"""
Data structures for sparse float data. Life is made simpler by dealing only
with float64 data
"""
# pylint: disable=E1101,E1103,W0231
import warnings
import numpy as np
import pandas._libs.index as libindex
import pandas._libs.sparse as splib
from pandas._libs.sparse import BlockIndex, IntIndex
import pandas.compat as compat
from pandas.compat.numpy import function as nv
from pandas.util._decorators import Appender, Substitution
from pandas.core.dtypes.common import is_integer, is_scalar
from pandas.core.dtypes.generic import ABCSeries, ABCSparseSeries
from pandas.core.dtypes.missing import isna, notna
from pandas.core import generic
from pandas.core.arrays import SparseArray
from pandas.core.arrays.sparse import SparseAccessor
from pandas.core.index import Index
from pandas.core.internals import SingleBlockManager
import pandas.core.ops as ops
from pandas.core.series import Series
from pandas.core.sparse.scipy_sparse import (
_coo_to_sparse_series, _sparse_series_to_coo)
_shared_doc_kwargs = dict(axes='index', klass='SparseSeries',
axes_single_arg="{0, 'index'}",
optional_labels='', optional_axis='')
class SparseSeries(Series):
"""Data structure for labeled, sparse floating point data
Parameters
----------
data : {array-like, Series, SparseSeries, dict}
.. versionchanged :: 0.23.0
If data is a dict, argument order is maintained for Python 3.6
and later.
kind : {'block', 'integer'}
fill_value : float
Code for missing value. Defaults depends on dtype.
0 for int dtype, False for bool dtype, and NaN for other dtypes
sparse_index : {BlockIndex, IntIndex}, optional
Only if you have one. Mainly used internally
Notes
-----
SparseSeries objects are immutable via the typical Python means. If you
must change values, convert to dense, make your changes, then convert back
to sparse
"""
_subtyp = 'sparse_series'
def __init__(self, data=None, index=None, sparse_index=None, kind='block',
fill_value=None, name=None, dtype=None, copy=False,
fastpath=False):
# TODO: Most of this should be refactored and shared with Series
# 1. BlockManager -> array
# 2. Series.index, Series.name, index, name reconciliation
# 3. Implicit reindexing
# 4. Implicit broadcasting
# 5. Dict construction
if data is None:
data = []
elif isinstance(data, SingleBlockManager):
index = data.index
data = data.blocks[0].values
elif isinstance(data, (ABCSeries, ABCSparseSeries)):
index = data.index if index is None else index
dtype = data.dtype if dtype is None else dtype
name = data.name if name is None else name
if index is not None:
data = data.reindex(index)
elif isinstance(data, compat.Mapping):
data, index = Series()._init_dict(data, index=index)
elif is_scalar(data) and index is not None:
data = np.full(len(index), fill_value=data)
super(SparseSeries, self).__init__(
SparseArray(data,
sparse_index=sparse_index,
kind=kind,
dtype=dtype,
fill_value=fill_value,
copy=copy),
index=index, name=name,
copy=False, fastpath=fastpath
)
def __array_ufunc__(self, ufunc, method, *inputs, **kwargs):
# avoid infinite recursion for other SparseSeries inputs
inputs = tuple(
x.values if isinstance(x, type(self)) else x
for x in inputs
)
result = self.values.__array_ufunc__(ufunc, method, *inputs, **kwargs)
return self._constructor(result, index=self.index,
sparse_index=self.sp_index,
fill_value=result.fill_value,
copy=False).__finalize__(self)
def __array_wrap__(self, result, context=None):
"""
Gets called prior to a ufunc (and after)
See SparseArray.__array_wrap__ for detail.
"""
result = self.values.__array_wrap__(result, context=context)
return self._constructor(result, index=self.index,
sparse_index=self.sp_index,
fill_value=result.fill_value,
copy=False).__finalize__(self)
def __array_finalize__(self, obj):
"""
Gets called after any ufunc or other array operations, necessary
to pass on the index.
"""
self.name = getattr(obj, 'name', None)
self.fill_value = getattr(obj, 'fill_value', None)
# unary ops
# TODO: See if this can be shared
def __pos__(self):
result = self.values.__pos__()
return self._constructor(result, index=self.index,
sparse_index=self.sp_index,
fill_value=result.fill_value,
copy=False).__finalize__(self)
def __neg__(self):
result = self.values.__neg__()
return self._constructor(result, index=self.index,
sparse_index=self.sp_index,
fill_value=result.fill_value,
copy=False).__finalize__(self)
def __invert__(self):
result = self.values.__invert__()
return self._constructor(result, index=self.index,
sparse_index=self.sp_index,
fill_value=result.fill_value,
copy=False).__finalize__(self)
@property
def block(self):
warnings.warn("SparseSeries.block is deprecated.", FutureWarning,
stacklevel=2)
return self._data._block
@property
def fill_value(self):
return self.values.fill_value
@fill_value.setter
def fill_value(self, v):
self.values.fill_value = v
@property
def sp_index(self):
return self.values.sp_index
@property
def sp_values(self):
return self.values.sp_values
@property
def npoints(self):
return self.values.npoints
@classmethod
def from_array(cls, arr, index=None, name=None, copy=False,
fill_value=None, fastpath=False):
"""Construct SparseSeries from array.
.. deprecated:: 0.23.0
Use the pd.SparseSeries(..) constructor instead.
"""
warnings.warn("'from_array' is deprecated and will be removed in a "
"future version. Please use the pd.SparseSeries(..) "
"constructor instead.", FutureWarning, stacklevel=2)
return cls(arr, index=index, name=name, copy=copy,
fill_value=fill_value, fastpath=fastpath)
@property
def _constructor(self):
return SparseSeries
@property
def _constructor_expanddim(self):
from pandas.core.sparse.api import SparseDataFrame
return SparseDataFrame
@property
def kind(self):
if isinstance(self.sp_index, BlockIndex):
return 'block'
elif isinstance(self.sp_index, IntIndex):
return 'integer'
def as_sparse_array(self, kind=None, fill_value=None, copy=False):
""" return my self as a sparse array, do not copy by default """
if fill_value is None:
fill_value = self.fill_value
if kind is None:
kind = self.kind
return SparseArray(self.values, sparse_index=self.sp_index,
fill_value=fill_value, kind=kind, copy=copy)
def __unicode__(self):
# currently, unicode is same as repr...fixes infinite loop
series_rep = Series.__unicode__(self)
rep = '{series}\n{index!r}'.format(series=series_rep,
index=self.sp_index)
return rep
def _reduce(self, op, name, axis=0, skipna=True, numeric_only=None,
filter_type=None, **kwds):
""" perform a reduction operation """
return op(self.get_values(), skipna=skipna, **kwds)
def __getstate__(self):
# pickling
return dict(_typ=self._typ, _subtyp=self._subtyp, _data=self._data,
fill_value=self.fill_value, name=self.name)
def _unpickle_series_compat(self, state):
nd_state, own_state = state
# recreate the ndarray
data = np.empty(nd_state[1], dtype=nd_state[2])
np.ndarray.__setstate__(data, nd_state)
index, fill_value, sp_index = own_state[:3]
name = None
if len(own_state) > 3:
name = own_state[3]
# create a sparse array
if not isinstance(data, SparseArray):
data = SparseArray(data, sparse_index=sp_index,
fill_value=fill_value, copy=False)
# recreate
data = SingleBlockManager(data, index, fastpath=True)
generic.NDFrame.__init__(self, data)
self._set_axis(0, index)
self.name = name
def _set_subtyp(self, is_all_dates):
if is_all_dates:
object.__setattr__(self, '_subtyp', 'sparse_time_series')
else:
object.__setattr__(self, '_subtyp', 'sparse_series')
def _ixs(self, i, axis=0):
"""
Return the i-th value or values in the SparseSeries by location
Parameters
----------
i : int, slice, or sequence of integers
Returns
-------
value : scalar (int) or Series (slice, sequence)
"""
label = self.index[i]
if isinstance(label, Index):
return self.take(i, axis=axis)
else:
return self._get_val_at(i)
def _get_val_at(self, loc):
""" forward to the array """
return self.values._get_val_at(loc)
def __getitem__(self, key):
# TODO: Document difference from Series.__getitem__, deprecate,
# and remove!
if is_integer(key) and key not in self.index:
return self._get_val_at(key)
else:
return super(SparseSeries, self).__getitem__(key)
def _get_values(self, indexer):
try:
return self._constructor(self._data.get_slice(indexer),
fastpath=True).__finalize__(self)
except Exception:
return self[indexer]
def _set_with_engine(self, key, value):
return self._set_value(key, value)
def abs(self):
"""
Return an object with absolute value taken. Only applicable to objects
that are all numeric
Returns
-------
abs: same type as caller
"""
return self._constructor(np.abs(self.values),
index=self.index).__finalize__(self)
def get(self, label, default=None):
"""
Returns value occupying requested label, default to specified
missing value if not present. Analogous to dict.get
Parameters
----------
label : object
Label value looking for
default : object, optional
Value to return if label not in index
Returns
-------
y : scalar
"""
if label in self.index:
loc = self.index.get_loc(label)
return self._get_val_at(loc)
else:
return default
def get_value(self, label, takeable=False):
Loading ...