"""
Module parse to/from Excel
"""
# ---------------------------------------------------------------------
# ExcelFile class
import abc
from datetime import date, datetime, time, timedelta
from distutils.version import LooseVersion
from io import UnsupportedOperation
import os
from textwrap import fill
import warnings
import numpy as np
import pandas._libs.json as json
import pandas.compat as compat
from pandas.compat import (
OrderedDict, add_metaclass, lrange, map, range, string_types, u, zip)
from pandas.errors import EmptyDataError
from pandas.util._decorators import Appender, deprecate_kwarg
from pandas.core.dtypes.common import (
is_bool, is_float, is_integer, is_list_like)
from pandas.core import config
from pandas.core.frame import DataFrame
from pandas.io.common import (
_NA_VALUES, _is_url, _stringify_path, _urlopen, _validate_header_arg,
get_filepath_or_buffer)
from pandas.io.formats.printing import pprint_thing
from pandas.io.parsers import TextParser
__all__ = ["read_excel", "ExcelWriter", "ExcelFile"]
_writer_extensions = ["xlsx", "xls", "xlsm"]
_writers = {}
_read_excel_doc = """
Read an Excel file into a pandas DataFrame.
Support both `xls` and `xlsx` file extensions from a local filesystem or URL.
Support an option to read a single sheet or a list of sheets.
Parameters
----------
io : str, file descriptor, pathlib.Path, ExcelFile or xlrd.Book
The string could be a URL. Valid URL schemes include http, ftp, s3,
gcs, and file. For file URLs, a host is expected. For instance, a local
file could be /path/to/workbook.xlsx.
sheet_name : str, int, list, or None, default 0
Strings are used for sheet names. Integers are used in zero-indexed
sheet positions. Lists of strings/integers are used to request
multiple sheets. Specify None to get all sheets.
Available cases:
* Defaults to ``0``: 1st sheet as a `DataFrame`
* ``1``: 2nd sheet as a `DataFrame`
* ``"Sheet1"``: Load sheet with name "Sheet1"
* ``[0, 1, "Sheet5"]``: Load first, second and sheet named "Sheet5"
as a dict of `DataFrame`
* None: All sheets.
header : int, list of int, default 0
Row (0-indexed) to use for the column labels of the parsed
DataFrame. If a list of integers is passed those row positions will
be combined into a ``MultiIndex``. Use None if there is no header.
names : array-like, default None
List of column names to use. If file contains no header row,
then you should explicitly pass header=None.
index_col : int, list of int, default None
Column (0-indexed) to use as the row labels of the DataFrame.
Pass None if there is no such column. If a list is passed,
those columns will be combined into a ``MultiIndex``. If a
subset of data is selected with ``usecols``, index_col
is based on the subset.
parse_cols : int or list, default None
Alias of `usecols`.
.. deprecated:: 0.21.0
Use `usecols` instead.
usecols : int, str, list-like, or callable default None
Return a subset of the columns.
* If None, then parse all columns.
* If int, then indicates last column to be parsed.
.. deprecated:: 0.24.0
Pass in a list of int instead from 0 to `usecols` inclusive.
* If str, then indicates comma separated list of Excel column letters
and column ranges (e.g. "A:E" or "A,C,E:F"). Ranges are inclusive of
both sides.
* If list of int, then indicates list of column numbers to be parsed.
* If list of string, then indicates list of column names to be parsed.
.. versionadded:: 0.24.0
* If callable, then evaluate each column name against it and parse the
column if the callable returns ``True``.
.. versionadded:: 0.24.0
squeeze : bool, default False
If the parsed data only contains one column then return a Series.
dtype : Type name or dict of column -> type, default None
Data type for data or columns. E.g. {'a': np.float64, 'b': np.int32}
Use `object` to preserve data as stored in Excel and not interpret dtype.
If converters are specified, they will be applied INSTEAD
of dtype conversion.
.. versionadded:: 0.20.0
engine : str, default None
If io is not a buffer or path, this must be set to identify io.
Acceptable values are None or xlrd.
converters : dict, default None
Dict of functions for converting values in certain columns. Keys can
either be integers or column labels, values are functions that take one
input argument, the Excel cell content, and return the transformed
content.
true_values : list, default None
Values to consider as True.
.. versionadded:: 0.19.0
false_values : list, default None
Values to consider as False.
.. versionadded:: 0.19.0
skiprows : list-like
Rows to skip at the beginning (0-indexed).
nrows : int, default None
Number of rows to parse.
.. versionadded:: 0.23.0
na_values : scalar, str, list-like, or dict, default None
Additional strings to recognize as NA/NaN. If dict passed, specific
per-column NA values. By default the following values are interpreted
as NaN: '""" + fill("', '".join(sorted(_NA_VALUES)), 70, subsequent_indent=" ") + """'.
keep_default_na : bool, default True
If na_values are specified and keep_default_na is False the default NaN
values are overridden, otherwise they're appended to.
verbose : bool, default False
Indicate number of NA values placed in non-numeric columns.
parse_dates : bool, list-like, or dict, default False
The behavior is as follows:
* bool. If True -> try parsing the index.
* list of int or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3
each as a separate date column.
* list of lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as
a single date column.
* dict, e.g. {{'foo' : [1, 3]}} -> parse columns 1, 3 as date and call
result 'foo'
If a column or index contains an unparseable date, the entire column or
index will be returned unaltered as an object data type. For non-standard
datetime parsing, use ``pd.to_datetime`` after ``pd.read_csv``
Note: A fast-path exists for iso8601-formatted dates.
date_parser : function, optional
Function to use for converting a sequence of string columns to an array of
datetime instances. The default uses ``dateutil.parser.parser`` to do the
conversion. Pandas will try to call `date_parser` in three different ways,
advancing to the next if an exception occurs: 1) Pass one or more arrays
(as defined by `parse_dates`) as arguments; 2) concatenate (row-wise) the
string values from the columns defined by `parse_dates` into a single array
and pass that; and 3) call `date_parser` once for each row using one or
more strings (corresponding to the columns defined by `parse_dates`) as
arguments.
thousands : str, default None
Thousands separator for parsing string columns to numeric. Note that
this parameter is only necessary for columns stored as TEXT in Excel,
any numeric columns will automatically be parsed, regardless of display
format.
comment : str, default None
Comments out remainder of line. Pass a character or characters to this
argument to indicate comments in the input file. Any data between the
comment string and the end of the current line is ignored.
skip_footer : int, default 0
Alias of `skipfooter`.
.. deprecated:: 0.23.0
Use `skipfooter` instead.
skipfooter : int, default 0
Rows at the end to skip (0-indexed).
convert_float : bool, default True
Convert integral floats to int (i.e., 1.0 --> 1). If False, all numeric
data will be read in as floats: Excel stores all numbers as floats
internally.
mangle_dupe_cols : bool, default True
Duplicate columns will be specified as 'X', 'X.1', ...'X.N', rather than
'X'...'X'. Passing in False will cause data to be overwritten if there
are duplicate names in the columns.
**kwds : optional
Optional keyword arguments can be passed to ``TextFileReader``.
Returns
-------
DataFrame or dict of DataFrames
DataFrame from the passed in Excel file. See notes in sheet_name
argument for more information on when a dict of DataFrames is returned.
See Also
--------
to_excel : Write DataFrame to an Excel file.
to_csv : Write DataFrame to a comma-separated values (csv) file.
read_csv : Read a comma-separated values (csv) file into DataFrame.
read_fwf : Read a table of fixed-width formatted lines into DataFrame.
Examples
--------
The file can be read using the file name as string or an open file object:
>>> pd.read_excel('tmp.xlsx', index_col=0) # doctest: +SKIP
Name Value
0 string1 1
1 string2 2
2 #Comment 3
>>> pd.read_excel(open('tmp.xlsx', 'rb'),
... sheet_name='Sheet3') # doctest: +SKIP
Unnamed: 0 Name Value
0 0 string1 1
1 1 string2 2
2 2 #Comment 3
Index and header can be specified via the `index_col` and `header` arguments
>>> pd.read_excel('tmp.xlsx', index_col=None, header=None) # doctest: +SKIP
0 1 2
0 NaN Name Value
1 0.0 string1 1
2 1.0 string2 2
3 2.0 #Comment 3
Column types are inferred but can be explicitly specified
>>> pd.read_excel('tmp.xlsx', index_col=0,
... dtype={'Name': str, 'Value': float}) # doctest: +SKIP
Name Value
0 string1 1.0
1 string2 2.0
2 #Comment 3.0
True, False, and NA values, and thousands separators have defaults,
but can be explicitly specified, too. Supply the values you would like
as strings or lists of strings!
>>> pd.read_excel('tmp.xlsx', index_col=0,
... na_values=['string1', 'string2']) # doctest: +SKIP
Name Value
0 NaN 1
1 NaN 2
2 #Comment 3
Comment lines in the excel input file can be skipped using the `comment` kwarg
>>> pd.read_excel('tmp.xlsx', index_col=0, comment='#') # doctest: +SKIP
Name Value
0 string1 1.0
1 string2 2.0
2 None NaN
"""
def register_writer(klass):
"""Adds engine to the excel writer registry. You must use this method to
integrate with ``to_excel``. Also adds config options for any new
``supported_extensions`` defined on the writer."""
if not compat.callable(klass):
raise ValueError("Can only register callables as engines")
engine_name = klass.engine
_writers[engine_name] = klass
for ext in klass.supported_extensions:
if ext.startswith('.'):
ext = ext[1:]
if ext not in _writer_extensions:
config.register_option("io.excel.{ext}.writer".format(ext=ext),
engine_name, validator=str)
_writer_extensions.append(ext)
def _get_default_writer(ext):
_default_writers = {'xlsx': 'openpyxl', 'xlsm': 'openpyxl', 'xls': 'xlwt'}
try:
import xlsxwriter # noqa
_default_writers['xlsx'] = 'xlsxwriter'
except ImportError:
pass
return _default_writers[ext]
def get_writer(engine_name):
try:
return _writers[engine_name]
except KeyError:
raise ValueError("No Excel writer '{engine}'"
.format(engine=engine_name))
@Appender(_read_excel_doc)
@deprecate_kwarg("parse_cols", "usecols")
@deprecate_kwarg("skip_footer", "skipfooter")
def read_excel(io,
sheet_name=0,
header=0,
names=None,
index_col=None,
parse_cols=None,
usecols=None,
squeeze=False,
dtype=None,
engine=None,
converters=None,
true_values=None,
false_values=None,
skiprows=None,
nrows=None,
na_values=None,
keep_default_na=True,
verbose=False,
parse_dates=False,
date_parser=None,
thousands=None,
comment=None,
skip_footer=0,
skipfooter=0,
convert_float=True,
mangle_dupe_cols=True,
**kwds):
# Can't use _deprecate_kwarg since sheetname=None has a special meaning
if is_integer(sheet_name) and sheet_name == 0 and 'sheetname' in kwds:
warnings.warn("The `sheetname` keyword is deprecated, use "
"`sheet_name` instead", FutureWarning, stacklevel=2)
sheet_name = kwds.pop("sheetname")
if 'sheet' in kwds:
Loading ...