿÿO P íÿÿk P êÿÿ P çÿÿ P äÿÿ° P áÿÿà P Þÿÿß P Ûÿÿþ P Øÿÿ P Õÿÿ# P Òÿÿ9 P ÏÿÿU P Ìÿÿh P Éÿÿ{ P Æÿÿ P Ãÿÿ¯ P ÀÿÿÓ P ½ÿÿô P ºÿÿ P ·ÿÿ# P ´ÿÿ; P ±ÿÿP P ®ÿÿi P «ÿÿ P ¨ÿÿ P ¥ÿÿÁ P ¢ÿÿâ P ÿÿû P ÿÿ P ÿÿ* P ÿÿ? P ÿÿS P ÿÿn P ÿÿ P ÿÿ¨ P ÿÿÆ P ÿÿï P ÿÿ P ~ÿÿ& P {ÿÿ= P xÿÿP P uÿÿf P rÿÿ P oÿÿ P lÿÿ² P iÿÿÌ P fÿÿá P cÿÿ÷ P `ÿÿ P ]ÿÿ) P ZÿÿB P Wÿÿ] P Tÿÿr P Qÿÿ P Nÿÿ± P KÿÿÈ P HÿÿÞ P Eÿÿø P Bÿÿ P ?ÿÿ- P <ÿÿC P 9ÿÿY P 6ÿÿ P 3ÿÿ P 0ÿÿ» P -ÿÿ× P *ÿÿð P 'ÿÿ P $ÿÿ( P !ÿÿA P ÿÿW P ÿÿs P ÿÿ P ÿÿ P ÿÿ½ P ÿÿÖ P ÿÿõ P ÿÿ P ÿÿ$ P ÿÿD P ÿÿ` P ýþÿx P úþÿ P ÷þÿ¥ P ôþÿ¿ P ñþÿØ P îþÿì P ëþÿ P èþÿ P åþÿ2 P âþÿG P ßþÿ` P Üþÿz P Ùþÿ P Öþÿ¬ P ÓþÿÅ P Ðþÿâ P Íþÿÿ P Êþÿ#
P ÇþÿF
P Äþÿ\
P Áþÿ
P ¾þÿ¥
P »þÿÃ
P ¸þÿá
P µþÿ P ²þÿ P ¯þÿH P ¬þÿe P ©þÿ P ¦þÿ P £þÿÆ P þÿÚ P þÿó P þÿ P þÿ P þÿ P þÿ% P þÿ3 P þÿ@ P þÿM P
þÿY P þÿg P þÿv P |þÿ P yþÿ P vþÿ¡ P sþÿ° P pþÿ¿ P mþÿË 9A`
YxR OTYd GLQ INl HMR MTY 9A` AIQq 9A` 9A` HMR HMR HMR HMR 9A` @HQr 9Ba 8A_ AJTu DNmu} M@G numpy.random.mtrand numpy/random/mtrand.pyx Cannot take a larger sample than population when 'replace=False' DeprecationWarning Fewer non-zero entries in p than size ImportError IndexError Invalid bit generator. The bit generator must be instantized. _MT19937 MT19937 Negative dimensions are not allowed OverflowError Providing a dtype with a non-native byteorder is not supported. If you require platform-independent byteorder, call byteswap when required.
In future version, providing byteorder will raise a ValueError RandomState RandomState.binomial (line 3353) RandomState.bytes (line 805) RandomState.chisquare (line 1910) RandomState.choice (line 841) RandomState.dirichlet (line 4394) RandomState.exponential (line 500) RandomState.f (line 1729) RandomState.gamma (line 1645) RandomState.geometric (line 3772) RandomState.gumbel (line 2764) RandomState.hypergeometric (line 3834) RandomState.laplace (line 2670) RandomState.logistic (line 2888) RandomState.lognormal (line 2974) RandomState.logseries (line 3969) RandomState.multinomial (line 4257) RandomState.multivariate_normal (line 4058) RandomState.negative_binomial (line 3505) RandomState.noncentral_chisquare (line 1986) RandomState.noncentral_f (line 1823) RandomState.normal (line 1454) RandomState.pareto (line 2354) RandomState.permutation (line 4668) RandomState.poisson (line 3593) RandomState.power (line 2561) RandomState.rand (line 1177) RandomState.randint (line 679) RandomState.randn (line 1221) RandomState.random_integers (line 1289) RandomState.random_sample (line 385) RandomState.rayleigh (line 3090) RandomState.seed (line 228) RandomState.shuffle (line 4543) RandomState.standard_cauchy (line 2075) RandomState.standard_exponential (line 577) RandomState.standard_gamma (line 1563) RandomState.standard_normal (line 1385) RandomState.standard_t (line 2150) RandomState.tomaxint (line 621) RandomState.triangular (line 3244) RandomState.uniform (line 1050) RandomState.vonmises (line 2265) RandomState.wald (line 3167) RandomState.weibull (line 2457) RandomState.zipf (line 3676) Range exceeds valid bounds RuntimeWarning Sequence Shuffling a one dimensional array subclass containing objects gives incorrect results for most array subclasses. Please use the new random number API instead: https://numpy.org/doc/stable/reference/random/index.html
The new API fixes this issue. This version will not be fixed due to stability guarantees of the API. T This function is deprecated. Please call randint(1, {low} + 1) instead This function is deprecated. Please call randint({low}, {high} + 1) instead TypeError Unsupported dtype %r for randint UserWarning ValueError ( ) * . ? a 'a' and 'p' must have same size 'a' cannot be empty unless no samples are taken a must be 1-dimensional a must be 1-dimensional or an integer a must be greater than 0 unless no samples are taken add all __all__ allclose alpha alpha <= 0 any arange args array array is read-only asarray astype at 0x{:X} atol b bg_type
binomial(n, p, size=None)
Draw samples from a binomial distribution.
Samples are drawn from a binomial distribution with specified
parameters, n trials and p probability of success where
n an integer >= 0 and p is in the interval [0,1]. (n may be
input as a float, but it is truncated to an integer in use)
.. note::
New code should use the `~numpy.random.Generator.binomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : int or array_like of ints
Parameter of the distribution, >= 0. Floats are also accepted,
but they will be truncated to integers.
p : float or array_like of floats
Parameter of the distribution, >= 0 and <=1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``n`` and ``p`` are both scalars.
Otherwise, ``np.broadcast(n, p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized binomial distribution, where
each sample is equal to the number of successes over the n trials.
See Also
--------
scipy.stats.binom : probability density function, distribution or
cumulative density function, etc.
random.Generator.binomial: which should be used for new code.
Notes
-----
The probability density for the binomial distribution is
.. math:: P(N) = \binom{n}{N}p^N(1-p)^{n-N},
where :math:`n` is the number of trials, :math:`p` is the probability
of success, and :math:`N` is the number of successes.
When estimating the standard error of a proportion in a population by
using a random sample, the normal distribution works well unless the
product p*n <=5, where p = population proportion estimate, and n =
number of samples, in which case the binomial distribution is used
instead. For example, a sample of 15 people shows 4 who are left
handed, and 11 who are right handed. Then p = 4/15 = 27%. 0.27*15 = 4,
so the binomial distribution should be used in this case.
References
----------
.. [1] Dalgaard, Peter, "Introductory Statistics with R",
Springer-Verlag, 2002.
.. [2] Glantz, Stanton A. "Primer of Biostatistics.", McGraw-Hill,
Fifth Edition, 2002.
.. [3] Lentner, Marvin, "Elementary Applied Statistics", Bogden
and Quigley, 1972.
.. [4] Weisstein, Eric W. "Binomial Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/BinomialDistribution.html
.. [5] Wikipedia, "Binomial distribution",
https://en.wikipedia.org/wiki/Binomial_distribution
Examples
--------
Draw samples from the distribution:
>>> n, p = 10, .5 # number of trials, probability of each trial
>>> s = np.random.binomial(n, p, 1000)
# result of flipping a coin 10 times, tested 1000 times.
A real world example. A company drills 9 wild-cat oil exploration
wells, each with an estimated probability of success of 0.1. All nine
wells fail. What is the probability of that happening?
Let's do 20,000 trials of the model, and count the number that
generate zero positive results.
>>> sum(np.random.binomial(9, 0.1, 20000) == 0)/20000.
# answer = 0.38885, or 38%.
bit_generator bitgen bool_
bytes(length)
Return random bytes.
.. note::
New code should use the `~numpy.random.Generator.bytes`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
length : int
Number of random bytes.
Returns
-------
out : bytes
String of length `length`.
See Also
--------
random.Generator.bytes: which should be used for new code.
Examples
--------
>>> np.random.bytes(10)
b' eh\x85\x022SZ\xbf\xa4' #random
can only re-seed a MT19937 BitGenerator capsule casting check_valid check_valid must equal 'warn', 'raise', or 'ignore'
chisquare(df, size=None)
Draw samples from a chi-square distribution.
When `df` independent random variables, each with standard normal
distributions (mean 0, variance 1), are squared and summed, the
resulting distribution is chi-square (see Notes). This distribution
is often used in hypothesis testing.
.. note::
New code should use the `~numpy.random.Generator.chisquare`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Number of degrees of freedom, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` is a scalar. Otherwise,
``np.array(df).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized chi-square distribution.
Raises
------
ValueError
When `df` <= 0 or when an inappropriate `size` (e.g. ``size=-1``)
is given.
See Also
--------
random.Generator.chisquare: which should be used for new code.
Notes
-----
The variable obtained by summing the squares of `df` independent,
standard normally distributed random variables:
.. math:: Q = \sum_{i=0}^{\mathtt{df}} X^2_i
is chi-square distributed, denoted
.. math:: Q \sim \chi^2_k.
The probability density function of the chi-squared distribution is
.. math:: p(x) = \frac{(1/2)^{k/2}}{\Gamma(k/2)}
x^{k/2 - 1} e^{-x/2},
where :math:`\Gamma` is the gamma function,
.. math:: \Gamma(x) = \int_0^{-\infty} t^{x - 1} e^{-t} dt.
References
----------
.. [1] NIST "Engineering Statistics Handbook"
https://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htm
Examples
--------
>>> np.random.chisquare(2,4)
array([ 1.89920014, 9.00867716, 3.13710533, 5.62318272]) # random
choice(a, size=None, replace=True, p=None)
Generates a random sample from a given 1-D array
.. versionadded:: 1.7.0
.. note::
New code should use the `~numpy.random.Generator.choice`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : 1-D array-like or int
If an ndarray, a random sample is generated from its elements.
If an int, the random sample is generated as if it were ``np.arange(a)``
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
replace : boolean, optional
Whether the sample is with or without replacement. Default is True,
meaning that a value of ``a`` can be selected multiple times.
p : 1-D array-like, optional
The probabilities associated with each entry in a.
If not given, the sample assumes a uniform distribution over all
entries in ``a``.
Returns
-------
samples : single item or ndarray
The generated random samples
Raises
------
ValueError
If a is an int and less than zero, if a or p are not 1-dimensional,
if a is an array-like of size 0, if p is not a vector of
probabilities, if a and p have different lengths, or if
replace=False and the sample size is greater than the population
size
See Also
--------
randint, shuffle, permutation
random.Generator.choice: which should be used in new code
Notes
-----
Setting user-specified probabilities through ``p`` uses a more general but less
efficient sampler than the default. The general sampler produces a different sample
than the optimized sampler even if each element of ``p`` is 1 / len(a).
Sampling random rows from a 2-D array is not possible with this function,
but is possible with `Generator.choice` through its ``axis`` keyword.
Examples
--------
Generate a uniform random sample from np.arange(5) of size 3:
>>> np.random.choice(5, 3)
array([0, 3, 4]) # random
>>> #This is equivalent to np.random.randint(0,5,3)
Generate a non-uniform random sample from np.arange(5) of size 3:
>>> np.random.choice(5, 3, p=[0.1, 0, 0.3, 0.6, 0])
array([3, 3, 0]) # random
Generate a uniform random sample from np.arange(5) of size 3 without
replacement:
>>> np.random.choice(5, 3, replace=False)
array([3,1,0]) # random
>>> #This is equivalent to np.random.permutation(np.arange(5))[:3]
Generate a non-uniform random sample from np.arange(5) of size
3 without replacement:
>>> np.random.choice(5, 3, replace=False, p=[0.1, 0, 0.3, 0.6, 0])
array([2, 3, 0]) # random
Any of the above can be repeated with an arbitrary array-like
instead of just integers. For instance:
>>> aa_milne_arr = ['pooh', 'rabbit', 'piglet', 'Christopher']
>>> np.random.choice(aa_milne_arr, 5, p=[0.5, 0.1, 0.1, 0.3])
array(['pooh', 'pooh', 'pooh', 'Christopher', 'piglet'], # random
dtype='<U11')
__class__ __class_getitem__ cline_in_traceback collections.abc copy count_nonzero cov cov must be 2 dimensional and square covariance is not symmetric positive-semidefinite. cumsum df dfden dfnum
dirichlet(alpha, size=None)
Draw samples from the Dirichlet distribution.
Draw `size` samples of dimension k from a Dirichlet distribution. A
Dirichlet-distributed random variable can be seen as a multivariate
generalization of a Beta distribution. The Dirichlet distribution
is a conjugate prior of a multinomial distribution in Bayesian
inference.
.. note::
New code should use the `~numpy.random.Generator.dirichlet`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
alpha : sequence of floats, length k
Parameter of the distribution (length ``k`` for sample of
length ``k``).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
vector of length ``k`` is returned.
Returns
-------
samples : ndarray,
The drawn samples, of shape ``(size, k)``.
Raises
------
ValueError
If any value in ``alpha`` is less than or equal to zero
See Also
--------
random.Generator.dirichlet: which should be used for new code.
Notes
-----
The Dirichlet distribution is a distribution over vectors
:math:`x` that fulfil the conditions :math:`x_i>0` and
:math:`\sum_{i=1}^k x_i = 1`.
The probability density function :math:`p` of a
Dirichlet-distributed random vector :math:`X` is
proportional to
.. math:: p(x) \propto \prod_{i=1}^{k}{x^{\alpha_i-1}_i},
where :math:`\alpha` is a vector containing the positive
concentration parameters.
The method uses the following property for computation: let :math:`Y`
be a random vector which has components that follow a standard gamma
distribution, then :math:`X = \frac{1}{\sum_{i=1}^k{Y_i}} Y`
is Dirichlet-distributed
References
----------
.. [1] David McKay, "Information Theory, Inference and Learning
Algorithms," chapter 23,
http://www.inference.org.uk/mackay/itila/
.. [2] Wikipedia, "Dirichlet distribution",
https://en.wikipedia.org/wiki/Dirichlet_distribution
Examples
--------
Taking an example cited in Wikipedia, this distribution can be used if
one wanted to cut strings (each of initial length 1.0) into K pieces
with different lengths, where each piece had, on average, a designated
average length, but allowing some variation in the relative sizes of
the pieces.
>>> s = np.random.dirichlet((10, 5, 3), 20).transpose()
>>> import matplotlib.pyplot as plt
>>> plt.barh(range(20), s[0])
>>> plt.barh(range(20), s[1], left=s[0], color='g')
>>> plt.barh(range(20), s[2], left=s[0]+s[1], color='r')
>>> plt.title("Lengths of Strings")
disable dot empty empty_like enable __enter__ eps equal __exit__
exponential(scale=1.0, size=None)
Draw samples from an exponential distribution.
Its probability density function is
.. math:: f(x; \frac{1}{\beta}) = \frac{1}{\beta} \exp(-\frac{x}{\beta}),
for ``x > 0`` and 0 elsewhere. :math:`\beta` is the scale parameter,
which is the inverse of the rate parameter :math:`\lambda = 1/\beta`.
The rate parameter is an alternative, widely used parameterization
of the exponential distribution [3]_.
The exponential distribution is a continuous analogue of the
geometric distribution. It describes many common situations, such as
the size of raindrops measured over many rainstorms [1]_, or the time
between page requests to Wikipedia [2]_.
.. note::
New code should use the `~numpy.random.Generator.exponential`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
scale : float or array_like of floats
The scale parameter, :math:`\beta = 1/\lambda`. Must be
non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``scale`` is a scalar. Otherwise,
``np.array(scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized exponential distribution.
Examples
--------
A real world example: Assume a company has 10000 customer support
agents and the average time between customer calls is 4 minutes.
>>> n = 10000
>>> time_between_calls = np.random.default_rng().exponential(scale=4, size=n)
What is the probability that a customer will call in the next
4 to 5 minutes?
>>> x = ((time_between_calls < 5).sum())/n
>>> y = ((time_between_calls < 4).sum())/n
>>> x-y
0.08 # may vary
See Also
--------
random.Generator.exponential: which should be used for new code.
References
----------
.. [1] Peyton Z. Peebles Jr., "Probability, Random Variables and
Random Signal Principles", 4th ed, 2001, p. 57.
.. [2] Wikipedia, "Poisson process",
https://en.wikipedia.org/wiki/Poisson_process
.. [3] Wikipedia, "Exponential distribution",
https://en.wikipedia.org/wiki/Exponential_distribution
f(dfnum, dfden, size=None)
Draw samples from an F distribution.
Samples are drawn from an F distribution with specified parameters,
`dfnum` (degrees of freedom in numerator) and `dfden` (degrees of
freedom in denominator), where both parameters must be greater than
zero.
The random variate of the F distribution (also known as the
Fisher distribution) is a continuous probability distribution
that arises in ANOVA tests, and is the ratio of two chi-square
variates.
.. note::
New code should use the `~numpy.random.Generator.f`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
dfnum : float or array_like of floats
Degrees of freedom in numerator, must be > 0.
dfden : float or array_like of float
Degrees of freedom in denominator, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``dfnum`` and ``dfden`` are both scalars.
Otherwise, ``np.broadcast(dfnum, dfden).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Fisher distribution.
See Also
--------
scipy.stats.f : probability density function, distribution or
cumulative density function, etc.
random.Generator.f: which should be used for new code.
Notes
-----
The F statistic is used to compare in-group variances to between-group
variances. Calculating the distribution depends on the sampling, and
so it is a function of the respective degrees of freedom in the
problem. The variable `dfnum` is the number of samples minus one, the
between-groups degrees of freedom, while `dfden` is the within-groups
degrees of freedom, the sum of the number of samples in each group
minus the number of groups.
References
----------
.. [1] Glantz, Stanton A. "Primer of Biostatistics.", McGraw-Hill,
Fifth Edition, 2002.
.. [2] Wikipedia, "F-distribution",
https://en.wikipedia.org/wiki/F-distribution
Examples
--------
An example from Glantz[1], pp 47-40:
Two groups, children of diabetics (25 people) and children from people
without diabetes (25 controls). Fasting blood glucose was measured,
case group had a mean value of 86.1, controls had a mean value of
82.2. Standard deviations were 2.09 and 2.49 respectively. Are these
data consistent with the null hypothesis that the parents diabetic
status does not affect their children's blood glucose levels?
Calculating the F statistic from the data gives a value of 36.01.
Draw samples from the distribution:
>>> dfnum = 1. # between group degrees of freedom
>>> dfden = 48. # within groups degrees of freedom
>>> s = np.random.f(dfnum, dfden, 1000)
The lower bound for the top 1% of the samples is :
>>> np.sort(s)[-10]
7.61988120985 # random
So there is about a 1% chance that the F statistic will exceed 7.62,
the measured value is 36, so the null hypothesis is rejected at the 1%
level.
finfo flags float64 format
gamma(shape, scale=1.0, size=None)
Draw samples from a Gamma distribution.
Samples are drawn from a Gamma distribution with specified parameters,
`shape` (sometimes designated "k") and `scale` (sometimes designated
"theta"), where both parameters are > 0.
.. note::
New code should use the `~numpy.random.Generator.gamma`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
shape : float or array_like of floats
The shape of the gamma distribution. Must be non-negative.
scale : float or array_like of floats, optional
The scale of the gamma distribution. Must be non-negative.
Default is equal to 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``shape`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(shape, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized gamma distribution.
See Also
--------
scipy.stats.gamma : probability density function, distribution or
cumulative density function, etc.
random.Generator.gamma: which should be used for new code.
Notes
-----
The probability density for the Gamma distribution is
.. math:: p(x) = x^{k-1}\frac{e^{-x/\theta}}{\theta^k\Gamma(k)},
where :math:`k` is the shape and :math:`\theta` the scale,
and :math:`\Gamma` is the Gamma function.
The Gamma distribution is often used to model the times to failure of
electronic components, and arises naturally in processes for which the
waiting times between Poisson distributed events are relevant.
References
----------
.. [1] Weisstein, Eric W. "Gamma Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/GammaDistribution.html
.. [2] Wikipedia, "Gamma distribution",
https://en.wikipedia.org/wiki/Gamma_distribution
Examples
--------
Draw samples from the distribution:
>>> shape, scale = 2., 2. # mean=4, std=2*sqrt(2)
>>> s = np.random.gamma(shape, scale, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> import scipy.special as sps # doctest: +SKIP
>>> count, bins, ignored = plt.hist(s, 50, density=True)
>>> y = bins**(shape-1)*(np.exp(-bins/scale) / # doctest: +SKIP
... (sps.gamma(shape)*scale**shape))
>>> plt.plot(bins, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
gauss gc
geometric(p, size=None)
Draw samples from the geometric distribution.
Bernoulli trials are experiments with one of two outcomes:
success or failure (an example of such an experiment is flipping
a coin). The geometric distribution models the number of trials
that must be run in order to achieve success. It is therefore
supported on the positive integers, ``k = 1, 2, ...``.
The probability mass function of the geometric distribution is
.. math:: f(k) = (1 - p)^{k - 1} p
where `p` is the probability of success of an individual trial.
.. note::
New code should use the `~numpy.random.Generator.geometric`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
p : float or array_like of floats
The probability of success of an individual trial.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``p`` is a scalar. Otherwise,
``np.array(p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized geometric distribution.
See Also
--------
random.Generator.geometric: which should be used for new code.
Examples
--------
Draw ten thousand values from the geometric distribution,
with the probability of an individual success equal to 0.35:
>>> z = np.random.geometric(p=0.35, size=10000)
How many trials succeeded after a single run?
>>> (z == 1).sum() / 10000.
0.34889999999999999 #random
get get_state and legacy can only be used with the MT19937 BitGenerator. To silence this warning, set `legacy` to False. greater
gumbel(loc=0.0, scale=1.0, size=None)
Draw samples from a Gumbel distribution.
Draw samples from a Gumbel distribution with specified location and
scale. For more information on the Gumbel distribution, see
Notes and References below.
.. note::
New code should use the `~numpy.random.Generator.gumbel`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
The location of the mode of the distribution. Default is 0.
scale : float or array_like of floats, optional
The scale parameter of the distribution. Default is 1. Must be non-
negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Gumbel distribution.
See Also
--------
scipy.stats.gumbel_l
scipy.stats.gumbel_r
scipy.stats.genextreme
weibull
random.Generator.gumbel: which should be used for new code.
Notes
-----
The Gumbel (or Smallest Extreme Value (SEV) or the Smallest Extreme
Value Type I) distribution is one of a class of Generalized Extreme
Value (GEV) distributions used in modeling extreme value problems.
The Gumbel is a special case of the Extreme Value Type I distribution
for maximums from distributions with "exponential-like" tails.
The probability density for the Gumbel distribution is
.. math:: p(x) = \frac{e^{-(x - \mu)/ \beta}}{\beta} e^{ -e^{-(x - \mu)/
\beta}},
where :math:`\mu` is the mode, a location parameter, and
:math:`\beta` is the scale parameter.
The Gumbel (named for German mathematician Emil Julius Gumbel) was used
very early in the hydrology literature, for modeling the occurrence of
flood events. It is also used for modeling maximum wind speed and
rainfall rates. It is a "fat-tailed" distribution - the probability of
an event in the tail of the distribution is larger than if one used a
Gaussian, hence the surprisingly frequent occurrence of 100-year
floods. Floods were initially modeled as a Gaussian process, which
underestimated the frequency of extreme events.
It is one of a class of extreme value distributions, the Generalized
Extreme Value (GEV) distributions, which also includes the Weibull and
Frechet.
The function has a mean of :math:`\mu + 0.57721\beta` and a variance
of :math:`\frac{\pi^2}{6}\beta^2`.
References
----------
.. [1] Gumbel, E. J., "Statistics of Extremes,"
New York: Columbia University Press, 1958.
.. [2] Reiss, R.-D. and Thomas, M., "Statistical Analysis of Extreme
Values from Insurance, Finance, Hydrology and Other Fields,"
Basel: Birkhauser Verlag, 2001.
Examples
--------
Draw samples from the distribution:
>>> mu, beta = 0, 0.1 # location and scale
>>> s = np.random.gumbel(mu, beta, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> plt.plot(bins, (1/beta)*np.exp(-(bins - mu)/beta)
... * np.exp( -np.exp( -(bins - mu) /beta) ),
... linewidth=2, color='r')
>>> plt.show()
Show how an extreme value distribution can arise from a Gaussian process
and compare to a Gaussian:
>>> means = []
>>> maxima = []
>>> for i in range(0,1000) :
... a = np.random.normal(mu, beta, 1000)
... means.append(a.mean())
... maxima.append(a.max())
>>> count, bins, ignored = plt.hist(maxima, 30, density=True)
>>> beta = np.std(maxima) * np.sqrt(6) / np.pi
>>> mu = np.mean(maxima) - 0.57721*beta
>>> plt.plot(bins, (1/beta)*np.exp(-(bins - mu)/beta)
... * np.exp(-np.exp(-(bins - mu)/beta)),
... linewidth=2, color='r')
>>> plt.plot(bins, 1/(beta * np.sqrt(2 * np.pi))
... * np.exp(-(bins - mu)**2 / (2 * beta**2)),
... linewidth=2, color='g')
>>> plt.show()
has_gauss high
hypergeometric(ngood, nbad, nsample, size=None)
Draw samples from a Hypergeometric distribution.
Samples are drawn from a hypergeometric distribution with specified
parameters, `ngood` (ways to make a good selection), `nbad` (ways to make
a bad selection), and `nsample` (number of items sampled, which is less
than or equal to the sum ``ngood + nbad``).
.. note::
New code should use the
`~numpy.random.Generator.hypergeometric`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
ngood : int or array_like of ints
Number of ways to make a good selection. Must be nonnegative.
nbad : int or array_like of ints
Number of ways to make a bad selection. Must be nonnegative.
nsample : int or array_like of ints
Number of items sampled. Must be at least 1 and at most
``ngood + nbad``.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if `ngood`, `nbad`, and `nsample`
are all scalars. Otherwise, ``np.broadcast(ngood, nbad, nsample).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized hypergeometric distribution. Each
sample is the number of good items within a randomly selected subset of
size `nsample` taken from a set of `ngood` good items and `nbad` bad items.
See Also
--------
scipy.stats.hypergeom : probability density function, distribution or
cumulative density function, etc.
random.Generator.hypergeometric: which should be used for new code.
Notes
-----
The probability density for the Hypergeometric distribution is
.. math:: P(x) = \frac{\binom{g}{x}\binom{b}{n-x}}{\binom{g+b}{n}},
where :math:`0 \le x \le n` and :math:`n-b \le x \le g`
for P(x) the probability of ``x`` good results in the drawn sample,
g = `ngood`, b = `nbad`, and n = `nsample`.
Consider an urn with black and white marbles in it, `ngood` of them
are black and `nbad` are white. If you draw `nsample` balls without
replacement, then the hypergeometric distribution describes the
distribution of black balls in the drawn sample.
Note that this distribution is very similar to the binomial
distribution, except that in this case, samples are drawn without
replacement, whereas in the Binomial case samples are drawn with
replacement (or the sample space is infinite). As the sample space
becomes large, this distribution approaches the binomial.
References
----------
.. [1] Lentner, Marvin, "Elementary Applied Statistics", Bogden
and Quigley, 1972.
.. [2] Weisstein, Eric W. "Hypergeometric Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/HypergeometricDistribution.html
.. [3] Wikipedia, "Hypergeometric distribution",
https://en.wikipedia.org/wiki/Hypergeometric_distribution
Examples
--------
Draw samples from the distribution:
>>> ngood, nbad, nsamp = 100, 2, 10
# number of good, number of bad, and number of samples
>>> s = np.random.hypergeometric(ngood, nbad, nsamp, 1000)
>>> from matplotlib.pyplot import hist
>>> hist(s)
# note that it is very unlikely to grab both bad items
Suppose you have an urn with 15 white and 15 black marbles.
If you pull 15 marbles at random, how likely is it that
12 or more of them are one color?
>>> s = np.random.hypergeometric(15, 15, 15, 100000)
>>> sum(s>=12)/100000. + sum(s<=3)/100000.
# answer = 0.003 ... pretty unlikely!
id ignore __import__ index _initializing int16 int32 int64 int8 intp isenabled isfinite isnan isnative isscalar issubdtype item itemsize kappa key kwargs l lam
laplace(loc=0.0, scale=1.0, size=None)
Draw samples from the Laplace or double exponential distribution with
specified location (or mean) and scale (decay).
The Laplace distribution is similar to the Gaussian/normal distribution,
but is sharper at the peak and has fatter tails. It represents the
difference between two independent, identically distributed exponential
random variables.
.. note::
New code should use the `~numpy.random.Generator.laplace`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
The position, :math:`\mu`, of the distribution peak. Default is 0.
scale : float or array_like of floats, optional
:math:`\lambda`, the exponential decay. Default is 1. Must be non-
negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Laplace distribution.
See Also
--------
random.Generator.laplace: which should be used for new code.
Notes
-----
It has the probability density function
.. math:: f(x; \mu, \lambda) = \frac{1}{2\lambda}
\exp\left(-\frac{|x - \mu|}{\lambda}\right).
The first law of Laplace, from 1774, states that the frequency
of an error can be expressed as an exponential function of the
absolute magnitude of the error, which leads to the Laplace
distribution. For many problems in economics and health
sciences, this distribution seems to model the data better
than the standard Gaussian distribution.
References
----------
.. [1] Abramowitz, M. and Stegun, I. A. (Eds.). "Handbook of
Mathematical Functions with Formulas, Graphs, and Mathematical
Tables, 9th printing," New York: Dover, 1972.
.. [2] Kotz, Samuel, et. al. "The Laplace Distribution and
Generalizations, " Birkhauser, 2001.
.. [3] Weisstein, Eric W. "Laplace Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/LaplaceDistribution.html
.. [4] Wikipedia, "Laplace distribution",
https://en.wikipedia.org/wiki/Laplace_distribution
Examples
--------
Draw samples from the distribution
>>> loc, scale = 0., 1.
>>> s = np.random.laplace(loc, scale, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> x = np.arange(-8., 8., .01)
>>> pdf = np.exp(-abs(x-loc)/scale)/(2.*scale)
>>> plt.plot(x, pdf)
Plot Gaussian for comparison:
>>> g = (1/(scale * np.sqrt(2 * np.pi)) *
... np.exp(-(x - loc)**2 / (2 * scale**2)))
>>> plt.plot(x,g)
left left > mode left == right legacy legacy can only be True when the underlyign bitgenerator is an instance of MT19937. _legacy_seeding length less less_equal loc lock logical_or
logistic(loc=0.0, scale=1.0, size=None)
Draw samples from a logistic distribution.
Samples are drawn from a logistic distribution with specified
parameters, loc (location or mean, also median), and scale (>0).
.. note::
New code should use the `~numpy.random.Generator.logistic`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
Parameter of the distribution. Default is 0.
scale : float or array_like of floats, optional
Parameter of the distribution. Must be non-negative.
Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized logistic distribution.
See Also
--------
scipy.stats.logistic : probability density function, distribution or
cumulative density function, etc.
random.Generator.logistic: which should be used for new code.
Notes
-----
The probability density for the Logistic distribution is
.. math:: P(x) = P(x) = \frac{e^{-(x-\mu)/s}}{s(1+e^{-(x-\mu)/s})^2},
where :math:`\mu` = location and :math:`s` = scale.
The Logistic distribution is used in Extreme Value problems where it
can act as a mixture of Gumbel distributions, in Epidemiology, and by
the World Chess Federation (FIDE) where it is used in the Elo ranking
system, assuming the performance of each player is a logistically
distributed random variable.
References
----------
.. [1] Reiss, R.-D. and Thomas M. (2001), "Statistical Analysis of
Extreme Values, from Insurance, Finance, Hydrology and Other
Fields," Birkhauser Verlag, Basel, pp 132-133.
.. [2] Weisstein, Eric W. "Logistic Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/LogisticDistribution.html
.. [3] Wikipedia, "Logistic-distribution",
https://en.wikipedia.org/wiki/Logistic_distribution
Examples
--------
Draw samples from the distribution:
>>> loc, scale = 10, 1
>>> s = np.random.logistic(loc, scale, 10000)
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, bins=50)
# plot against distribution
>>> def logist(x, loc, scale):
... return np.exp((loc-x)/scale)/(scale*(1+np.exp((loc-x)/scale))**2)
>>> lgst_val = logist(bins, loc, scale)
>>> plt.plot(bins, lgst_val * count.max() / lgst_val.max())
>>> plt.show()
lognormal(mean=0.0, sigma=1.0, size=None)
Draw samples from a log-normal distribution.
Draw samples from a log-normal distribution with specified mean,
standard deviation, and array shape. Note that the mean and standard
deviation are not the values for the distribution itself, but of the
underlying normal distribution it is derived from.
.. note::
New code should use the `~numpy.random.Generator.lognormal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : float or array_like of floats, optional
Mean value of the underlying normal distribution. Default is 0.
sigma : float or array_like of floats, optional
Standard deviation of the underlying normal distribution. Must be
non-negative. Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mean`` and ``sigma`` are both scalars.
Otherwise, ``np.broadcast(mean, sigma).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized log-normal distribution.
See Also
--------
scipy.stats.lognorm : probability density function, distribution,
cumulative density function, etc.
random.Generator.lognormal: which should be used for new code.
Notes
-----
A variable `x` has a log-normal distribution if `log(x)` is normally
distributed. The probability density function for the log-normal
distribution is:
.. math:: p(x) = \frac{1}{\sigma x \sqrt{2\pi}}
e^{(-\frac{(ln(x)-\mu)^2}{2\sigma^2})}
where :math:`\mu` is the mean and :math:`\sigma` is the standard
deviation of the normally distributed logarithm of the variable.
A log-normal distribution results if a random variable is the *product*
of a large number of independent, identically-distributed variables in
the same way that a normal distribution results if the variable is the
*sum* of a large number of independent, identically-distributed
variables.
References
----------
.. [1] Limpert, E., Stahel, W. A., and Abbt, M., "Log-normal
Distributions across the Sciences: Keys and Clues,"
BioScience, Vol. 51, No. 5, May, 2001.
https://stat.ethz.ch/~stahel/lognormal/bioscience.pdf
.. [2] Reiss, R.D. and Thomas, M., "Statistical Analysis of Extreme
Values," Basel: Birkhauser Verlag, 2001, pp. 31-32.
Examples
--------
Draw samples from the distribution:
>>> mu, sigma = 3., 1. # mean and standard deviation
>>> s = np.random.lognormal(mu, sigma, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 100, density=True, align='mid')
>>> x = np.linspace(min(bins), max(bins), 10000)
>>> pdf = (np.exp(-(np.log(x) - mu)**2 / (2 * sigma**2))
... / (x * sigma * np.sqrt(2 * np.pi)))
>>> plt.plot(x, pdf, linewidth=2, color='r')
>>> plt.axis('tight')
>>> plt.show()
Demonstrate that taking the products of random samples from a uniform
distribution can be fit well by a log-normal probability density
function.
>>> # Generate a thousand samples: each is the product of 100 random
>>> # values, drawn from a normal distribution.
>>> b = []
>>> for i in range(1000):
... a = 10. + np.random.standard_normal(100)
... b.append(np.prod(a))
>>> b = np.array(b) / np.min(b) # scale values to be positive
>>> count, bins, ignored = plt.hist(b, 100, density=True, align='mid')
>>> sigma = np.std(np.log(b))
>>> mu = np.mean(np.log(b))
>>> x = np.linspace(min(bins), max(bins), 10000)
>>> pdf = (np.exp(-(np.log(x) - mu)**2 / (2 * sigma**2))
... / (x * sigma * np.sqrt(2 * np.pi)))
>>> plt.plot(x, pdf, color='r', linewidth=2)
>>> plt.show()
logseries(p, size=None)
Draw samples from a logarithmic series distribution.
Samples are drawn from a log series distribution with specified
shape parameter, 0 <= ``p`` < 1.
.. note::
New code should use the `~numpy.random.Generator.logseries`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
p : float or array_like of floats
Shape parameter for the distribution. Must be in the range [0, 1).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``p`` is a scalar. Otherwise,
``np.array(p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized logarithmic series distribution.
See Also
--------
scipy.stats.logser : probability density function, distribution or
cumulative density function, etc.
random.Generator.logseries: which should be used for new code.
Notes
-----
The probability density for the Log Series distribution is
.. math:: P(k) = \frac{-p^k}{k \ln(1-p)},
where p = probability.
The log series distribution is frequently used to represent species
richness and occurrence, first proposed by Fisher, Corbet, and
Williams in 1943 [2]. It may also be used to model the numbers of
occupants seen in cars [3].
References
----------
.. [1] Buzas, Martin A.; Culver, Stephen J., Understanding regional
species diversity through the log series distribution of
occurrences: BIODIVERSITY RESEARCH Diversity & Distributions,
Volume 5, Number 5, September 1999 , pp. 187-195(9).
.. [2] Fisher, R.A,, A.S. Corbet, and C.B. Williams. 1943. The
relation between the number of species and the number of
individuals in a random sample of an animal population.
Journal of Animal Ecology, 12:42-58.
.. [3] D. J. Hand, F. Daly, D. Lunn, E. Ostrowski, A Handbook of Small
Data Sets, CRC Press, 1994.
.. [4] Wikipedia, "Logarithmic distribution",
https://en.wikipedia.org/wiki/Logarithmic_distribution
Examples
--------
Draw samples from the distribution:
>>> a = .6
>>> s = np.random.logseries(a, 10000)
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s)
# plot against distribution
>>> def logseries(k, p):
... return -p**k/(k*np.log(1-p))
>>> plt.plot(bins, logseries(bins, a)*count.max()/
... logseries(bins, a).max(), 'r')
>>> plt.show()
low __main__ may_share_memory mean mean and cov must have same length mean must be 1 dimensional mode mode > right _mt19937 mu
multinomial(n, pvals, size=None)
Draw samples from a multinomial distribution.
The multinomial distribution is a multivariate generalization of the
binomial distribution. Take an experiment with one of ``p``
possible outcomes. An example of such an experiment is throwing a dice,
where the outcome can be 1 through 6. Each sample drawn from the
distribution represents `n` such experiments. Its values,
``X_i = [X_0, X_1, ..., X_p]``, represent the number of times the
outcome was ``i``.
.. note::
New code should use the `~numpy.random.Generator.multinomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : int
Number of experiments.
pvals : sequence of floats, length p
Probabilities of each of the ``p`` different outcomes. These
must sum to 1 (however, the last element is always assumed to
account for the remaining probability, as long as
``sum(pvals[:-1]) <= 1)``.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : ndarray
The drawn samples, of shape *size*, if that was provided. If not,
the shape is ``(N,)``.
In other words, each entry ``out[i,j,...,:]`` is an N-dimensional
value drawn from the distribution.
See Also
--------
random.Generator.multinomial: which should be used for new code.
Examples
--------
Throw a dice 20 times:
>>> np.random.multinomial(20, [1/6.]*6, size=1)
array([[4, 1, 7, 5, 2, 1]]) # random
It landed 4 times on 1, once on 2, etc.
Now, throw the dice 20 times, and 20 times again:
>>> np.random.multinomial(20, [1/6.]*6, size=2)
array([[3, 4, 3, 3, 4, 3], # random
[2, 4, 3, 4, 0, 7]])
For the first run, we threw 3 times 1, 4 times 2, etc. For the second,
we threw 2 times 1, 4 times 2, etc.
A loaded die is more likely to land on number 6:
>>> np.random.multinomial(100, [1/7.]*5 + [2/7.])
array([11, 16, 14, 17, 16, 26]) # random
The probability inputs should be normalized. As an implementation
detail, the value of the last entry is ignored and assumed to take
up any leftover probability mass, but this should not be relied on.
A biased coin which has twice as much weight on one side as on the
other should be sampled like so:
>>> np.random.multinomial(100, [1.0 / 3, 2.0 / 3]) # RIGHT
array([38, 62]) # random
not like:
>>> np.random.multinomial(100, [1.0, 2.0]) # WRONG
Traceback (most recent call last):
ValueError: pvals < 0, pvals > 1 or pvals contains NaNs
multivariate_normal(mean, cov, size=None, check_valid='warn', tol=1e-8)
Draw random samples from a multivariate normal distribution.
The multivariate normal, multinormal or Gaussian distribution is a
generalization of the one-dimensional normal distribution to higher
dimensions. Such a distribution is specified by its mean and
covariance matrix. These parameters are analogous to the mean
(average or "center") and variance (standard deviation, or "width,"
squared) of the one-dimensional normal distribution.
.. note::
New code should use the
`~numpy.random.Generator.multivariate_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : 1-D array_like, of length N
Mean of the N-dimensional distribution.
cov : 2-D array_like, of shape (N, N)
Covariance matrix of the distribution. It must be symmetric and
positive-semidefinite for proper sampling.
size : int or tuple of ints, optional
Given a shape of, for example, ``(m,n,k)``, ``m*n*k`` samples are
generated, and packed in an `m`-by-`n`-by-`k` arrangement. Because
each sample is `N`-dimensional, the output shape is ``(m,n,k,N)``.
If no shape is specified, a single (`N`-D) sample is returned.
check_valid : { 'warn', 'raise', 'ignore' }, optional
Behavior when the covariance matrix is not positive semidefinite.
tol : float, optional
Tolerance when checking the singular values in covariance matrix.
cov is cast to double before the check.
Returns
-------
out : ndarray
The drawn samples, of shape *size*, if that was provided. If not,
the shape is ``(N,)``.
In other words, each entry ``out[i,j,...,:]`` is an N-dimensional
value drawn from the distribution.
See Also
--------
random.Generator.multivariate_normal: which should be used for new code.
Notes
-----
The mean is a coordinate in N-dimensional space, which represents the
location where samples are most likely to be generated. This is
analogous to the peak of the bell curve for the one-dimensional or
univariate normal distribution.
Covariance indicates the level to which two variables vary together.
From the multivariate normal distribution, we draw N-dimensional
samples, :math:`X = [x_1, x_2, ... x_N]`. The covariance matrix
element :math:`C_{ij}` is the covariance of :math:`x_i` and :math:`x_j`.
The element :math:`C_{ii}` is the variance of :math:`x_i` (i.e. its
"spread").
Instead of specifying the full covariance matrix, popular
approximations include:
- Spherical covariance (`cov` is a multiple of the identity matrix)
- Diagonal covariance (`cov` has non-negative elements, and only on
the diagonal)
This geometrical property can be seen in two dimensions by plotting
generated data-points:
>>> mean = [0, 0]
>>> cov = [[1, 0], [0, 100]] # diagonal covariance
Diagonal covariance means that points are oriented along x or y-axis:
>>> import matplotlib.pyplot as plt
>>> x, y = np.random.multivariate_normal(mean, cov, 5000).T
>>> plt.plot(x, y, 'x')
>>> plt.axis('equal')
>>> plt.show()
Note that the covariance matrix must be positive semidefinite (a.k.a.
nonnegative-definite). Otherwise, the behavior of this method is
undefined and backwards compatibility is not guaranteed.
References
----------
.. [1] Papoulis, A., "Probability, Random Variables, and Stochastic
Processes," 3rd ed., New York: McGraw-Hill, 1991.
.. [2] Duda, R. O., Hart, P. E., and Stork, D. G., "Pattern
Classification," 2nd ed., New York: Wiley, 2001.
Examples
--------
>>> mean = (1, 2)
>>> cov = [[1, 0], [0, 1]]
>>> x = np.random.multivariate_normal(mean, cov, (3, 3))
>>> x.shape
(3, 3, 2)
Here we generate 800 samples from the bivariate normal distribution
with mean [0, 0] and covariance matrix [[6, -3], [-3, 3.5]]. The
expected variances of the first and second components of the sample
are 6 and 3.5, respectively, and the expected correlation
coefficient is -3/sqrt(6*3.5) ≈ -0.65465.
>>> cov = np.array([[6, -3], [-3, 3.5]])
>>> pts = np.random.multivariate_normal([0, 0], cov, size=800)
Check that the mean, covariance, and correlation coefficient of the
sample are close to the expected values:
>>> pts.mean(axis=0)
array([ 0.0326911 , -0.01280782]) # may vary
>>> np.cov(pts.T)
array([[ 5.96202397, -2.85602287],
[-2.85602287, 3.47613949]]) # may vary
>>> np.corrcoef(pts.T)[0, 1]
-0.6273591314603949 # may vary
We can visualize this data with a scatter plot. The orientation
of the point cloud illustrates the negative correlation of the
components of this sample.
>>> import matplotlib.pyplot as plt
>>> plt.plot(pts[:, 0], pts[:, 1], '.', alpha=0.5)
>>> plt.axis('equal')
>>> plt.grid()
>>> plt.show()
n __name__ nbad ndim
negative_binomial(n, p, size=None)
Draw samples from a negative binomial distribution.
Samples are drawn from a negative binomial distribution with specified
parameters, `n` successes and `p` probability of success where `n`
is > 0 and `p` is in the interval [0, 1].
.. note::
New code should use the
`~numpy.random.Generator.negative_binomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : float or array_like of floats
Parameter of the distribution, > 0.
p : float or array_like of floats
Parameter of the distribution, >= 0 and <=1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``n`` and ``p`` are both scalars.
Otherwise, ``np.broadcast(n, p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized negative binomial distribution,
where each sample is equal to N, the number of failures that
occurred before a total of n successes was reached.
See Also
--------
random.Generator.negative_binomial: which should be used for new code.
Notes
-----
The probability mass function of the negative binomial distribution is
.. math:: P(N;n,p) = \frac{\Gamma(N+n)}{N!\Gamma(n)}p^{n}(1-p)^{N},
where :math:`n` is the number of successes, :math:`p` is the
probability of success, :math:`N+n` is the number of trials, and
:math:`\Gamma` is the gamma function. When :math:`n` is an integer,
:math:`\frac{\Gamma(N+n)}{N!\Gamma(n)} = \binom{N+n-1}{N}`, which is
the more common form of this term in the pmf. The negative
binomial distribution gives the probability of N failures given n
successes, with a success on the last trial.
If one throws a die repeatedly until the third time a "1" appears,
then the probability distribution of the number of non-"1"s that
appear before the third "1" is a negative binomial distribution.
References
----------
.. [1] Weisstein, Eric W. "Negative Binomial Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/NegativeBinomialDistribution.html
.. [2] Wikipedia, "Negative binomial distribution",
https://en.wikipedia.org/wiki/Negative_binomial_distribution
Examples
--------
Draw samples from the distribution:
A real world example. A company drills wild-cat oil
exploration wells, each with an estimated probability of
success of 0.1. What is the probability of having one success
for each successive well, that is what is the probability of a
single success after drilling 5 wells, after 6 wells, etc.?
>>> s = np.random.negative_binomial(1, 0.1, 100000)
>>> for i in range(1, 11): # doctest: +SKIP
... probability = sum(s<i) / 100000.
... print(i, "wells drilled, probability of one success =", probability)
newbyteorder ngood ngood + nbad < nsample nonc
noncentral_chisquare(df, nonc, size=None)
Draw samples from a noncentral chi-square distribution.
The noncentral :math:`\chi^2` distribution is a generalization of
the :math:`\chi^2` distribution.
.. note::
New code should use the
`~numpy.random.Generator.noncentral_chisquare`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Degrees of freedom, must be > 0.
.. versionchanged:: 1.10.0
Earlier NumPy versions required dfnum > 1.
nonc : float or array_like of floats
Non-centrality, must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` and ``nonc`` are both scalars.
Otherwise, ``np.broadcast(df, nonc).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized noncentral chi-square distribution.
See Also
--------
random.Generator.noncentral_chisquare: which should be used for new code.
Notes
-----
The probability density function for the noncentral Chi-square
distribution is
.. math:: P(x;df,nonc) = \sum^{\infty}_{i=0}
\frac{e^{-nonc/2}(nonc/2)^{i}}{i!}
P_{Y_{df+2i}}(x),
where :math:`Y_{q}` is the Chi-square with q degrees of freedom.
References
----------
.. [1] Wikipedia, "Noncentral chi-squared distribution"
https://en.wikipedia.org/wiki/Noncentral_chi-squared_distribution
Examples
--------
Draw values from the distribution and plot the histogram
>>> import matplotlib.pyplot as plt
>>> values = plt.hist(np.random.noncentral_chisquare(3, 20, 100000),
... bins=200, density=True)
>>> plt.show()
Draw values from a noncentral chisquare with very small noncentrality,
and compare to a chisquare.
>>> plt.figure()
>>> values = plt.hist(np.random.noncentral_chisquare(3, .0000001, 100000),
... bins=np.arange(0., 25, .1), density=True)
>>> values2 = plt.hist(np.random.chisquare(3, 100000),
... bins=np.arange(0., 25, .1), density=True)
>>> plt.plot(values[1][0:-1], values[0]-values2[0], 'ob')
>>> plt.show()
Demonstrate how large values of non-centrality lead to a more symmetric
distribution.
>>> plt.figure()
>>> values = plt.hist(np.random.noncentral_chisquare(3, 20, 100000),
... bins=200, density=True)
>>> plt.show()
noncentral_f(dfnum, dfden, nonc, size=None)
Draw samples from the noncentral F distribution.
Samples are drawn from an F distribution with specified parameters,
`dfnum` (degrees of freedom in numerator) and `dfden` (degrees of
freedom in denominator), where both parameters > 1.
`nonc` is the non-centrality parameter.
.. note::
New code should use the
`~numpy.random.Generator.noncentral_f`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
dfnum : float or array_like of floats
Numerator degrees of freedom, must be > 0.
.. versionchanged:: 1.14.0
Earlier NumPy versions required dfnum > 1.
dfden : float or array_like of floats
Denominator degrees of freedom, must be > 0.
nonc : float or array_like of floats
Non-centrality parameter, the sum of the squares of the numerator
means, must be >= 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``dfnum``, ``dfden``, and ``nonc``
are all scalars. Otherwise, ``np.broadcast(dfnum, dfden, nonc).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized noncentral Fisher distribution.
See Also
--------
random.Generator.noncentral_f: which should be used for new code.
Notes
-----
When calculating the power of an experiment (power = probability of
rejecting the null hypothesis when a specific alternative is true) the
non-central F statistic becomes important. When the null hypothesis is
true, the F statistic follows a central F distribution. When the null
hypothesis is not true, then it follows a non-central F statistic.
References
----------
.. [1] Weisstein, Eric W. "Noncentral F-Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/NoncentralF-Distribution.html
.. [2] Wikipedia, "Noncentral F-distribution",
https://en.wikipedia.org/wiki/Noncentral_F-distribution
Examples
--------
In a study, testing for a specific alternative to the null hypothesis
requires use of the Noncentral F distribution. We need to calculate the
area in the tail of the distribution that exceeds the value of the F
distribution for the null hypothesis. We'll plot the two probability
distributions for comparison.
>>> dfnum = 3 # between group deg of freedom
>>> dfden = 20 # within groups degrees of freedom
>>> nonc = 3.0
>>> nc_vals = np.random.noncentral_f(dfnum, dfden, nonc, 1000000)
>>> NF = np.histogram(nc_vals, bins=50, density=True)
>>> c_vals = np.random.f(dfnum, dfden, 1000000)
>>> F = np.histogram(c_vals, bins=50, density=True)
>>> import matplotlib.pyplot as plt
>>> plt.plot(F[1][1:], F[0])
>>> plt.plot(NF[1][1:], NF[0])
>>> plt.show()
normal(loc=0.0, scale=1.0, size=None)
Draw random samples from a normal (Gaussian) distribution.
The probability density function of the normal distribution, first
derived by De Moivre and 200 years later by both Gauss and Laplace
independently [2]_, is often called the bell curve because of
its characteristic shape (see the example below).
The normal distributions occurs often in nature. For example, it
describes the commonly occurring distribution of samples influenced
by a large number of tiny, random disturbances, each with its own
unique distribution [2]_.
.. note::
New code should use the `~numpy.random.Generator.normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats
Mean ("centre") of the distribution.
scale : float or array_like of floats
Standard deviation (spread or "width") of the distribution. Must be
non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized normal distribution.
See Also
--------
scipy.stats.norm : probability density function, distribution or
cumulative density function, etc.
random.Generator.normal: which should be used for new code.
Notes
-----
The probability density for the Gaussian distribution is
.. math:: p(x) = \frac{1}{\sqrt{ 2 \pi \sigma^2 }}
e^{ - \frac{ (x - \mu)^2 } {2 \sigma^2} },
where :math:`\mu` is the mean and :math:`\sigma` the standard
deviation. The square of the standard deviation, :math:`\sigma^2`,
is called the variance.
The function has its peak at the mean, and its "spread" increases with
the standard deviation (the function reaches 0.607 times its maximum at
:math:`x + \sigma` and :math:`x - \sigma` [2]_). This implies that
normal is more likely to return samples lying close to the mean, rather
than those far away.
References
----------
.. [1] Wikipedia, "Normal distribution",
https://en.wikipedia.org/wiki/Normal_distribution
.. [2] P. R. Peebles Jr., "Central Limit Theorem" in "Probability,
Random Variables and Random Signal Principles", 4th ed., 2001,
pp. 51, 51, 125.
Examples
--------
Draw samples from the distribution:
>>> mu, sigma = 0, 0.1 # mean and standard deviation
>>> s = np.random.normal(mu, sigma, 1000)
Verify the mean and the variance:
>>> abs(mu - np.mean(s))
0.0 # may vary
>>> abs(sigma - np.std(s, ddof=1))
0.1 # may vary
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) *
... np.exp( - (bins - mu)**2 / (2 * sigma**2) ),
... linewidth=2, color='r')
>>> plt.show()
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> np.random.normal(3, 2.5, size=(2, 4))
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
np nsample numpy.core.multiarray failed to import numpy.core.umath failed to import numpy.linalg object_ ' object which is not a subclass of 'Sequence'; `shuffle` is not guaranteed to behave correctly. E.g., non-numpy array/tensor objects with view semantics may contain duplicates after shuffling. operator p 'p' must be 1-dimensional
pareto(a, size=None)
Draw samples from a Pareto II or Lomax distribution with
specified shape.
The Lomax or Pareto II distribution is a shifted Pareto
distribution. The classical Pareto distribution can be
obtained from the Lomax distribution by adding 1 and
multiplying by the scale parameter ``m`` (see Notes). The
smallest value of the Lomax distribution is zero while for the
classical Pareto distribution it is ``mu``, where the standard
Pareto distribution has location ``mu = 1``. Lomax can also
be considered as a simplified version of the Generalized
Pareto distribution (available in SciPy), with the scale set
to one and the location set to zero.
The Pareto distribution must be greater than zero, and is
unbounded above. It is also known as the "80-20 rule". In
this distribution, 80 percent of the weights are in the lowest
20 percent of the range, while the other 20 percent fill the
remaining 80 percent of the range.
.. note::
New code should use the `~numpy.random.Generator.pareto`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Shape of the distribution. Must be positive.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Pareto distribution.
See Also
--------
scipy.stats.lomax : probability density function, distribution or
cumulative density function, etc.
scipy.stats.genpareto : probability density function, distribution or
cumulative density function, etc.
random.Generator.pareto: which should be used for new code.
Notes
-----
The probability density for the Pareto distribution is
.. math:: p(x) = \frac{am^a}{x^{a+1}}
where :math:`a` is the shape and :math:`m` the scale.
The Pareto distribution, named after the Italian economist
Vilfredo Pareto, is a power law probability distribution
useful in many real world problems. Outside the field of
economics it is generally referred to as the Bradford
distribution. Pareto developed the distribution to describe
the distribution of wealth in an economy. It has also found
use in insurance, web page access statistics, oil field sizes,
and many other problems, including the download frequency for
projects in Sourceforge [1]_. It is one of the so-called
"fat-tailed" distributions.
References
----------
.. [1] Francis Hunt and Paul Johnson, On the Pareto Distribution of
Sourceforge projects.
.. [2] Pareto, V. (1896). Course of Political Economy. Lausanne.
.. [3] Reiss, R.D., Thomas, M.(2001), Statistical Analysis of Extreme
Values, Birkhauser Verlag, Basel, pp 23-30.
.. [4] Wikipedia, "Pareto distribution",
https://en.wikipedia.org/wiki/Pareto_distribution
Examples
--------
Draw samples from the distribution:
>>> a, m = 3., 2. # shape and mode
>>> s = (np.random.pareto(a, 1000) + 1) * m
Display the histogram of the samples, along with the probability
density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, _ = plt.hist(s, 100, density=True)
>>> fit = a*m**a / bins**(a+1)
>>> plt.plot(bins, max(count)*fit/max(fit), linewidth=2, color='r')
>>> plt.show()
permutation(x)
Randomly permute a sequence, or return a permuted range.
If `x` is a multi-dimensional array, it is only shuffled along its
first index.
.. note::
New code should use the
`~numpy.random.Generator.permutation`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
x : int or array_like
If `x` is an integer, randomly permute ``np.arange(x)``.
If `x` is an array, make a copy and shuffle the elements
randomly.
Returns
-------
out : ndarray
Permuted sequence or array range.
See Also
--------
random.Generator.permutation: which should be used for new code.
Examples
--------
>>> np.random.permutation(10)
array([1, 7, 4, 3, 0, 9, 2, 5, 8, 6]) # random
>>> np.random.permutation([1, 4, 9, 12, 15])
array([15, 1, 9, 4, 12]) # random
>>> arr = np.arange(9).reshape((3, 3))
>>> np.random.permutation(arr)
array([[6, 7, 8], # random
[0, 1, 2],
[3, 4, 5]])
_pickle
poisson(lam=1.0, size=None)
Draw samples from a Poisson distribution.
The Poisson distribution is the limit of the binomial distribution
for large N.
.. note::
New code should use the `~numpy.random.Generator.poisson`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
lam : float or array_like of floats
Expected number of events occurring in a fixed-time interval,
must be >= 0. A sequence must be broadcastable over the requested
size.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``lam`` is a scalar. Otherwise,
``np.array(lam).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Poisson distribution.
See Also
--------
random.Generator.poisson: which should be used for new code.
Notes
-----
The Poisson distribution
.. math:: f(k; \lambda)=\frac{\lambda^k e^{-\lambda}}{k!}
For events with an expected separation :math:`\lambda` the Poisson
distribution :math:`f(k; \lambda)` describes the probability of
:math:`k` events occurring within the observed
interval :math:`\lambda`.
Because the output is limited to the range of the C int64 type, a
ValueError is raised when `lam` is within 10 sigma of the maximum
representable value.
References
----------
.. [1] Weisstein, Eric W. "Poisson Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/PoissonDistribution.html
.. [2] Wikipedia, "Poisson distribution",
https://en.wikipedia.org/wiki/Poisson_distribution
Examples
--------
Draw samples from the distribution:
>>> import numpy as np
>>> s = np.random.poisson(5, 10000)
Display histogram of the sample:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 14, density=True)
>>> plt.show()
Draw each 100 values for lambda 100 and 500:
>>> s = np.random.poisson(lam=(100., 500.), size=(100, 2))
_poisson_lam_max pos
power(a, size=None)
Draws samples in [0, 1] from a power distribution with positive
exponent a - 1.
Also known as the power function distribution.
.. note::
New code should use the `~numpy.random.Generator.power`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Parameter of the distribution. Must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized power distribution.
Raises
------
ValueError
If a <= 0.
See Also
--------
random.Generator.power: which should be used for new code.
Notes
-----
The probability density function is
.. math:: P(x; a) = ax^{a-1}, 0 \le x \le 1, a>0.
The power function distribution is just the inverse of the Pareto
distribution. It may also be seen as a special case of the Beta
distribution.
It is used, for example, in modeling the over-reporting of insurance
claims.
References
----------
.. [1] Christian Kleiber, Samuel Kotz, "Statistical size distributions
in economics and actuarial sciences", Wiley, 2003.
.. [2] Heckert, N. A. and Filliben, James J. "NIST Handbook 148:
Dataplot Reference Manual, Volume 2: Let Subcommands and Library
Functions", National Institute of Standards and Technology
Handbook Series, June 2003.
https://www.itl.nist.gov/div898/software/dataplot/refman2/auxillar/powpdf.pdf
Examples
--------
Draw samples from the distribution:
>>> a = 5. # shape
>>> samples = 1000
>>> s = np.random.power(a, samples)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, bins=30)
>>> x = np.linspace(0, 1, 100)
>>> y = a*x**(a-1.)
>>> normed_y = samples*np.diff(bins)[0]*y
>>> plt.plot(x, normed_y)
>>> plt.show()
Compare the power function distribution to the inverse of the Pareto.
>>> from scipy import stats # doctest: +SKIP
>>> rvs = np.random.power(5, 1000000)
>>> rvsp = np.random.pareto(5, 1000000)
>>> xx = np.linspace(0,1,100)
>>> powpdf = stats.powerlaw.pdf(xx,5) # doctest: +SKIP
>>> plt.figure()
>>> plt.hist(rvs, bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('np.random.power(5)')
>>> plt.figure()
>>> plt.hist(1./(1.+rvsp), bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('inverse of 1 + np.random.pareto(5)')
>>> plt.figure()
>>> plt.hist(1./(1.+rvsp), bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('inverse of stats.pareto(5)')
probabilities are not non-negative probabilities contain NaN probabilities do not sum to 1 prod pvals pvals must be a 1-d sequence __pyx_vtable__ raise _rand
rand(d0, d1, ..., dn)
Random values in a given shape.
.. note::
This is a convenience function for users porting code from Matlab,
and wraps `random_sample`. That function takes a
tuple to specify the size of the output, which is consistent with
other NumPy functions like `numpy.zeros` and `numpy.ones`.
Create an array of the given shape and populate it with
random samples from a uniform distribution
over ``[0, 1)``.
Parameters
----------
d0, d1, ..., dn : int, optional
The dimensions of the returned array, must be non-negative.
If no argument is given a single Python float is returned.
Returns
-------
out : ndarray, shape ``(d0, d1, ..., dn)``
Random values.
See Also
--------
random
Examples
--------
>>> np.random.rand(3,2)
array([[ 0.14022471, 0.96360618], #random
[ 0.37601032, 0.25528411], #random
[ 0.49313049, 0.94909878]]) #random
randint(low, high=None, size=None, dtype=int)
Return random integers from `low` (inclusive) to `high` (exclusive).
Return random integers from the "discrete uniform" distribution of
the specified dtype in the "half-open" interval [`low`, `high`). If
`high` is None (the default), then results are from [0, `low`).
.. note::
New code should use the `~numpy.random.Generator.integers`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
low : int or array-like of ints
Lowest (signed) integers to be drawn from the distribution (unless
``high=None``, in which case this parameter is one above the
*highest* such integer).
high : int or array-like of ints, optional
If provided, one above the largest (signed) integer to be drawn
from the distribution (see above for behavior if ``high=None``).
If array-like, must contain integer values
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
dtype : dtype, optional
Desired dtype of the result. Byteorder must be native.
The default value is int.
.. versionadded:: 1.11.0
Returns
-------
out : int or ndarray of ints
`size`-shaped array of random integers from the appropriate
distribution, or a single such random int if `size` not provided.
See Also
--------
random_integers : similar to `randint`, only for the closed
interval [`low`, `high`], and 1 is the lowest value if `high` is
omitted.
random.Generator.integers: which should be used for new code.
Examples
--------
>>> np.random.randint(2, size=10)
array([1, 0, 0, 0, 1, 1, 0, 0, 1, 0]) # random
>>> np.random.randint(1, size=10)
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
Generate a 2 x 4 array of ints between 0 and 4, inclusive:
>>> np.random.randint(5, size=(2, 4))
array([[4, 0, 2, 1], # random
[3, 2, 2, 0]])
Generate a 1 x 3 array with 3 different upper bounds
>>> np.random.randint(1, [3, 5, 10])
array([2, 2, 9]) # random
Generate a 1 by 3 array with 3 different lower bounds
>>> np.random.randint([1, 5, 7], 10)
array([9, 8, 7]) # random
Generate a 2 by 4 array using broadcasting with dtype of uint8
>>> np.random.randint([1, 3, 5, 7], [[10], [20]], dtype=np.uint8)
array([[ 8, 6, 9, 7], # random
[ 1, 16, 9, 12]], dtype=uint8)
randn(d0, d1, ..., dn)
Return a sample (or samples) from the "standard normal" distribution.
.. note::
This is a convenience function for users porting code from Matlab,
and wraps `standard_normal`. That function takes a
tuple to specify the size of the output, which is consistent with
other NumPy functions like `numpy.zeros` and `numpy.ones`.
.. note::
New code should use the
`~numpy.random.Generator.standard_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
If positive int_like arguments are provided, `randn` generates an array
of shape ``(d0, d1, ..., dn)``, filled
with random floats sampled from a univariate "normal" (Gaussian)
distribution of mean 0 and variance 1. A single float randomly sampled
from the distribution is returned if no argument is provided.
Parameters
----------
d0, d1, ..., dn : int, optional
The dimensions of the returned array, must be non-negative.
If no argument is given a single Python float is returned.
Returns
-------
Z : ndarray or float
A ``(d0, d1, ..., dn)``-shaped array of floating-point samples from
the standard normal distribution, or a single such float if
no parameters were supplied.
See Also
--------
standard_normal : Similar, but takes a tuple as its argument.
normal : Also accepts mu and sigma arguments.
random.Generator.standard_normal: which should be used for new code.
Notes
-----
For random samples from the normal distribution with mean ``mu`` and
standard deviation ``sigma``, use::
sigma * np.random.randn(...) + mu
Examples
--------
>>> np.random.randn()
2.1923875335537315 # random
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> 3 + 2.5 * np.random.randn(2, 4)
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
random_integers(low, high=None, size=None)
Random integers of type `np.int_` between `low` and `high`, inclusive.
Return random integers of type `np.int_` from the "discrete uniform"
distribution in the closed interval [`low`, `high`]. If `high` is
None (the default), then results are from [1, `low`]. The `np.int_`
type translates to the C long integer type and its precision
is platform dependent.
This function has been deprecated. Use randint instead.
.. deprecated:: 1.11.0
Parameters
----------
low : int
Lowest (signed) integer to be drawn from the distribution (unless
``high=None``, in which case this parameter is the *highest* such
integer).
high : int, optional
If provided, the largest (signed) integer to be drawn from the
distribution (see above for behavior if ``high=None``).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : int or ndarray of ints
`size`-shaped array of random integers from the appropriate
distribution, or a single such random int if `size` not provided.
See Also
--------
randint : Similar to `random_integers`, only for the half-open
interval [`low`, `high`), and 0 is the lowest value if `high` is
omitted.
Notes
-----
To sample from N evenly spaced floating-point numbers between a and b,
use::
a + (b - a) * (np.random.random_integers(N) - 1) / (N - 1.)
Examples
--------
>>> np.random.random_integers(5)
4 # random
>>> type(np.random.random_integers(5))
<class 'numpy.int64'>
>>> np.random.random_integers(5, size=(3,2))
array([[5, 4], # random
[3, 3],
[4, 5]])
Choose five random numbers from the set of five evenly-spaced
numbers between 0 and 2.5, inclusive (*i.e.*, from the set
:math:`{0, 5/8, 10/8, 15/8, 20/8}`):
>>> 2.5 * (np.random.random_integers(5, size=(5,)) - 1) / 4.
array([ 0.625, 1.25 , 0.625, 0.625, 2.5 ]) # random
Roll two six sided dice 1000 times and sum the results:
>>> d1 = np.random.random_integers(1, 6, 1000)
>>> d2 = np.random.random_integers(1, 6, 1000)
>>> dsums = d1 + d2
Display results as a histogram:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(dsums, 11, density=True)
>>> plt.show()
random_sample(size=None)
Return random floats in the half-open interval [0.0, 1.0).
Results are from the "continuous uniform" distribution over the
stated interval. To sample :math:`Unif[a, b), b > a` multiply
the output of `random_sample` by `(b-a)` and add `a`::
(b - a) * random_sample() + a
.. note::
New code should use the `~numpy.random.Generator.random`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray of floats
Array of random floats of shape `size` (unless ``size=None``, in which
case a single float is returned).
See Also
--------
random.Generator.random: which should be used for new code.
Examples
--------
>>> np.random.random_sample()
0.47108547995356098 # random
>>> type(np.random.random_sample())
<class 'float'>
>>> np.random.random_sample((5,))
array([ 0.30220482, 0.86820401, 0.1654503 , 0.11659149, 0.54323428]) # random
Three-by-two array of random numbers from [-5, 0):
>>> 5 * np.random.random_sample((3, 2)) - 5
array([[-3.99149989, -0.52338984], # random
[-2.99091858, -0.79479508],
[-1.23204345, -1.75224494]])
__randomstate_ctor range ravel
rayleigh(scale=1.0, size=None)
Draw samples from a Rayleigh distribution.
The :math:`\chi` and Weibull distributions are generalizations of the
Rayleigh.
.. note::
New code should use the `~numpy.random.Generator.rayleigh`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
scale : float or array_like of floats, optional
Scale, also equals the mode. Must be non-negative. Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``scale`` is a scalar. Otherwise,
``np.array(scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Rayleigh distribution.
See Also
--------
random.Generator.rayleigh: which should be used for new code.
Notes
-----
The probability density function for the Rayleigh distribution is
.. math:: P(x;scale) = \frac{x}{scale^2}e^{\frac{-x^2}{2 \cdotp scale^2}}
The Rayleigh distribution would arise, for example, if the East
and North components of the wind velocity had identical zero-mean
Gaussian distributions. Then the wind speed would have a Rayleigh
distribution.
References
----------
.. [1] Brighton Webs Ltd., "Rayleigh Distribution,"
https://web.archive.org/web/20090514091424/http://brighton-webs.co.uk:80/distributions/rayleigh.asp
.. [2] Wikipedia, "Rayleigh distribution"
https://en.wikipedia.org/wiki/Rayleigh_distribution
Examples
--------
Draw values from the distribution and plot the histogram
>>> from matplotlib.pyplot import hist
>>> values = hist(np.random.rayleigh(3, 100000), bins=200, density=True)
Wave heights tend to follow a Rayleigh distribution. If the mean wave
height is 1 meter, what fraction of waves are likely to be larger than 3
meters?
>>> meanvalue = 1
>>> modevalue = np.sqrt(2 / np.pi) * meanvalue
>>> s = np.random.rayleigh(modevalue, 1000000)
The percentage of waves larger than 3 meters is:
>>> 100.*sum(s>3)/1000000.
0.087300000000000003 # random
reduce replace reshape return_index reversed right rtol scale searchsorted
seed(seed=None)
Reseed a legacy MT19937 BitGenerator
Notes
-----
This is a convenience, legacy function.
The best practice is to **not** reseed a BitGenerator, rather to
recreate a new one. This method is here for legacy reasons.
This example demonstrates best practice.
>>> from numpy.random import MT19937
>>> from numpy.random import RandomState, SeedSequence
>>> rs = RandomState(MT19937(SeedSequence(123456789)))
# Later, you want to restart the stream
>>> rs = RandomState(MT19937(SeedSequence(987654321)))
set_state can only be used with legacy MT19937 state instances. shape
shuffle(x)
Modify a sequence in-place by shuffling its contents.
This function only shuffles the array along the first axis of a
multi-dimensional array. The order of sub-arrays is changed but
their contents remains the same.
.. note::
New code should use the `~numpy.random.Generator.shuffle`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
x : ndarray or MutableSequence
The array, list or mutable sequence to be shuffled.
Returns
-------
None
See Also
--------
random.Generator.shuffle: which should be used for new code.
Examples
--------
>>> arr = np.arange(10)
>>> np.random.shuffle(arr)
>>> arr
[1 7 5 2 9 4 3 6 0 8] # random
Multi-dimensional arrays are only shuffled along the first axis:
>>> arr = np.arange(9).reshape((3, 3))
>>> np.random.shuffle(arr)
>>> arr
array([[3, 4, 5], # random
[6, 7, 8],
[0, 1, 2]])
side sigma singleton size sort __spec__ sqrt stacklevel
standard_cauchy(size=None)
Draw samples from a standard Cauchy distribution with mode = 0.
Also known as the Lorentz distribution.
.. note::
New code should use the
`~numpy.random.Generator.standard_cauchy`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
samples : ndarray or scalar
The drawn samples.
See Also
--------
random.Generator.standard_cauchy: which should be used for new code.
Notes
-----
The probability density function for the full Cauchy distribution is
.. math:: P(x; x_0, \gamma) = \frac{1}{\pi \gamma \bigl[ 1+
(\frac{x-x_0}{\gamma})^2 \bigr] }
and the Standard Cauchy distribution just sets :math:`x_0=0` and
:math:`\gamma=1`
The Cauchy distribution arises in the solution to the driven harmonic
oscillator problem, and also describes spectral line broadening. It
also describes the distribution of values at which a line tilted at
a random angle will cut the x axis.
When studying hypothesis tests that assume normality, seeing how the
tests perform on data from a Cauchy distribution is a good indicator of
their sensitivity to a heavy-tailed distribution, since the Cauchy looks
very much like a Gaussian distribution, but with heavier tails.
References
----------
.. [1] NIST/SEMATECH e-Handbook of Statistical Methods, "Cauchy
Distribution",
https://www.itl.nist.gov/div898/handbook/eda/section3/eda3663.htm
.. [2] Weisstein, Eric W. "Cauchy Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/CauchyDistribution.html
.. [3] Wikipedia, "Cauchy distribution"
https://en.wikipedia.org/wiki/Cauchy_distribution
Examples
--------
Draw samples and plot the distribution:
>>> import matplotlib.pyplot as plt
>>> s = np.random.standard_cauchy(1000000)
>>> s = s[(s>-25) & (s<25)] # truncate distribution so it plots well
>>> plt.hist(s, bins=100)
>>> plt.show()
standard_exponential(size=None)
Draw samples from the standard exponential distribution.
`standard_exponential` is identical to the exponential distribution
with a scale parameter of 1.
.. note::
New code should use the
`~numpy.random.Generator.standard_exponential`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray
Drawn samples.
See Also
--------
random.Generator.standard_exponential: which should be used for new code.
Examples
--------
Output a 3x8000 array:
>>> n = np.random.standard_exponential((3, 8000))
standard_gamma(shape, size=None)
Draw samples from a standard Gamma distribution.
Samples are drawn from a Gamma distribution with specified parameters,
shape (sometimes designated "k") and scale=1.
.. note::
New code should use the
`~numpy.random.Generator.standard_gamma`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
shape : float or array_like of floats
Parameter, must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``shape`` is a scalar. Otherwise,
``np.array(shape).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized standard gamma distribution.
See Also
--------
scipy.stats.gamma : probability density function, distribution or
cumulative density function, etc.
random.Generator.standard_gamma: which should be used for new code.
Notes
-----
The probability density for the Gamma distribution is
.. math:: p(x) = x^{k-1}\frac{e^{-x/\theta}}{\theta^k\Gamma(k)},
where :math:`k` is the shape and :math:`\theta` the scale,
and :math:`\Gamma` is the Gamma function.
The Gamma distribution is often used to model the times to failure of
electronic components, and arises naturally in processes for which the
waiting times between Poisson distributed events are relevant.
References
----------
.. [1] Weisstein, Eric W. "Gamma Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/GammaDistribution.html
.. [2] Wikipedia, "Gamma distribution",
https://en.wikipedia.org/wiki/Gamma_distribution
Examples
--------
Draw samples from the distribution:
>>> shape, scale = 2., 1. # mean and width
>>> s = np.random.standard_gamma(shape, 1000000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> import scipy.special as sps # doctest: +SKIP
>>> count, bins, ignored = plt.hist(s, 50, density=True)
>>> y = bins**(shape-1) * ((np.exp(-bins/scale))/ # doctest: +SKIP
... (sps.gamma(shape) * scale**shape))
>>> plt.plot(bins, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
standard_normal(size=None)
Draw samples from a standard Normal distribution (mean=0, stdev=1).
.. note::
New code should use the
`~numpy.random.Generator.standard_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray
A floating-point array of shape ``size`` of drawn samples, or a
single sample if ``size`` was not specified.
See Also
--------
normal :
Equivalent function with additional ``loc`` and ``scale`` arguments
for setting the mean and standard deviation.
random.Generator.standard_normal: which should be used for new code.
Notes
-----
For random samples from the normal distribution with mean ``mu`` and
standard deviation ``sigma``, use one of::
mu + sigma * np.random.standard_normal(size=...)
np.random.normal(mu, sigma, size=...)
Examples
--------
>>> np.random.standard_normal()
2.1923875335537315 #random
>>> s = np.random.standard_normal(8000)
>>> s
array([ 0.6888893 , 0.78096262, -0.89086505, ..., 0.49876311, # random
-0.38672696, -0.4685006 ]) # random
>>> s.shape
(8000,)
>>> s = np.random.standard_normal(size=(3, 4, 2))
>>> s.shape
(3, 4, 2)
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> 3 + 2.5 * np.random.standard_normal(size=(2, 4))
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
standard_t(df, size=None)
Draw samples from a standard Student's t distribution with `df` degrees
of freedom.
A special case of the hyperbolic distribution. As `df` gets
large, the result resembles that of the standard normal
distribution (`standard_normal`).
.. note::
New code should use the `~numpy.random.Generator.standard_t`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Degrees of freedom, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` is a scalar. Otherwise,
``np.array(df).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized standard Student's t distribution.
See Also
--------
random.Generator.standard_t: which should be used for new code.
Notes
-----
The probability density function for the t distribution is
.. math:: P(x, df) = \frac{\Gamma(\frac{df+1}{2})}{\sqrt{\pi df}
\Gamma(\frac{df}{2})}\Bigl( 1+\frac{x^2}{df} \Bigr)^{-(df+1)/2}
The t test is based on an assumption that the data come from a
Normal distribution. The t test provides a way to test whether
the sample mean (that is the mean calculated from the data) is
a good estimate of the true mean.
The derivation of the t-distribution was first published in
1908 by William Gosset while working for the Guinness Brewery
in Dublin. Due to proprietary issues, he had to publish under
a pseudonym, and so he used the name Student.
References
----------
.. [1] Dalgaard, Peter, "Introductory Statistics With R",
Springer, 2002.
.. [2] Wikipedia, "Student's t-distribution"
https://en.wikipedia.org/wiki/Student's_t-distribution
Examples
--------
From Dalgaard page 83 [1]_, suppose the daily energy intake for 11
women in kilojoules (kJ) is:
>>> intake = np.array([5260., 5470, 5640, 6180, 6390, 6515, 6805, 7515, \
... 7515, 8230, 8770])
Does their energy intake deviate systematically from the recommended
value of 7725 kJ? Our null hypothesis will be the absence of deviation,
and the alternate hypothesis will be the presence of an effect that could be
either positive or negative, hence making our test 2-tailed.
Because we are estimating the mean and we have N=11 values in our sample,
we have N-1=10 degrees of freedom. We set our significance level to 95% and
compute the t statistic using the empirical mean and empirical standard
deviation of our intake. We use a ddof of 1 to base the computation of our
empirical standard deviation on an unbiased estimate of the variance (note:
the final estimate is not unbiased due to the concave nature of the square
root).
>>> np.mean(intake)
6753.636363636364
>>> intake.std(ddof=1)
1142.1232221373727
>>> t = (np.mean(intake)-7725)/(intake.std(ddof=1)/np.sqrt(len(intake)))
>>> t
-2.8207540608310198
We draw 1000000 samples from Student's t distribution with the adequate
degrees of freedom.
>>> import matplotlib.pyplot as plt
>>> s = np.random.standard_t(10, size=1000000)
>>> h = plt.hist(s, bins=100, density=True)
Does our t statistic land in one of the two critical regions found at
both tails of the distribution?
>>> np.sum(np.abs(t) < np.abs(s)) / float(len(s))
0.018318 #random < 0.05, statistic is in critical region
The probability value for this 2-tailed test is about 1.83%, which is
lower than the 5% pre-determined significance threshold.
Therefore, the probability of observing values as extreme as our intake
conditionally on the null hypothesis being true is too low, and we reject
the null hypothesis of no deviation.
state state dictionary is not valid. state must be a dict or a tuple. __str__ strides subtract sum sum(pvals[:-1]) > 1.0 sum(pvals[:-1].astype(np.float64)) > 1.0. The pvals array is cast to 64-bit floating point prior to checking the sum. Precision changes when casting may cause problems even if the sum of the original pvals is valid. svd take __test__ tobytes tol
tomaxint(size=None)
Return a sample of uniformly distributed random integers in the interval
[0, ``np.iinfo(np.int_).max``]. The `np.int_` type translates to the C long
integer type and its precision is platform dependent.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : ndarray
Drawn samples, with shape `size`.
See Also
--------
randint : Uniform sampling over a given half-open interval of integers.
random_integers : Uniform sampling over a given closed interval of
integers.
Examples
--------
>>> rs = np.random.RandomState() # need a RandomState object
>>> rs.tomaxint((2,2,2))
array([[[1170048599, 1600360186], # random
[ 739731006, 1947757578]],
[[1871712945, 752307660],
[1601631370, 1479324245]]])
>>> rs.tomaxint((2,2,2)) < np.iinfo(np.int_).max
array([[[ True, True],
[ True, True]],
[[ True, True],
[ True, True]]])
triangular(left, mode, right, size=None)
Draw samples from the triangular distribution over the
interval ``[left, right]``.
The triangular distribution is a continuous probability
distribution with lower limit left, peak at mode, and upper
limit right. Unlike the other distributions, these parameters
directly define the shape of the pdf.
.. note::
New code should use the `~numpy.random.Generator.triangular`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
left : float or array_like of floats
Lower limit.
mode : float or array_like of floats
The value where the peak of the distribution occurs.
The value must fulfill the condition ``left <= mode <= right``.
right : float or array_like of floats
Upper limit, must be larger than `left`.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``left``, ``mode``, and ``right``
are all scalars. Otherwise, ``np.broadcast(left, mode, right).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized triangular distribution.
See Also
--------
random.Generator.triangular: which should be used for new code.
Notes
-----
The probability density function for the triangular distribution is
.. math:: P(x;l, m, r) = \begin{cases}
\frac{2(x-l)}{(r-l)(m-l)}& \text{for $l \leq x \leq m$},\\
\frac{2(r-x)}{(r-l)(r-m)}& \text{for $m \leq x \leq r$},\\
0& \text{otherwise}.
\end{cases}
The triangular distribution is often used in ill-defined
problems where the underlying distribution is not known, but
some knowledge of the limits and mode exists. Often it is used
in simulations.
References
----------
.. [1] Wikipedia, "Triangular distribution"
https://en.wikipedia.org/wiki/Triangular_distribution
Examples
--------
Draw values from the distribution and plot the histogram:
>>> import matplotlib.pyplot as plt
>>> h = plt.hist(np.random.triangular(-3, 0, 8, 100000), bins=200,
... density=True)
>>> plt.show()
<u4 uint16 uint32 uint64 uint8
uniform(low=0.0, high=1.0, size=None)
Draw samples from a uniform distribution.
Samples are uniformly distributed over the half-open interval
``[low, high)`` (includes low, but excludes high). In other words,
any value within the given interval is equally likely to be drawn
by `uniform`.
.. note::
New code should use the `~numpy.random.Generator.uniform`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
low : float or array_like of floats, optional
Lower boundary of the output interval. All values generated will be
greater than or equal to low. The default value is 0.
high : float or array_like of floats
Upper boundary of the output interval. All values generated will be
less than or equal to high. The high limit may be included in the
returned array of floats due to floating-point rounding in the
equation ``low + (high-low) * random_sample()``. The default value
is 1.0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``low`` and ``high`` are both scalars.
Otherwise, ``np.broadcast(low, high).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized uniform distribution.
See Also
--------
randint : Discrete uniform distribution, yielding integers.
random_integers : Discrete uniform distribution over the closed
interval ``[low, high]``.
random_sample : Floats uniformly distributed over ``[0, 1)``.
random : Alias for `random_sample`.
rand : Convenience function that accepts dimensions as input, e.g.,
``rand(2,2)`` would generate a 2-by-2 array of floats,
uniformly distributed over ``[0, 1)``.
random.Generator.uniform: which should be used for new code.
Notes
-----
The probability density function of the uniform distribution is
.. math:: p(x) = \frac{1}{b - a}
anywhere within the interval ``[a, b)``, and zero elsewhere.
When ``high`` == ``low``, values of ``low`` will be returned.
If ``high`` < ``low``, the results are officially undefined
and may eventually raise an error, i.e. do not rely on this
function to behave when passed arguments satisfying that
inequality condition. The ``high`` limit may be included in the
returned array of floats due to floating-point rounding in the
equation ``low + (high-low) * random_sample()``. For example:
>>> x = np.float32(5*0.99999999)
>>> x
5.0
Examples
--------
Draw samples from the distribution:
>>> s = np.random.uniform(-1,0,1000)
All values are within the given interval:
>>> np.all(s >= -1)
True
>>> np.all(s < 0)
True
Display the histogram of the samples, along with the
probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 15, density=True)
>>> plt.plot(bins, np.ones_like(bins), linewidth=2, color='r')
>>> plt.show()
unique unsafe
vonmises(mu, kappa, size=None)
Draw samples from a von Mises distribution.
Samples are drawn from a von Mises distribution with specified mode
(mu) and dispersion (kappa), on the interval [-pi, pi].
The von Mises distribution (also known as the circular normal
distribution) is a continuous probability distribution on the unit
circle. It may be thought of as the circular analogue of the normal
distribution.
.. note::
New code should use the `~numpy.random.Generator.vonmises`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mu : float or array_like of floats
Mode ("center") of the distribution.
kappa : float or array_like of floats
Dispersion of the distribution, has to be >=0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mu`` and ``kappa`` are both scalars.
Otherwise, ``np.broadcast(mu, kappa).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized von Mises distribution.
See Also
--------
scipy.stats.vonmises : probability density function, distribution, or
cumulative density function, etc.
random.Generator.vonmises: which should be used for new code.
Notes
-----
The probability density for the von Mises distribution is
.. math:: p(x) = \frac{e^{\kappa cos(x-\mu)}}{2\pi I_0(\kappa)},
where :math:`\mu` is the mode and :math:`\kappa` the dispersion,
and :math:`I_0(\kappa)` is the modified Bessel function of order 0.
The von Mises is named for Richard Edler von Mises, who was born in
Austria-Hungary, in what is now the Ukraine. He fled to the United
States in 1939 and became a professor at Harvard. He worked in
probability theory, aerodynamics, fluid mechanics, and philosophy of
science.
References
----------
.. [1] Abramowitz, M. and Stegun, I. A. (Eds.). "Handbook of
Mathematical Functions with Formulas, Graphs, and Mathematical
Tables, 9th printing," New York: Dover, 1972.
.. [2] von Mises, R., "Mathematical Theory of Probability
and Statistics", New York: Academic Press, 1964.
Examples
--------
Draw samples from the distribution:
>>> mu, kappa = 0.0, 4.0 # mean and dispersion
>>> s = np.random.vonmises(mu, kappa, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> from scipy.special import i0 # doctest: +SKIP
>>> plt.hist(s, 50, density=True)
>>> x = np.linspace(-np.pi, np.pi, num=51)
>>> y = np.exp(kappa*np.cos(x-mu))/(2*np.pi*i0(kappa)) # doctest: +SKIP
>>> plt.plot(x, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
wald(mean, scale, size=None)
Draw samples from a Wald, or inverse Gaussian, distribution.
As the scale approaches infinity, the distribution becomes more like a
Gaussian. Some references claim that the Wald is an inverse Gaussian
with mean equal to 1, but this is by no means universal.
The inverse Gaussian distribution was first studied in relationship to
Brownian motion. In 1956 M.C.K. Tweedie used the name inverse Gaussian
because there is an inverse relationship between the time to cover a
unit distance and distance covered in unit time.
.. note::
New code should use the `~numpy.random.Generator.wald`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : float or array_like of floats
Distribution mean, must be > 0.
scale : float or array_like of floats
Scale parameter, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mean`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(mean, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Wald distribution.
See Also
--------
random.Generator.wald: which should be used for new code.
Notes
-----
The probability density function for the Wald distribution is
.. math:: P(x;mean,scale) = \sqrt{\frac{scale}{2\pi x^3}}e^
\frac{-scale(x-mean)^2}{2\cdotp mean^2x}
As noted above the inverse Gaussian distribution first arise
from attempts to model Brownian motion. It is also a
competitor to the Weibull for use in reliability modeling and
modeling stock returns and interest rate processes.
References
----------
.. [1] Brighton Webs Ltd., Wald Distribution,
https://web.archive.org/web/20090423014010/http://www.brighton-webs.co.uk:80/distributions/wald.asp
.. [2] Chhikara, Raj S., and Folks, J. Leroy, "The Inverse Gaussian
Distribution: Theory : Methodology, and Applications", CRC Press,
1988.
.. [3] Wikipedia, "Inverse Gaussian distribution"
https://en.wikipedia.org/wiki/Inverse_Gaussian_distribution
Examples
--------
Draw values from the distribution and plot the histogram:
>>> import matplotlib.pyplot as plt
>>> h = plt.hist(np.random.wald(3, 2, 100000), bins=200, density=True)
>>> plt.show()
warn warnings
weibull(a, size=None)
Draw samples from a Weibull distribution.
Draw samples from a 1-parameter Weibull distribution with the given
shape parameter `a`.
.. math:: X = (-ln(U))^{1/a}
Here, U is drawn from the uniform distribution over (0,1].
The more common 2-parameter Weibull, including a scale parameter
:math:`\lambda` is just :math:`X = \lambda(-ln(U))^{1/a}`.
.. note::
New code should use the `~numpy.random.Generator.weibull`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Shape parameter of the distribution. Must be nonnegative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Weibull distribution.
See Also
--------
scipy.stats.weibull_max
scipy.stats.weibull_min
scipy.stats.genextreme
gumbel
random.Generator.weibull: which should be used for new code.
Notes
-----
The Weibull (or Type III asymptotic extreme value distribution
for smallest values, SEV Type III, or Rosin-Rammler
distribution) is one of a class of Generalized Extreme Value
(GEV) distributions used in modeling extreme value problems.
This class includes the Gumbel and Frechet distributions.
The probability density for the Weibull distribution is
.. math:: p(x) = \frac{a}
{\lambda}(\frac{x}{\lambda})^{a-1}e^{-(x/\lambda)^a},
where :math:`a` is the shape and :math:`\lambda` the scale.
The function has its peak (the mode) at
:math:`\lambda(\frac{a-1}{a})^{1/a}`.
When ``a = 1``, the Weibull distribution reduces to the exponential
distribution.
References
----------
.. [1] Waloddi Weibull, Royal Technical University, Stockholm,
1939 "A Statistical Theory Of The Strength Of Materials",
Ingeniorsvetenskapsakademiens Handlingar Nr 151, 1939,
Generalstabens Litografiska Anstalts Forlag, Stockholm.
.. [2] Waloddi Weibull, "A Statistical Distribution Function of
Wide Applicability", Journal Of Applied Mechanics ASME Paper
1951.
.. [3] Wikipedia, "Weibull distribution",
https://en.wikipedia.org/wiki/Weibull_distribution
Examples
--------
Draw samples from the distribution:
>>> a = 5. # shape
>>> s = np.random.weibull(a, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> x = np.arange(1,100.)/50.
>>> def weib(x,n,a):
... return (a / n) * (x / n)**(a - 1) * np.exp(-(x / n)**a)
>>> count, bins, ignored = plt.hist(np.random.weibull(5.,1000))
>>> x = np.arange(1,100.)/50.
>>> scale = count.max()/weib(x, 1., 5.).max()
>>> plt.plot(x, weib(x, 1., 5.)*scale)
>>> plt.show()
writeable x x must be an integer or at least 1-dimensional you are shuffling a ' zeros
zipf(a, size=None)
Draw samples from a Zipf distribution.
Samples are drawn from a Zipf distribution with specified parameter
`a` > 1.
The Zipf distribution (also known as the zeta distribution) is a
discrete probability distribution that satisfies Zipf's law: the
frequency of an item is inversely proportional to its rank in a
frequency table.
.. note::
New code should use the `~numpy.random.Generator.zipf`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Distribution parameter. Must be greater than 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Zipf distribution.
See Also
--------
scipy.stats.zipf : probability density function, distribution, or
cumulative density function, etc.
random.Generator.zipf: which should be used for new code.
Notes
-----
The probability density for the Zipf distribution is
.. math:: p(k) = \frac{k^{-a}}{\zeta(a)},
for integers :math:`k \geq 1`, where :math:`\zeta` is the Riemann Zeta
function.
It is named for the American linguist George Kingsley Zipf, who noted
that the frequency of any word in a sample of a language is inversely
proportional to its rank in the frequency table.
References
----------
.. [1] Zipf, G. K., "Selected Studies of the Principle of Relative
Frequency in Language," Cambridge, MA: Harvard Univ. Press,
1932.
Examples
--------
Draw samples from the distribution:
>>> a = 4.0
>>> n = 20000
>>> s = np.random.zipf(a, n)
Display the histogram of the samples, along with
the expected histogram based on the probability
density function:
>>> import matplotlib.pyplot as plt
>>> from scipy.special import zeta # doctest: +SKIP
`bincount` provides a fast histogram for small integers.
>>> count = np.bincount(s)
>>> k = np.arange(1, s.max() + 1)
>>> plt.bar(k, count[1:], alpha=0.5, label='sample count')
>>> plt.plot(k, n*(k**-a)/zeta(a), 'k.-', alpha=0.5,
... label='expected count') # doctest: +SKIP
>>> plt.semilogy()
>>> plt.grid(alpha=0.4)
>>> plt.legend()
>>> plt.title(f'Zipf sample, a={a}, size={n}')
>>> plt.show()
__reduce__ seed
seed(seed=None)
Reseed a legacy MT19937 BitGenerator
Notes
-----
This is a convenience, legacy function.
The best practice is to **not** reseed a BitGenerator, rather to
recreate a new one. This method is here for legacy reasons.
This example demonstrates best practice.
>>> from numpy.random import MT19937
>>> from numpy.random import RandomState, SeedSequence
>>> rs = RandomState(MT19937(SeedSequence(123456789)))
# Later, you want to restart the stream
>>> rs = RandomState(MT19937(SeedSequence(987654321)))
get_state
get_state(legacy=True)
Return a tuple representing the internal state of the generator.
For more details, see `set_state`.
Parameters
----------
legacy : bool, optional
Flag indicating to return a legacy tuple state when the BitGenerator
is MT19937, instead of a dict. Raises ValueError if the underlying
bit generator is not an instance of MT19937.
Returns
-------
out : {tuple(str, ndarray of 624 uints, int, int, float), dict}
If legacy is True, the returned tuple has the following items:
1. the string 'MT19937'.
2. a 1-D array of 624 unsigned integer keys.
3. an integer ``pos``.
4. an integer ``has_gauss``.
5. a float ``cached_gaussian``.
If `legacy` is False, or the BitGenerator is not MT19937, then
state is returned as a dictionary.
See Also
--------
set_state
Notes
-----
`set_state` and `get_state` are not needed to work with any of the
random distributions in NumPy. If the internal state is manually altered,
the user should know exactly what he/she is doing.
set_state
set_state(state)
Set the internal state of the generator from a tuple.
For use if one has reason to manually (re-)set the internal state of
the bit generator used by the RandomState instance. By default,
RandomState uses the "Mersenne Twister"[1]_ pseudo-random number
generating algorithm.
Parameters
----------
state : {tuple(str, ndarray of 624 uints, int, int, float), dict}
The `state` tuple has the following items:
1. the string 'MT19937', specifying the Mersenne Twister algorithm.
2. a 1-D array of 624 unsigned integers ``keys``.
3. an integer ``pos``.
4. an integer ``has_gauss``.
5. a float ``cached_gaussian``.
If state is a dictionary, it is directly set using the BitGenerators
`state` property.
Returns
-------
out : None
Returns 'None' on success.
See Also
--------
get_state
Notes
-----
`set_state` and `get_state` are not needed to work with any of the
random distributions in NumPy. If the internal state is manually altered,
the user should know exactly what he/she is doing.
For backwards compatibility, the form (str, array of 624 uints, int) is
also accepted although it is missing some information about the cached
Gaussian value: ``state = ('MT19937', keys, pos)``.
References
----------
.. [1] M. Matsumoto and T. Nishimura, "Mersenne Twister: A
623-dimensionally equidistributed uniform pseudorandom number
generator," *ACM Trans. on Modeling and Computer Simulation*,
Vol. 8, No. 1, pp. 3-30, Jan. 1998.
random_sample
random_sample(size=None)
Return random floats in the half-open interval [0.0, 1.0).
Results are from the "continuous uniform" distribution over the
stated interval. To sample :math:`Unif[a, b), b > a` multiply
the output of `random_sample` by `(b-a)` and add `a`::
(b - a) * random_sample() + a
.. note::
New code should use the `~numpy.random.Generator.random`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray of floats
Array of random floats of shape `size` (unless ``size=None``, in which
case a single float is returned).
See Also
--------
random.Generator.random: which should be used for new code.
Examples
--------
>>> np.random.random_sample()
0.47108547995356098 # random
>>> type(np.random.random_sample())
<class 'float'>
>>> np.random.random_sample((5,))
array([ 0.30220482, 0.86820401, 0.1654503 , 0.11659149, 0.54323428]) # random
Three-by-two array of random numbers from [-5, 0):
>>> 5 * np.random.random_sample((3, 2)) - 5
array([[-3.99149989, -0.52338984], # random
[-2.99091858, -0.79479508],
[-1.23204345, -1.75224494]])
random
random(size=None)
Return random floats in the half-open interval [0.0, 1.0). Alias for
`random_sample` to ease forward-porting to the new random API.
beta
beta(a, b, size=None)
Draw samples from a Beta distribution.
The Beta distribution is a special case of the Dirichlet distribution,
and is related to the Gamma distribution. It has the probability
distribution function
.. math:: f(x; a,b) = \frac{1}{B(\alpha, \beta)} x^{\alpha - 1}
(1 - x)^{\beta - 1},
where the normalization, B, is the beta function,
.. math:: B(\alpha, \beta) = \int_0^1 t^{\alpha - 1}
(1 - t)^{\beta - 1} dt.
It is often seen in Bayesian inference and order statistics.
.. note::
New code should use the `~numpy.random.Generator.beta`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Alpha, positive (>0).
b : float or array_like of floats
Beta, positive (>0).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` and ``b`` are both scalars.
Otherwise, ``np.broadcast(a, b).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized beta distribution.
See Also
--------
random.Generator.beta: which should be used for new code.
exponential
exponential(scale=1.0, size=None)
Draw samples from an exponential distribution.
Its probability density function is
.. math:: f(x; \frac{1}{\beta}) = \frac{1}{\beta} \exp(-\frac{x}{\beta}),
for ``x > 0`` and 0 elsewhere. :math:`\beta` is the scale parameter,
which is the inverse of the rate parameter :math:`\lambda = 1/\beta`.
The rate parameter is an alternative, widely used parameterization
of the exponential distribution [3]_.
The exponential distribution is a continuous analogue of the
geometric distribution. It describes many common situations, such as
the size of raindrops measured over many rainstorms [1]_, or the time
between page requests to Wikipedia [2]_.
.. note::
New code should use the `~numpy.random.Generator.exponential`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
scale : float or array_like of floats
The scale parameter, :math:`\beta = 1/\lambda`. Must be
non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``scale`` is a scalar. Otherwise,
``np.array(scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized exponential distribution.
Examples
--------
A real world example: Assume a company has 10000 customer support
agents and the average time between customer calls is 4 minutes.
>>> n = 10000
>>> time_between_calls = np.random.default_rng().exponential(scale=4, size=n)
What is the probability that a customer will call in the next
4 to 5 minutes?
>>> x = ((time_between_calls < 5).sum())/n
>>> y = ((time_between_calls < 4).sum())/n
>>> x-y
0.08 # may vary
See Also
--------
random.Generator.exponential: which should be used for new code.
References
----------
.. [1] Peyton Z. Peebles Jr., "Probability, Random Variables and
Random Signal Principles", 4th ed, 2001, p. 57.
.. [2] Wikipedia, "Poisson process",
https://en.wikipedia.org/wiki/Poisson_process
.. [3] Wikipedia, "Exponential distribution",
https://en.wikipedia.org/wiki/Exponential_distribution
standard_exponential
standard_exponential(size=None)
Draw samples from the standard exponential distribution.
`standard_exponential` is identical to the exponential distribution
with a scale parameter of 1.
.. note::
New code should use the
`~numpy.random.Generator.standard_exponential`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray
Drawn samples.
See Also
--------
random.Generator.standard_exponential: which should be used for new code.
Examples
--------
Output a 3x8000 array:
>>> n = np.random.standard_exponential((3, 8000))
tomaxint(size=None)
Return a sample of uniformly distributed random integers in the interval
[0, ``np.iinfo(np.int_).max``]. The `np.int_` type translates to the C long
integer type and its precision is platform dependent.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : ndarray
Drawn samples, with shape `size`.
See Also
--------
randint : Uniform sampling over a given half-open interval of integers.
random_integers : Uniform sampling over a given closed interval of
integers.
Examples
--------
>>> rs = np.random.RandomState() # need a RandomState object
>>> rs.tomaxint((2,2,2))
array([[[1170048599, 1600360186], # random
[ 739731006, 1947757578]],
[[1871712945, 752307660],
[1601631370, 1479324245]]])
>>> rs.tomaxint((2,2,2)) < np.iinfo(np.int_).max
array([[[ True, True],
[ True, True]],
[[ True, True],
[ True, True]]])
randint
randint(low, high=None, size=None, dtype=int)
Return random integers from `low` (inclusive) to `high` (exclusive).
Return random integers from the "discrete uniform" distribution of
the specified dtype in the "half-open" interval [`low`, `high`). If
`high` is None (the default), then results are from [0, `low`).
.. note::
New code should use the `~numpy.random.Generator.integers`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
low : int or array-like of ints
Lowest (signed) integers to be drawn from the distribution (unless
``high=None``, in which case this parameter is one above the
*highest* such integer).
high : int or array-like of ints, optional
If provided, one above the largest (signed) integer to be drawn
from the distribution (see above for behavior if ``high=None``).
If array-like, must contain integer values
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
dtype : dtype, optional
Desired dtype of the result. Byteorder must be native.
The default value is int.
.. versionadded:: 1.11.0
Returns
-------
out : int or ndarray of ints
`size`-shaped array of random integers from the appropriate
distribution, or a single such random int if `size` not provided.
See Also
--------
random_integers : similar to `randint`, only for the closed
interval [`low`, `high`], and 1 is the lowest value if `high` is
omitted.
random.Generator.integers: which should be used for new code.
Examples
--------
>>> np.random.randint(2, size=10)
array([1, 0, 0, 0, 1, 1, 0, 0, 1, 0]) # random
>>> np.random.randint(1, size=10)
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
Generate a 2 x 4 array of ints between 0 and 4, inclusive:
>>> np.random.randint(5, size=(2, 4))
array([[4, 0, 2, 1], # random
[3, 2, 2, 0]])
Generate a 1 x 3 array with 3 different upper bounds
>>> np.random.randint(1, [3, 5, 10])
array([2, 2, 9]) # random
Generate a 1 by 3 array with 3 different lower bounds
>>> np.random.randint([1, 5, 7], 10)
array([9, 8, 7]) # random
Generate a 2 by 4 array using broadcasting with dtype of uint8
>>> np.random.randint([1, 3, 5, 7], [[10], [20]], dtype=np.uint8)
array([[ 8, 6, 9, 7], # random
[ 1, 16, 9, 12]], dtype=uint8)
bytes
bytes(length)
Return random bytes.
.. note::
New code should use the `~numpy.random.Generator.bytes`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
length : int
Number of random bytes.
Returns
-------
out : bytes
String of length `length`.
See Also
--------
random.Generator.bytes: which should be used for new code.
Examples
--------
>>> np.random.bytes(10)
b' eh\x85\x022SZ\xbf\xa4' #random
choice
choice(a, size=None, replace=True, p=None)
Generates a random sample from a given 1-D array
.. versionadded:: 1.7.0
.. note::
New code should use the `~numpy.random.Generator.choice`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : 1-D array-like or int
If an ndarray, a random sample is generated from its elements.
If an int, the random sample is generated as if it were ``np.arange(a)``
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
replace : boolean, optional
Whether the sample is with or without replacement. Default is True,
meaning that a value of ``a`` can be selected multiple times.
p : 1-D array-like, optional
The probabilities associated with each entry in a.
If not given, the sample assumes a uniform distribution over all
entries in ``a``.
Returns
-------
samples : single item or ndarray
The generated random samples
Raises
------
ValueError
If a is an int and less than zero, if a or p are not 1-dimensional,
if a is an array-like of size 0, if p is not a vector of
probabilities, if a and p have different lengths, or if
replace=False and the sample size is greater than the population
size
See Also
--------
randint, shuffle, permutation
random.Generator.choice: which should be used in new code
Notes
-----
Setting user-specified probabilities through ``p`` uses a more general but less
efficient sampler than the default. The general sampler produces a different sample
than the optimized sampler even if each element of ``p`` is 1 / len(a).
Sampling random rows from a 2-D array is not possible with this function,
but is possible with `Generator.choice` through its ``axis`` keyword.
Examples
--------
Generate a uniform random sample from np.arange(5) of size 3:
>>> np.random.choice(5, 3)
array([0, 3, 4]) # random
>>> #This is equivalent to np.random.randint(0,5,3)
Generate a non-uniform random sample from np.arange(5) of size 3:
>>> np.random.choice(5, 3, p=[0.1, 0, 0.3, 0.6, 0])
array([3, 3, 0]) # random
Generate a uniform random sample from np.arange(5) of size 3 without
replacement:
>>> np.random.choice(5, 3, replace=False)
array([3,1,0]) # random
>>> #This is equivalent to np.random.permutation(np.arange(5))[:3]
Generate a non-uniform random sample from np.arange(5) of size
3 without replacement:
>>> np.random.choice(5, 3, replace=False, p=[0.1, 0, 0.3, 0.6, 0])
array([2, 3, 0]) # random
Any of the above can be repeated with an arbitrary array-like
instead of just integers. For instance:
>>> aa_milne_arr = ['pooh', 'rabbit', 'piglet', 'Christopher']
>>> np.random.choice(aa_milne_arr, 5, p=[0.5, 0.1, 0.1, 0.3])
array(['pooh', 'pooh', 'pooh', 'Christopher', 'piglet'], # random
dtype='<U11')
uniform
uniform(low=0.0, high=1.0, size=None)
Draw samples from a uniform distribution.
Samples are uniformly distributed over the half-open interval
``[low, high)`` (includes low, but excludes high). In other words,
any value within the given interval is equally likely to be drawn
by `uniform`.
.. note::
New code should use the `~numpy.random.Generator.uniform`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
low : float or array_like of floats, optional
Lower boundary of the output interval. All values generated will be
greater than or equal to low. The default value is 0.
high : float or array_like of floats
Upper boundary of the output interval. All values generated will be
less than or equal to high. The high limit may be included in the
returned array of floats due to floating-point rounding in the
equation ``low + (high-low) * random_sample()``. The default value
is 1.0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``low`` and ``high`` are both scalars.
Otherwise, ``np.broadcast(low, high).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized uniform distribution.
See Also
--------
randint : Discrete uniform distribution, yielding integers.
random_integers : Discrete uniform distribution over the closed
interval ``[low, high]``.
random_sample : Floats uniformly distributed over ``[0, 1)``.
random : Alias for `random_sample`.
rand : Convenience function that accepts dimensions as input, e.g.,
``rand(2,2)`` would generate a 2-by-2 array of floats,
uniformly distributed over ``[0, 1)``.
random.Generator.uniform: which should be used for new code.
Notes
-----
The probability density function of the uniform distribution is
.. math:: p(x) = \frac{1}{b - a}
anywhere within the interval ``[a, b)``, and zero elsewhere.
When ``high`` == ``low``, values of ``low`` will be returned.
If ``high`` < ``low``, the results are officially undefined
and may eventually raise an error, i.e. do not rely on this
function to behave when passed arguments satisfying that
inequality condition. The ``high`` limit may be included in the
returned array of floats due to floating-point rounding in the
equation ``low + (high-low) * random_sample()``. For example:
>>> x = np.float32(5*0.99999999)
>>> x
5.0
Examples
--------
Draw samples from the distribution:
>>> s = np.random.uniform(-1,0,1000)
All values are within the given interval:
>>> np.all(s >= -1)
True
>>> np.all(s < 0)
True
Display the histogram of the samples, along with the
probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 15, density=True)
>>> plt.plot(bins, np.ones_like(bins), linewidth=2, color='r')
>>> plt.show()
rand
rand(d0, d1, ..., dn)
Random values in a given shape.
.. note::
This is a convenience function for users porting code from Matlab,
and wraps `random_sample`. That function takes a
tuple to specify the size of the output, which is consistent with
other NumPy functions like `numpy.zeros` and `numpy.ones`.
Create an array of the given shape and populate it with
random samples from a uniform distribution
over ``[0, 1)``.
Parameters
----------
d0, d1, ..., dn : int, optional
The dimensions of the returned array, must be non-negative.
If no argument is given a single Python float is returned.
Returns
-------
out : ndarray, shape ``(d0, d1, ..., dn)``
Random values.
See Also
--------
random
Examples
--------
>>> np.random.rand(3,2)
array([[ 0.14022471, 0.96360618], #random
[ 0.37601032, 0.25528411], #random
[ 0.49313049, 0.94909878]]) #random
randn
randn(d0, d1, ..., dn)
Return a sample (or samples) from the "standard normal" distribution.
.. note::
This is a convenience function for users porting code from Matlab,
and wraps `standard_normal`. That function takes a
tuple to specify the size of the output, which is consistent with
other NumPy functions like `numpy.zeros` and `numpy.ones`.
.. note::
New code should use the
`~numpy.random.Generator.standard_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
If positive int_like arguments are provided, `randn` generates an array
of shape ``(d0, d1, ..., dn)``, filled
with random floats sampled from a univariate "normal" (Gaussian)
distribution of mean 0 and variance 1. A single float randomly sampled
from the distribution is returned if no argument is provided.
Parameters
----------
d0, d1, ..., dn : int, optional
The dimensions of the returned array, must be non-negative.
If no argument is given a single Python float is returned.
Returns
-------
Z : ndarray or float
A ``(d0, d1, ..., dn)``-shaped array of floating-point samples from
the standard normal distribution, or a single such float if
no parameters were supplied.
See Also
--------
standard_normal : Similar, but takes a tuple as its argument.
normal : Also accepts mu and sigma arguments.
random.Generator.standard_normal: which should be used for new code.
Notes
-----
For random samples from the normal distribution with mean ``mu`` and
standard deviation ``sigma``, use::
sigma * np.random.randn(...) + mu
Examples
--------
>>> np.random.randn()
2.1923875335537315 # random
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> 3 + 2.5 * np.random.randn(2, 4)
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
random_integers
random_integers(low, high=None, size=None)
Random integers of type `np.int_` between `low` and `high`, inclusive.
Return random integers of type `np.int_` from the "discrete uniform"
distribution in the closed interval [`low`, `high`]. If `high` is
None (the default), then results are from [1, `low`]. The `np.int_`
type translates to the C long integer type and its precision
is platform dependent.
This function has been deprecated. Use randint instead.
.. deprecated:: 1.11.0
Parameters
----------
low : int
Lowest (signed) integer to be drawn from the distribution (unless
``high=None``, in which case this parameter is the *highest* such
integer).
high : int, optional
If provided, the largest (signed) integer to be drawn from the
distribution (see above for behavior if ``high=None``).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : int or ndarray of ints
`size`-shaped array of random integers from the appropriate
distribution, or a single such random int if `size` not provided.
See Also
--------
randint : Similar to `random_integers`, only for the half-open
interval [`low`, `high`), and 0 is the lowest value if `high` is
omitted.
Notes
-----
To sample from N evenly spaced floating-point numbers between a and b,
use::
a + (b - a) * (np.random.random_integers(N) - 1) / (N - 1.)
Examples
--------
>>> np.random.random_integers(5)
4 # random
>>> type(np.random.random_integers(5))
<class 'numpy.int64'>
>>> np.random.random_integers(5, size=(3,2))
array([[5, 4], # random
[3, 3],
[4, 5]])
Choose five random numbers from the set of five evenly-spaced
numbers between 0 and 2.5, inclusive (*i.e.*, from the set
:math:`{0, 5/8, 10/8, 15/8, 20/8}`):
>>> 2.5 * (np.random.random_integers(5, size=(5,)) - 1) / 4.
array([ 0.625, 1.25 , 0.625, 0.625, 2.5 ]) # random
Roll two six sided dice 1000 times and sum the results:
>>> d1 = np.random.random_integers(1, 6, 1000)
>>> d2 = np.random.random_integers(1, 6, 1000)
>>> dsums = d1 + d2
Display results as a histogram:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(dsums, 11, density=True)
>>> plt.show()
standard_normal
standard_normal(size=None)
Draw samples from a standard Normal distribution (mean=0, stdev=1).
.. note::
New code should use the
`~numpy.random.Generator.standard_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray
A floating-point array of shape ``size`` of drawn samples, or a
single sample if ``size`` was not specified.
See Also
--------
normal :
Equivalent function with additional ``loc`` and ``scale`` arguments
for setting the mean and standard deviation.
random.Generator.standard_normal: which should be used for new code.
Notes
-----
For random samples from the normal distribution with mean ``mu`` and
standard deviation ``sigma``, use one of::
mu + sigma * np.random.standard_normal(size=...)
np.random.normal(mu, sigma, size=...)
Examples
--------
>>> np.random.standard_normal()
2.1923875335537315 #random
>>> s = np.random.standard_normal(8000)
>>> s
array([ 0.6888893 , 0.78096262, -0.89086505, ..., 0.49876311, # random
-0.38672696, -0.4685006 ]) # random
>>> s.shape
(8000,)
>>> s = np.random.standard_normal(size=(3, 4, 2))
>>> s.shape
(3, 4, 2)
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> 3 + 2.5 * np.random.standard_normal(size=(2, 4))
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
normal
normal(loc=0.0, scale=1.0, size=None)
Draw random samples from a normal (Gaussian) distribution.
The probability density function of the normal distribution, first
derived by De Moivre and 200 years later by both Gauss and Laplace
independently [2]_, is often called the bell curve because of
its characteristic shape (see the example below).
The normal distributions occurs often in nature. For example, it
describes the commonly occurring distribution of samples influenced
by a large number of tiny, random disturbances, each with its own
unique distribution [2]_.
.. note::
New code should use the `~numpy.random.Generator.normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats
Mean ("centre") of the distribution.
scale : float or array_like of floats
Standard deviation (spread or "width") of the distribution. Must be
non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized normal distribution.
See Also
--------
scipy.stats.norm : probability density function, distribution or
cumulative density function, etc.
random.Generator.normal: which should be used for new code.
Notes
-----
The probability density for the Gaussian distribution is
.. math:: p(x) = \frac{1}{\sqrt{ 2 \pi \sigma^2 }}
e^{ - \frac{ (x - \mu)^2 } {2 \sigma^2} },
where :math:`\mu` is the mean and :math:`\sigma` the standard
deviation. The square of the standard deviation, :math:`\sigma^2`,
is called the variance.
The function has its peak at the mean, and its "spread" increases with
the standard deviation (the function reaches 0.607 times its maximum at
:math:`x + \sigma` and :math:`x - \sigma` [2]_). This implies that
normal is more likely to return samples lying close to the mean, rather
than those far away.
References
----------
.. [1] Wikipedia, "Normal distribution",
https://en.wikipedia.org/wiki/Normal_distribution
.. [2] P. R. Peebles Jr., "Central Limit Theorem" in "Probability,
Random Variables and Random Signal Principles", 4th ed., 2001,
pp. 51, 51, 125.
Examples
--------
Draw samples from the distribution:
>>> mu, sigma = 0, 0.1 # mean and standard deviation
>>> s = np.random.normal(mu, sigma, 1000)
Verify the mean and the variance:
>>> abs(mu - np.mean(s))
0.0 # may vary
>>> abs(sigma - np.std(s, ddof=1))
0.1 # may vary
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) *
... np.exp( - (bins - mu)**2 / (2 * sigma**2) ),
... linewidth=2, color='r')
>>> plt.show()
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> np.random.normal(3, 2.5, size=(2, 4))
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
standard_gamma
standard_gamma(shape, size=None)
Draw samples from a standard Gamma distribution.
Samples are drawn from a Gamma distribution with specified parameters,
shape (sometimes designated "k") and scale=1.
.. note::
New code should use the
`~numpy.random.Generator.standard_gamma`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
shape : float or array_like of floats
Parameter, must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``shape`` is a scalar. Otherwise,
``np.array(shape).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized standard gamma distribution.
See Also
--------
scipy.stats.gamma : probability density function, distribution or
cumulative density function, etc.
random.Generator.standard_gamma: which should be used for new code.
Notes
-----
The probability density for the Gamma distribution is
.. math:: p(x) = x^{k-1}\frac{e^{-x/\theta}}{\theta^k\Gamma(k)},
where :math:`k` is the shape and :math:`\theta` the scale,
and :math:`\Gamma` is the Gamma function.
The Gamma distribution is often used to model the times to failure of
electronic components, and arises naturally in processes for which the
waiting times between Poisson distributed events are relevant.
References
----------
.. [1] Weisstein, Eric W. "Gamma Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/GammaDistribution.html
.. [2] Wikipedia, "Gamma distribution",
https://en.wikipedia.org/wiki/Gamma_distribution
Examples
--------
Draw samples from the distribution:
>>> shape, scale = 2., 1. # mean and width
>>> s = np.random.standard_gamma(shape, 1000000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> import scipy.special as sps # doctest: +SKIP
>>> count, bins, ignored = plt.hist(s, 50, density=True)
>>> y = bins**(shape-1) * ((np.exp(-bins/scale))/ # doctest: +SKIP
... (sps.gamma(shape) * scale**shape))
>>> plt.plot(bins, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
gamma
gamma(shape, scale=1.0, size=None)
Draw samples from a Gamma distribution.
Samples are drawn from a Gamma distribution with specified parameters,
`shape` (sometimes designated "k") and `scale` (sometimes designated
"theta"), where both parameters are > 0.
.. note::
New code should use the `~numpy.random.Generator.gamma`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
shape : float or array_like of floats
The shape of the gamma distribution. Must be non-negative.
scale : float or array_like of floats, optional
The scale of the gamma distribution. Must be non-negative.
Default is equal to 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``shape`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(shape, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized gamma distribution.
See Also
--------
scipy.stats.gamma : probability density function, distribution or
cumulative density function, etc.
random.Generator.gamma: which should be used for new code.
Notes
-----
The probability density for the Gamma distribution is
.. math:: p(x) = x^{k-1}\frac{e^{-x/\theta}}{\theta^k\Gamma(k)},
where :math:`k` is the shape and :math:`\theta` the scale,
and :math:`\Gamma` is the Gamma function.
The Gamma distribution is often used to model the times to failure of
electronic components, and arises naturally in processes for which the
waiting times between Poisson distributed events are relevant.
References
----------
.. [1] Weisstein, Eric W. "Gamma Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/GammaDistribution.html
.. [2] Wikipedia, "Gamma distribution",
https://en.wikipedia.org/wiki/Gamma_distribution
Examples
--------
Draw samples from the distribution:
>>> shape, scale = 2., 2. # mean=4, std=2*sqrt(2)
>>> s = np.random.gamma(shape, scale, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> import scipy.special as sps # doctest: +SKIP
>>> count, bins, ignored = plt.hist(s, 50, density=True)
>>> y = bins**(shape-1)*(np.exp(-bins/scale) / # doctest: +SKIP
... (sps.gamma(shape)*scale**shape))
>>> plt.plot(bins, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
f
f(dfnum, dfden, size=None)
Draw samples from an F distribution.
Samples are drawn from an F distribution with specified parameters,
`dfnum` (degrees of freedom in numerator) and `dfden` (degrees of
freedom in denominator), where both parameters must be greater than
zero.
The random variate of the F distribution (also known as the
Fisher distribution) is a continuous probability distribution
that arises in ANOVA tests, and is the ratio of two chi-square
variates.
.. note::
New code should use the `~numpy.random.Generator.f`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
dfnum : float or array_like of floats
Degrees of freedom in numerator, must be > 0.
dfden : float or array_like of float
Degrees of freedom in denominator, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``dfnum`` and ``dfden`` are both scalars.
Otherwise, ``np.broadcast(dfnum, dfden).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Fisher distribution.
See Also
--------
scipy.stats.f : probability density function, distribution or
cumulative density function, etc.
random.Generator.f: which should be used for new code.
Notes
-----
The F statistic is used to compare in-group variances to between-group
variances. Calculating the distribution depends on the sampling, and
so it is a function of the respective degrees of freedom in the
problem. The variable `dfnum` is the number of samples minus one, the
between-groups degrees of freedom, while `dfden` is the within-groups
degrees of freedom, the sum of the number of samples in each group
minus the number of groups.
References
----------
.. [1] Glantz, Stanton A. "Primer of Biostatistics.", McGraw-Hill,
Fifth Edition, 2002.
.. [2] Wikipedia, "F-distribution",
https://en.wikipedia.org/wiki/F-distribution
Examples
--------
An example from Glantz[1], pp 47-40:
Two groups, children of diabetics (25 people) and children from people
without diabetes (25 controls). Fasting blood glucose was measured,
case group had a mean value of 86.1, controls had a mean value of
82.2. Standard deviations were 2.09 and 2.49 respectively. Are these
data consistent with the null hypothesis that the parents diabetic
status does not affect their children's blood glucose levels?
Calculating the F statistic from the data gives a value of 36.01.
Draw samples from the distribution:
>>> dfnum = 1. # between group degrees of freedom
>>> dfden = 48. # within groups degrees of freedom
>>> s = np.random.f(dfnum, dfden, 1000)
The lower bound for the top 1% of the samples is :
>>> np.sort(s)[-10]
7.61988120985 # random
So there is about a 1% chance that the F statistic will exceed 7.62,
the measured value is 36, so the null hypothesis is rejected at the 1%
level.
noncentral_f
noncentral_f(dfnum, dfden, nonc, size=None)
Draw samples from the noncentral F distribution.
Samples are drawn from an F distribution with specified parameters,
`dfnum` (degrees of freedom in numerator) and `dfden` (degrees of
freedom in denominator), where both parameters > 1.
`nonc` is the non-centrality parameter.
.. note::
New code should use the
`~numpy.random.Generator.noncentral_f`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
dfnum : float or array_like of floats
Numerator degrees of freedom, must be > 0.
.. versionchanged:: 1.14.0
Earlier NumPy versions required dfnum > 1.
dfden : float or array_like of floats
Denominator degrees of freedom, must be > 0.
nonc : float or array_like of floats
Non-centrality parameter, the sum of the squares of the numerator
means, must be >= 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``dfnum``, ``dfden``, and ``nonc``
are all scalars. Otherwise, ``np.broadcast(dfnum, dfden, nonc).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized noncentral Fisher distribution.
See Also
--------
random.Generator.noncentral_f: which should be used for new code.
Notes
-----
When calculating the power of an experiment (power = probability of
rejecting the null hypothesis when a specific alternative is true) the
non-central F statistic becomes important. When the null hypothesis is
true, the F statistic follows a central F distribution. When the null
hypothesis is not true, then it follows a non-central F statistic.
References
----------
.. [1] Weisstein, Eric W. "Noncentral F-Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/NoncentralF-Distribution.html
.. [2] Wikipedia, "Noncentral F-distribution",
https://en.wikipedia.org/wiki/Noncentral_F-distribution
Examples
--------
In a study, testing for a specific alternative to the null hypothesis
requires use of the Noncentral F distribution. We need to calculate the
area in the tail of the distribution that exceeds the value of the F
distribution for the null hypothesis. We'll plot the two probability
distributions for comparison.
>>> dfnum = 3 # between group deg of freedom
>>> dfden = 20 # within groups degrees of freedom
>>> nonc = 3.0
>>> nc_vals = np.random.noncentral_f(dfnum, dfden, nonc, 1000000)
>>> NF = np.histogram(nc_vals, bins=50, density=True)
>>> c_vals = np.random.f(dfnum, dfden, 1000000)
>>> F = np.histogram(c_vals, bins=50, density=True)
>>> import matplotlib.pyplot as plt
>>> plt.plot(F[1][1:], F[0])
>>> plt.plot(NF[1][1:], NF[0])
>>> plt.show()
chisquare
chisquare(df, size=None)
Draw samples from a chi-square distribution.
When `df` independent random variables, each with standard normal
distributions (mean 0, variance 1), are squared and summed, the
resulting distribution is chi-square (see Notes). This distribution
is often used in hypothesis testing.
.. note::
New code should use the `~numpy.random.Generator.chisquare`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Number of degrees of freedom, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` is a scalar. Otherwise,
``np.array(df).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized chi-square distribution.
Raises
------
ValueError
When `df` <= 0 or when an inappropriate `size` (e.g. ``size=-1``)
is given.
See Also
--------
random.Generator.chisquare: which should be used for new code.
Notes
-----
The variable obtained by summing the squares of `df` independent,
standard normally distributed random variables:
.. math:: Q = \sum_{i=0}^{\mathtt{df}} X^2_i
is chi-square distributed, denoted
.. math:: Q \sim \chi^2_k.
The probability density function of the chi-squared distribution is
.. math:: p(x) = \frac{(1/2)^{k/2}}{\Gamma(k/2)}
x^{k/2 - 1} e^{-x/2},
where :math:`\Gamma` is the gamma function,
.. math:: \Gamma(x) = \int_0^{-\infty} t^{x - 1} e^{-t} dt.
References
----------
.. [1] NIST "Engineering Statistics Handbook"
https://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htm
Examples
--------
>>> np.random.chisquare(2,4)
array([ 1.89920014, 9.00867716, 3.13710533, 5.62318272]) # random
noncentral_chisquare
noncentral_chisquare(df, nonc, size=None)
Draw samples from a noncentral chi-square distribution.
The noncentral :math:`\chi^2` distribution is a generalization of
the :math:`\chi^2` distribution.
.. note::
New code should use the
`~numpy.random.Generator.noncentral_chisquare`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Degrees of freedom, must be > 0.
.. versionchanged:: 1.10.0
Earlier NumPy versions required dfnum > 1.
nonc : float or array_like of floats
Non-centrality, must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` and ``nonc`` are both scalars.
Otherwise, ``np.broadcast(df, nonc).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized noncentral chi-square distribution.
See Also
--------
random.Generator.noncentral_chisquare: which should be used for new code.
Notes
-----
The probability density function for the noncentral Chi-square
distribution is
.. math:: P(x;df,nonc) = \sum^{\infty}_{i=0}
\frac{e^{-nonc/2}(nonc/2)^{i}}{i!}
P_{Y_{df+2i}}(x),
where :math:`Y_{q}` is the Chi-square with q degrees of freedom.
References
----------
.. [1] Wikipedia, "Noncentral chi-squared distribution"
https://en.wikipedia.org/wiki/Noncentral_chi-squared_distribution
Examples
--------
Draw values from the distribution and plot the histogram
>>> import matplotlib.pyplot as plt
>>> values = plt.hist(np.random.noncentral_chisquare(3, 20, 100000),
... bins=200, density=True)
>>> plt.show()
Draw values from a noncentral chisquare with very small noncentrality,
and compare to a chisquare.
>>> plt.figure()
>>> values = plt.hist(np.random.noncentral_chisquare(3, .0000001, 100000),
... bins=np.arange(0., 25, .1), density=True)
>>> values2 = plt.hist(np.random.chisquare(3, 100000),
... bins=np.arange(0., 25, .1), density=True)
>>> plt.plot(values[1][0:-1], values[0]-values2[0], 'ob')
>>> plt.show()
Demonstrate how large values of non-centrality lead to a more symmetric
distribution.
>>> plt.figure()
>>> values = plt.hist(np.random.noncentral_chisquare(3, 20, 100000),
... bins=200, density=True)
>>> plt.show()
standard_cauchy
standard_cauchy(size=None)
Draw samples from a standard Cauchy distribution with mode = 0.
Also known as the Lorentz distribution.
.. note::
New code should use the
`~numpy.random.Generator.standard_cauchy`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
samples : ndarray or scalar
The drawn samples.
See Also
--------
random.Generator.standard_cauchy: which should be used for new code.
Notes
-----
The probability density function for the full Cauchy distribution is
.. math:: P(x; x_0, \gamma) = \frac{1}{\pi \gamma \bigl[ 1+
(\frac{x-x_0}{\gamma})^2 \bigr] }
and the Standard Cauchy distribution just sets :math:`x_0=0` and
:math:`\gamma=1`
The Cauchy distribution arises in the solution to the driven harmonic
oscillator problem, and also describes spectral line broadening. It
also describes the distribution of values at which a line tilted at
a random angle will cut the x axis.
When studying hypothesis tests that assume normality, seeing how the
tests perform on data from a Cauchy distribution is a good indicator of
their sensitivity to a heavy-tailed distribution, since the Cauchy looks
very much like a Gaussian distribution, but with heavier tails.
References
----------
.. [1] NIST/SEMATECH e-Handbook of Statistical Methods, "Cauchy
Distribution",
https://www.itl.nist.gov/div898/handbook/eda/section3/eda3663.htm
.. [2] Weisstein, Eric W. "Cauchy Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/CauchyDistribution.html
.. [3] Wikipedia, "Cauchy distribution"
https://en.wikipedia.org/wiki/Cauchy_distribution
Examples
--------
Draw samples and plot the distribution:
>>> import matplotlib.pyplot as plt
>>> s = np.random.standard_cauchy(1000000)
>>> s = s[(s>-25) & (s<25)] # truncate distribution so it plots well
>>> plt.hist(s, bins=100)
>>> plt.show()
standard_t
standard_t(df, size=None)
Draw samples from a standard Student's t distribution with `df` degrees
of freedom.
A special case of the hyperbolic distribution. As `df` gets
large, the result resembles that of the standard normal
distribution (`standard_normal`).
.. note::
New code should use the `~numpy.random.Generator.standard_t`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Degrees of freedom, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` is a scalar. Otherwise,
``np.array(df).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized standard Student's t distribution.
See Also
--------
random.Generator.standard_t: which should be used for new code.
Notes
-----
The probability density function for the t distribution is
.. math:: P(x, df) = \frac{\Gamma(\frac{df+1}{2})}{\sqrt{\pi df}
\Gamma(\frac{df}{2})}\Bigl( 1+\frac{x^2}{df} \Bigr)^{-(df+1)/2}
The t test is based on an assumption that the data come from a
Normal distribution. The t test provides a way to test whether
the sample mean (that is the mean calculated from the data) is
a good estimate of the true mean.
The derivation of the t-distribution was first published in
1908 by William Gosset while working for the Guinness Brewery
in Dublin. Due to proprietary issues, he had to publish under
a pseudonym, and so he used the name Student.
References
----------
.. [1] Dalgaard, Peter, "Introductory Statistics With R",
Springer, 2002.
.. [2] Wikipedia, "Student's t-distribution"
https://en.wikipedia.org/wiki/Student's_t-distribution
Examples
--------
From Dalgaard page 83 [1]_, suppose the daily energy intake for 11
women in kilojoules (kJ) is:
>>> intake = np.array([5260., 5470, 5640, 6180, 6390, 6515, 6805, 7515, \
... 7515, 8230, 8770])
Does their energy intake deviate systematically from the recommended
value of 7725 kJ? Our null hypothesis will be the absence of deviation,
and the alternate hypothesis will be the presence of an effect that could be
either positive or negative, hence making our test 2-tailed.
Because we are estimating the mean and we have N=11 values in our sample,
we have N-1=10 degrees of freedom. We set our significance level to 95% and
compute the t statistic using the empirical mean and empirical standard
deviation of our intake. We use a ddof of 1 to base the computation of our
empirical standard deviation on an unbiased estimate of the variance (note:
the final estimate is not unbiased due to the concave nature of the square
root).
>>> np.mean(intake)
6753.636363636364
>>> intake.std(ddof=1)
1142.1232221373727
>>> t = (np.mean(intake)-7725)/(intake.std(ddof=1)/np.sqrt(len(intake)))
>>> t
-2.8207540608310198
We draw 1000000 samples from Student's t distribution with the adequate
degrees of freedom.
>>> import matplotlib.pyplot as plt
>>> s = np.random.standard_t(10, size=1000000)
>>> h = plt.hist(s, bins=100, density=True)
Does our t statistic land in one of the two critical regions found at
both tails of the distribution?
>>> np.sum(np.abs(t) < np.abs(s)) / float(len(s))
0.018318 #random < 0.05, statistic is in critical region
The probability value for this 2-tailed test is about 1.83%, which is
lower than the 5% pre-determined significance threshold.
Therefore, the probability of observing values as extreme as our intake
conditionally on the null hypothesis being true is too low, and we reject
the null hypothesis of no deviation.
vonmises
vonmises(mu, kappa, size=None)
Draw samples from a von Mises distribution.
Samples are drawn from a von Mises distribution with specified mode
(mu) and dispersion (kappa), on the interval [-pi, pi].
The von Mises distribution (also known as the circular normal
distribution) is a continuous probability distribution on the unit
circle. It may be thought of as the circular analogue of the normal
distribution.
.. note::
New code should use the `~numpy.random.Generator.vonmises`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mu : float or array_like of floats
Mode ("center") of the distribution.
kappa : float or array_like of floats
Dispersion of the distribution, has to be >=0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mu`` and ``kappa`` are both scalars.
Otherwise, ``np.broadcast(mu, kappa).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized von Mises distribution.
See Also
--------
scipy.stats.vonmises : probability density function, distribution, or
cumulative density function, etc.
random.Generator.vonmises: which should be used for new code.
Notes
-----
The probability density for the von Mises distribution is
.. math:: p(x) = \frac{e^{\kappa cos(x-\mu)}}{2\pi I_0(\kappa)},
where :math:`\mu` is the mode and :math:`\kappa` the dispersion,
and :math:`I_0(\kappa)` is the modified Bessel function of order 0.
The von Mises is named for Richard Edler von Mises, who was born in
Austria-Hungary, in what is now the Ukraine. He fled to the United
States in 1939 and became a professor at Harvard. He worked in
probability theory, aerodynamics, fluid mechanics, and philosophy of
science.
References
----------
.. [1] Abramowitz, M. and Stegun, I. A. (Eds.). "Handbook of
Mathematical Functions with Formulas, Graphs, and Mathematical
Tables, 9th printing," New York: Dover, 1972.
.. [2] von Mises, R., "Mathematical Theory of Probability
and Statistics", New York: Academic Press, 1964.
Examples
--------
Draw samples from the distribution:
>>> mu, kappa = 0.0, 4.0 # mean and dispersion
>>> s = np.random.vonmises(mu, kappa, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> from scipy.special import i0 # doctest: +SKIP
>>> plt.hist(s, 50, density=True)
>>> x = np.linspace(-np.pi, np.pi, num=51)
>>> y = np.exp(kappa*np.cos(x-mu))/(2*np.pi*i0(kappa)) # doctest: +SKIP
>>> plt.plot(x, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
pareto
pareto(a, size=None)
Draw samples from a Pareto II or Lomax distribution with
specified shape.
The Lomax or Pareto II distribution is a shifted Pareto
distribution. The classical Pareto distribution can be
obtained from the Lomax distribution by adding 1 and
multiplying by the scale parameter ``m`` (see Notes). The
smallest value of the Lomax distribution is zero while for the
classical Pareto distribution it is ``mu``, where the standard
Pareto distribution has location ``mu = 1``. Lomax can also
be considered as a simplified version of the Generalized
Pareto distribution (available in SciPy), with the scale set
to one and the location set to zero.
The Pareto distribution must be greater than zero, and is
unbounded above. It is also known as the "80-20 rule". In
this distribution, 80 percent of the weights are in the lowest
20 percent of the range, while the other 20 percent fill the
remaining 80 percent of the range.
.. note::
New code should use the `~numpy.random.Generator.pareto`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Shape of the distribution. Must be positive.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Pareto distribution.
See Also
--------
scipy.stats.lomax : probability density function, distribution or
cumulative density function, etc.
scipy.stats.genpareto : probability density function, distribution or
cumulative density function, etc.
random.Generator.pareto: which should be used for new code.
Notes
-----
The probability density for the Pareto distribution is
.. math:: p(x) = \frac{am^a}{x^{a+1}}
where :math:`a` is the shape and :math:`m` the scale.
The Pareto distribution, named after the Italian economist
Vilfredo Pareto, is a power law probability distribution
useful in many real world problems. Outside the field of
economics it is generally referred to as the Bradford
distribution. Pareto developed the distribution to describe
the distribution of wealth in an economy. It has also found
use in insurance, web page access statistics, oil field sizes,
and many other problems, including the download frequency for
projects in Sourceforge [1]_. It is one of the so-called
"fat-tailed" distributions.
References
----------
.. [1] Francis Hunt and Paul Johnson, On the Pareto Distribution of
Sourceforge projects.
.. [2] Pareto, V. (1896). Course of Political Economy. Lausanne.
.. [3] Reiss, R.D., Thomas, M.(2001), Statistical Analysis of Extreme
Values, Birkhauser Verlag, Basel, pp 23-30.
.. [4] Wikipedia, "Pareto distribution",
https://en.wikipedia.org/wiki/Pareto_distribution
Examples
--------
Draw samples from the distribution:
>>> a, m = 3., 2. # shape and mode
>>> s = (np.random.pareto(a, 1000) + 1) * m
Display the histogram of the samples, along with the probability
density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, _ = plt.hist(s, 100, density=True)
>>> fit = a*m**a / bins**(a+1)
>>> plt.plot(bins, max(count)*fit/max(fit), linewidth=2, color='r')
>>> plt.show()
weibull
weibull(a, size=None)
Draw samples from a Weibull distribution.
Draw samples from a 1-parameter Weibull distribution with the given
shape parameter `a`.
.. math:: X = (-ln(U))^{1/a}
Here, U is drawn from the uniform distribution over (0,1].
The more common 2-parameter Weibull, including a scale parameter
:math:`\lambda` is just :math:`X = \lambda(-ln(U))^{1/a}`.
.. note::
New code should use the `~numpy.random.Generator.weibull`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Shape parameter of the distribution. Must be nonnegative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Weibull distribution.
See Also
--------
scipy.stats.weibull_max
scipy.stats.weibull_min
scipy.stats.genextreme
gumbel
random.Generator.weibull: which should be used for new code.
Notes
-----
The Weibull (or Type III asymptotic extreme value distribution
for smallest values, SEV Type III, or Rosin-Rammler
distribution) is one of a class of Generalized Extreme Value
(GEV) distributions used in modeling extreme value problems.
This class includes the Gumbel and Frechet distributions.
The probability density for the Weibull distribution is
.. math:: p(x) = \frac{a}
{\lambda}(\frac{x}{\lambda})^{a-1}e^{-(x/\lambda)^a},
where :math:`a` is the shape and :math:`\lambda` the scale.
The function has its peak (the mode) at
:math:`\lambda(\frac{a-1}{a})^{1/a}`.
When ``a = 1``, the Weibull distribution reduces to the exponential
distribution.
References
----------
.. [1] Waloddi Weibull, Royal Technical University, Stockholm,
1939 "A Statistical Theory Of The Strength Of Materials",
Ingeniorsvetenskapsakademiens Handlingar Nr 151, 1939,
Generalstabens Litografiska Anstalts Forlag, Stockholm.
.. [2] Waloddi Weibull, "A Statistical Distribution Function of
Wide Applicability", Journal Of Applied Mechanics ASME Paper
1951.
.. [3] Wikipedia, "Weibull distribution",
https://en.wikipedia.org/wiki/Weibull_distribution
Examples
--------
Draw samples from the distribution:
>>> a = 5. # shape
>>> s = np.random.weibull(a, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> x = np.arange(1,100.)/50.
>>> def weib(x,n,a):
... return (a / n) * (x / n)**(a - 1) * np.exp(-(x / n)**a)
>>> count, bins, ignored = plt.hist(np.random.weibull(5.,1000))
>>> x = np.arange(1,100.)/50.
>>> scale = count.max()/weib(x, 1., 5.).max()
>>> plt.plot(x, weib(x, 1., 5.)*scale)
>>> plt.show()
power
power(a, size=None)
Draws samples in [0, 1] from a power distribution with positive
exponent a - 1.
Also known as the power function distribution.
.. note::
New code should use the `~numpy.random.Generator.power`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Parameter of the distribution. Must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized power distribution.
Raises
------
ValueError
If a <= 0.
See Also
--------
random.Generator.power: which should be used for new code.
Notes
-----
The probability density function is
.. math:: P(x; a) = ax^{a-1}, 0 \le x \le 1, a>0.
The power function distribution is just the inverse of the Pareto
distribution. It may also be seen as a special case of the Beta
distribution.
It is used, for example, in modeling the over-reporting of insurance
claims.
References
----------
.. [1] Christian Kleiber, Samuel Kotz, "Statistical size distributions
in economics and actuarial sciences", Wiley, 2003.
.. [2] Heckert, N. A. and Filliben, James J. "NIST Handbook 148:
Dataplot Reference Manual, Volume 2: Let Subcommands and Library
Functions", National Institute of Standards and Technology
Handbook Series, June 2003.
https://www.itl.nist.gov/div898/software/dataplot/refman2/auxillar/powpdf.pdf
Examples
--------
Draw samples from the distribution:
>>> a = 5. # shape
>>> samples = 1000
>>> s = np.random.power(a, samples)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, bins=30)
>>> x = np.linspace(0, 1, 100)
>>> y = a*x**(a-1.)
>>> normed_y = samples*np.diff(bins)[0]*y
>>> plt.plot(x, normed_y)
>>> plt.show()
Compare the power function distribution to the inverse of the Pareto.
>>> from scipy import stats # doctest: +SKIP
>>> rvs = np.random.power(5, 1000000)
>>> rvsp = np.random.pareto(5, 1000000)
>>> xx = np.linspace(0,1,100)
>>> powpdf = stats.powerlaw.pdf(xx,5) # doctest: +SKIP
>>> plt.figure()
>>> plt.hist(rvs, bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('np.random.power(5)')
>>> plt.figure()
>>> plt.hist(1./(1.+rvsp), bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('inverse of 1 + np.random.pareto(5)')
>>> plt.figure()
>>> plt.hist(1./(1.+rvsp), bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('inverse of stats.pareto(5)')
laplace
laplace(loc=0.0, scale=1.0, size=None)
Draw samples from the Laplace or double exponential distribution with
specified location (or mean) and scale (decay).
The Laplace distribution is similar to the Gaussian/normal distribution,
but is sharper at the peak and has fatter tails. It represents the
difference between two independent, identically distributed exponential
random variables.
.. note::
New code should use the `~numpy.random.Generator.laplace`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
The position, :math:`\mu`, of the distribution peak. Default is 0.
scale : float or array_like of floats, optional
:math:`\lambda`, the exponential decay. Default is 1. Must be non-
negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Laplace distribution.
See Also
--------
random.Generator.laplace: which should be used for new code.
Notes
-----
It has the probability density function
.. math:: f(x; \mu, \lambda) = \frac{1}{2\lambda}
\exp\left(-\frac{|x - \mu|}{\lambda}\right).
The first law of Laplace, from 1774, states that the frequency
of an error can be expressed as an exponential function of the
absolute magnitude of the error, which leads to the Laplace
distribution. For many problems in economics and health
sciences, this distribution seems to model the data better
than the standard Gaussian distribution.
References
----------
.. [1] Abramowitz, M. and Stegun, I. A. (Eds.). "Handbook of
Mathematical Functions with Formulas, Graphs, and Mathematical
Tables, 9th printing," New York: Dover, 1972.
.. [2] Kotz, Samuel, et. al. "The Laplace Distribution and
Generalizations, " Birkhauser, 2001.
.. [3] Weisstein, Eric W. "Laplace Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/LaplaceDistribution.html
.. [4] Wikipedia, "Laplace distribution",
https://en.wikipedia.org/wiki/Laplace_distribution
Examples
--------
Draw samples from the distribution
>>> loc, scale = 0., 1.
>>> s = np.random.laplace(loc, scale, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> x = np.arange(-8., 8., .01)
>>> pdf = np.exp(-abs(x-loc)/scale)/(2.*scale)
>>> plt.plot(x, pdf)
Plot Gaussian for comparison:
>>> g = (1/(scale * np.sqrt(2 * np.pi)) *
... np.exp(-(x - loc)**2 / (2 * scale**2)))
>>> plt.plot(x,g)
gumbel
gumbel(loc=0.0, scale=1.0, size=None)
Draw samples from a Gumbel distribution.
Draw samples from a Gumbel distribution with specified location and
scale. For more information on the Gumbel distribution, see
Notes and References below.
.. note::
New code should use the `~numpy.random.Generator.gumbel`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
The location of the mode of the distribution. Default is 0.
scale : float or array_like of floats, optional
The scale parameter of the distribution. Default is 1. Must be non-
negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Gumbel distribution.
See Also
--------
scipy.stats.gumbel_l
scipy.stats.gumbel_r
scipy.stats.genextreme
weibull
random.Generator.gumbel: which should be used for new code.
Notes
-----
The Gumbel (or Smallest Extreme Value (SEV) or the Smallest Extreme
Value Type I) distribution is one of a class of Generalized Extreme
Value (GEV) distributions used in modeling extreme value problems.
The Gumbel is a special case of the Extreme Value Type I distribution
for maximums from distributions with "exponential-like" tails.
The probability density for the Gumbel distribution is
.. math:: p(x) = \frac{e^{-(x - \mu)/ \beta}}{\beta} e^{ -e^{-(x - \mu)/
\beta}},
where :math:`\mu` is the mode, a location parameter, and
:math:`\beta` is the scale parameter.
The Gumbel (named for German mathematician Emil Julius Gumbel) was used
very early in the hydrology literature, for modeling the occurrence of
flood events. It is also used for modeling maximum wind speed and
rainfall rates. It is a "fat-tailed" distribution - the probability of
an event in the tail of the distribution is larger than if one used a
Gaussian, hence the surprisingly frequent occurrence of 100-year
floods. Floods were initially modeled as a Gaussian process, which
underestimated the frequency of extreme events.
It is one of a class of extreme value distributions, the Generalized
Extreme Value (GEV) distributions, which also includes the Weibull and
Frechet.
The function has a mean of :math:`\mu + 0.57721\beta` and a variance
of :math:`\frac{\pi^2}{6}\beta^2`.
References
----------
.. [1] Gumbel, E. J., "Statistics of Extremes,"
New York: Columbia University Press, 1958.
.. [2] Reiss, R.-D. and Thomas, M., "Statistical Analysis of Extreme
Values from Insurance, Finance, Hydrology and Other Fields,"
Basel: Birkhauser Verlag, 2001.
Examples
--------
Draw samples from the distribution:
>>> mu, beta = 0, 0.1 # location and scale
>>> s = np.random.gumbel(mu, beta, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> plt.plot(bins, (1/beta)*np.exp(-(bins - mu)/beta)
... * np.exp( -np.exp( -(bins - mu) /beta) ),
... linewidth=2, color='r')
>>> plt.show()
Show how an extreme value distribution can arise from a Gaussian process
and compare to a Gaussian:
>>> means = []
>>> maxima = []
>>> for i in range(0,1000) :
... a = np.random.normal(mu, beta, 1000)
... means.append(a.mean())
... maxima.append(a.max())
>>> count, bins, ignored = plt.hist(maxima, 30, density=True)
>>> beta = np.std(maxima) * np.sqrt(6) / np.pi
>>> mu = np.mean(maxima) - 0.57721*beta
>>> plt.plot(bins, (1/beta)*np.exp(-(bins - mu)/beta)
... * np.exp(-np.exp(-(bins - mu)/beta)),
... linewidth=2, color='r')
>>> plt.plot(bins, 1/(beta * np.sqrt(2 * np.pi))
... * np.exp(-(bins - mu)**2 / (2 * beta**2)),
... linewidth=2, color='g')
>>> plt.show()
logistic
logistic(loc=0.0, scale=1.0, size=None)
Draw samples from a logistic distribution.
Samples are drawn from a logistic distribution with specified
parameters, loc (location or mean, also median), and scale (>0).
.. note::
New code should use the `~numpy.random.Generator.logistic`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
Parameter of the distribution. Default is 0.
scale : float or array_like of floats, optional
Parameter of the distribution. Must be non-negative.
Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized logistic distribution.
See Also
--------
scipy.stats.logistic : probability density function, distribution or
cumulative density function, etc.
random.Generator.logistic: which should be used for new code.
Notes
-----
The probability density for the Logistic distribution is
.. math:: P(x) = P(x) = \frac{e^{-(x-\mu)/s}}{s(1+e^{-(x-\mu)/s})^2},
where :math:`\mu` = location and :math:`s` = scale.
The Logistic distribution is used in Extreme Value problems where it
can act as a mixture of Gumbel distributions, in Epidemiology, and by
the World Chess Federation (FIDE) where it is used in the Elo ranking
system, assuming the performance of each player is a logistically
distributed random variable.
References
----------
.. [1] Reiss, R.-D. and Thomas M. (2001), "Statistical Analysis of
Extreme Values, from Insurance, Finance, Hydrology and Other
Fields," Birkhauser Verlag, Basel, pp 132-133.
.. [2] Weisstein, Eric W. "Logistic Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/LogisticDistribution.html
.. [3] Wikipedia, "Logistic-distribution",
https://en.wikipedia.org/wiki/Logistic_distribution
Examples
--------
Draw samples from the distribution:
>>> loc, scale = 10, 1
>>> s = np.random.logistic(loc, scale, 10000)
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, bins=50)
# plot against distribution
>>> def logist(x, loc, scale):
... return np.exp((loc-x)/scale)/(scale*(1+np.exp((loc-x)/scale))**2)
>>> lgst_val = logist(bins, loc, scale)
>>> plt.plot(bins, lgst_val * count.max() / lgst_val.max())
>>> plt.show()
lognormal
lognormal(mean=0.0, sigma=1.0, size=None)
Draw samples from a log-normal distribution.
Draw samples from a log-normal distribution with specified mean,
standard deviation, and array shape. Note that the mean and standard
deviation are not the values for the distribution itself, but of the
underlying normal distribution it is derived from.
.. note::
New code should use the `~numpy.random.Generator.lognormal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : float or array_like of floats, optional
Mean value of the underlying normal distribution. Default is 0.
sigma : float or array_like of floats, optional
Standard deviation of the underlying normal distribution. Must be
non-negative. Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mean`` and ``sigma`` are both scalars.
Otherwise, ``np.broadcast(mean, sigma).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized log-normal distribution.
See Also
--------
scipy.stats.lognorm : probability density function, distribution,
cumulative density function, etc.
random.Generator.lognormal: which should be used for new code.
Notes
-----
A variable `x` has a log-normal distribution if `log(x)` is normally
distributed. The probability density function for the log-normal
distribution is:
.. math:: p(x) = \frac{1}{\sigma x \sqrt{2\pi}}
e^{(-\frac{(ln(x)-\mu)^2}{2\sigma^2})}
where :math:`\mu` is the mean and :math:`\sigma` is the standard
deviation of the normally distributed logarithm of the variable.
A log-normal distribution results if a random variable is the *product*
of a large number of independent, identically-distributed variables in
the same way that a normal distribution results if the variable is the
*sum* of a large number of independent, identically-distributed
variables.
References
----------
.. [1] Limpert, E., Stahel, W. A., and Abbt, M., "Log-normal
Distributions across the Sciences: Keys and Clues,"
BioScience, Vol. 51, No. 5, May, 2001.
https://stat.ethz.ch/~stahel/lognormal/bioscience.pdf
.. [2] Reiss, R.D. and Thomas, M., "Statistical Analysis of Extreme
Values," Basel: Birkhauser Verlag, 2001, pp. 31-32.
Examples
--------
Draw samples from the distribution:
>>> mu, sigma = 3., 1. # mean and standard deviation
>>> s = np.random.lognormal(mu, sigma, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 100, density=True, align='mid')
>>> x = np.linspace(min(bins), max(bins), 10000)
>>> pdf = (np.exp(-(np.log(x) - mu)**2 / (2 * sigma**2))
... / (x * sigma * np.sqrt(2 * np.pi)))
>>> plt.plot(x, pdf, linewidth=2, color='r')
>>> plt.axis('tight')
>>> plt.show()
Demonstrate that taking the products of random samples from a uniform
distribution can be fit well by a log-normal probability density
function.
>>> # Generate a thousand samples: each is the product of 100 random
>>> # values, drawn from a normal distribution.
>>> b = []
>>> for i in range(1000):
... a = 10. + np.random.standard_normal(100)
... b.append(np.prod(a))
>>> b = np.array(b) / np.min(b) # scale values to be positive
>>> count, bins, ignored = plt.hist(b, 100, density=True, align='mid')
>>> sigma = np.std(np.log(b))
>>> mu = np.mean(np.log(b))
>>> x = np.linspace(min(bins), max(bins), 10000)
>>> pdf = (np.exp(-(np.log(x) - mu)**2 / (2 * sigma**2))
... / (x * sigma * np.sqrt(2 * np.pi)))
>>> plt.plot(x, pdf, color='r', linewidth=2)
>>> plt.show()
rayleigh
rayleigh(scale=1.0, size=None)
Draw samples from a Rayleigh distribution.
The :math:`\chi` and Weibull distributions are generalizations of the
Rayleigh.
.. note::
New code should use the `~numpy.random.Generator.rayleigh`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
scale : float or array_like of floats, optional
Scale, also equals the mode. Must be non-negative. Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``scale`` is a scalar. Otherwise,
``np.array(scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Rayleigh distribution.
See Also
--------
random.Generator.rayleigh: which should be used for new code.
Notes
-----
The probability density function for the Rayleigh distribution is
.. math:: P(x;scale) = \frac{x}{scale^2}e^{\frac{-x^2}{2 \cdotp scale^2}}
The Rayleigh distribution would arise, for example, if the East
and North components of the wind velocity had identical zero-mean
Gaussian distributions. Then the wind speed would have a Rayleigh
distribution.
References
----------
.. [1] Brighton Webs Ltd., "Rayleigh Distribution,"
https://web.archive.org/web/20090514091424/http://brighton-webs.co.uk:80/distributions/rayleigh.asp
.. [2] Wikipedia, "Rayleigh distribution"
https://en.wikipedia.org/wiki/Rayleigh_distribution
Examples
--------
Draw values from the distribution and plot the histogram
>>> from matplotlib.pyplot import hist
>>> values = hist(np.random.rayleigh(3, 100000), bins=200, density=True)
Wave heights tend to follow a Rayleigh distribution. If the mean wave
height is 1 meter, what fraction of waves are likely to be larger than 3
meters?
>>> meanvalue = 1
>>> modevalue = np.sqrt(2 / np.pi) * meanvalue
>>> s = np.random.rayleigh(modevalue, 1000000)
The percentage of waves larger than 3 meters is:
>>> 100.*sum(s>3)/1000000.
0.087300000000000003 # random
wald
wald(mean, scale, size=None)
Draw samples from a Wald, or inverse Gaussian, distribution.
As the scale approaches infinity, the distribution becomes more like a
Gaussian. Some references claim that the Wald is an inverse Gaussian
with mean equal to 1, but this is by no means universal.
The inverse Gaussian distribution was first studied in relationship to
Brownian motion. In 1956 M.C.K. Tweedie used the name inverse Gaussian
because there is an inverse relationship between the time to cover a
unit distance and distance covered in unit time.
.. note::
New code should use the `~numpy.random.Generator.wald`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : float or array_like of floats
Distribution mean, must be > 0.
scale : float or array_like of floats
Scale parameter, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mean`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(mean, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Wald distribution.
See Also
--------
random.Generator.wald: which should be used for new code.
Notes
-----
The probability density function for the Wald distribution is
.. math:: P(x;mean,scale) = \sqrt{\frac{scale}{2\pi x^3}}e^
\frac{-scale(x-mean)^2}{2\cdotp mean^2x}
As noted above the inverse Gaussian distribution first arise
from attempts to model Brownian motion. It is also a
competitor to the Weibull for use in reliability modeling and
modeling stock returns and interest rate processes.
References
----------
.. [1] Brighton Webs Ltd., Wald Distribution,
https://web.archive.org/web/20090423014010/http://www.brighton-webs.co.uk:80/distributions/wald.asp
.. [2] Chhikara, Raj S., and Folks, J. Leroy, "The Inverse Gaussian
Distribution: Theory : Methodology, and Applications", CRC Press,
1988.
.. [3] Wikipedia, "Inverse Gaussian distribution"
https://en.wikipedia.org/wiki/Inverse_Gaussian_distribution
Examples
--------
Draw values from the distribution and plot the histogram:
>>> import matplotlib.pyplot as plt
>>> h = plt.hist(np.random.wald(3, 2, 100000), bins=200, density=True)
>>> plt.show()
triangular
triangular(left, mode, right, size=None)
Draw samples from the triangular distribution over the
interval ``[left, right]``.
The triangular distribution is a continuous probability
distribution with lower limit left, peak at mode, and upper
limit right. Unlike the other distributions, these parameters
directly define the shape of the pdf.
.. note::
New code should use the `~numpy.random.Generator.triangular`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
left : float or array_like of floats
Lower limit.
mode : float or array_like of floats
The value where the peak of the distribution occurs.
The value must fulfill the condition ``left <= mode <= right``.
right : float or array_like of floats
Upper limit, must be larger than `left`.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``left``, ``mode``, and ``right``
are all scalars. Otherwise, ``np.broadcast(left, mode, right).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized triangular distribution.
See Also
--------
random.Generator.triangular: which should be used for new code.
Notes
-----
The probability density function for the triangular distribution is
.. math:: P(x;l, m, r) = \begin{cases}
\frac{2(x-l)}{(r-l)(m-l)}& \text{for $l \leq x \leq m$},\\
\frac{2(r-x)}{(r-l)(r-m)}& \text{for $m \leq x \leq r$},\\
0& \text{otherwise}.
\end{cases}
The triangular distribution is often used in ill-defined
problems where the underlying distribution is not known, but
some knowledge of the limits and mode exists. Often it is used
in simulations.
References
----------
.. [1] Wikipedia, "Triangular distribution"
https://en.wikipedia.org/wiki/Triangular_distribution
Examples
--------
Draw values from the distribution and plot the histogram:
>>> import matplotlib.pyplot as plt
>>> h = plt.hist(np.random.triangular(-3, 0, 8, 100000), bins=200,
... density=True)
>>> plt.show()
binomial
binomial(n, p, size=None)
Draw samples from a binomial distribution.
Samples are drawn from a binomial distribution with specified
parameters, n trials and p probability of success where
n an integer >= 0 and p is in the interval [0,1]. (n may be
input as a float, but it is truncated to an integer in use)
.. note::
New code should use the `~numpy.random.Generator.binomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : int or array_like of ints
Parameter of the distribution, >= 0. Floats are also accepted,
but they will be truncated to integers.
p : float or array_like of floats
Parameter of the distribution, >= 0 and <=1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``n`` and ``p`` are both scalars.
Otherwise, ``np.broadcast(n, p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized binomial distribution, where
each sample is equal to the number of successes over the n trials.
See Also
--------
scipy.stats.binom : probability density function, distribution or
cumulative density function, etc.
random.Generator.binomial: which should be used for new code.
Notes
-----
The probability density for the binomial distribution is
.. math:: P(N) = \binom{n}{N}p^N(1-p)^{n-N},
where :math:`n` is the number of trials, :math:`p` is the probability
of success, and :math:`N` is the number of successes.
When estimating the standard error of a proportion in a population by
using a random sample, the normal distribution works well unless the
product p*n <=5, where p = population proportion estimate, and n =
number of samples, in which case the binomial distribution is used
instead. For example, a sample of 15 people shows 4 who are left
handed, and 11 who are right handed. Then p = 4/15 = 27%. 0.27*15 = 4,
so the binomial distribution should be used in this case.
References
----------
.. [1] Dalgaard, Peter, "Introductory Statistics with R",
Springer-Verlag, 2002.
.. [2] Glantz, Stanton A. "Primer of Biostatistics.", McGraw-Hill,
Fifth Edition, 2002.
.. [3] Lentner, Marvin, "Elementary Applied Statistics", Bogden
and Quigley, 1972.
.. [4] Weisstein, Eric W. "Binomial Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/BinomialDistribution.html
.. [5] Wikipedia, "Binomial distribution",
https://en.wikipedia.org/wiki/Binomial_distribution
Examples
--------
Draw samples from the distribution:
>>> n, p = 10, .5 # number of trials, probability of each trial
>>> s = np.random.binomial(n, p, 1000)
# result of flipping a coin 10 times, tested 1000 times.
A real world example. A company drills 9 wild-cat oil exploration
wells, each with an estimated probability of success of 0.1. All nine
wells fail. What is the probability of that happening?
Let's do 20,000 trials of the model, and count the number that
generate zero positive results.
>>> sum(np.random.binomial(9, 0.1, 20000) == 0)/20000.
# answer = 0.38885, or 38%.
negative_binomial
negative_binomial(n, p, size=None)
Draw samples from a negative binomial distribution.
Samples are drawn from a negative binomial distribution with specified
parameters, `n` successes and `p` probability of success where `n`
is > 0 and `p` is in the interval [0, 1].
.. note::
New code should use the
`~numpy.random.Generator.negative_binomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : float or array_like of floats
Parameter of the distribution, > 0.
p : float or array_like of floats
Parameter of the distribution, >= 0 and <=1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``n`` and ``p`` are both scalars.
Otherwise, ``np.broadcast(n, p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized negative binomial distribution,
where each sample is equal to N, the number of failures that
occurred before a total of n successes was reached.
See Also
--------
random.Generator.negative_binomial: which should be used for new code.
Notes
-----
The probability mass function of the negative binomial distribution is
.. math:: P(N;n,p) = \frac{\Gamma(N+n)}{N!\Gamma(n)}p^{n}(1-p)^{N},
where :math:`n` is the number of successes, :math:`p` is the
probability of success, :math:`N+n` is the number of trials, and
:math:`\Gamma` is the gamma function. When :math:`n` is an integer,
:math:`\frac{\Gamma(N+n)}{N!\Gamma(n)} = \binom{N+n-1}{N}`, which is
the more common form of this term in the pmf. The negative
binomial distribution gives the probability of N failures given n
successes, with a success on the last trial.
If one throws a die repeatedly until the third time a "1" appears,
then the probability distribution of the number of non-"1"s that
appear before the third "1" is a negative binomial distribution.
References
----------
.. [1] Weisstein, Eric W. "Negative Binomial Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/NegativeBinomialDistribution.html
.. [2] Wikipedia, "Negative binomial distribution",
https://en.wikipedia.org/wiki/Negative_binomial_distribution
Examples
--------
Draw samples from the distribution:
A real world example. A company drills wild-cat oil
exploration wells, each with an estimated probability of
success of 0.1. What is the probability of having one success
for each successive well, that is what is the probability of a
single success after drilling 5 wells, after 6 wells, etc.?
>>> s = np.random.negative_binomial(1, 0.1, 100000)
>>> for i in range(1, 11): # doctest: +SKIP
... probability = sum(s<i) / 100000.
... print(i, "wells drilled, probability of one success =", probability)
poisson
poisson(lam=1.0, size=None)
Draw samples from a Poisson distribution.
The Poisson distribution is the limit of the binomial distribution
for large N.
.. note::
New code should use the `~numpy.random.Generator.poisson`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
lam : float or array_like of floats
Expected number of events occurring in a fixed-time interval,
must be >= 0. A sequence must be broadcastable over the requested
size.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``lam`` is a scalar. Otherwise,
``np.array(lam).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Poisson distribution.
See Also
--------
random.Generator.poisson: which should be used for new code.
Notes
-----
The Poisson distribution
.. math:: f(k; \lambda)=\frac{\lambda^k e^{-\lambda}}{k!}
For events with an expected separation :math:`\lambda` the Poisson
distribution :math:`f(k; \lambda)` describes the probability of
:math:`k` events occurring within the observed
interval :math:`\lambda`.
Because the output is limited to the range of the C int64 type, a
ValueError is raised when `lam` is within 10 sigma of the maximum
representable value.
References
----------
.. [1] Weisstein, Eric W. "Poisson Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/PoissonDistribution.html
.. [2] Wikipedia, "Poisson distribution",
https://en.wikipedia.org/wiki/Poisson_distribution
Examples
--------
Draw samples from the distribution:
>>> import numpy as np
>>> s = np.random.poisson(5, 10000)
Display histogram of the sample:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 14, density=True)
>>> plt.show()
Draw each 100 values for lambda 100 and 500:
>>> s = np.random.poisson(lam=(100., 500.), size=(100, 2))
zipf
zipf(a, size=None)
Draw samples from a Zipf distribution.
Samples are drawn from a Zipf distribution with specified parameter
`a` > 1.
The Zipf distribution (also known as the zeta distribution) is a
discrete probability distribution that satisfies Zipf's law: the
frequency of an item is inversely proportional to its rank in a
frequency table.
.. note::
New code should use the `~numpy.random.Generator.zipf`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Distribution parameter. Must be greater than 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Zipf distribution.
See Also
--------
scipy.stats.zipf : probability density function, distribution, or
cumulative density function, etc.
random.Generator.zipf: which should be used for new code.
Notes
-----
The probability density for the Zipf distribution is
.. math:: p(k) = \frac{k^{-a}}{\zeta(a)},
for integers :math:`k \geq 1`, where :math:`\zeta` is the Riemann Zeta
function.
It is named for the American linguist George Kingsley Zipf, who noted
that the frequency of any word in a sample of a language is inversely
proportional to its rank in the frequency table.
References
----------
.. [1] Zipf, G. K., "Selected Studies of the Principle of Relative
Frequency in Language," Cambridge, MA: Harvard Univ. Press,
1932.
Examples
--------
Draw samples from the distribution:
>>> a = 4.0
>>> n = 20000
>>> s = np.random.zipf(a, n)
Display the histogram of the samples, along with
the expected histogram based on the probability
density function:
>>> import matplotlib.pyplot as plt
>>> from scipy.special import zeta # doctest: +SKIP
`bincount` provides a fast histogram for small integers.
>>> count = np.bincount(s)
>>> k = np.arange(1, s.max() + 1)
>>> plt.bar(k, count[1:], alpha=0.5, label='sample count')
>>> plt.plot(k, n*(k**-a)/zeta(a), 'k.-', alpha=0.5,
... label='expected count') # doctest: +SKIP
>>> plt.semilogy()
>>> plt.grid(alpha=0.4)
>>> plt.legend()
>>> plt.title(f'Zipf sample, a={a}, size={n}')
>>> plt.show()
geometric
geometric(p, size=None)
Draw samples from the geometric distribution.
Bernoulli trials are experiments with one of two outcomes:
success or failure (an example of such an experiment is flipping
a coin). The geometric distribution models the number of trials
that must be run in order to achieve success. It is therefore
supported on the positive integers, ``k = 1, 2, ...``.
The probability mass function of the geometric distribution is
.. math:: f(k) = (1 - p)^{k - 1} p
where `p` is the probability of success of an individual trial.
.. note::
New code should use the `~numpy.random.Generator.geometric`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
p : float or array_like of floats
The probability of success of an individual trial.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``p`` is a scalar. Otherwise,
``np.array(p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized geometric distribution.
See Also
--------
random.Generator.geometric: which should be used for new code.
Examples
--------
Draw ten thousand values from the geometric distribution,
with the probability of an individual success equal to 0.35:
>>> z = np.random.geometric(p=0.35, size=10000)
How many trials succeeded after a single run?
>>> (z == 1).sum() / 10000.
0.34889999999999999 #random
hypergeometric
hypergeometric(ngood, nbad, nsample, size=None)
Draw samples from a Hypergeometric distribution.
Samples are drawn from a hypergeometric distribution with specified
parameters, `ngood` (ways to make a good selection), `nbad` (ways to make
a bad selection), and `nsample` (number of items sampled, which is less
than or equal to the sum ``ngood + nbad``).
.. note::
New code should use the
`~numpy.random.Generator.hypergeometric`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
ngood : int or array_like of ints
Number of ways to make a good selection. Must be nonnegative.
nbad : int or array_like of ints
Number of ways to make a bad selection. Must be nonnegative.
nsample : int or array_like of ints
Number of items sampled. Must be at least 1 and at most
``ngood + nbad``.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if `ngood`, `nbad`, and `nsample`
are all scalars. Otherwise, ``np.broadcast(ngood, nbad, nsample).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized hypergeometric distribution. Each
sample is the number of good items within a randomly selected subset of
size `nsample` taken from a set of `ngood` good items and `nbad` bad items.
See Also
--------
scipy.stats.hypergeom : probability density function, distribution or
cumulative density function, etc.
random.Generator.hypergeometric: which should be used for new code.
Notes
-----
The probability density for the Hypergeometric distribution is
.. math:: P(x) = \frac{\binom{g}{x}\binom{b}{n-x}}{\binom{g+b}{n}},
where :math:`0 \le x \le n` and :math:`n-b \le x \le g`
for P(x) the probability of ``x`` good results in the drawn sample,
g = `ngood`, b = `nbad`, and n = `nsample`.
Consider an urn with black and white marbles in it, `ngood` of them
are black and `nbad` are white. If you draw `nsample` balls without
replacement, then the hypergeometric distribution describes the
distribution of black balls in the drawn sample.
Note that this distribution is very similar to the binomial
distribution, except that in this case, samples are drawn without
replacement, whereas in the Binomial case samples are drawn with
replacement (or the sample space is infinite). As the sample space
becomes large, this distribution approaches the binomial.
References
----------
.. [1] Lentner, Marvin, "Elementary Applied Statistics", Bogden
and Quigley, 1972.
.. [2] Weisstein, Eric W. "Hypergeometric Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/HypergeometricDistribution.html
.. [3] Wikipedia, "Hypergeometric distribution",
https://en.wikipedia.org/wiki/Hypergeometric_distribution
Examples
--------
Draw samples from the distribution:
>>> ngood, nbad, nsamp = 100, 2, 10
# number of good, number of bad, and number of samples
>>> s = np.random.hypergeometric(ngood, nbad, nsamp, 1000)
>>> from matplotlib.pyplot import hist
>>> hist(s)
# note that it is very unlikely to grab both bad items
Suppose you have an urn with 15 white and 15 black marbles.
If you pull 15 marbles at random, how likely is it that
12 or more of them are one color?
>>> s = np.random.hypergeometric(15, 15, 15, 100000)
>>> sum(s>=12)/100000. + sum(s<=3)/100000.
# answer = 0.003 ... pretty unlikely!
logseries
logseries(p, size=None)
Draw samples from a logarithmic series distribution.
Samples are drawn from a log series distribution with specified
shape parameter, 0 <= ``p`` < 1.
.. note::
New code should use the `~numpy.random.Generator.logseries`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
p : float or array_like of floats
Shape parameter for the distribution. Must be in the range [0, 1).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``p`` is a scalar. Otherwise,
``np.array(p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized logarithmic series distribution.
See Also
--------
scipy.stats.logser : probability density function, distribution or
cumulative density function, etc.
random.Generator.logseries: which should be used for new code.
Notes
-----
The probability density for the Log Series distribution is
.. math:: P(k) = \frac{-p^k}{k \ln(1-p)},
where p = probability.
The log series distribution is frequently used to represent species
richness and occurrence, first proposed by Fisher, Corbet, and
Williams in 1943 [2]. It may also be used to model the numbers of
occupants seen in cars [3].
References
----------
.. [1] Buzas, Martin A.; Culver, Stephen J., Understanding regional
species diversity through the log series distribution of
occurrences: BIODIVERSITY RESEARCH Diversity & Distributions,
Volume 5, Number 5, September 1999 , pp. 187-195(9).
.. [2] Fisher, R.A,, A.S. Corbet, and C.B. Williams. 1943. The
relation between the number of species and the number of
individuals in a random sample of an animal population.
Journal of Animal Ecology, 12:42-58.
.. [3] D. J. Hand, F. Daly, D. Lunn, E. Ostrowski, A Handbook of Small
Data Sets, CRC Press, 1994.
.. [4] Wikipedia, "Logarithmic distribution",
https://en.wikipedia.org/wiki/Logarithmic_distribution
Examples
--------
Draw samples from the distribution:
>>> a = .6
>>> s = np.random.logseries(a, 10000)
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s)
# plot against distribution
>>> def logseries(k, p):
... return -p**k/(k*np.log(1-p))
>>> plt.plot(bins, logseries(bins, a)*count.max()/
... logseries(bins, a).max(), 'r')
>>> plt.show()
multivariate_normal
multivariate_normal(mean, cov, size=None, check_valid='warn', tol=1e-8)
Draw random samples from a multivariate normal distribution.
The multivariate normal, multinormal or Gaussian distribution is a
generalization of the one-dimensional normal distribution to higher
dimensions. Such a distribution is specified by its mean and
covariance matrix. These parameters are analogous to the mean
(average or "center") and variance (standard deviation, or "width,"
squared) of the one-dimensional normal distribution.
.. note::
New code should use the
`~numpy.random.Generator.multivariate_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : 1-D array_like, of length N
Mean of the N-dimensional distribution.
cov : 2-D array_like, of shape (N, N)
Covariance matrix of the distribution. It must be symmetric and
positive-semidefinite for proper sampling.
size : int or tuple of ints, optional
Given a shape of, for example, ``(m,n,k)``, ``m*n*k`` samples are
generated, and packed in an `m`-by-`n`-by-`k` arrangement. Because
each sample is `N`-dimensional, the output shape is ``(m,n,k,N)``.
If no shape is specified, a single (`N`-D) sample is returned.
check_valid : { 'warn', 'raise', 'ignore' }, optional
Behavior when the covariance matrix is not positive semidefinite.
tol : float, optional
Tolerance when checking the singular values in covariance matrix.
cov is cast to double before the check.
Returns
-------
out : ndarray
The drawn samples, of shape *size*, if that was provided. If not,
the shape is ``(N,)``.
In other words, each entry ``out[i,j,...,:]`` is an N-dimensional
value drawn from the distribution.
See Also
--------
random.Generator.multivariate_normal: which should be used for new code.
Notes
-----
The mean is a coordinate in N-dimensional space, which represents the
location where samples are most likely to be generated. This is
analogous to the peak of the bell curve for the one-dimensional or
univariate normal distribution.
Covariance indicates the level to which two variables vary together.
From the multivariate normal distribution, we draw N-dimensional
samples, :math:`X = [x_1, x_2, ... x_N]`. The covariance matrix
element :math:`C_{ij}` is the covariance of :math:`x_i` and :math:`x_j`.
The element :math:`C_{ii}` is the variance of :math:`x_i` (i.e. its
"spread").
Instead of specifying the full covariance matrix, popular
approximations include:
- Spherical covariance (`cov` is a multiple of the identity matrix)
- Diagonal covariance (`cov` has non-negative elements, and only on
the diagonal)
This geometrical property can be seen in two dimensions by plotting
generated data-points:
>>> mean = [0, 0]
>>> cov = [[1, 0], [0, 100]] # diagonal covariance
Diagonal covariance means that points are oriented along x or y-axis:
>>> import matplotlib.pyplot as plt
>>> x, y = np.random.multivariate_normal(mean, cov, 5000).T
>>> plt.plot(x, y, 'x')
>>> plt.axis('equal')
>>> plt.show()
Note that the covariance matrix must be positive semidefinite (a.k.a.
nonnegative-definite). Otherwise, the behavior of this method is
undefined and backwards compatibility is not guaranteed.
References
----------
.. [1] Papoulis, A., "Probability, Random Variables, and Stochastic
Processes," 3rd ed., New York: McGraw-Hill, 1991.
.. [2] Duda, R. O., Hart, P. E., and Stork, D. G., "Pattern
Classification," 2nd ed., New York: Wiley, 2001.
Examples
--------
>>> mean = (1, 2)
>>> cov = [[1, 0], [0, 1]]
>>> x = np.random.multivariate_normal(mean, cov, (3, 3))
>>> x.shape
(3, 3, 2)
Here we generate 800 samples from the bivariate normal distribution
with mean [0, 0] and covariance matrix [[6, -3], [-3, 3.5]]. The
expected variances of the first and second components of the sample
are 6 and 3.5, respectively, and the expected correlation
coefficient is -3/sqrt(6*3.5) ≈ -0.65465.
>>> cov = np.array([[6, -3], [-3, 3.5]])
>>> pts = np.random.multivariate_normal([0, 0], cov, size=800)
Check that the mean, covariance, and correlation coefficient of the
sample are close to the expected values:
>>> pts.mean(axis=0)
array([ 0.0326911 , -0.01280782]) # may vary
>>> np.cov(pts.T)
array([[ 5.96202397, -2.85602287],
[-2.85602287, 3.47613949]]) # may vary
>>> np.corrcoef(pts.T)[0, 1]
-0.6273591314603949 # may vary
We can visualize this data with a scatter plot. The orientation
of the point cloud illustrates the negative correlation of the
components of this sample.
>>> import matplotlib.pyplot as plt
>>> plt.plot(pts[:, 0], pts[:, 1], '.', alpha=0.5)
>>> plt.axis('equal')
>>> plt.grid()
>>> plt.show()
multinomial
multinomial(n, pvals, size=None)
Draw samples from a multinomial distribution.
The multinomial distribution is a multivariate generalization of the
binomial distribution. Take an experiment with one of ``p``
possible outcomes. An example of such an experiment is throwing a dice,
where the outcome can be 1 through 6. Each sample drawn from the
distribution represents `n` such experiments. Its values,
``X_i = [X_0, X_1, ..., X_p]``, represent the number of times the
outcome was ``i``.
.. note::
New code should use the `~numpy.random.Generator.multinomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : int
Number of experiments.
pvals : sequence of floats, length p
Probabilities of each of the ``p`` different outcomes. These
must sum to 1 (however, the last element is always assumed to
account for the remaining probability, as long as
``sum(pvals[:-1]) <= 1)``.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : ndarray
The drawn samples, of shape *size*, if that was provided. If not,
the shape is ``(N,)``.
In other words, each entry ``out[i,j,...,:]`` is an N-dimensional
value drawn from the distribution.
See Also
--------
random.Generator.multinomial: which should be used for new code.
Examples
--------
Throw a dice 20 times:
>>> np.random.multinomial(20, [1/6.]*6, size=1)
array([[4, 1, 7, 5, 2, 1]]) # random
It landed 4 times on 1, once on 2, etc.
Now, throw the dice 20 times, and 20 times again:
>>> np.random.multinomial(20, [1/6.]*6, size=2)
array([[3, 4, 3, 3, 4, 3], # random
[2, 4, 3, 4, 0, 7]])
For the first run, we threw 3 times 1, 4 times 2, etc. For the second,
we threw 2 times 1, 4 times 2, etc.
A loaded die is more likely to land on number 6:
>>> np.random.multinomial(100, [1/7.]*5 + [2/7.])
array([11, 16, 14, 17, 16, 26]) # random
The probability inputs should be normalized. As an implementation
detail, the value of the last entry is ignored and assumed to take
up any leftover probability mass, but this should not be relied on.
A biased coin which has twice as much weight on one side as on the
other should be sampled like so:
>>> np.random.multinomial(100, [1.0 / 3, 2.0 / 3]) # RIGHT
array([38, 62]) # random
not like:
>>> np.random.multinomial(100, [1.0, 2.0]) # WRONG
Traceback (most recent call last):
ValueError: pvals < 0, pvals > 1 or pvals contains NaNs
dirichlet
dirichlet(alpha, size=None)
Draw samples from the Dirichlet distribution.
Draw `size` samples of dimension k from a Dirichlet distribution. A
Dirichlet-distributed random variable can be seen as a multivariate
generalization of a Beta distribution. The Dirichlet distribution
is a conjugate prior of a multinomial distribution in Bayesian
inference.
.. note::
New code should use the `~numpy.random.Generator.dirichlet`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
alpha : sequence of floats, length k
Parameter of the distribution (length ``k`` for sample of
length ``k``).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
vector of length ``k`` is returned.
Returns
-------
samples : ndarray,
The drawn samples, of shape ``(size, k)``.
Raises
------
ValueError
If any value in ``alpha`` is less than or equal to zero
See Also
--------
random.Generator.dirichlet: which should be used for new code.
Notes
-----
The Dirichlet distribution is a distribution over vectors
:math:`x` that fulfil the conditions :math:`x_i>0` and
:math:`\sum_{i=1}^k x_i = 1`.
The probability density function :math:`p` of a
Dirichlet-distributed random vector :math:`X` is
proportional to
.. math:: p(x) \propto \prod_{i=1}^{k}{x^{\alpha_i-1}_i},
where :math:`\alpha` is a vector containing the positive
concentration parameters.
The method uses the following property for computation: let :math:`Y`
be a random vector which has components that follow a standard gamma
distribution, then :math:`X = \frac{1}{\sum_{i=1}^k{Y_i}} Y`
is Dirichlet-distributed
References
----------
.. [1] David McKay, "Information Theory, Inference and Learning
Algorithms," chapter 23,
http://www.inference.org.uk/mackay/itila/
.. [2] Wikipedia, "Dirichlet distribution",
https://en.wikipedia.org/wiki/Dirichlet_distribution
Examples
--------
Taking an example cited in Wikipedia, this distribution can be used if
one wanted to cut strings (each of initial length 1.0) into K pieces
with different lengths, where each piece had, on average, a designated
average length, but allowing some variation in the relative sizes of
the pieces.
>>> s = np.random.dirichlet((10, 5, 3), 20).transpose()
>>> import matplotlib.pyplot as plt
>>> plt.barh(range(20), s[0])
>>> plt.barh(range(20), s[1], left=s[0], color='g')
>>> plt.barh(range(20), s[2], left=s[0]+s[1], color='r')
>>> plt.title("Lengths of Strings")
shuffle
shuffle(x)
Modify a sequence in-place by shuffling its contents.
This function only shuffles the array along the first axis of a
multi-dimensional array. The order of sub-arrays is changed but
their contents remains the same.
.. note::
New code should use the `~numpy.random.Generator.shuffle`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
x : ndarray or MutableSequence
The array, list or mutable sequence to be shuffled.
Returns
-------
None
See Also
--------
random.Generator.shuffle: which should be used for new code.
Examples
--------
>>> arr = np.arange(10)
>>> np.random.shuffle(arr)
>>> arr
[1 7 5 2 9 4 3 6 0 8] # random
Multi-dimensional arrays are only shuffled along the first axis:
>>> arr = np.arange(9).reshape((3, 3))
>>> np.random.shuffle(arr)
>>> arr
array([[3, 4, 5], # random
[6, 7, 8],
[0, 1, 2]])
permutation
permutation(x)
Randomly permute a sequence, or return a permuted range.
If `x` is a multi-dimensional array, it is only shuffled along its
first index.
.. note::
New code should use the
`~numpy.random.Generator.permutation`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
x : int or array_like
If `x` is an integer, randomly permute ``np.arange(x)``.
If `x` is an array, make a copy and shuffle the elements
randomly.
Returns
-------
out : ndarray
Permuted sequence or array range.
See Also
--------
random.Generator.permutation: which should be used for new code.
Examples
--------
>>> np.random.permutation(10)
array([1, 7, 4, 3, 0, 9, 2, 5, 8, 6]) # random
>>> np.random.permutation([1, 4, 9, 12, 15])
array([15, 1, 9, 4, 12]) # random
>>> arr = np.arange(9).reshape((3, 3))
>>> np.random.permutation(arr)
array([[6, 7, 8], # random
[0, 1, 2],
[3, 4, 5]])
_bit_generator type numpy dtype double
seed(seed=None)
Reseed the singleton RandomState instance.
Notes
-----
This is a convenience, legacy function that exists to support
older code that uses the singleton RandomState. Best practice
is to use a dedicated ``Generator`` instance rather than
the random variate generation methods exposed directly in
the random module.
See Also
--------
numpy.random.Generator
get_bit_generator
Returns the singleton RandomState's bit generator
Returns
-------
BitGenerator
The bit generator that underlies the singleton RandomState instance
Notes
-----
The singleton RandomState provides the random variate generators in the
``numpy.random`` namespace. This function, and its counterpart set method,
provides a path to hot-swap the default MT19937 bit generator with a
user provided alternative. These function are intended to provide
a continuous path where a single underlying bit generator can be
used both with an instance of ``Generator`` and with the singleton
instance of RandomState.
See Also
--------
set_bit_generator
numpy.random.Generator
set_bit_generator
Sets the singleton RandomState's bit generator
Parameters
----------
bitgen
A bit generator instance
Notes
-----
The singleton RandomState provides the random variate generators in the
``numpy.random``namespace. This function, and its counterpart get method,
provides a path to hot-swap the default MT19937 bit generator with a
user provided alternative. These function are intended to provide
a continuous path where a single underlying bit generator can be
used both with an instance of ``Generator`` and with the singleton
instance of RandomState.
See Also
--------
get_bit_generator
numpy.random.Generator
sample
This is an alias of `random_sample`. See `random_sample` for the complete
documentation.
ranf
This is an alias of `random_sample`. See `random_sample` for the complete
documentation.
Á]¿ìdÑ<A]X`<+M[I²Öj<º[©5q<s*Jåæ"u<zÂûPx<̷yïÑ8{<½m·Øì}<<\ÆIð;<pöÖ$Ûp<3&ڐ<Ên=þ³<!þ Æń<ÃJøͅ<½+§ð@φ<ÐÚÍɇ<o`ÓTY¾<Ò7"U<R]¾ȗ<ģÝݥ}<?×{_<6|ñM¢=<Zsñxf<ªO_Ï ð< 2h]Òď<XujívK<üGH³<¯õIó< ßKë<çI>é&ä<.ÿ8eÒG< h#ឪ<KÚ&¥ <mâÒm< b!ÑSΓ<HgpÊ(.<ç5_\< Íkøë<Mox)J<ý¾¸=§<Ï.Ýǘ<àh m-a<D©úbS½<»yy<sy#nt<r~|oϗ<ÕþS*<ìá+/w<*ÅÐPޘ<D¢ý½S8<8Bޑ<¿ÿu,ë<J¾BD<aҖS%<É$òDØõ<Ly_N<?³¾¦<þYùþ<ÒpW<ÛZÂ+¯<ûæðò<kØñ½^<WBju¶<þ1|÷<Dσ´e<bâåA½<âÆ<µþW+Fl<¡©eÂß<Ù<
<b±
ö]9 <øvr e <r K»㐠<7q¼ <f/z |è <¬9R¡<¾}po0@¡<ûwál¡<#=© ¡<R=Ýġ<âĩð¡<±Ó' ¢<)£³MH¢<Ð;t¢<ª͋tɠ¢<];¥d!͢<!ù¢<vû|
&£<¡ªR£<ð
F£<üïÏL¬£<m3ÀÝأ<Ä Oôͤ<ÐlFæ×2¤<§lqü_¤<ăÈü<¤<¤k º¤<êEËôè¤<û ف®¥<øµ,ÄgC¥<'o1¼Aq¥<ùNk=¥<5Ô[ͥ<&ÏVúû¥<.sã*¦<\X¦<îëÓE¦<ß<~ ¶¦<¦YË$å¦<û©PS§< úa¬C§<0ÑwÑ1s§<
$±v䢧<÷}kÅҧ<wrÎÌÕ¨<*æߺ3¨<çaYc¨<T¤Ï.¨<`ÌHŨ<þóö¨<ás\'©<5²ØX©<ô»@9©<]ÇÚ}¼©<QéÝܨî©<-YЊ!ª<ÆV5¶Sª<óÐ2ª<zeß9ª<ÿ¬ʝ(íª<µnÖÓ «<B%ÏøÃT«<¶O2{ú«<&Ûx½«<
ý-@ò«<-àBNS'¬<¤±ꂲ\¬<û##Ø_¬<l¥ó\Ȭ<q탫þ¬<ò0AM5<þ£ íCl<
¥S£<5ÒJ7ۭ<P&´7®<R¤|K®<#ôO®<xvJk½®<h[üèö®<¼ nË0¯<Ð^Qk¯<åáï³ƥ¯<Ø Ý
äà¯<Ôùz7°<9ï4,°<£$kJ°<Û&ÏÜh°<:ω°<È3÷s¦°<o ©Ű<·ÏïPå°<Îï f¯±<Jj$±<+:oìÍD±<ÁąEe±<®oݱ< x¢§
§±<Z*x¦aȱ<p3ªê±<¢ôðò ²<PåOR3.²<º;@æÆP²<¦ÚÇa¯s²<+SBé<QÛE´º²<p-|<eY&Yγ<Ч* '³<eÉ;³L³<V¨ør³<CQ4õ³<zD¾³<Ðޭå³<îõé/ ´<øB½ÉÒ3´<,É
í[´<2Ә´<L¡]§´<'± {0״<¹Oµ<²ª¬qø+µ<Z§ø1Wµ<aDLýµ<á8úa¯µ<½dܵ<y
¶<.{$U8¶<2ôÃ`Og¶<îHJý¶< {/eǶ<%ô±ø¶<Ò\Î}*·<Ãq½â<]·<ùqkµҐ·<Óv}Gŷ<né£ú·<þÀ,ñ0¸<Bsh9h¸<«[i΅ ¸<6;âٸ<DuóÒZ¹<*ü4ûO¹<ØñЌ¹<êÙ$:êʹ<xñI>V
º<;LèC%Kº<ꆭÂhº<ÄE3Ѻ<
¶»<êP±]»<^Úvґ¦»<wïKÞTñ»<§àÂA>¼<ôÈÈBô¼<©òì<Å8'k1½<ì;ìo½<ñN¯Pà½<` nò;¾<Có*¯¾<JêPgÂü¾<§÷nb¿<åÆöCþ˿<.ìb³â À<ïõVÀ<N¥ËÍQÀ< H]x1ÐÀ<¦C¨Á<*DugxVÁ<Ö³¼Á<|úɠ¼ëÁ<Y¶+=Â<¥ªI®õÂ<ðDãðÂ<^÷Ì'îTÃ<a¸ÈÇNÁÃ<bäf7Ä<ÑQGÍÄ<ösÏ<ØJÅ<ÒsázîÅ<r¿KmgªÆ</ÆêÖPÇ<íò染È<
{H
ÜéÉ<üqÚQÃË<»~)ÙÉÎ<Ɨ$'R ~1×[} <?õn ®°2· |D÷'Ñ e r9\-þ ²kÕ[~ p,Ý4É ȝ¬ß 6xÔq{3 ¢·|Z lo B{ >®¯
ðN±õ® Ve´½Ã ΙðöÕ Vn®æ Ð 6Ênô ¤ÔÝvK ¶§ã z÷ñic p%E ò t¨Q®) 2U¹±1 ÁWQ9 Linëâ? ú×23F : ¿L "3\LQ Àìà ¡V Ùf[ Ðà_ rWDÝd x
ö h æ+*Åk ôä2=Ko :ñq r Ö MÈu À\Çx ô?A{ FS~ 8â;æ b=Z ¹V`±
bB²í útu ¬9=º JÐEÌ >ñ àX½ دG¬w ÚdO 8cx¸ A ºFẙ i¼& zqV
ØÏYם Ρag À6 X 83:뇡 üÄko¢ Îɣ ¢jî_ۤ | Mªä¥ gä^å¦ Ä ¥Üݧ t¨æ|Ψ î_Γ·© X¸pª 2X^t« t£H¬ 蟿 W;ޭ l ò ® ~°$\¯ z[° ô߁İ úñ¶Pp± :²² J¨ß+º² N!X³ ¾ɦñ³ ֬ ᆴ üÇóµ ªýÅ ¥µ Xþ7(.¶
Ɉ³¶ µ?5· ¨}Üh³· ºÖ .¸ öG{¥¸ t¹ rº
¹ &oyaø¹ âî=cº ìA/˺ D´H0» ⤮» È<ò» )Ò9O¼ Ô@ᣩ¼ T½ rÞûV½ jª½ @?˷ú½ Þds I¾ ^iÉ@¾ (±0߾ taÞö&¿ ⊂l¿ Ä©1°¿ °ýºñ¿ EA1À ²T[ÏnÀ &mªÀ i#äÀ d)ùÁ B}õQÁ Jw Á ´t}¸Á Bê éÁ ÞÕî þ<
E ÂOvp c/ Fé< ´ÆҢè ì"Ae
à އ0à Æ~ Rà øfßúqà (*Qà útà H3DÈà @«Ìäáà ¨M÷ùà `P¸}Ä hýwx%Ä ƿµè8Ä *ÏJÄ èGô+[Ä ElÿiÄ ²PIwÄ ¸û+ Ä öE>Ä ҙçÄ °0ÝÄ 2´y¢Ä ü¦Ä ûëø¨Ä êΩÄ 4úA ©Ä (N¦Ä t.Ȱ¢Ä â-æÄ ô-
̕Ä À^&܌Ä z#ì;Ä æޖæuÄ ~ÖgÄ 6 XÄ .pmFÄ Ë 3Ä n
Ë Ä ��Ä bËH²íà <Y>ÄÒà ´Ã Laõà EZ và póRà (²Á-à x½_à bò˿Ü ¹Ӱ ðü dñyÚQ Ӷ¬  VgñèÁ <»7°Á Í܆uÁ ¶Öt®7Á $»ööÀ ¤MH³À lÀ dó "À ¸rqտ H)݄¿
Æ/Å0¿ Æ wپ Ú}2}¾ ¦K ¾ D5zº½ &ø¹§R½ Æcæ¼ äM,}u¼ ª·c¿ÿ» ¢æ?ò» ѠÙ» ¬p5º ¶¿ó¹ ü«Ô.b¹ J3ʸ T[vv+¸ \[
· UÕ@ض BiÙ÷"¶ à7oLeµ Òi¿¿´ FçÈγ >SÏô² R(D2² Z> ± ÂáB0$° ¦yÄ1¯ ágW® r-¿ެ
@樫 (ÿóaª ¢foe© <P³§ òÑ&¦ êÔ{¤ ÀœƢ ó}ôô
¾k3 ¼ùy+ñ īD¸ ¸/x[U x?ЫÕ òñΩý äÚü ø
s¹ Gì* ÛùE
6Ãý &é9xB| Ì*X£ w $ q *5·4j f⨠c ÄãOfZ rÎNrP Úo\fÇD ¢Y£å6
4P4& {> æËWú®ö ¡Ó °- ¦¢ |&ÇaY ° ¬+öÝ ÀèäÙMÛ e'5ìÄ2µV227©2Â2ÆÙ2Æfï2ß3ن 3À3H 3®(&3Åo.3z63oN>3ËòE3lM3F¾T3/í[3ßûb3íi34Ãp3fw3&~3·[3B
3ψ3gü37!3>3÷T3Õd3n3r3Fq¡3ãj¤3Ã_§31Pª3r<3Æ$°3k ³3êµ3ȸ3q£»3|{¾3ÛPÁ3¹#Ä3CôÆ3ÂÉ3òÌ3dYÏ3"Ò3+éÔ3®×3ürÚ3ö5Ý3Í÷ß3¸â3xå37è3ðõê3«³í3àpð3¤-ó3êõ37¦ø31bû3 þ3ùl 4ðÊ4ù(4 4hå4áC4¢4
4¿` 4MÀ 47 4
4?á4nB4¤4L4 i4aÌ4T04í45ú42` 4îÆ 4p. 4¿!4åÿ"4èi$4ÑÔ%4¨@'4t(4>*4+4ëù,4ßj.4ðÜ/4'P14Ä24):44±54&)74¢84c :4;4$=4+>4®@4¶A4K C4v¡D4B(F4¸°G4à:I4ÆÆJ4rTL4ïãM4GuO4Q4²R4Ú4T4ÎU4EiW4Y4 ¦Z4ÔG\4Çë]4_4:a4åb4ÿd4èBf4\õg4jªi4 bk4 m4ºÙn4¾p4¤\r4}"t4Yëu4H·w4[y4¥X{46.}4 4¼q4§a4]S4æF4N<4 3
4å,4+(4{%4ã$4o&4,*4'04m84
C4P4_4q474{4w·4>ԕ4àó4s4<4¶d44¿4$ò4 (4a 4¡4lߢ4 $¤4Ål¥4¹¦4x
¨4Ä_©4¹ª4ê¬4{4 ã®4EP°4©±4{:³4귴4);¶4nķ4îS¹4çéº4¼4<*¾4 տ4Á4ÈAÃ4.Å4ÏÆ4עÈ4ÚÊ4fÌ4RWÎ4²RÐ4*YÒ4FkÔ4Ö4δØ4íÚ44Ý4§ß4²ðá4¢gä4ðæ4ké4¤<ì4
ï4ßñ4yÕô4æ÷4uû4ò_þ4ç 5°555@5ó
5 ø 5å]5^é55 5q§5v
5»¼!5¾Î%5ÂV*5×s/5;S55:<5ÿD5àNO5ó ^5ÉNv5QHq oõM ֻa Ýnj Do tTr ùot oùu Ó$w 'x îÍx ,jy íy 7\z z ô{ ÜW{ S{ »Ñ{ .| 3| ]| ȃ| ¸¦| ÆÆ| Iä| ÿ| Í} C0} F} Z} m} } S} ( } ¯} -½} Ê} "×} ã} |î} Mù} ~ i
~ Æ~ ¶ ~ B(~ o0~ C8~ Ä?~ öF~ ßM~ T~ âZ~ a~ ìf~ l~ r~ ]w~ v|~ `~ ~ ¶~ $~ m~ ~ ~ w~ :£~ ަ~ fª~ ѭ~ #±~ Z´~ y·~ º~ q½~ KÀ~ Ã~ ÁÅ~ ^È~ éÊ~ aÍ~ ÇÏ~ Ò~ `Ô~ Ö~ ¹Ø~ ÎÚ~ ÕÜ~ ÎÞ~ ¸à~ â~ fä~ *æ~ âç~ é~ -ë~ Áì~ Jî~ Éï~ =ñ~ §ò~ ô~ \õ~ ¨ö~ ë÷~ $ù~ Uú~ }û~ ü~ ²ý~ Áþ~ Çÿ~ Å » ª p H â ¤ `  i
£ 6 Â H
È
A ´ ! è B ä + m ¨ Ý 5 X t ¤ § ¤ t W 3 Ø ` Ì w · K × \ Ø
L
· s Ã
G { ¤ Â Ö ß Ü Í ² Vÿ~ þ~ Ãü~ dû~ öù~ xø~ êö~ Kõ~ ó~ Öñ~ ÿï~ î~ ì~ ýé~ Ïç~ å~ )ã~ ®à~ Þ~ aÛ~ Ø~ Õ~ {Ò~ ;Ï~ ÓË~ AÈ~ Ä~ À~ m¼~ ¸~ z³~ ¤®~ ©~ "¤~ k~ ]~ ï~ ~ ԃ~ |~ Ås~ áj~ Ua~ W~ ÷K~ ó?~ æ2~ ¬$~ ~ ÷~
ñ} Ü} Ä} ª} } i} ÉA} } Û| Q| øD| ¼Ú{ 3N{ z ey Ùww 7ms yÙx;IÏ<Æöýã <´[,<¯P<a;D8¹|< §/èü<¼ÐL. #<÷a8/M <trtZ/¬<ÃÕL-H2<»'2M <C];õ <w6A¦¡<õz¢'¢<Øc8.µ¢<õWÀ?<£</±¢^½£<Uÿï9¤<§þ=6»±¤<tÓbu%¥<Χ¥<ê~ÙÏ1¦<=|£aÒk¦<p ¢Ҧ<¦øFÓÚ6§<w*³§<CõFEø§<w
CSÌU¨<v{d±¨<ÏN©. ©<ê ,Gc©<FÅ8ɹ©<,§¤Ü̪<YÍwmgbª<0n´ª<lm±«<)zBU«<:R6¤«<2¿*Öñ«<óNYùp>¬<a;2¥¬<&rþÉԬ<H· < ä)g<ø# ί<Svñ©:÷<þíҵë=®< oz3郮<ù½:ɮ<&bðç
¯<öØTöQ¯<®ׇm¯<¬.ú}Sد<ì4BàV
°<9õ@.°<ü¥êN°< r[Vo°< ôq°<a¼}¯°<ÌKf=ϰ<kKÈî°<î2 ±<¾1G-±<A>L±< Ŀk±<4Úx§±<mîQ¨±<Ë*øøfƱ<.ÔӋä±< @²<éÆÄre ²< Ãé} >²<ûk© ´[²<Ó f*y²<×ǁ²<Ú.¸b»³²<S¸ábØв<©ËèÙí²<×Hn
Á
³<0¹ôá'³<¡^&pDD³<ÕRʺâ`³<jX¾j}³<d²²oݙ³<=¸¿;¶³<à Vҳ<Zrî³<tàqå
´<]t¦-û&´<¤0<è C´<]ÇÊs÷^´<6Ãfßz´</H2º´<]A��<ܳ¬Iδ<¦8 ê´<bU^﫵<Z
òM!µ<OfjÕæ<µ<ȲNwXµ<x_U tµ<
Ɓµ<Y$#ýªµ<=s}ÑrƵ<ӌ/{ãáµ<8^ÈOýµ<à £`¸¶<¢°¢è 4¶< &·O¶<rÉWâj¶<71±B¶<±²P)¢¡¶<»C³è½¶<RÓ(abض<Tøa1Äó¶<ëh÷'·<ÆiQ*·<ÜîpÜ÷E·< så5ea·<IôïúÖ|·<½ºÈM·< <ʳ·<û"ÛóLϷ<çÞsÖê·< ꆤg¸<vÈÚ "¸<=¸<½õÑ NY¸<Å~zou¸<-÷G_и<CÀ¬¸< ¡«eȸ<'jDQIä¸<µs): ¹<G(Ü8 ¹<ü
ïF8¹<¢ybT¹<îÕp»p¹<1*.ˌ¹<¿?©¹<,ÙՌyŹ<to+ìá¹<JÒú&rþ¹<6ù9 º<[Ȣ!»7º<» Tº<¤©JrZqº<=1 dLº<ñ>V«º<ÎõZÍxȺ<6³á´åº<¡ÃO »<[ð| »< à
>»<=ÎAµ[»<'?¹}y»<<÷åñd»<n%
Ûkµ»<¢À.kӻ<®Üñ»< ìlH¼<-zðå×.¼<
nM¼<ìfl¼<¦ëàf¼<«¢6½ª¼<Ö;Çáɼ<7àh0^é¼<n2 ½< ï7Û(½<GÆ3ÞH½<#ñçi½<¥û×ôs½<pn ª½<IüøÒʽ<7.RÑë½< ÒIû
¾<öFêÄt.¾<ÑY P¾<%þ/ r¾<
¿*K!¾<o÷¶¾<:§v#پ<©ìaü¾<!S2 ¿<mM·¤B¿<hÉ _f¿<f¿<¿"q»®¿<
ç/Ò`ӿ< öÁYø¿<u ÓGÔÀ<Gɏ¨!À<«©©4À<Çõ>NÚGÀ<~³ö;[À<h&§#ÐnÀ<.cÀ<T¢èÀ<ÄÀquͪÀ<HÔîÑ=¿À<0=ª4êÓÀ<eÏÔèÀ<¶¦ïÿýÀ<Ap nÁ<5]»!)Á<m Äi ?Á<;.`HdUÁ<óî;ùkÁ<aÒt߂Á<¬ëNVÁ</w±Á<¦q©ÉÁ<9®äûëáÁ<ÙâúÁ<̼Â<îÓozG-Â<$¬¤EGÂ<àXvǼaÂ<.Y¨ú²|Â<xwÍ.Â<R
*S7´Â<ۖ1ÔÐÂ<õx©±
îÂ<î®VÒì Ã<£¤h^{*Ã<£®ÄIÃ<@¨3zÒiÃ<
AV³Ã<ú®pu¬Ã<¦³'ÏÃ<uô`ªÛòÃ<Ú幜¤Ä<^T=Ä<:§DÎdÄ<¼CubÄ<'Zks·Ä<Í
%ãÄ<A¬éSÅ<B~:R@Å<äJ©±qÅ<ٍq%Å<þÐ:$ÜÅ<L ÏiÆ<êj {ÎSÆ<Ã埾@Æ<2â kÛÆ<4z_ð('Ç<s VyÇ<ÎÖô-ÔÇ<4ò)9È<|ª¿«È<Doà.É<«W@îËÉ<ZwxÊ<±ýx8 Ë<3 ´;Í<jï%=ó ¨Æû¾ B½úT£
êîÁ~öQ ~÷ÓéU² ¹Ê~Kï ªDú
G Ëÿaí7 \%aFO £ä¥a ¤Suzp D(ì²| ÓWc ñ Þ%W¦ ÚÐMÇ$ õÛ© túõ`£ øK[Þo¨ ÜTÓ`ñ¬ ¹gû° ÆtS´ wþf#ì· å¡éìº í «½ Wlÿ`0À H¢7 Ñ[âz¦Ä 1îz¢Æ ¤(©zÈ
ÞK^2Ê #éÌË Ä9øMÍ ìMµÎ 0É ¿Ð æÄÖMFÑ Pôâ¨rÒ ÉðOÓ x´Ô S¸Õ 왎 Ö 2èȩn× è{THØ ,Ù ҭ§ÝÙ ^pÚ .À]MÛ Ðü[\ùÛ }¹ëÜ r;Ý /4ÒÝ d6dcÞ NQpîÞ .´¦tß @íeôß ò$¼äoà X¢%Âæà L¸(<Yá ?¼Çá ª Ûé1â څâ Aµûâ JU3[ã * Й·ã éä 4wÔFgä \ LӺä $Ү å x¼N÷Yå äȥå >ïå xÙo6æ xÕÆu{æ ª f¾æ òôåUÿæ § Y>ç 9>{ç ¢ppã¶ç CBwðç ðS(è :5û^è dܓè ¼ÎðAÇè öN}8ùè Ì)é êÓ Yé ¢ûé fHq¬³é ն&ßé |æ«s ê ¤fñ2ê ,2«Zê tզê ð ޗ§ê Ùó
Ìê <æexðê ì/vë J*þ
5ë ´b1®Vë úâôvë æ_ë |Ïô´ë ÐIô¸Òë >.n±ïë è½ ã ì Z±R'ì ӯBì ñ)ý[ì ôîl@uì ´ Pҍì ¶¥ì þ'Äð¼ì ûTÓì ³Ȉtéì ·Äþì (
5wí I'í L/$;í nXûMí ÝØT`í èOA rí ©äWí È,¤í ·
+¤í ´jtȳí RfAßÂí Rn¤qÑí ӊ<ßí íí Ô úí ÄK®î ZÙÀî àW î $eKs)î ¼ä
4î <¸=>î ô)îGî ° 'Qî A@éYî .´(5bî ñX jî z>lqî {2Xxî º{Ï~î ²JH҄î Cc¶`î QÈÌzî Ú%~ î ê)¨Qî \Hî ôsrUî ®Ìb'¢î ¬Bk¤î q-üh¦î úÖnקî
úΨî ;3èK©î d)P©î ^À٨î Tvç§î $ Hx¦î ¢¤î Úä" ¢î $ 5.î .¯&¼î äò$ŗî :
<Gî uU@î z6®î ý=î ¸§Þ{î ÿ7ÿtî ^½©Ãlî ~ Rdî (£E[î ¶WNQî Ï JGî P,áS<î Ø*à²0î b$î Z<¸^î G*¢ î ÌIã'ûí l!vêëí ~"äÛí Ó9ÎËí ô,d¹í É8éܦí é7rí 6¨8 í +9Òií ®Sí "¤ÞA<í Ø/jç#í Dæ/s
í 4þÚïì ¸·Ôì ´n·ì Á0¶ì x©
yì þ1õWì bɆf5ì 5³´Lì Ðoëë ¶ )Äë Ü îõë B
Éáoë ÓBë K- °ë éYâê W"®®ê &㎍xê åsýÏ?ê öٍLê ;V/ÖÅé ¤G©;é (G G?é ÖÅv½öè æèÄ]ªè ê±zàYè @©öè À3H«ç ¥j uLç ¢*èæ ث¶ }æ ~08 æ B÷8så rpå Xô6ԋä 7 ý¿ùã ±î5]ã þä/µâ WU â x<á °gîÄhà ªq+°ß ªþ~ŇÞ ý;Æ uÝ ¿)åFÜ .øøÚ uº²á
Ù ÏHïæ× e½Ö ðâIÔ ¬Ǵ§¡Ñ vâÎ ²^بË "-ÍnÒÇ í" /+à :¸e½ 4T Ķ t(*X@¬ E ü ¤Hú ,0ð÷Åf J 3KZ ð?ðyÉjDï?©l[T·î?wð'à?î?Þ§oÓí?ò¼Wpí?Ü¡xIí?ë-§¨3½ì?x©Î^jì?êºîÙ ì?ÜáNëÎë?Rõ:e
ë?Ý4:>ë?¢èl?*ùê?%zñþµê?áÉPՋtê?¯õýª4ê?Ø eî;öé?$"¹é?ÁzaWF}é?GzBé?Oq1½ñé?¨
æOUÐè?ߺHè?¬¼7üëaè?nÏV,è?Ëâ Kíöç?XhwÂç?հ <ç?VØp \ç?m?ôå)ç?îzêºPøæ?ZcXÇæ?*;Q^÷æ?#ã*'gæ? Uâ7æ?e&$ æ?jÿJoèÚå?\Ȭ)å?L&äå?FðSå?ÕleZµ&å?g¶ èÄúä?ÀNIO?Ïä?xRÜr!¤ä?Pß_hyä?y6IJOä?ã_5%ä?[X~ûã?£1¯>Òã?Íb¦U©ã?Õ Ú+Àã?éPõXã?5:pɗ0ã?ï8dýúã?î;êU¬áâ?Jתºâ?͓òâ?í)mâ?ېZ]Gâ?ò÷/©|!â? ©àûá?iTþÖá?Ñ?Wq±á?P<pá?Ú9há?©^Cá?8 1H á?Y2¢³ûà? BAØà?®Ùp¦´à?] và?6<ðÌ}nà?.?¦¯¼Kà?*á1)à?Äʸ
Üà?¡½{wÉß?Ê ©§
ß?óz/Ë)Bß?~qÿÞ?T ½ n¼Þ?ÅÃNj#zÞ?
_ê88Þ? :vGöÝ?±V 2µÝ?3Þ&dtÝ?¡64Ý?m[®´ôÜ?H¨ÀsU´Ü?Ç× »ètÜ?¸, oÒ5Ü?ja|÷Û?mq֤¸Û?xzÛ?Ê1³bÄ<Û?R
¡NÿÚ?Z_:)ÂÚ?ؤJS
Ú?MÀ êËHÚ?>F9 Ú?ߓ ^¥ÐÙ?ÆÀÙ?àۮYÙ?Ë3£ Ù?ñ¹üáãØ?Þ?i©Ø?¶Z¬¨8oØ?Ù
ªO5Ø?ٸû×?°ô¯PÂ×?ëR¯9×?í±ÇigP×?La©;Ù×?ªLßÖ?!ވ§Ö?âË%ÁoÖ?å{7=8Ö?ÈҀtú Ö?DÂvCøÉÕ?¾îÖ6Õ? =p³\Õ?í;SÂo&Õ?m¿jðÔ?¢W£ºÔ?Ôj
Ô?þ$ÃïÌOÔ?z5ѼÔ?ÛҎÐèåÓ?®Cñ|P±Ó?yhó|Ó?Ñù%ÑHÓ?/öZMéÓ?f!w;áÒ?Ý?>ǭÒ? ±MAzÒ?Þ GÒ?Ì÷yÀÒ?ö.âÑ?PðÂ9կÑ?èTTí²}Ñ?gî4»ÇKÑ?#$ÏOÑ?Ä YèÐ?ÚB²M·Ð?6C;Ð?ÙéB"_UÐ?~tÇö·$Ð?œ߉èÏ?52¸Ï?Ҙélþ'Ï?DɤTÈÎ?Ý<(²iÎ?qE8
Î?
ÇUīÍ?OQ²ø¶MÍ?Ìo^ðÌ?Sßq͒Ì?Gطð5Ì?¡¾zxÙË?ª1zd}Ë?:ÑÌR´!Ë?W¢gÆÊ?~& ~kÊ?=~-2÷Ê?ZþҿҶÉ?'|j_]É?iút¿¯É?[°ªÈ?8RÈ?uq bÕùÇ?#£hÓø¡Ç?¦µz|JÇ?G~`óÆ?\ò!>¤Æ?ñ¢GFÆ?ùøvJðÅ?l Å?5hȩmEÅ?Á 㭍ðÄ?-Îõl Ä?ÕuÂéGÄ?®1i%ôÃ?î×調 Ã?«´¸MÃ?e*|ûÂ?zèÂ?·^¢ÕVÂ?4<%FÂ?B}u´Á?c-¨å@cÁ?¹n¢ ËÁ?º R=³ÂÀ?
¿¸KùrÀ?*}T#À?,"kË>©¿? R)ÿ ¿?K¥ò{o¾?èvaµӽ?命¹«8½?
t;I_¼? hм?3âòxÿk»?3öÊéìӺ?bê3<º?[ܦ¹?« ¤u0¹?R(¿ {¸?Öï>Êæ·?vªZ9S·?LJisk6?M
$a.¶?¤ftWµ?®+ú µ?"@á|´?&#ïí³?p>ÙäÅ_³?1ÏfҲ?
ÝDÓE²?}¾ º±?òÐ/±?%,�?ä0°?5nl+,&¯?Q²GÕ®?bñþ. ?,*(>ý«?p_8óª?cU)ùê©?«µh*àã¨? '¯wûާ?dИ³éۦ?ԭò<²ڥ?]']ۤ?ËîÎòݣ?ô=è|â¢?¼j é¡?.ñ ?ĥׁø?uÛ? ̓0?øë"NR?
Á ¶Ñy?¿ ôڥ?d°ûòê֔?^«8
?0`4I?IÝrO*?¬O'¤?x¤
A?àÏBë?/)¥?7hìø`á|?]¸ ٨v?ý±° p?g°ÁC_e?÷¹¶¦T?ÜIú4_hÜ2z
3Êå+3ç@3aQ3i`3{am3Ay3i3*¨353=3r©3þá3öì3|ϡ3ڍ¥3«+©3¬¬3°3^³3¶3¹3iż3-¿3c®Â3%Å3uYÈ3<Ë3LÎÍ3gvÐ3;Ó3k¥Õ3-Ø3$¬Ú3´!Ý3±ß3óá3Pä3P¦æ3øôè3é<ë3p~í3չï3^ïñ3J ô3ÖIö3<oø3³ú3m«ü3Âþ3·j 4r4Uw4³z45|4ì{4ëy4Bv4q48j 4õa
4FX 49M 4Û@
4834]$4U4,4ìð4 Ý4SÉ4´44Æ4Ïn4V4w<4$"44Vë4ëÎ 4ޱ 45 4÷u 4,W 4Ù7!4"4¼÷"4ýÖ#4ҵ$4@%4Mr&4P'4_-(4p
)47ç)4ºÃ*4 +4|,4éW-43.4 /4~ê/4ÃÅ04ï 14|24W34244
54è54Ã64"74@y84sT94¿/:4* ;4¸æ;4nÂ<4R=4hz>4´V?4=3@4A4íA4qÊB4¨C4D4udE4-CF4K"G4ÑH4ÇáH41ÂI4£J4vK4\fL4ÍHM4Ì+N4aO4óO4bØP4ٽQ4ý£R4ԊS4crT4²ZU4ÆCV4§-W4ZX4èY4UðY4ªÝZ4îË[4(»\4_«]4^4å_4C`4¿va4alb40cc47[d4~Te4Of4òJg42Hh4ÙFi4ñFj4
Hk4 Kl4MPm4Vn4^o48hp4¦sq4år4s4
¡t4´u4 Év4Càw4ùx4 z4ù2{40S|4Ùu}4~4ÎÂ4¢v4@
4L¥4Ò>4àق4v4Ä4¸´4lV
4ïù
4R4¦F4ÿï4p4
I4ëø4"«4Ê_4ü4ÓЌ4l4åL4`4þԏ4坐4<j4-:4æ
4å4vT4»¡4¢4np4g_4ÛS4 N4N4U4¬c4>y4ݖ4%½ 4Áì¡4r&£4k¤4»¥4(§4û¨4 ª4«4.4Qä®4N³°4t²4ª´4\۶4H9¹4«̻4p¡¾4ÈÁ4~XÅ4wÉ4p_Î4ä~Ô4úÀÜ4¤Ýé4ìw õE` ¨m ´r ¯u \zw 8Êx k¿y 5zz /
{ ԃ{ å{ 7| 3}| &¹| Hí| } C} g} ۇ} ü¤} a¿} g×} ]í} ~ ~ 4%~ 5~ ÕC~ Q~ g^~ ij~ ªu~ >~ 2~ ~ r~ դ~ Ƭ~ N´~ u»~ CÂ~ ¼È~ èÎ~ ÌÔ~ kÚ~ Ëß~ ïä~ Üé~ î~ ó~ t÷~ û~ £ÿ~ 6 Ê
< Ä Ü Ú ½ :# ×% ]( Ð* .- z/ ³1 Ü3 ó5 û7 ó9 Ü; ·= ? EA øB D :F ÊG NI ÈJ 8L M ùN LP Q ÕR
T =U dV W X ¬Y µZ ¸[ ³\ ¨] ^ ~_ _` ;a b àb ªc od .e èe f Lg ög h <i Ùi pj k k l l !m m n n ün ho Ño 5p p óp Lq ¡q òq ?r r Ïr s Ps s Ãs ös 't St |t ¡t Ãt àt ût u $u 3u ?u Fu Ju Ku Gu ?u 4u $u u ùt Þt ¾t t rt Et t ßs ¥s fs #s Úr r :r ãq q #q »p Mp Ùo _o ßn Xn Ëm 7m l ùk Ok j âi i Th g ¡f ¸e Æd Èc Àb «a ` ]_ !^ Ø\ [ Z X W uU ÄS þQ "P /N "L úI ¶G SE ÏB (@ Z= d: A7 í3 e0 ¤, ¤( _$ Î ê © ä F ü~ >ô~ ¨ë~ 7â~ È×~ /Ì~ 7¿~ °~
~
~ w~ G]~ >~ Y~ ,ë} 6°} b} ¹ô| ÒO| 06{ ÒÒx ?V#z?£ºu?øq?}n?k?L¢h?ée?öRc?çØ`?Zw^?*+\?ÔñY?RÉW?ø¯U?_¤S?X¥Q?߱O?ÉM?3êK?J?GH?ªF?jÅD?`C?(`A?j·??Ô>?x<?øà:?0O9?Â7?Å:6?»·4?993?¿1?%I0?C×.?Mi-?!ÿ+? *?«5)?'Ö'?úy&? !%?CË#?x"?Ì(!?õÛ ?ñ ?J ? ?$Ä?¾?ØG?c
?QÕ??!l?ë:?å ?ß?@´?
?Üd ?)@ ?i
?ü?Ý?À?4¥?±?îs?å]?I?ä6 ?¼Kþ>í,ü>Nú>Ôø÷>qãõ>Ñó>ÇÁñ>jµï>ú«í>k¥ë>µ¡é>Πç>¬¢å>F§ã>®á>¸ß>'ÅÝ>\ÔÛ>#æÙ>uú×>JÖ>*Ô>_FÒ>dÐ>+
Î>$¨Ì>wÍÊ> õÈ> Ç>JKÅ>ÅyÃ>|ªÁ>iݿ>
¾>ÍI¼>;º>ʾ¸>tü¶>5<µ> ~³>êq>Ô°>ÂO®>±¬>åª>~3©>T§>ե>Í(¤>g~¢>çՠ>G/>>ç>F>J§>Ü >:n>bԓ>Q<>¦>x>ª~>í>>^>Ј>«D>lº
>Ü1>ùª>À%>\D>@|>ó?y>¥Bv>Hs>ÁQp>#^m>¸mj>|g>md>¯a>ÄË^>$ë[>£
Y>=3V>ð[S>ºP>¶M>èJ>~ H>
UE>B>«Î?>Ç=>åS:>7>"å4>=22>T/>dÕ,>m+*>m'>cà$>N?">,¡ >ý >Àm>tØ>F>¶>1*>¥
> >Y>>ʗ>ë >öIý=ù_ø=à{ó=«î=^Åé=úòä=&à=ü_Û=gÖ=ÊäÑ='0Í=È=åØÃ=P6¿=˙º=\¶= s±=Ûè¬=Ød¨=
ç£=yo=/þ=6=.=fЍ=§x=i'
=½܀=a1y=ª¶p=xIh=ðé_==W=TO= G=Ü÷>=Nß6=Õ.=èÚ&=ï =ç=-H=L=Äÿ<אð<̀á<úÒ<ÎÃ<Ø.µ<X·¦<Äi<H<R©x<i$]< B<²\'<,
< ç;Gõ´;øP;úü*;.0¥: ð?7åEî?ñÿP¦Ðì?'{ë{ åë?*æ!ë?çúb¥ºvê?mUÞé?9ªUÄ1Té?/ÒÓv£Ôè?¸Åxè]è?&1$-îç?~Ô n
ç?cK©[»!ç?ÆIÃÂæ?\Omúgæ?f¯§Áíæ?u¬Li=½å?sڂlå?xº å?¯øQÁfÓä?iàûjä?%ᨯCä?±+Ëþã?ÑáDܻã?Ùݧzã?cE#;ã?^ÚEã#ýâ?$O ¶Àâ?½2m
â?£P"Kâ?È>ºêâ?{sÛá?%; Ç¥á?îoÎmÎoá?3¼;á?à J9á?+ +ØÕà?*ÐT[¤à?};î1¹sà?HeÒëèCà?$ó`±âà?vE!þ=Íß?úſ-rß?MBëцß?K=ÀÞ?QÓ}6EiÞ?ü7áuÞ? !§ ¿Ý?zí¹}ÙkÝ? ~é½Ý?à@ÜÁÈÜ?`ûÙÜxÜ?¥Ð*Ü?µî®8ÜÛ? QiÛ?oTCÛ?_ï(4°øÚ?åöýָ®Ú?@£j§eÚ?ô!u v Ú?7Zi ÖÙ?¨{ òÙ?ìIÙ?]TÙ?9]·çÀØ??¼}Ø?8aDµé:Ø?Yζiù×? Ɲҷ×?ãr^sSw×?ꍰ07×?d>[øÖ?éä%۹Ö?
Əþ{Ö?ä'HBÂ>Ö?vXï #Ö?lî1& ÆÕ?ï©:l°Õ?磽!×OÕ?õލÕ? ù&×ÛÔ?Óڋ«¢Ô?ﾀ+ jÔ?âAëî1Ô?N¡0ZúÓ?
²«0HÃÓ?ï}±G·Ó?ÝÐü(¥VÓ?5$1Æ!Ó?pB9 õëÒ?b"®FS·Ò?)vEW(Ò?ývG}rOÒ?ÿ~ ñ/ Ò?Û {÷^éÑ?Z¼áý¶Ñ?
Ñ?ïâބSÑ?ººÌi"Ñ?l¦ÙR¸ñÐ?3SønÁÐ?>éNÐ?Ґ]ðbÐ?,|yõ2Ð?jG«>Ð?TÿLҫÏ?~>\çOÏ?àèºôÎ?ò@Y HÎ?§/֎@Î?9O"HçÍ?¸îã>Í?ý1´ ¢7Í?Ðö8¶àÌ?ÎOxÌ?]æ4Ì?5D9gþßË?¥är|¾Ë?>ïܸ$8Ë? [ëB/åÊ?I<ÀKܒÊ?¼\ß*AÊ?ÅäÑðÉ?#>䠟É?¡æÆOÉ?y»%d É?ÕbPޱÈ?ùÄÍcÈ?æçPRÈ?®
ÈjÉÇ?þF¹}Ç?9(¹Q1Ç?êîc æÆ?(ڦ^wÆ?¬Ñ0U^QÆ?1j°úÐÆ?¶ÂT ξÅ?õx.BTvÅ?Imb.Å?ú¶<X÷æÄ?0Ø Ä?ÆÌ-ɰYÄ?j8 ÓÄ?©ø
wÎÃ?ÉՔ&Ã?¯ úßBEÃ?n}¾ªgÃ?4Ï
¾Â?@`r*{Â?xè»{Æ8Â?eÊ=¯ÝöÁ?fÖ1 oµÁ?x®ðæytÁ?/qÉ ý3Á? ìï÷óÀ?/¶T{i´À?¾¥·îPuÀ?nz6À?ê˦üð¿?f
u¿?<îóú¾?̹F¾?ûºaõz¾?½?×M½?Wýk[£¼?¯.ô .¼?&qW¹»?He5TF»?eTe±CӺ?·8Ù=]aº?(ôFÐMð¹?pk3G¹?¹t刯¹?;SZ ¢¸?ºÄ;,`4¸?ó¦׀sǷ? <W[·?¶H ð¶? ¶0܍
¶?÷ÞÊ\Þ¶?>»íû²µ?6ÐY¹åJµ?)ِòã´?\CÓ}´?±%d´?w²³?çÆSN³?эvöê²?pÎa²?,Q&²?@£o¨ű?SuFe±?PÊVȱ?;§°?Èõ×I°?viºÐׯ?4èDô ¯?å².¥g®?X1Iα?Jy ý¬?é!d¼J¬?
پz«?j»éª?8ñG;ª?L|{ʎ©?mwnã¨?k9: è9¨?«´¼§?R¯¶yë¦?A &ÇòE¦?ÊÒÅU¢¥?ëŖò< ¥?k&«_¤?ÿÿG #?®?~ #£? ÀVÉ#¢?Ôó_´ì¡?¡³ÐS¡?QÖ| z¼ ?îú
Y²& ?¯Çö$?htQz®ÿ? 3Tݜ?pXúP¡¾?Næ梚?H*g?gìS(u?üÚ1c?w@¢rT?Q«¦=I?¾ðÎQA?]1%Ò<?2:¹áÉ;?__rTE>?ð RD?ÎljÞý?W'n¹¶?-ÉBUú؊?½§hê?õtªæ¶4?Ëä n
?boQx°?qv³íiû?ù×_)òN?Å]túQW}?6HÔé#z? 6ì7w?ý"ãΗús?C@Wi=q?Ḱ³Xl?ÿþ¡óØf?$£á¨ka?%> Tµ+Y?¹ü÷
²O?K 2 Ã=? ?/*p?3
f?(_?xY?յS?¹ôN?¡J? ¥F?DïB?Qt??u+<?Û
9?6?Ó?3?n0?ëé-?Äd+?Ñõ(?6&?XS$?Í "?Yö ?âÞ ?mÕ?Ù? é?Æ?i+?q\?V?Û?Æ(
?s~ ?>Ü ?ÊA?Į?Ü"?ʝ?G ?§ ?ðiþ>lû>7Äø>êö>*Jó>ð>ìøí>Ì^ë>ïÍè>Fæ>çÆã>7Pá>ÁáÞ>K{Ü> Ú>Å×>ÇuÕ>;-Ó>±ëÐ>û°Î>ð|Ì>eOÊ>4(È>8Æ>LìÃ>N×Á>ȿ>¾½>º»>¼¹>Ú·>Ùε>ô߳>ö±>°>ñ0®>U¬>¹~ª>|¬¨>¸ަ>Y¥>IP£>w¡>Ðҟ>B>ºe>)µ>~>©_>º>C>{>á>øJ>>X(>'>N>Í>x >b>x>¬>õ!>^}>;z>Хw>@Òt>wr>b<o>ñyl>½i>²g>ÂSd>3§a>óÿ^>ô]\>&ÁY>z)W>âT>P R>·O>ýL>5~J>3H>õE>n C>²@>VK>>®è;>9>ë07>»Û4>ó2>>0>pö->¢²+>s)>»7'> %>Í"> >¼s >éL >*>= >Tð>TÙ>4Æ>í¶>y«
>ϣ >é > >L£>ª>lµ>åÿ=+¬û=×÷=0
ô=ØCð=ì=8Ìè=Ûå=hpá=ÓÌÝ=0Ú= Ö=ê
Ó=nÏ=¢ Ì=|
È=ôÅ=£Á=;¾=¼ں=Z·=o,´=óް=ߗ=.Wª=Ø §=×è£=%» =½=r=´W= C=4=M,=4*=D.=y8
=ÏH=¾~=¥÷x=õ<s=rm=ìg=ãUb=ÑË\=ÞMW=
ÜQ=TvL=» G=AÏA=æ<=¬X7=/2=©-=è(=Yý"= =ì= 9=£e=
=Ðã=5=¶'ù<týï<ìæ< õÝ<7Õ<8SÌ<C©Ã<»<\¤²<íIª<
¢<æ<Oޑ<+ò<"<ïßt<ɵe<ÓÇV<SH<·¥9<t+<ƅ <OÛ<w<ºê;O Ñ;ú$¸;¾ԟ;ë9;Åb;HÄ6;]£ ;«]É:X}:âî9mtrand name loader __loader__ origin __file__ parent __package__ submodule_search_locations __path__ Interpreter change detected - this module can only be loaded into one interpreter per process. Module 'mtrand' has already been imported. Re-initialisation is not supported. builtins cython_runtime __builtins__ init numpy.random.mtrand numpy/__init__.cython-30.pxd compile time Python version %d.%d of module '%.100s' %s runtime version %d.%d does not match 4294967296 name '%U' is not defined BitGenerator numpy.random.mtrand.RandomState._initialize_bit_generator while calling a Python object NULL result without error in PyObject_Call calling %R should have returned an instance of BaseException, not %R raise: exception class must be a subclass of BaseException numpy.random.mtrand.RandomState
RandomState(seed=None)
Container for the slow Mersenne Twister pseudo-random number generator.
Consider using a different BitGenerator with the Generator container
instead.
`RandomState` and `Generator` expose a number of methods for generating
random numbers drawn from a variety of probability distributions. In
addition to the distribution-specific arguments, each method takes a
keyword argument `size` that defaults to ``None``. If `size` is ``None``,
then a single value is generated and returned. If `size` is an integer,
then a 1-D array filled with generated values is returned. If `size` is a
tuple, then an array with that shape is filled and returned.
**Compatibility Guarantee**
A fixed bit generator using a fixed seed and a fixed series of calls to
'RandomState' methods using the same parameters will always produce the
same results up to roundoff error except when the values were incorrect.
`RandomState` is effectively frozen and will only receive updates that
are required by changes in the internals of Numpy. More substantial
changes, including algorithmic improvements, are reserved for
`Generator`.
Parameters
----------
seed : {None, int, array_like, BitGenerator}, optional
Random seed used to initialize the pseudo-random number generator or
an instantized BitGenerator. If an integer or array, used as a seed for
the MT19937 BitGenerator. Values can be any integer between 0 and
2**32 - 1 inclusive, an array (or other sequence) of such integers,
or ``None`` (the default). If `seed` is ``None``, then the `MT19937`
BitGenerator is initialized by reading data from ``/dev/urandom``
(or the Windows analogue) if available or seed from the clock
otherwise.
Notes
-----
The Python stdlib module "random" also contains a Mersenne Twister
pseudo-random number generator with a number of methods that are similar
to the ones available in `RandomState`. `RandomState`, besides being
NumPy-aware, has the advantage that it provides a much larger number
of probability distributions to choose from.
See Also
--------
Generator
MT19937
numpy.random.BitGenerator
numpy.random.mtrand.RandomState.__repr__ numpy.random.mtrand.RandomState.__str__ __repr__ __getstate__ __setstate__ tomaxint at least at most exactly %.200s() takes %.8s %zd positional argument%.1s (%zd given) s %.200s() keywords must be strings %s() got an unexpected keyword argument '%U' numpy.random.mtrand.RandomState.__getstate__ numpy.random.mtrand.RandomState.__setstate__ %s() got multiple values for keyword argument '%U' numpy.random.mtrand.RandomState.__reduce__ too many values to unpack (expected %zd) need more than %zd value%.1s to unpack numpy.random.mtrand.RandomState.seed numpy.random.mtrand.RandomState.get_state numpy.random.mtrand.RandomState.set_state value too large to convert to int int an integer is required __int__ returned non-int (type %.200s). The ability to return an instance of a strict subclass of int is deprecated, and may be removed in a future version of Python. __%.4s__ returned non-%.4s (type %.200s) numpy.random.mtrand.RandomState.random_sample numpy.random.mtrand.RandomState.random numpy.random.mtrand.RandomState.beta numpy.random.mtrand.RandomState.exponential numpy.random.mtrand.RandomState.standard_exponential numpy.random.mtrand.RandomState.tomaxint numpy.random.mtrand.RandomState.randint numpy.random.mtrand.RandomState.bytes '%.200s' object is unsliceable numpy.random.mtrand.RandomState.choice Missing type object Cannot convert %.200s to %.200s '%.200s' object does not support slice %.10s assignment deletion cannot fit '%.200s' into an index-sized integer '%.200s' object is not subscriptable numpy.random.mtrand.RandomState.uniform numpy.random.mtrand.RandomState.rand numpy.random.mtrand.RandomState.randn numpy.random.mtrand.RandomState.random_integers numpy.random.mtrand.RandomState.standard_normal numpy.random.mtrand.RandomState.normal numpy.random.mtrand.RandomState.standard_gamma numpy.random.mtrand.RandomState.gamma numpy.random.mtrand.RandomState.f numpy.random.mtrand.RandomState.noncentral_f numpy.random.mtrand.RandomState.chisquare numpy.random.mtrand.RandomState.noncentral_chisquare numpy.random.mtrand.RandomState.standard_cauchy numpy.random.mtrand.RandomState.standard_t numpy.random.mtrand.RandomState.vonmises numpy.random.mtrand.RandomState.pareto numpy.random.mtrand.RandomState.weibull numpy.random.mtrand.RandomState.power numpy.random.mtrand.RandomState.laplace numpy.random.mtrand.RandomState.gumbel numpy.random.mtrand.RandomState.logistic numpy.random.mtrand.RandomState.lognormal numpy.random.mtrand.RandomState.rayleigh numpy.random.mtrand.RandomState.wald numpy.random.mtrand.RandomState.triangular numpy.random.mtrand.RandomState.binomial numpy.PyArray_MultiIterNew2 numpy.PyArray_MultiIterNew3 numpy.random.mtrand.RandomState.negative_binomial numpy.random.mtrand.int64_to_long numpy.random.mtrand.RandomState.poisson numpy.random.mtrand.RandomState.zipf numpy.random.mtrand.RandomState.geometric numpy.random.mtrand.RandomState.hypergeometric numpy.random.mtrand.RandomState.logseries numpy.random.mtrand.RandomState.multivariate_normal numpy.random.mtrand.RandomState.multinomial numpy.random.mtrand.RandomState.dirichlet numpy.random.mtrand.RandomState.shuffle join() result is too long for a Python string numpy.random.mtrand.RandomState.permutation __init__ numpy.random.mtrand.RandomState.__init__ hasattr(): attribute name must be string base class '%.200s' is not a heap type extension type '%.200s' has no __dict__ slot, but base type '%.200s' has: either add 'cdef dict __dict__' to the extension type or add '__slots__ = [...]' to the base type multiple bases have vtable conflict: '%.200s' and '%.200s' invalid vtable found for imported type bool complex flatiter broadcast ndarray generic number integer signedinteger unsignedinteger inexact floating complexfloating flexible character ufunc numpy.random.bit_generator SeedSequence SeedlessSequence %.200s.%.200s is not a type object %.200s.%.200s size changed, may indicate binary incompatibility. Expected %zd from C header, got %zd from PyObject %s.%s size changed, may indicate binary incompatibility. Expected %zd from C header, got %zd from PyObject numpy.random._common POISSON_LAM_MAX LEGACY_POISSON_LAM_MAX MAXSIZE uint64_t __pyx_capi__ %.200s does not export expected C variable %.200s C variable %.200s.%.200s has wrong signature (expected %.500s, got %.500s) numpy.random._bounded_integers _rand_uint64 PyObject *(PyObject *, PyObject *, PyObject *, int, int, bitgen_t *, PyObject *) _rand_uint32 _rand_uint16 _rand_uint8 _rand_bool _rand_int64 _rand_int32 _rand_int16 _rand_int8 check_constraint int (double, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type) check_array_constraint int (PyArrayObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type) kahan_sum double (double *, npy_intp) double_fill PyObject *(void *, bitgen_t *, PyObject *, PyObject *, PyObject *) validate_output_shape PyObject *(PyObject *, PyArrayObject *) cont PyObject *(void *, void *, PyObject *, PyObject *, int, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *) disc PyObject *(void *, void *, PyObject *, PyObject *, int, int, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type) cont_broadcast_3 PyObject *(void *, void *, PyObject *, PyObject *, PyArrayObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyArrayObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyArrayObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type) discrete_broadcast_iii %.200s does not export expected C function %.200s C function %.200s.%.200s has wrong signature (expected %.500s, got %.500s) cannot import name %S numpy.import_array numpy.core._multiarray_umath _ARRAY_API _ARRAY_API is not PyCapsule object _ARRAY_API is NULL pointer module compiled against ABI version 0x%x but this version of numpy is 0x%x module compiled against API version 0x%x but this version of numpy is 0x%x . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem . FATAL: module compiled as unknown endian FATAL: module compiled as little endian, but detected different endianness at runtime numpy.random.mtrand.seed numpy.random.mtrand.get_bit_generator numpy.random.mtrand.set_bit_generator numpy.random.mtrand.sample numpy.random.mtrand.ranf %s (%s:%d) numpy/random/mtrand.cpython-312-iphonesimulator.so.p/numpy/random/mtrand.pyx.c d d 8K I H @ HO hO $T \] ¸_ \` ¤a f xf ¬ ¬¬ ® p® D¯ |± ³ $¶ P¶ · $¹ ü¹ PÁ ¸Á pÂ É (Ê DÌ HÌ ¬Î lí
Ôø HJÜ\d@Í4å
dZ
s$ ød ä àܖx¨ ô
Ð ü ¤ $# $ °(¬) <l´d ě<¡p¡¡ ,¢$£<¤H¥¦ L§¨ à¨Tª ª´®D³¨³´³¸µàµȶD· ¹4¹
¹ ̹ȼ
°½ ¾0¾$¿ ¿Ä HÄÈÊXÌÍ
0ÏÒüÒdÓÔÕäÕxÖ ¬ÙÝðÝ8â ¨æ @çèpé é ìÔì,íí ï
dï `ó ó äô@ö
öàö|÷¬ú´ú,û0û\ý ìO øO P P P (P 4P @P LP XP dP pP |P P P P ¬P ¸P ÄP ÐP ÜP èP ôP Q Q Q $Q 0Q <Q HQ TQ `Q lQ xQ Q Q Q ¨Q ´Q ÀQ ÌQ ØQ äQ ðQ üQ R R R ,R 8R DR PR \R hR tR R R R ¤R °R ¼R ÈR ÔR àR ìR øR S S S (S 4S @S LS XS dS pS |S S S S ¬S ¸S ÄS ÐS ÜS èS ôS T T T $T 0T <T HT TT `T lT xT T T T ¨T ´T ÀT ÌT ØT äT ðT üT U U U ,U 8U DU PU \U hU tU U U U ¤U °U ¼U ÈU ÔU àU ìU øU V V V @Ö (N D DK xN ÿÿÿÿÿÿÿÿ @Ù ð \ 4 P D `Ù ð pF 0M ¨
Ô ©â | D ²â ¿â ä /n :n ' ?n ¶p ,- Àp °u ¤8 ºu Å| D Ó| ðF G ÐJ L J ÌO ͊ b ¼S w Ìâ ¼V g ~ª ª " ) øº » É ¨ $É Í è« Í ÃÖ ¼¯ ÓÖ æá @¿ öá pê @ wê Iú @Ç Xú w ,Ë } Ð ª Õ · '- àÚ 1- g6 ÌÞ |6 }B Èã B ÎL Ðæ ÙL [^ ¼ê d^ gk ¸ï nk e{ ¤ó m{ [ ÷ a Q |û Y +¥ 2¥ S¸ \¸ ÌÄ
ÖÄ ¤Ö Ö Íà | Òà =ì x Hì Ôö l0 Ýö à P ò r äU z y $Z ~ G) L^ Q) Ì0 tb Û0 IA P~ SA IM x ]M Qc h ]c ®o <¥ ¸o | T¾ !| р ,À ݀ ͅ TÓ tÓ :n ìØ ô
á ± Hã © ` üæ g ύ ¸é ԍ " `
FpRDpp0pp p(p SDpp(pp`RBRBRBRBRASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASASAp SGRASASASASAQ >@_PyBaseObject_Type Qq @_PyBool_Type @_PyCFunction_Type @_PyCapsule_Type @_PyDict_Type @_PyExc_AttributeError @_PyExc_DeprecationWarning @_PyExc_Exception @_PyExc_ImportError @_PyExc_IndexError @_PyExc_KeyError @_PyExc_NameError @_PyExc_OverflowError @_PyExc_RuntimeError @_PyExc_StopIteration @_PyExc_SystemError @_PyExc_TypeError @_PyExc_ValueError @_PyFloat_Type @_PyList_Type @_PyLong_Type @_PyMethod_Type @_PyObject_GenericGetAttr @_PyTuple_Type @_PyUnicode_Type @_Py_Version @__Py_EllipsisObject @__Py_FalseStruct @__Py_NoneStruct @__Py_TrueStruct @___stack_chk_guard @dyld_stub_binder r >@_PyBytes_FromStringAndSize r>@_PyCMethod_New r>@_PyCapsule_GetName r>@_PyCapsule_GetPointer r >@_PyCapsule_IsValid r(>@_PyCapsule_New r0>@_PyCode_NewEmpty r8>@_PyDict_Copy r@>@_PyDict_GetItemString rH>@_PyDict_GetItemWithError rP>@_PyDict_New rX>@_PyDict_Next r`>@_PyDict_SetItem rh>@_PyDict_SetItemString rp>@_PyDict_Size rx>@_PyErr_Clear r>@_PyErr_ExceptionMatches r>@_PyErr_Format r>@_PyErr_GivenExceptionMatches r>@_PyErr_NormalizeException r >@_PyErr_Occurred r¨>@_PyErr_SetObject r°>@_PyErr_SetString r¸>@_PyErr_WarnEx rÀ>@_PyErr_WarnFormat rÈ>@_PyEval_RestoreThread rÐ>@_PyEval_SaveThread rØ>@_PyException_GetTraceback rà>@_PyException_SetTraceback rè>@_PyFloat_AsDouble rð>@_PyFloat_FromDouble rø>@_PyFrame_New r>@_PyGC_Disable r>@_PyGC_Enable r>@_PyImport_AddModule r>@_PyImport_GetModule r >@_PyImport_GetModuleDict r¨>@_PyImport_ImportModule r°>@_PyImport_ImportModuleLevelObject r¸>@_PyInterpreterState_GetID rÀ>@_PyList_Append rÈ>@_PyList_AsTuple rÐ>@_PyList_New rØ>@_PyLong_AsLong rà>@_PyLong_AsSsize_t rè>@_PyLong_FromLong rð>@_PyLong_FromSsize_t rø>@_PyLong_FromString r>@_PyMem_Malloc r>@_PyMem_Realloc r>@_PyModuleDef_Init r>@_PyModule_GetDict r >@_PyModule_GetName r¨>@_PyModule_NewObject r°>@_PyNumber_Add r¸>@_PyNumber_InPlaceAdd rÀ>@_PyNumber_InPlaceTrueDivide rÈ>@_PyNumber_Index rÐ>@_PyNumber_Long rØ>@_PyNumber_Multiply rà>@_PyNumber_Remainder rè>@_PyNumber_Subtract rð>@_PyOS_snprintf rø>@_PyObject_Call r>@_PyObject_CallFinalizerFromDealloc r>@_PyObject_Format r>@_PyObject_GC_IsFinalized r>@_PyObject_GC_UnTrack r >@_PyObject_GetAttr r¨>@_PyObject_GetAttrString r°>@_PyObject_GetItem r¸>@_PyObject_GetIter rÀ>@_PyObject_Hash rÈ>@_PyObject_IsInstance rÐ>@_PyObject_IsTrue rØ>@_PyObject_Not rà>@_PyObject_RichCompare rè>@_PyObject_SetAttr rð>@_PyObject_SetAttrString rø>@_PyObject_SetItem r>@_PyObject_Size r>@_PyObject_VectorcallDict r>@_PySequence_Contains r>@_PySequence_List r >@_PySequence_Tuple r¨>@_PySlice_New r°>@_PyThreadState_Get r¸>@_PyTraceBack_Here rÀ>@_PyTuple_New rÈ>@_PyTuple_Pack rÐ>@_PyType_IsSubtype rØ>@_PyType_Modified rà>@_PyType_Ready rè>@_PyUnicode_AsUTF8 rð>@_PyUnicode_Compare rø>@_PyUnicode_Concat r>@_PyUnicode_Decode r>@_PyUnicode_Format r>@_PyUnicode_FromFormat r>@_PyUnicode_FromString r >@_PyUnicode_FromStringAndSize r¨>@_PyUnicode_InternFromString r°>@_PyUnicode_New r¸>@_PyUnstable_Code_NewWithPosOnlyArgs rÀ>@_PyVectorcall_Function rÈ>@_Py_EnterRecursiveCall rÐ>@_Py_LeaveRecursiveCall rØ>@__PyDict_GetItem_KnownHash rà>@__PyDict_NewPresized rè>@__PyObject_GenericGetAttrWithDict rð>@__PyObject_GetDictPtr rø>@__PyThreadState_UncheckedGet r>@__PyType_Lookup r>@__PyUnicode_FastCopyCharacters r>@__Py_Dealloc r@___stack_chk_fail r @_acos r¨@_cos r°@_exp r¸@_expf rÀ@_expm1 rÈ@_fmod rÐ@_free rØ@_log rà@_log1p rè@_log1pf rð@_logf rø@_malloc r@_memcmp r@_memcpy r@_memset r@_pow r @_powf _PyInit_mtrand ¸ ¸ ´ ¼ ð ÄܤÈèl
ø}¬\PÔ¸HxØx,ÌԴظh¸¬ä¤ øèäàü ðÈ Bô %ÔÔ
ìð ü È ìü ìü ììì
ðü ô/°@È
À¨¨Ü7¨ð Ô92Ø°,Ôì¬Üxüؤ èüÔ¤þ¬Ø´,¨Ø¨ü üÄY°`ü ¬Øøø°¬´¼¼4L`ø¼XpÌHôH $ (è4$$È(`8èü`T,ô\ @
À\¬Ôøh¨Ì°ðèðl ¨Ð ØØ0ì$PTX(Dð\ÌØÜü@ÄÜ`@°x¬ DK xN ° ¼ Ú \ ú L¤ P¥ B ¨ \ ðª j « | ܬ D± µ °± É @¸ î 8÷
ä÷ &
@ø U
Xù z
¨ù
|ú ¶
´ü Ù
üü tý + Lþ < Äþ \ ¿ ú T ( \ Q 4 P Â ø ð + ¨
d Ô ` ² | ÿ < ä y µ ' ë ,- & ¤8 a D ðF Ø ÐJ ÌO K ¼S ¼V Ë g ; s ¬ ¨ â è« ¼¯ Z @¿ @Â Ó @Ç ,Ë J Ð } Õ » àÚ ö ÌÞ < Èã } Ðæ ¹ ¼ê ó ¸ï + ¤ó d ÷ |û Ô F
» | ñ x - l0 g P ª äU ã $Z L^ T tb P~ Ï x h S <¥ T¾ É ,À \Ö " 0× ? Ú W ÈÜ u ¤Ý Þ à ´ ðà È â â °â Pã ! àã 6 Èå M \æ i Xç ,é º Ph Ò üh â Ôi û k 4k 3 Ük L 4m i \n ~ Xo ¬ ès Ä ät
¨¡ D ØÑ [ TÓ tÓ á øÓ ò ¤Ô ! üÕ '! t× D! ìØ k! á ! Hã Ó! üæ ü! ¸é #" tì >" ¨ì W" ¸ì u" í " dí ²" \î Ô" tï ó" ð # ¼ñ =# ò e# ò }# Ðó # ô ´# õ Ó# Ôõ ê# ìù $ |þ $ þ 1$ Àþ F$ àþ S$ ìþ b$ ð q$
$ $ 4 £$ X ³$ | À$ D Ò$ l Ü$ Ì ô$ % ì % !% 1% @% è Q% < c% h t% \
% ¸
% @ ±% Ç% â% ó% P & ` %& ¼ 2& h C& < U& 4 n& & Ä & P ©& ! ¼& °! Í& D" ä& ô# ' ä$ $' Ì& C' ¼( a' () }' È+ ' p- µ' À/ Ð' à1 ê' x2 þ' Ð3 ( ¨4 )( Ø4 @( D7 N( h7 ]( ¸7 m( 8 {( d8 ( 8 ( Ð8 »( @: Ð( : Ý( è; ì( À< þ( = ) > +) Ø> C) @ P) xA Z) ØA n) B ) ´B ¤) äE ») èE Ï) ìE è) dF * hF * H &* ØV P* W l* ,W * RW «* ^W ¿* iW é* §W ú* °W
+ ¸W 7+ ÜW N+ êW x+ µX + ÁX µ+ âX Ù+ ÿX , !Y ', ?Y P, aY z, Y , Y À, ¼Y é, ÞY - ýY 8- $Z _- DZ - eZ °- Z Ù- ©Z . ÍZ ,. ùZ V. #[ . P[ ª. u[ Ð. [ ö. ³[ / ×[ G/ ÷[ l/ \ / 2\ ¶/ Q\ Û/ o\ 0 \ /0 ¼\ W0 Ý\ z0 ù\ ¡0 ] Ë0 A] õ0 m] 1 ] H1 ¼] r1 ß] 1 ÿ] Ã1 "^ ê1 B^ 2 c^ 62 ^ ]2 ^ 2 ½^ ¥2 Ø^ ½2 ç^ Ï2 ð^ ù2 .` 3 0` .3 w` Z3 Ã` m3 Í` 3 î` «3 ú` ¿3 a Ë3 a ×3 a ä3 a ð3
a ý3 a 4 a -4 1a V4 aa w4 ya ¡4 a Ê4 Ôa ×4 Øa ä4 Üa ó4 äa 5 ía 5 óa %5 þa 25 b B5 b P5 b _5 b {5 'b 5 /b 5 6b 5 Ab »5 Fb Æ5 Hb ×5 Pb 6 Sq 6 aq '6 hq 56 nq ^6 t 6 4t 6 <t ª6 Dt ¿6 Pt é6 t 7 º} ;7 J7 a7 ¥ }7 ¸ 7 ȋ ¤7 ͋ »7 ۋ È7 ߋ ò7 8 7 ,8 > 88 A G8 G V8 M ~8 ® 8 ¶ 8 º «8 ¿8 ˘ Ï8 Ҙ Þ8 ܘ ë8 à ú8 æ 9 ï 19 £ Z9 ± i9 ¦± x9 ¬± 9 ´± 9 »± Â9 ʽ Ñ9 н Ý9 ӽ : NÅ : RÅ =: ÇÅ N: ÏÅ w: ðØ : úØ : ÿØ Á: mé Í: pé Ý: wé í: é ü: é ; é !; é 0; ¢é ?; ¨é M; é [; ²é n; ¼é ; Åé ; Ëé ¡; Ôé ³; Ýé Ç; èé Õ; íé ç; öé ö; üé < ê < ê < ê +<
ê S< ß÷ a< ä÷ t< ð÷ < þ÷ < ø Â< Yø Ú< iø ê< pø ø< uø = ø = ø '= ø ;= ø d= = Ò ¶= È" Ã= Ì" Ñ= Õ" ë= æ" ù= ë" #> # G> )# U> .# i> ;# z> D# > G# ¯> / Ø> E ã> E ñ> E ÿ> E
? ¡E 6? !S L? .S [? 4S w? KS
? PS ®? Q_ ×? Ál @ | @ | @ | F@ Å| p@ ç| @ ô| @ ü| ¾@ ¾} Ð@ Ç} Û@ É} ü@ ã} %A ڍ MA ʒ ]A Ғ
A ќ A â «A æ ÔA ֪ þA ùª !B « HB 1« VB 6« eB <« B Y« B h« ®B n« ¾B t« æB å¯ C [» 7C Ä `C Ï C JÖ ¢C ]Ö ±C cÖ ÀC iÖ éC à ûC à D à D à 3D à ED ¶à TD ¼à bD Áà qD Çà D Ôà ¯D Kã ØD ã çD ã E Aè E Fè ,E Lè ?E Vè ME [è [E `è iE iè wE nè E yè ³E ºò ÛE ðö F +F
TF cF F 0 ³F Q ÀF Y ÑF a ãF j ðF n G 2G \ ?G ` MG e [G n lG v yG z ¢G Í" ËG Y- ×G ]- çG d- ÷G k- H r- H x- ?H ; OH ; _H ¥; H ¨H °H T ¾H T ÐH !T ùH b I b I b AI Jb ^I `b mI fb I ?n ÍI Àp J ºu EJ Ó|
J ¾J L õJ ͊ 3K w zK µK ïK ª 'L ) `L » L $É ÑL Í M ÓÖ KM öá M wê ÆM Xú N } ?N sN · ²N 1- îN |6 5O B wO ÙL ´O d^ ïO nk (P m{ bP a P Y ÔP 2¥
Q \¸ HQ ÖÄ Q Ö ¿Q Òà öQ Hì 3R Ýö nR ò ²R z ìR ~ #S Q) _S Û0 S SA ÜS ]M #T ]c bT ¸o T !| ÚT ݀ U ô
@U ± uU © ªU g ÔU ԍ üU @ V @ V @ V @¢ &V @¦ 1V @® <V @¶ GV @¾ QV @Â [V @Æ eV @Ê pV @Ò zV (D V 0D V D ±V ÈD åV ÐD W pF FW 0M xW M W
N ´W (N ÃW HN ßW _ X _ d .X d ÂX d ÏX f ô¬g . 8K $ 8K $ N 8K . DK Y $ DK $ 4 N DK . xN $ xN $ L N xN . ° $ $ N . ¼ $ $ ¼ N . \ Ú $ \ $ ð N \ . L¤ ú $ L¤ $ N L¤ . P¥ $ P¥ $ D N P¥ . ¨ B $ ¨ $ \ N ¨ . ðª \ $ ðª $ ¤ N ðª . « j $ « $ H N « . ܬ | $ ܬ $ h N ܬ . D± $ D± $ l N D± . °± µ $ °± $ N °± . @¸ É $ @¸ $ ø> N @¸ . 8÷ î $ 8÷ $ ¬ N 8÷ . ä÷
$ ä÷ $ \ N ä÷ . @ø &
$ @ø $ N @ø . Xù U
$ Xù $ P N Xù . ¨ù z
$ ¨ù $ Ô N ¨ù . |ú
$ |ú $ 8 N |ú . ´ü ¶
$ ´ü $ H N ´ü . üü Ù
$ üü $ x N üü . tý $ tý $ Ø N tý . Lþ + $ Lþ $ x N Lþ . Äþ < $ Äþ $ N Äþ . \ $ \ $ , N \ . ¿ $ $ Ì N . T ú $ T $ Ô N T . ( $ ( $ 4 N ( . \ $ \ $ Ø N \ . 4 Q $ 4 $ N 4 . P $ P $ 8 N P . Â $ $ h N . ð ø $ ð $ ¸ N ð . ¨
+ $ ¨
$ , N ¨
. Ô d $ Ô $ N Ô . ` $ ` $ N ` . | ² $ | $ N | . ÿ $ $ d N . ä < $ ä $ N ä . y $ $
N . ' µ $ ' $ ¤ N ' . ,- ë $ ,- $ x N ,- . ¤8 & $ ¤8 $ h N ¤8 . D a $ D $ ä N D . ðF $ ðF $ à N ðF . ÐJ Ø $ ÐJ $ ü N ÐJ . ÌO $ ÌO $ ð N ÌO . ¼S K $ ¼S $ N ¼S . ¼V $ ¼V $ H N ¼V . g Ë $ g $ ! N g . $ $ N . ; $ $ ô N . s $ $ N . ¨ ¬ $ ¨ $ Ô N ¨ . è« â $ è« $ Ô N è« . ¼¯ $ ¼¯ $ N ¼¯ . @¿ Z $ @¿ $ N @¿ . @ $ @ $ N @ . @Ç Ó $ @Ç $ ì N @Ç . ,Ë $ ,Ë $ ð N ,Ë . Ð J $ Ð $ ü N Ð . Õ } $ Õ $ È N Õ . àÚ » $ àÚ $ ì N àÚ . ÌÞ ö $ ÌÞ $ ü N ÌÞ . Èã < $ Èã $ N Èã . Ðæ } $ Ðæ $ ì N Ðæ . ¼ê ¹ $ ¼ê $ ü N ¼ê . ¸ï ó $ ¸ï $ ì N ¸ï . ¤ó + $ ¤ó $ ì N ¤ó . ÷ d $ ÷ $ ì N ÷ . |û $ |û $ N |û . Ô $ $ N . $ $ N .
F $
$ N
. $ $ ð N . | » $ | $ ü N | . x ñ $ x $ ô N x . l0 - $ l0 $ 0 N l0 . P g $ P $ H N P . äU ª $ äU $ @ N äU . $Z ã $ $Z $ ( N $Z . L^ $ L^ $ ( N L^ . tb T $ tb $ Ü N tb . P~ $ P~ $ ( N P~ . x Ï $ x $ ð N x . h $ h $ Ô N h . <¥ S $ <¥ $ N <¥ . T¾ $ T¾ $ Ø N T¾ . ,À É $ ,À $ 0 N ,À . \Ö $ \Ö $ Ô N \Ö . 0× " $ 0× $ l N 0× . Ú ? $ Ú $ , N Ú . ÈÜ W $ ÈÜ $ Ü N ÈÜ . ¤Ý u $ ¤Ý $ x N ¤Ý . Þ $ Þ $ ü N Þ . à $ à $ Ø N à . ðà ´ $ ðà $ $ N ðà . â È $ â $ N â . °â â $ °â $ N °â . Pã $ Pã $ N Pã . àã ! $ àã $ è N àã . Èå 6 $ Èå $ N Èå . \æ M $ \æ $ ü N \æ . Xç i $ Xç $ Ô N Xç . ,é $ ,é $ $ N ,é . Ph º $ Ph $ ¬ N Ph . üh Ò $ üh $ Ø N üh . Ôi â $ Ôi $ 4 N Ôi . k û $ k $ , N k . 4k $ 4k $ ¨ N 4k . Ük 3 $ Ük $ X N Ük . 4m L $ 4m $ ( N 4m . \n i $ \n $ ü N \n . Xo ~ $ Xo $ N Xo . ès ¬ $ ès $ ü N ès . ät Ä $ ät $ Ä, N ät . ¨¡
$ ¨¡ $ 00 N ¨¡ . ØÑ D $ ØÑ $ | N ØÑ . TÓ [ $ TÓ $ N TÓ . tÓ $ tÓ $ N tÓ . øÓ á $ øÓ $ ¬ N øÓ . ¤Ô ò $ ¤Ô $ X N ¤Ô . üÕ ! $ üÕ $ x N üÕ . t× '! $ t× $ x N t× . ìØ D! $ ìØ $ ° N ìØ . á k! $ á $ ¬ N á . Hã ! $ Hã $ ´ N Hã . üæ Ó! $ üæ $ ¼ N üæ . ¸é ü! $ ¸é $ ¼ N ¸é &* & ØV P* & W l* & ,W * & RW «* & ^W ¿* & iW é* & §W ú* & °W
+ & ¸W 7+ & ÜW N+ & êW x+ & µX + & ÁX µ+ & âX Ù+ & ÿX , & !Y ', & ?Y P, & aY z, & Y , & Y À, & ¼Y é, & ÞY - & ýY 8- & $Z _- & DZ - & eZ °- & Z Ù- & ©Z . & ÍZ ,. & ùZ V. & #[ . & P[ ª. & u[ Ð. & [ ö. & ³[ / & ×[ G/ & ÷[ l/ & \ / & 2\ ¶/ & Q\ Û/ & o\ 0 & \ /0 & ¼\ W0 & Ý\ z0 & ù\ ¡0 & ] Ë0 & A] õ0 & m] 1 & ] H1 & ¼] r1 & ß] 1 & ÿ] Ã1 & "^ ê1 & B^ 2 & c^ 62 & ^ ]2 & ^ 2 & ½^ ¥2 & Ø^ ½2 & ç^ Ï2 & ð^ ù2 & .` 3 & 0` .3 & w` Z3 & Ã` m3 & Í` 3 & î` «3 & ú` ¿3 & a Ë3 & a ×3 & a ä3 & a ð3 &
a ý3 & a 4 & a -4 & 1a V4 & aa w4 & ya ¡4 & a Ê4 & Ôa ×4 & Øa ä4 & Üa ó4 & äa 5 & ía 5 & óa %5 & þa 25 & b B5 & b P5 & b _5 & b {5 & 'b 5 & /b 5 & 6b 5 & Ab »5 & Fb Æ5 & Hb ×5 & Pb 6 & Sq 6 & aq '6 & hq 56 & nq ^6 & t 6 & 4t 6 & <t ª6 & Dt ¿6 & Pt é6 & t 7 & º} ;7 & J7 & a7 & ¥ }7 & ¸ 7 & ȋ ¤7 & ͋ »7 & ۋ È7 & ߋ ò7 & 8 & 7 ,8 & > 88 & A G8 & G V8 & M ~8 & ® 8 & ¶ 8 & º «8 & ¿8 & ˘ Ï8 & Ҙ Þ8 & ܘ ë8 & à ú8 & æ 9 & ï 19 & £ Z9 & ± i9 & ¦± x9 & ¬± 9 & ´± 9 & »± Â9 & ʽ Ñ9 & н Ý9 & ӽ : & NÅ : & RÅ =: & ÇÅ N: & ÏÅ w: & ðØ : & úØ : & ÿØ Á: & mé Í: & pé Ý: & wé í: & é ü: & é ; & é !; & é 0; & ¢é ?; & ¨é M; & é [; & ²é n; & ¼é ; & Åé ; & Ëé ¡; & Ôé ³; & Ýé Ç; & èé Õ; & íé ç; & öé ö; & üé < & ê < & ê < & ê +< &
ê S< & ß÷ a< & ä÷ t< & ð÷ < & þ÷ < & ø Â< & Yø Ú< & iø ê< & pø ø< & uø = & ø = & ø '= & ø ;= & ø d= & = & Ò ¶= & È" Ã= & Ì" Ñ= & Õ" ë= & æ" ù= & ë" #> & # G> & )# U> & .# i> & ;# z> & D# > & G# ¯> & / Ø> & E ã> & E ñ> & E ÿ> & E
? & ¡E 6? & !S L? & .S [? & 4S w? & KS
? & PS ®? & Q_ ×? & Ál @ & | @ & | @ & | F@ & Å| p@ & ç| @ & ô| @ & ü| ¾@ & ¾} Ð@ & Ç} Û@ & É} ü@ & ã} %A & ڍ MA & ʒ ]A & Ғ
A & ќ A & â «A & æ ÔA & ֪ þA & ùª !B & « HB & 1« VB & 6« eB & <« B & Y« B & h« ®B & n« ¾B & t« æB & å¯ C & [» 7C & Ä `C & Ï C & JÖ ¢C & ]Ö ±C & cÖ ÀC & iÖ éC & à ûC & à D & à D & à 3D & à ED & ¶à TD & ¼à bD & Áà qD & Çà D & Ôà ¯D & Kã ØD & ã çD & ã E & Aè E & Fè ,E & Lè ?E & Vè ME & [è [E & `è iE & iè wE & nè E & yè ³E & ºò ÛE & ðö F & +F &
TF & cF & F & 0 ³F & Q ÀF & Y ÑF & a ãF & j ðF & n G & 2G & \ ?G & ` MG & e [G & n lG & v yG & z ¢G & Í" ËG & Y- ×G & ]- çG & d- ÷G & k- H & r- H & x- ?H & ; OH & ; _H & ¥; H & ¨H °H & T ¾H & T ÐH & !T ùH & b I & b I & b AI & Jb ^I & `b mI & fb I & ?n ÍI & Àp J & ºu EJ & Ó|
J & ¾J & L õJ & ͊ 3K & w zK & µK & ïK & ª 'L & ) `L & » L & $É ÑL & Í M & ÓÖ KM & öá M & wê ÆM & Xú N & } ?N & sN & · ²N & 1- îN & |6 5O & B wO & ÙL ´O & d^ ïO & nk (P & m{ bP & a P & Y ÔP & 2¥
Q & \¸ HQ & ÖÄ Q & Ö ¿Q & Òà öQ & Hì 3R & Ýö nR & ò ²R & z ìR & ~ #S & Q) _S & Û0 S & SA ÜS & ]M #T & ]c bT & ¸o T & !| ÚT & ݀ U & ô
@U & ± uU & © ªU & g ÔU & ԍ V & 0D V & D ±V & ÈD åV & ÐD W & pF FW & 0M xW & M W ´W & (N ÃW & HN ßW & _ X & _ d Y d Z d Z f oô¬g . tì #" $ tì $ 4 N tì . ¨ì >" $ ¨ì $ N ¨ì . ¸ì W" $ ¸ì $ L N ¸ì . í u" $ í $ ` N í . dí " $ dí $ ø N dí . \î ²" $ \î $ N \î . tï Ô" $ tï $ N tï . ð ó" $ ð $ < N ð . ¼ñ # $ ¼ñ $ X N ¼ñ . ò =# $ ò $ p N ò . ò e# $ ò $ L N ò . Ðó }# $ Ðó $ H N Ðó . ô # $ ô $ t N ô . õ ´# $ õ $ H N õ . Ôõ Ó# $ Ôõ $ N Ôõ . ìù ê# $ ìù $ N ìù . |þ $ $ |þ $ N |þ . þ $ $ þ $ $ N þ . Àþ 1$ $ Àþ $ N Àþ . àþ F$ $ àþ $ N àþ . ìþ S$ $ ìþ $ N ìþ . ð b$ $ ð $ ( N ð . q$ $ $ è N .
$ $ $ 4 N . 4 $ $ 4 $ $ N 4 . X £$ $ X $ $ N X . | ³$ $ | $ È N | . D À$ $ D $ ( N D . l Ò$ $ l $ ` N l . Ì Ü$ $ Ì $ 8 N Ì . ô$ $ $ è N . ì % $ ì $ N ì . % $ $ ü N . !% $ $ N . 1% $ $ ` N . è @% $ è $ T N è . < Q% $ < $ , N < . h c% $ h $ ô N h . \
t% $ \
$ \ N \
. ¸
% $ ¸
$ N ¸
. @ % $ @ $ @ N @ . ±% $ $ N . Ç% $ $ N . â% $ $ À N . P ó% $ P $ N P . ` & $ ` $ \ N ` . ¼ %& $ ¼ $ ¬ N ¼ . h 2& $ h $ Ô N h . < C& $ < $ ø N < . 4 U& $ 4 $ h N 4 . n& $ $ ( N . Ä & $ Ä $ N Ä . P & $ P $ Ì N P . ! ©& $ ! $ N ! . °! ¼& $ °! $ N °! . D" Í& $ D" $ ° N D" . ô# ä& $ ô# $ ð N ô# . ä$ ' $ ä$ $ è N ä$ . Ì& $' $ Ì& $ ð N Ì& . ¼( C' $ ¼( $ l N ¼( . () a' $ () $ N () . È+ }' $ È+ $ ¨ N È+ . p- ' $ p- $ P N p- . À/ µ' $ À/ $ N À/ . à1 Ð' $ à1 $ N à1 . x2 ê' $ x2 $ X N x2 üU & @ V & @ V & @ V & @¢ &V & @¦ 1V & @® <V & @¶ GV & @¾ QV & @Â [V & @Æ eV & @Ê pV & @Ò d ÃZ d 0[ d G[ f pô¬g . Ð3 þ' $ Ð3 $ Ø N Ð3 . ¨4 ( $ ¨4 $ 0 N ¨4 . Ø4 )( $ Ø4 $ l N Ø4 . D7 @( $ D7 $ $ N D7 . h7 N( $ h7 $ P N h7 . ¸7 ]( $ ¸7 $ T N ¸7 . 8 m( $ 8 $ X N 8 . d8 {( $ d8 $ ( N d8 . 8 ( $ 8 $ D N 8 . Ð8 ( $ Ð8 $ p N Ð8 . @: »( $ @: $ \ N @: . : Ð( $ : $ L N : . è; Ý( $ è; $ Ø N è; . À< ì( $ À< $ Ü N À< . = þ( $ = $ ü N = . > ) $ > $ @ N > . Ø> +) $ Ø> $ D N Ø> . @ C) $ @ $ \ N @ . xA P) $ xA $ ` N xA . ØA Z) $ ØA $ @ N ØA . B n) $ B $ N B . ´B ) $ ´B $ 0 N ´B . äE ¤) $ äE $ N äE . èE ») $ èE $ N èE . ìE Ï) $ ìE $ x N ìE . dF è) $ dF $ N dF . hF * $ hF $ , N hF . H * $ H $ N H d 8K þ $ þ 1 þ L þ ^ þ m þ þ þ © þ ¸ þ È þ Ù þ æ þ ü þ þ ! þ . þ > þ T þ a þ n þ { þ þ ¡ þ ¾ þ Ø þ è þ ù þ
þ þ * þ @ þ S þ i þ þ þ § þ ¹ þ É þ Ú þ ï þ þ þ + þ < þ N þ h þ þ þ ¨ þ ¶ þ Ã þ Ñ þ Þ þ ò þ þ þ 5 þ W þ q þ þ þ þ © þ ¸ þ Ê þ Û þ ï þ þ þ þ , þ ; þ M þ _ þ q þ
þ þ ¨ þ Ä þ Ô þ ã þ ö þ
þ þ , þ ; þ ^ þ o þ þ þ ¶ þ È þ à þ ò þ þ þ ( þ 9 þ G þ ] þ o þ þ þ ¨ þ Á þ Ö þ ç þ ù þ þ þ + þ 8 þ F þ T þ f þ w þ
þ þ ª þ ¼ þ Î þ à þ ö þ þ ) þ E þ T þ d þ þ þ ¶ þ Í þ Ù þ ô þ
þ +
þ A
þ ^
þ n
þ
þ
þ ®
þ ¿
þ Ï
þ ß
ñ
! ' - 2 9 A G O W _ g l r w y z { | }
¢ £ ¤ ¥ § ¨ © ª « ¬ ® ¯ ° ± ² ´ µ ¶ · ¸ º » ½ ¾ ¿ À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ð Ñ Ò Ó Ô Õ Ö × Ø Ù Ú Û Ü Ý Þ ß à á â ã ä å ç è é ê ë ì í î ï ð ñ ò ó õ ö ÷ ø ú û ü ý þ ÿ
u v x ~ ¡ ¦ ³ ¹ ¼ Ï æ ô ù w y z { | }
¢ £ ¤ ¥ § ¨ © ª « ¬ ® ¯ ° ± ² ´ µ ¶ · ¸ º » ½ ¾ ¿ À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ð Ñ Ò Ó Ô Õ Ö × Ø Ù Ú Û Ü Ý Þ ß à á â ã ä å ç è é ê ë ì í î ï ð ñ ò ó õ ö ÷ ø ú û ü ý þ ÿ
_PyInit_mtrand _PyBaseObject_Type _PyBool_Type _PyBytes_FromStringAndSize _PyCFunction_Type _PyCMethod_New _PyCapsule_GetName _PyCapsule_GetPointer _PyCapsule_IsValid _PyCapsule_New _PyCapsule_Type _PyCode_NewEmpty _PyDict_Copy _PyDict_GetItemString _PyDict_GetItemWithError _PyDict_New _PyDict_Next _PyDict_SetItem _PyDict_SetItemString _PyDict_Size _PyDict_Type _PyErr_Clear _PyErr_ExceptionMatches _PyErr_Format _PyErr_GivenExceptionMatches _PyErr_NormalizeException _PyErr_Occurred _PyErr_SetObject _PyErr_SetString _PyErr_WarnEx _PyErr_WarnFormat _PyEval_RestoreThread _PyEval_SaveThread _PyExc_AttributeError _PyExc_DeprecationWarning _PyExc_Exception _PyExc_ImportError _PyExc_IndexError _PyExc_KeyError _PyExc_NameError _PyExc_OverflowError _PyExc_RuntimeError _PyExc_StopIteration _PyExc_SystemError _PyExc_TypeError _PyExc_ValueError _PyException_GetTraceback _PyException_SetTraceback _PyFloat_AsDouble _PyFloat_FromDouble _PyFloat_Type _PyFrame_New _PyGC_Disable _PyGC_Enable _PyImport_AddModule _PyImport_GetModule _PyImport_GetModuleDict _PyImport_ImportModule _PyImport_ImportModuleLevelObject _PyInterpreterState_GetID _PyList_Append _PyList_AsTuple _PyList_New _PyList_Type _PyLong_AsLong _PyLong_AsSsize_t _PyLong_FromLong _PyLong_FromSsize_t _PyLong_FromString _PyLong_Type _PyMem_Malloc _PyMem_Realloc _PyMethod_Type _PyModuleDef_Init _PyModule_GetDict _PyModule_GetName _PyModule_NewObject _PyNumber_Add _PyNumber_InPlaceAdd _PyNumber_InPlaceTrueDivide _PyNumber_Index _PyNumber_Long _PyNumber_Multiply _PyNumber_Remainder _PyNumber_Subtract _PyOS_snprintf _PyObject_Call _PyObject_CallFinalizerFromDealloc _PyObject_Format _PyObject_GC_IsFinalized _PyObject_GC_UnTrack _PyObject_GenericGetAttr _PyObject_GetAttr _PyObject_GetAttrString _PyObject_GetItem _PyObject_GetIter _PyObject_Hash _PyObject_IsInstance _PyObject_IsTrue _PyObject_Not _PyObject_RichCompare _PyObject_SetAttr _PyObject_SetAttrString _PyObject_SetItem _PyObject_Size _PyObject_VectorcallDict _PySequence_Contains _PySequence_List _PySequence_Tuple _PySlice_New _PyThreadState_Get _PyTraceBack_Here _PyTuple_New _PyTuple_Pack _PyTuple_Type _PyType_IsSubtype _PyType_Modified _PyType_Ready _PyUnicode_AsUTF8 _PyUnicode_Compare _PyUnicode_Concat _PyUnicode_Decode _PyUnicode_Format _PyUnicode_FromFormat _PyUnicode_FromString _PyUnicode_FromStringAndSize _PyUnicode_InternFromString _PyUnicode_New _PyUnicode_Type _PyUnstable_Code_NewWithPosOnlyArgs _PyVectorcall_Function _Py_EnterRecursiveCall _Py_LeaveRecursiveCall _Py_Version __PyDict_GetItem_KnownHash __PyDict_NewPresized __PyObject_GenericGetAttrWithDict __PyObject_GetDictPtr __PyThreadState_UncheckedGet __PyType_Lookup __PyUnicode_FastCopyCharacters __Py_Dealloc __Py_EllipsisObject __Py_FalseStruct __Py_NoneStruct __Py_TrueStruct ___stack_chk_fail ___stack_chk_guard _acos _cos _exp _expf _expm1 _fmod _free _log _log1p _log1pf _logf _malloc _memcmp _memcpy _memset _pow _powf dyld_stub_binder ___pyx_pymod_create ___pyx_pymod_exec_mtrand _Py_XDECREF ___Pyx_modinit_type_init_code ___Pyx_modinit_type_import_code ___Pyx_modinit_variable_import_code ___Pyx_modinit_function_import_code ___Pyx_ImportDottedModule ___Pyx_Import ___Pyx_ImportFrom ___pyx_f_5numpy_import_array ___Pyx__GetModuleGlobalName ___Pyx_AddTraceback ___Pyx_CreateStringTabAndInitStrings ___Pyx_GetBuiltinName ___Pyx_PyObject_GetAttrStrNoError ___Pyx_PyObject_GetAttrStr_ClearAttributeError ___Pyx_PyErr_ExceptionMatchesInState ___Pyx_ErrRestoreInState ___Pyx_PyErr_ExceptionMatchesTuple ___Pyx_PyErr_GivenExceptionMatches ___Pyx_inner_PyErr_GivenExceptionMatches2 ___Pyx_PyErr_GivenExceptionMatchesTuple ___Pyx_IsSubtype ___pyx_f_5numpy_6random_6mtrand_11RandomState__initialize_bit_generator ___pyx_f_5numpy_6random_6mtrand_11RandomState__reset_gauss ___pyx_f_5numpy_6random_6mtrand_11RandomState__shuffle_raw ___Pyx_PyObject_Call ___Pyx_Raise ___pyx_tp_dealloc_5numpy_6random_6mtrand_RandomState ___pyx_pw_5numpy_6random_6mtrand_11RandomState_3__repr__ ___pyx_pw_5numpy_6random_6mtrand_11RandomState_5__str__ ___pyx_tp_traverse_5numpy_6random_6mtrand_RandomState ___pyx_tp_clear_5numpy_6random_6mtrand_RandomState ___pyx_pw_5numpy_6random_6mtrand_11RandomState_1__init__ ___pyx_tp_new_5numpy_6random_6mtrand_RandomState ___Pyx_PyObject_FastCallDict ___pyx_specialmethod___pyx_pw_5numpy_6random_6mtrand_11RandomState_3__repr__ ___pyx_pw_5numpy_6random_6mtrand_11RandomState_7__getstate__ ___pyx_pw_5numpy_6random_6mtrand_11RandomState_9__setstate__ ___pyx_pw_5numpy_6random_6mtrand_11RandomState_11__reduce__ ___pyx_pw_5numpy_6random_6mtrand_11RandomState_13seed ___pyx_pw_5numpy_6random_6mtrand_11RandomState_15get_state ___pyx_pw_5numpy_6random_6mtrand_11RandomState_17set_state ___pyx_pw_5numpy_6random_6mtrand_11RandomState_19random_sample ___pyx_pw_5numpy_6random_6mtrand_11RandomState_21random ___pyx_pw_5numpy_6random_6mtrand_11RandomState_23beta ___pyx_pw_5numpy_6random_6mtrand_11RandomState_25exponential ___pyx_pw_5numpy_6random_6mtrand_11RandomState_27standard_exponential ___pyx_pw_5numpy_6random_6mtrand_11RandomState_29tomaxint ___pyx_pw_5numpy_6random_6mtrand_11RandomState_31randint ___pyx_pw_5numpy_6random_6mtrand_11RandomState_33bytes ___pyx_pw_5numpy_6random_6mtrand_11RandomState_35choice ___pyx_pw_5numpy_6random_6mtrand_11RandomState_37uniform ___pyx_pw_5numpy_6random_6mtrand_11RandomState_39rand ___pyx_pw_5numpy_6random_6mtrand_11RandomState_41randn ___pyx_pw_5numpy_6random_6mtrand_11RandomState_43random_integers ___pyx_pw_5numpy_6random_6mtrand_11RandomState_45standard_normal ___pyx_pw_5numpy_6random_6mtrand_11RandomState_47normal ___pyx_pw_5numpy_6random_6mtrand_11RandomState_49standard_gamma ___pyx_pw_5numpy_6random_6mtrand_11RandomState_51gamma ___pyx_pw_5numpy_6random_6mtrand_11RandomState_53f ___pyx_pw_5numpy_6random_6mtrand_11RandomState_55noncentral_f ___pyx_pw_5numpy_6random_6mtrand_11RandomState_57chisquare ___pyx_pw_5numpy_6random_6mtrand_11RandomState_59noncentral_chisquare ___pyx_pw_5numpy_6random_6mtrand_11RandomState_61standard_cauchy ___pyx_pw_5numpy_6random_6mtrand_11RandomState_63standard_t ___pyx_pw_5numpy_6random_6mtrand_11RandomState_65vonmises ___pyx_pw_5numpy_6random_6mtrand_11RandomState_67pareto ___pyx_pw_5numpy_6random_6mtrand_11RandomState_69weibull ___pyx_pw_5numpy_6random_6mtrand_11RandomState_71power ___pyx_pw_5numpy_6random_6mtrand_11RandomState_73laplace ___pyx_pw_5numpy_6random_6mtrand_11RandomState_75gumbel ___pyx_pw_5numpy_6random_6mtrand_11RandomState_77logistic ___pyx_pw_5numpy_6random_6mtrand_11RandomState_79lognormal ___pyx_pw_5numpy_6random_6mtrand_11RandomState_81rayleigh ___pyx_pw_5numpy_6random_6mtrand_11RandomState_83wald ___pyx_pw_5numpy_6random_6mtrand_11RandomState_85triangular ___pyx_pw_5numpy_6random_6mtrand_11RandomState_87binomial ___pyx_pw_5numpy_6random_6mtrand_11RandomState_89negative_binomial ___pyx_pw_5numpy_6random_6mtrand_11RandomState_91poisson ___pyx_pw_5numpy_6random_6mtrand_11RandomState_93zipf ___pyx_pw_5numpy_6random_6mtrand_11RandomState_95geometric ___pyx_pw_5numpy_6random_6mtrand_11RandomState_97hypergeometric ___pyx_pw_5numpy_6random_6mtrand_11RandomState_99logseries ___pyx_pw_5numpy_6random_6mtrand_11RandomState_101multivariate_normal ___pyx_pw_5numpy_6random_6mtrand_11RandomState_103multinomial ___pyx_pw_5numpy_6random_6mtrand_11RandomState_105dirichlet ___pyx_pw_5numpy_6random_6mtrand_11RandomState_107shuffle ___pyx_pw_5numpy_6random_6mtrand_11RandomState_109permutation ___Pyx_CheckKeywordStrings ___Pyx_ParseOptionalKeywords ___Pyx_PyUnicode_Equals ___Pyx_IternextUnpackEndCheck ___Pyx_IterFinish ___Pyx_GetItemInt_Fast ___Pyx_PyDict_GetItem ___Pyx_PyInt_As_int ___Pyx_PyNumber_IntOrLong ___Pyx_PyNumber_IntOrLongWrongResultType ___Pyx__ExceptionSave ___Pyx__GetException ___Pyx__ExceptionReset ___Pyx_PyInt_As_Py_intptr_t ___Pyx_PyObject_GetSlice ___pyx_pf_5numpy_6random_6mtrand_11RandomState_34choice ___Pyx_PyInt_BoolEqObjC ___Pyx_TypeTest ___Pyx_PyObject_SetSlice ___Pyx_PyObject_GetItem ___Pyx_PyObject_IsTrueAndDecref ___Pyx_PyObject_GetIndex ___Pyx_PyObject_GetItem_Slow ___Pyx_PyInt_As_long ___pyx_f_5numpy_6random_6mtrand_int64_to_long ___Pyx_PyInt_As_int64_t ___pyx_pf_5numpy_6random_6mtrand_11RandomState_100multivariate_normal ___pyx_pf_5numpy_6random_6mtrand_11RandomState_106shuffle ___Pyx_SetItemInt_Fast ___pyx_getprop_5numpy_6random_6mtrand_11RandomState__bit_generator ___pyx_setprop_5numpy_6random_6mtrand_11RandomState__bit_generator ___Pyx_GetVtable ___Pyx_ImportType_3_0_12 ___Pyx_ImportVoidPtr_3_0_12 ___Pyx_ImportFunction_3_0_12 ___pyx_pw_5numpy_6random_6mtrand_1seed ___pyx_pw_5numpy_6random_6mtrand_3get_bit_generator ___pyx_pw_5numpy_6random_6mtrand_5set_bit_generator ___pyx_pw_5numpy_6random_6mtrand_7sample ___pyx_pw_5numpy_6random_6mtrand_9ranf _random_standard_uniform_f _random_standard_uniform _random_standard_uniform_fill _random_standard_uniform_fill_f _random_standard_exponential _random_standard_exponential_fill _random_standard_exponential_f _random_standard_exponential_fill_f _random_standard_exponential_inv_fill _random_standard_exponential_inv_fill_f _random_standard_normal _random_standard_normal_fill _random_standard_normal_f _random_standard_normal_fill_f _random_standard_gamma _random_standard_gamma_f _random_positive_int64 _random_positive_int32 _random_positive_int _random_uint _random_loggam _random_normal _random_exponential _random_uniform _random_gamma _random_gamma_f _random_beta _random_chisquare _random_f _random_standard_cauchy _random_pareto _random_weibull _random_power _random_laplace _random_gumbel _random_logistic _random_lognormal _random_rayleigh _random_standard_t _random_poisson _random_negative_binomial _random_binomial_btpe _random_binomial_inversion _random_binomial _random_noncentral_chisquare _random_noncentral_f _random_wald _random_vonmises _random_logseries _random_geometric_search _random_geometric_inversion _random_geometric _random_zipf _random_triangular _random_interval _random_bounded_uint64 _random_buffered_bounded_uint32 _random_buffered_bounded_uint16 _random_buffered_bounded_uint8 _random_buffered_bounded_bool _random_bounded_uint64_fill _random_bounded_uint32_fill _random_bounded_uint16_fill _random_bounded_uint8_fill _random_bounded_bool_fill _random_multinomial _legacy_gauss _legacy_standard_exponential _legacy_standard_gamma _legacy_gamma _legacy_pareto _legacy_weibull _legacy_power _legacy_chisquare _legacy_rayleigh _legacy_noncentral_chisquare _legacy_noncentral_f _legacy_wald _legacy_normal _legacy_lognormal _legacy_standard_t _legacy_negative_binomial _legacy_standard_cauchy _legacy_beta _legacy_f _legacy_exponential _legacy_random_binomial _legacy_random_hypergeometric _legacy_random_poisson _legacy_random_zipf _legacy_random_geometric _legacy_random_multinomial _legacy_vonmises _legacy_logseries ___pyx_k_Cannot_take_a_larger_sample_than ___pyx_k_DeprecationWarning ___pyx_k_Fewer_non_zero_entries_in_p_than ___pyx_k_ImportError ___pyx_k_IndexError ___pyx_k_Invalid_bit_generator_The_bit_ge ___pyx_k_MT19937 ___pyx_k_MT19937_2 ___pyx_k_Negative_dimensions_are_not_allo ___pyx_k_OverflowError ___pyx_k_Providing_a_dtype_with_a_non_nat ___pyx_k_RandomState ___pyx_k_RandomState_binomial_line_3353 ___pyx_k_RandomState_bytes_line_805 ___pyx_k_RandomState_chisquare_line_1910 ___pyx_k_RandomState_choice_line_841 ___pyx_k_RandomState_dirichlet_line_4394 ___pyx_k_RandomState_exponential_line_500 ___pyx_k_RandomState_f_line_1729 ___pyx_k_RandomState_gamma_line_1645 ___pyx_k_RandomState_geometric_line_3772 ___pyx_k_RandomState_gumbel_line_2764 ___pyx_k_RandomState_hypergeometric_line ___pyx_k_RandomState_laplace_line_2670 ___pyx_k_RandomState_logistic_line_2888 ___pyx_k_RandomState_lognormal_line_2974 ___pyx_k_RandomState_logseries_line_3969 ___pyx_k_RandomState_multinomial_line_425 ___pyx_k_RandomState_multivariate_normal ___pyx_k_RandomState_negative_binomial_li ___pyx_k_RandomState_noncentral_chisquare ___pyx_k_RandomState_noncentral_f_line_18 ___pyx_k_RandomState_normal_line_1454 ___pyx_k_RandomState_pareto_line_2354 ___pyx_k_RandomState_permutation_line_466 ___pyx_k_RandomState_poisson_line_3593 ___pyx_k_RandomState_power_line_2561 ___pyx_k_RandomState_rand_line_1177 ___pyx_k_RandomState_randint_line_679 ___pyx_k_RandomState_randn_line_1221 ___pyx_k_RandomState_random_integers_line ___pyx_k_RandomState_random_sample_line_3 ___pyx_k_RandomState_rayleigh_line_3090 ___pyx_k_RandomState_seed_line_228 ___pyx_k_RandomState_shuffle_line_4543 ___pyx_k_RandomState_standard_cauchy_line ___pyx_k_RandomState_standard_exponential ___pyx_k_RandomState_standard_gamma_line ___pyx_k_RandomState_standard_normal_line ___pyx_k_RandomState_standard_t_line_2150 ___pyx_k_RandomState_tomaxint_line_621 ___pyx_k_RandomState_triangular_line_3244 ___pyx_k_RandomState_uniform_line_1050 ___pyx_k_RandomState_vonmises_line_2265 ___pyx_k_RandomState_wald_line_3167 ___pyx_k_RandomState_weibull_line_2457 ___pyx_k_RandomState_zipf_line_3676 ___pyx_k_Range_exceeds_valid_bounds ___pyx_k_RuntimeWarning ___pyx_k_Sequence ___pyx_k_Shuffling_a_one_dimensional_arra ___pyx_k_T ___pyx_k_This_function_is_deprecated_Plea ___pyx_k_This_function_is_deprecated_Plea_2 ___pyx_k_TypeError ___pyx_k_Unsupported_dtype_r_for_randint ___pyx_k_UserWarning ___pyx_k_ValueError ___pyx_k__4 ___pyx_k__5 ___pyx_k__53 ___pyx_k__6 ___pyx_k__62 ___pyx_k_a ___pyx_k_a_and_p_must_have_same_size ___pyx_k_a_cannot_be_empty_unless_no_sam ___pyx_k_a_must_be_1_dimensional ___pyx_k_a_must_be_1_dimensional_or_an_in ___pyx_k_a_must_be_greater_than_0_unless ___pyx_k_add ___pyx_k_all ___pyx_k_all_2 ___pyx_k_allclose ___pyx_k_alpha ___pyx_k_alpha_0 ___pyx_k_any ___pyx_k_arange ___pyx_k_args ___pyx_k_array ___pyx_k_array_is_read_only ___pyx_k_asarray ___pyx_k_astype ___pyx_k_at_0x_X ___pyx_k_atol ___pyx_k_b ___pyx_k_bg_type ___pyx_k_binomial_n_p_size_None_Draw_sam ___pyx_k_bit_generator ___pyx_k_bitgen ___pyx_k_bool ___pyx_k_bytes_length_Return_random_byte ___pyx_k_can_only_re_seed_a_MT19937_BitGe ___pyx_k_capsule ___pyx_k_casting ___pyx_k_check_valid ___pyx_k_check_valid_must_equal_warn_rais ___pyx_k_chisquare_df_size_None_Draw_sam ___pyx_k_choice_a_size_None_replace_True ___pyx_k_class ___pyx_k_class_getitem ___pyx_k_cline_in_traceback ___pyx_k_collections_abc ___pyx_k_copy ___pyx_k_count_nonzero ___pyx_k_cov ___pyx_k_cov_must_be_2_dimensional_and_sq ___pyx_k_covariance_is_not_symmetric_posi ___pyx_k_cumsum ___pyx_k_df ___pyx_k_dfden ___pyx_k_dfnum ___pyx_k_dirichlet_alpha_size_None_Draw ___pyx_k_disable ___pyx_k_dot ___pyx_k_empty ___pyx_k_empty_like ___pyx_k_enable ___pyx_k_enter ___pyx_k_eps ___pyx_k_equal ___pyx_k_exit ___pyx_k_exponential_scale_1_0_size_None ___pyx_k_f_dfnum_dfden_size_None_Draw_sa ___pyx_k_finfo ___pyx_k_flags ___pyx_k_float64 ___pyx_k_format ___pyx_k_gamma_shape_scale_1_0_size_None ___pyx_k_gauss ___pyx_k_gc ___pyx_k_geometric_p_size_None_Draw_samp ___pyx_k_get ___pyx_k_get_state_and_legacy_can_only_be ___pyx_k_greater ___pyx_k_gumbel_loc_0_0_scale_1_0_size_N ___pyx_k_has_gauss ___pyx_k_high ___pyx_k_hypergeometric_ngood_nbad_nsamp ___pyx_k_id ___pyx_k_ignore ___pyx_k_import ___pyx_k_index ___pyx_k_initializing ___pyx_k_int16 ___pyx_k_int32 ___pyx_k_int64 ___pyx_k_int8 ___pyx_k_intp ___pyx_k_isenabled ___pyx_k_isfinite ___pyx_k_isnan ___pyx_k_isnative ___pyx_k_isscalar ___pyx_k_issubdtype ___pyx_k_item ___pyx_k_itemsize ___pyx_k_kappa ___pyx_k_key ___pyx_k_kwargs ___pyx_k_l ___pyx_k_lam ___pyx_k_laplace_loc_0_0_scale_1_0_size ___pyx_k_left ___pyx_k_left_mode ___pyx_k_left_right ___pyx_k_legacy ___pyx_k_legacy_can_only_be_True_when_the ___pyx_k_legacy_seeding ___pyx_k_length ___pyx_k_less ___pyx_k_less_equal ___pyx_k_loc ___pyx_k_lock ___pyx_k_logical_or ___pyx_k_logistic_loc_0_0_scale_1_0_size ___pyx_k_lognormal_mean_0_0_sigma_1_0_si ___pyx_k_logseries_p_size_None_Draw_samp ___pyx_k_low ___pyx_k_main ___pyx_k_may_share_memory ___pyx_k_mean ___pyx_k_mean_and_cov_must_have_same_leng ___pyx_k_mean_must_be_1_dimensional ___pyx_k_mode ___pyx_k_mode_right ___pyx_k_mt19937 ___pyx_k_mu ___pyx_k_multinomial_n_pvals_size_None_D ___pyx_k_multivariate_normal_mean_cov_si ___pyx_k_n ___pyx_k_name ___pyx_k_nbad ___pyx_k_ndim ___pyx_k_negative_binomial_n_p_size_None ___pyx_k_newbyteorder ___pyx_k_ngood ___pyx_k_ngood_nbad_nsample ___pyx_k_nonc ___pyx_k_noncentral_chisquare_df_nonc_si ___pyx_k_noncentral_f_dfnum_dfden_nonc_s ___pyx_k_normal_loc_0_0_scale_1_0_size_N ___pyx_k_np ___pyx_k_nsample ___pyx_k_numpy_core_multiarray_failed_to ___pyx_k_numpy_core_umath_failed_to_impor ___pyx_k_numpy_linalg ___pyx_k_object ___pyx_k_object_which_is_not_a_subclass ___pyx_k_operator ___pyx_k_p ___pyx_k_p_must_be_1_dimensional ___pyx_k_pareto_a_size_None_Draw_samples ___pyx_k_permutation_x_Randomly_permute ___pyx_k_pickle ___pyx_k_poisson_lam_1_0_size_None_Draw ___pyx_k_poisson_lam_max ___pyx_k_pos ___pyx_k_power_a_size_None_Draws_samples ___pyx_k_probabilities_are_not_non_negati ___pyx_k_probabilities_contain_NaN ___pyx_k_probabilities_do_not_sum_to_1 ___pyx_k_prod ___pyx_k_pvals ___pyx_k_pvals_must_be_a_1_d_sequence ___pyx_k_pyx_vtable ___pyx_k_raise ___pyx_k_rand_2 ___pyx_k_rand_d0_d1_dn_Random_values_in ___pyx_k_randint_low_high_None_size_None ___pyx_k_randn_d0_d1_dn_Return_a_sample ___pyx_k_random_integers_low_high_None_s ___pyx_k_random_sample_size_None_Return ___pyx_k_randomstate_ctor ___pyx_k_range ___pyx_k_ravel ___pyx_k_rayleigh_scale_1_0_size_None_Dr ___pyx_k_reduce_2 ___pyx_k_replace ___pyx_k_reshape ___pyx_k_return_index ___pyx_k_reversed ___pyx_k_right ___pyx_k_rtol ___pyx_k_scale ___pyx_k_searchsorted ___pyx_k_seed_seed_None_Reseed_a_legacy ___pyx_k_set_state_can_only_be_used_with ___pyx_k_shape ___pyx_k_shuffle_x_Modify_a_sequence_in ___pyx_k_side ___pyx_k_sigma ___pyx_k_singleton ___pyx_k_size ___pyx_k_sort ___pyx_k_spec ___pyx_k_sqrt ___pyx_k_stacklevel ___pyx_k_standard_cauchy_size_None_Draw ___pyx_k_standard_exponential_size_None ___pyx_k_standard_gamma_shape_size_None ___pyx_k_standard_normal_size_None_Draw ___pyx_k_standard_t_df_size_None_Draw_sa ___pyx_k_state ___pyx_k_state_dictionary_is_not_valid ___pyx_k_state_must_be_a_dict_or_a_tuple ___pyx_k_str ___pyx_k_strides ___pyx_k_subtract ___pyx_k_sum ___pyx_k_sum_pvals_1_1_0 ___pyx_k_sum_pvals_1_astype_np_float64_1 ___pyx_k_svd ___pyx_k_take ___pyx_k_test ___pyx_k_tobytes ___pyx_k_tol ___pyx_k_tomaxint_size_None_Return_a_sam ___pyx_k_triangular_left_mode_right_size ___pyx_k_u4 ___pyx_k_uint16 ___pyx_k_uint32 ___pyx_k_uint64 ___pyx_k_uint8 ___pyx_k_uniform_low_0_0_high_1_0_size_N ___pyx_k_unique ___pyx_k_unsafe ___pyx_k_vonmises_mu_kappa_size_None_Dra ___pyx_k_wald_mean_scale_size_None_Draw ___pyx_k_warn ___pyx_k_warnings ___pyx_k_weibull_a_size_None_Draw_sample ___pyx_k_writeable ___pyx_k_x ___pyx_k_x_must_be_an_integer_or_at_least ___pyx_k_you_are_shuffling_a ___pyx_k_zeros ___pyx_k_zipf_a_size_None_Draw_samples_f ___pyx_doc_5numpy_6random_6mtrand_11RandomState_12seed ___pyx_doc_5numpy_6random_6mtrand_11RandomState_14get_state ___pyx_doc_5numpy_6random_6mtrand_11RandomState_16set_state ___pyx_doc_5numpy_6random_6mtrand_11RandomState_18random_sample ___pyx_doc_5numpy_6random_6mtrand_11RandomState_20random ___pyx_doc_5numpy_6random_6mtrand_11RandomState_22beta ___pyx_doc_5numpy_6random_6mtrand_11RandomState_24exponential ___pyx_doc_5numpy_6random_6mtrand_11RandomState_26standard_exponential ___pyx_doc_5numpy_6random_6mtrand_11RandomState_28tomaxint ___pyx_doc_5numpy_6random_6mtrand_11RandomState_30randint ___pyx_doc_5numpy_6random_6mtrand_11RandomState_32bytes ___pyx_doc_5numpy_6random_6mtrand_11RandomState_34choice ___pyx_doc_5numpy_6random_6mtrand_11RandomState_36uniform ___pyx_doc_5numpy_6random_6mtrand_11RandomState_38rand ___pyx_doc_5numpy_6random_6mtrand_11RandomState_40randn ___pyx_doc_5numpy_6random_6mtrand_11RandomState_42random_integers ___pyx_doc_5numpy_6random_6mtrand_11RandomState_44standard_normal ___pyx_doc_5numpy_6random_6mtrand_11RandomState_46normal ___pyx_doc_5numpy_6random_6mtrand_11RandomState_48standard_gamma ___pyx_doc_5numpy_6random_6mtrand_11RandomState_50gamma ___pyx_doc_5numpy_6random_6mtrand_11RandomState_52f ___pyx_doc_5numpy_6random_6mtrand_11RandomState_54noncentral_f ___pyx_doc_5numpy_6random_6mtrand_11RandomState_56chisquare ___pyx_doc_5numpy_6random_6mtrand_11RandomState_58noncentral_chisquare ___pyx_doc_5numpy_6random_6mtrand_11RandomState_60standard_cauchy ___pyx_doc_5numpy_6random_6mtrand_11RandomState_62standard_t ___pyx_doc_5numpy_6random_6mtrand_11RandomState_64vonmises ___pyx_doc_5numpy_6random_6mtrand_11RandomState_66pareto ___pyx_doc_5numpy_6random_6mtrand_11RandomState_68weibull ___pyx_doc_5numpy_6random_6mtrand_11RandomState_70power ___pyx_doc_5numpy_6random_6mtrand_11RandomState_72laplace ___pyx_doc_5numpy_6random_6mtrand_11RandomState_74gumbel ___pyx_doc_5numpy_6random_6mtrand_11RandomState_76logistic ___pyx_doc_5numpy_6random_6mtrand_11RandomState_78lognormal ___pyx_doc_5numpy_6random_6mtrand_11RandomState_80rayleigh ___pyx_doc_5numpy_6random_6mtrand_11RandomState_82wald ___pyx_doc_5numpy_6random_6mtrand_11RandomState_84triangular ___pyx_doc_5numpy_6random_6mtrand_11RandomState_86binomial ___pyx_doc_5numpy_6random_6mtrand_11RandomState_88negative_binomial ___pyx_doc_5numpy_6random_6mtrand_11RandomState_90poisson ___pyx_doc_5numpy_6random_6mtrand_11RandomState_92zipf ___pyx_doc_5numpy_6random_6mtrand_11RandomState_94geometric ___pyx_doc_5numpy_6random_6mtrand_11RandomState_96hypergeometric ___pyx_doc_5numpy_6random_6mtrand_11RandomState_98logseries ___pyx_doc_5numpy_6random_6mtrand_11RandomState_100multivariate_normal ___pyx_doc_5numpy_6random_6mtrand_11RandomState_102multinomial ___pyx_doc_5numpy_6random_6mtrand_11RandomState_104dirichlet ___pyx_doc_5numpy_6random_6mtrand_11RandomState_106shuffle ___pyx_doc_5numpy_6random_6mtrand_11RandomState_108permutation ___pyx_doc_5numpy_6random_6mtrand_seed ___pyx_doc_5numpy_6random_6mtrand_2get_bit_generator ___pyx_doc_5numpy_6random_6mtrand_4set_bit_generator ___pyx_doc_5numpy_6random_6mtrand_6sample ___pyx_doc_5numpy_6random_6mtrand_8ranf _we_double _ke_double _we_float _ke_float _wi_double _ki_double _fi_double _wi_float _ki_float _fi_float _fe_double _fe_float __dyld_private ___pyx_moduledef ___pyx_moduledef_slots ___Pyx_check_single_interpreter.main_interpreter_id ___pyx_type_5numpy_6random_6mtrand_RandomState ___pyx_methods_5numpy_6random_6mtrand_RandomState ___pyx_getsets_5numpy_6random_6mtrand_RandomState __MergedGlobals ___pyx_module_is_main_numpy__random__mtrand ___pyx_methods ___pyx_mstate_global_static ___pyx_vtabptr_5numpy_6random_13bit_generator_SeedSequence __MergedGlobals.318 /Users/appveyor/projects/mobile-forge/build/cp312/numpy/1.26.4/.mesonpy-e5oisdy3/numpy/random/mtrand.cpython-312-iphonesimulator.so.p/numpy/random/ mtrand.pyx.c /Users/appveyor/projects/mobile-forge/build/cp312/numpy/1.26.4/.mesonpy-e5oisdy3/numpy/random/mtrand.cpython-312-iphonesimulator.so.p/meson-generated_numpy_random_mtrand.pyx.c.o ___pyx_pymod_create /Users/appveyor/projects/mobile-forge/build/cp312/numpy/1.26.4/.mesonpy-e5oisdy3/../numpy/random/src/distributions/ distributions.c /Users/appveyor/projects/mobile-forge/build/cp312/numpy/1.26.4/.mesonpy-e5oisdy3/numpy/random/mtrand.cpython-312-iphonesimulator.so.p/src_distributions_distributions.c.o /Users/appveyor/projects/mobile-forge/build/cp312/numpy/1.26.4/.mesonpy-e5oisdy3/../numpy/random/src/legacy/ legacy-distributions.c /Users/appveyor/projects/mobile-forge/build/cp312/numpy/1.26.4/.mesonpy-e5oisdy3/numpy/random/mtrand.cpython-312-iphonesimulator.so.p/src_legacy_legacy-distributions.c.o úÞ À úÞ ~ ~ X ¨
sà þ` mtrand.cpython-312-iphonesimulator.so IÅ3M&êô<vþôÜÅߓªÛÞLÏÅZ¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§6ØÄ àðÃЩ)³ ´U¢+)\]
1-£¯Ey*úÞHiû. B´ñh©'ò;T]шõú:®ɭÏál QKàÑÆߪÄ.B<®¼âRs·º¥x¨9Éu
v·çÿ¯۹ "ûáyPU½÷䟻Îe©ОuX·ù¹W~ŮÖ-eM´ ò¶1/Հ&ùº"å¼£UhT⧪Y·è§B«q·U~@]øþÎ9·ù DÀZËhE;ôI±=¥ÛÆgQVHÄÉÍëÞ-3S@eÀ4"տ÷ë=R®æöñëé6DDIv>1½Ny넯l°2¿+Öù%Eê¡ÿō`ÚT3ÉÇú ±iB[»RáX3Þ]E8S«æÂ賢(MÎ,¹rzÑzæ¶pLG¯uÎIô)Zäݬ¼ÛÝLÛd×-°sûUí~z¬<-íå%«±Æ×ʈþSB®]
¦ö ;Ðs±Ø) ¡Tpk0Q÷é f==ÐÈ'úDrýõËç^âF7.5Ô IÄ|4'öƠÊû^¶$?mÃkËm'CvTÖL¬ÏÌQ Û¢ù¨UáPÛâ!¾>ÖçïàÌgö~ &þÐ)éNHíå9C^âçK©?͇á»0iYaw ¾¬Ù 4Õzzá|}*¢$± 8õ7z8 <h®$
·¶µç2³Ljé±hCA¼eº¯hûfb?-ëë,õ\
å\5|IÐ`}j>#ßQ#qÅ7ª1ägÔcÂN;E=4_Qm~뇷¹÷>às \®ÜqƏSÉLªÃÝ2
6ùZí7¯Sµ.Úá
A_Ìî¦^.ÉüzÖD¼í7D%cà9vf¿ÆI¶ÍmÅûÌ3Àñ _øðÇ:èè¯ޚ:Ð3Ä,·(
lmªößüø¾¼GΞ%5ú»áG7É,-¥9nØü-¥~t [hА¬¥ÛW*V[Ät»§8¢fFãåM ¬JEà<½fwËxݿ Ç&sa$ fñ¦Ìn
«ïZ÷˙Àhց¡óëAoÕ#'¼{{ÊÖ{TËÈ]¬3¤Äò|ãvÈAÿcçÀÒ?ͮ¤ĪýJ¬u-»©¹5ï\%Ò VÁ&ÎzybeבÜ+êh¼nÝdsØÔT§Å;¦hë¾Y¡m ü`\é½>ã݁©ö,y.^«½Tj¨ËÛCrm¶þgårù§å{w« ¨G[ÓH:pÓ6eWK§ìº9¨çqDɔüà"ƹV
Êïè_õPçóº|FîبWó/öãx÷õT ¦ÕQuªXDÎáY ¾ڜè`7å`0×äè~Ãîñ?
Þ^dî@T^ãuj2)½þ?þ2¾ã´ X§°õåf
=´ hHÂ`¨í_ ¯"1
¨ïO*µ´Øï]«èP¥)Zì²DÍ.e òË^Uí,:ä%|ö nsêÎ/ѷô·AF#Jµ¢y®]mG\¢`IKIØÆ¢ùµÜØØ 6§rzRDFðï½è' /£ijڽxfÍR|øì¯LøSњO?&²£Z«I Lg}{C±ÚnÂd¬KÐÙ0ɟµ¥£HI`4搫:Loë÷u§Û& êÅZb<x!+©ñ1æä.YyåXw Ïkºd8pا#Ñ úʄM+úøèˢ)ZëQDæÑÇUÒà¦Þl9UKgmJV¤Â/îÀ6Lò,'Øà²cµm8©ééø´»ûr
LO&ù#ÑíE¿X[( àøÞù=lQ/wnA3¸¯ޥ HdO4ÑoÐ%Ýà2OÛçZxiÊ~ÁÂZâ"áæýÿ/£Âô¯ÊY_'±r#mv*̢isެ'Jä*ʲzù¶'&üQ«ç8ú3{Hêq Ö0Twû»xJ«FóeMÓ
¾J@%KäÞϺy8ÆÈϦ_ÿVù~3ò&Îrã6[ °iÇv¥2BÃaҭ¢$Ä|¥¡Wjþ¥øC +ÿύx-¶
²¡bÅÚ%| ҽ9³æHÄÎ z³~Çü.@öûMRu3'½)7ÑH¡¿½¨0̷CM°!*" t[äG´²Ŕ߅GõaêûxÕàqÎRlF)X/prâv.ùúï ¶ÞթFrN[ΚïÆDM9ÞzDa:4xl´$ôZS»$uª;®w`Ì܂l»,%{=`,S¨ËÒÌўå~ªµX¨Ę©Jª¬Ê&%
q[dwÀðI= æô83ȞCrHÇß6Ø_żÿõ¬¡ì 3«hqwr/.Ò
ùFÎ cØ÷ HQ¼ÈưrØNmeL ?Ulâ<y
ª<÷j)U¶ù6ªmʆîjøÉhâqµ°w|Fÿ]¯t³ñìQ¦±xäX'Û× 4oC :6 Ī¼®âþZ2\´ÖL½ÎASÅ8ÌӋÊ7§z ª'óÖEDAo.M® ²ËÛ^æó=I`P*¥4?áDÁôro÷ëÝ Ø&SöÄ*<íîùzi$+ ·F×54Ô$åꀌ»KÈRÉöҨ´ òäØZhܟÏkOºL´¼»&¹Ò µµç9&2W=;78ÕóÂü þDëÂ_ ֮¢®ª;Údsm!|no³)ùí¥þÛuñ#º^ñð7§zìÔÜÍæQ±±¹l ¬M%$©&¨-@e´"p²7sک½¯ïe?°
ªÁ՛nSä'Ù௯/öª~h·«F<COïÉRÏr|ÞÒLá%.ÈJà ـp?ZíMÎû p&ûjî1^2ûnÓ >u¢мÂÓ]CMá?aäul×.M8B÷7±·нlA:ò`å.I7òb*ü\[$AöC¿Ðõ:s°I3¶ÁǍd|fdÅ1Âñb6¼ÇVϜ:Éù
^äé?ÀKõ÷[2ëÀ
òs|Ò#pÔNq肋Ìjâý~Í_;¹|,
劷SÉýN°ÅÖ{:y
\õõ ZMcǣ¿TuûðÉI¸§bfPy§qÍ4:y %¢ØÖ׀},aÖY+VäTd÷¸ù©ýF¶m÷^¡ÙÁ~v4íZS®@2@3¬, !íكÈt°0G¤åUýü2GÝ!ýaËF
ÜÔ -U_èâ;þ_rd$½¿Ì́cFiBPÍhmXW!é_Ì1]j7MaèÆë<´îK÷Úcª䏙{iDÈx ]+?®h$â-s°'L "D:Ëcû4l}t:I
Ë}úH£U«9ê ýV
:%ù7H¯ë\BmVàãDڔN!!²#7å"°ç½>?5⩥¿yòÁ Rkey$µáÿEnùV|ßӡ#ãå]2Q*ÜN
ÿ\¼;z¸Ç*°C¿ ºº·Së ó¦Ûä[Úà-ëáûÿã
uÎEÃÒ; Ðàhý$.LrôÕyñQ)¾ö÷Ԁ¼HH «̰C 띥@©ô(¡L2)@jk²O=á ¤õ }Ø#xBRdªֽ;ÛC}É=ætðê\r: »Ôg
±¶g¶´ôÇèì¼P«F3å@±æÎêWDÔùv4¤8
|ûg½j$ÜÙoøN°â7¼«;ÔÃÿ͵ ©/Go§(öu ð2qyåॠs°¡\ò¤ »ûV+Jïë£vÂ<6 ½d¨ hÝ|-×êºJ¦Ûu±ßVÌǐ¥3µpkô¸üú$f÷7Ï ø¥ Tm±'^Cwº!ÝoµÓmqÏB®3Gx¥O«ç+áxmýìǾ.Ѝ¸ÎlZ
a²½u¾Ăg°!¯,l&Èg,%Mjö$mõærv>w rÀ"XmƹÀLO¸gG´²^20]cmý£XÚOLß|ªmXDUküù2Iùº¬4/´XïJ¶IJvНú IޯMKê½(!ÍV4k3¥Y©â¡cÛìWoÓ#\¢Aҁ@} ûV5ÁR [È>Zëf âûø ©FóY°Ã ]ܱÀÁñWù
Îl] *!±A¤a>H
åíâÎ^}NW²>BlÉ\ѐ©bÔ|MoÇFJ{¥PkVö³(®ÿU7sãNhþ颈Lw©güjnrR) ʉ(àé6þ±'$r
C¾-ÂÊfÀ9âóyìû:ÄíÇ*eàm乡8=FÁ
2ð¾)Çr?ټ£¼AÏ!p#
:¡-þƶ`ò#Öõ+KYr!0ÔHVd#Ѕ<kÕIJ^\½ý×öWfí
^f µ*°;஢dÏÜ«¯ζ»¼EC¹À{jKiJ
ýâØ@Xø0º©~'é¿7¦íAÃvkí@CJ0;Ȋ³.KûØÖ~É9¾ Ù]rٮT/ì8蔛JUñ¤]0k+ýTmTé0å
8Õõç§ÛñɔY¤Ö[¶dQMH¥ C I¾ êGªöÜZÀy¦ Láä0îÇбm! è L3 M7~Û à áïõ"Äþµ/=b,¹O>B»ªÛ> rÿA¥w5WF¯HÐÚús!·îúZÖó ±¯î ô͐2«´af2`&T}~ Øu<Zø
K,>ٚnM¿?º{iQ² ÿUcôÕù7åñ=_<þ¦ݕu& ´Ç%gÖÆá
TÐ;pôI \{<ߟ9jÙP® íëáÁPæå½Nþ2¨}ÇzØç%Ϯ!{´ ©Á}N%Îāv}æ;jn_Yz@fSLáR%̤¦"s+῁¡_
J¶Úôì½}áí Bܤ
¶ÀƢÊÿ7mR-ÏsO©üà¤ۣ4ÇhåA×[EÐÎÞ NÀæÎ:¯Áэõ~6%Õ/TÕõlµÉØSÀG «Ø١³#ºd$dd© t¸ 1urÝ©ré;lÄ݈ӳjïDB��Ôâ4¥t«7Ov(ñ G~¢%Ë ب;(¨%L æԆ幘vO"¯º._dQ¬3Ec;G§¡ï`ªB \é Ɯú
1p"C&!ºpZx®ò÷~7*ã =)Úz Ϧ¿8Y©ý¦%*\`¥
ªðòCþÄìËSv
Ìy!ã½ÊúXàÕ *4 n÷\±¦ºCXų»
2|ìEVÀ ·ñéԝF <¾j Âû¹"5úÒ+$i ˉ6÷üÁÆKcüèßÃIË$
BÊ{«}÷Oþ8 ¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§ò¦Ôï ;âá
Ú:5ͻ*ÇÆ )ÁU 5d0Pӭ¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§¬²XoÆéfÀ×ÑÑkOXÿ|´|z
ڽH,§hme¼îFG\ì2oÏ)ìdj¯UYK>¦Ô<xG%¸6}oH©Õ"¡Ùú>ü÷s?ïÒûù¯·óî 'á%¦
¸1^¤àpK LÊÂ'5·×øxJì-gcºÿg.$¤ÒKKGô$¥u%É[GùǾPÈ%(ðïÈץi®Æý¨ÿ¾¬ %Väcü ¬"ÊØ˔kÉ]²±.{>sPè&þ£´"+ÞÝö,gÜÏp²°¤-ö¯܁u
ðÒÉ^ó-8ҥ8ÂZ09ÈÚÀY/1\wQîUz¬YºâäVMÏðz%ÁVu¨½e7X
Ø ã¤aQÐÏUjËDË{a{Ò4dèJۉ5õ}£ôA õÑÑâ§Q>ßB(cß
²±ûªßJ(߂
#u>ǎ¯üÕg¥³âó Á"_nBÅ$ѹ:ÁëÿxiDRR °͛ÒE<
烏"µÉuQîË3«}>èdöEƷ»îƪéߟ°öXQþ FheñϻչÀGp \3ٝÑ×Ùcr4L_x/"ѾÆCùõ ©¨zq&n¡tÅÜY IÁv+äÐÐER8ìýxhfr=tx+úêWÉBøGLÿª