U
|
¬ý°dq/ ã @ sÄ d Z ddlmZ ddlmZ ddlZddlmZ ddl m
|
Z
|
ddl m Z m Z ddlmZ dd lmZ erxdd
|
lmZmZ G d d d Ze ed dddgddG dd dee ZG dd dee ZdS )zSparse accessoré )Ú annotations)Ú TYPE_CHECKINGN)Úimport_optional_dependency)Úfind_common_type)ÚPandasDelegateÚdelegate_names)Ú SparseArray)Ú SparseDtype)Ú DataFrameÚSeriesc @ s( e Zd ZdZd ddddZdd ZdS )
|
Ú BaseAccessorz5Can only use the '.sparse' accessor with Sparse data.NÚNone©Úreturnc C s || _ | |¡ d S ©N)Ú_parentÚ _validate©ÚselfÚdata© r úYd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/core/arrays/sparse/accessor.pyÚ__init__ s zBaseAccessor.__init__c C s t d S r )ÚNotImplementedErrorr r r r r ! s zBaseAccessor._validate)N)Ú__name__Ú
|
__module__Ú __qualname__Ú_validation_msgr r r r r r r s r ZnpointsÚdensityÚ
|
fill_valueÚ sp_valuesÚproperty)Útypc @ s\ e Zd ZdZdd Zdd Zdd Zedd d
|
d d d Zdd dddZ d
|
dddZ
|
dS )ÚSparseAccessorzH
|
Accessor for SparseSparse from other sparse matrix data types.
|
c C s t |jtst| jd S r )Ú
|
isinstanceÚdtyper ÚAttributeErrorr r r r r r - s zSparseAccessor._validatec O s t | jj|S r )Úgetattrr Úarray©r ÚnameÚargsÚkwargsr r r Ú_delegate_property_get1 s z%SparseAccessor._delegate_property_getc O s0 |dkr| j ||S |dkr(| j||S td S )NÚfrom_cooÚto_coo)r. r/ Ú
|
ValueErrorr) r r r Ú_delegate_method4 s
|
z SparseAccessor._delegate_methodFÚboolr )Ú dense_indexr c C s: ddl m} ddlm} |||d}||j|jdd}|S )am
|
Create a Series with sparse values from a scipy.sparse.coo_matrix.
|
|
Parameters
|
----------
|
A : scipy.sparse.coo_matrix
|
dense_index : bool, default False
|
If False (default), the index consists of only the
|
coords of the non-null entries of the original coo_matrix.
|
If True, the index consists of the full sorted
|
(row, col) coordinates of the coo_matrix.
|
|
Returns
|
-------
|
s : Series
|
A Series with sparse values.
|
|
Examples
|
--------
|
>>> from scipy import sparse
|
|
>>> A = sparse.coo_matrix(
|
... ([3.0, 1.0, 2.0], ([1, 0, 0], [0, 2, 3])), shape=(3, 4)
|
... )
|
>>> A
|
<3x4 sparse matrix of type '<class 'numpy.float64'>'
|
with 3 stored elements in COOrdinate format>
|
|
>>> A.todense()
|
matrix([[0., 0., 1., 2.],
|
[3., 0., 0., 0.],
|
[0., 0., 0., 0.]])
|
|
>>> ss = pd.Series.sparse.from_coo(A)
|
>>> ss
|
0 2 1.0
|
3 2.0
|
1 0 3.0
|
dtype: Sparse[float64, nan]
|
r ©r )Úcoo_to_sparse_series)r3 F)ÚindexÚcopy)Úpandasr Ú&pandas.core.arrays.sparse.scipy_sparser5 r( r6 )ÚclsÚAr3 r r5 Úresultr r r r. < s
|
* zSparseAccessor.from_coo©r ©é ©Ú sort_labelsc C s. ddl m} || j|||d\}}}|||fS )a
|
Create a scipy.sparse.coo_matrix from a Series with MultiIndex.
|
|
Use row_levels and column_levels to determine the row and column
|
coordinates respectively. row_levels and column_levels are the names
|
(labels) or numbers of the levels. {row_levels, column_levels} must be
|
a partition of the MultiIndex level names (or numbers).
|
|
Parameters
|
----------
|
row_levels : tuple/list
|
column_levels : tuple/list
|
sort_labels : bool, default False
|
Sort the row and column labels before forming the sparse matrix.
|
When `row_levels` and/or `column_levels` refer to a single level,
|
set to `True` for a faster execution.
|
|
Returns
|
-------
|
y : scipy.sparse.coo_matrix
|
rows : list (row labels)
|
columns : list (column labels)
|
|
Examples
|
--------
|
>>> s = pd.Series([3.0, np.nan, 1.0, 3.0, np.nan, np.nan])
|
>>> s.index = pd.MultiIndex.from_tuples(
|
... [
|
... (1, 2, "a", 0),
|
... (1, 2, "a", 1),
|
... (1, 1, "b", 0),
|
... (1, 1, "b", 1),
|
... (2, 1, "b", 0),
|
... (2, 1, "b", 1)
|
... ],
|
... names=["A", "B", "C", "D"],
|
... )
|
>>> s
|
A B C D
|
1 2 a 0 3.0
|
1 NaN
|
1 b 0 1.0
|
1 3.0
|
2 1 b 0 NaN
|
1 NaN
|
dtype: float64
|
|
>>> ss = s.astype("Sparse")
|
>>> ss
|
A B C D
|
1 2 a 0 3.0
|
1 NaN
|
1 b 0 1.0
|
1 3.0
|
2 1 b 0 NaN
|
1 NaN
|
dtype: Sparse[float64, nan]
|
|
>>> A, rows, columns = ss.sparse.to_coo(
|
... row_levels=["A", "B"], column_levels=["C", "D"], sort_labels=True
|
... )
|
>>> A
|
<3x4 sparse matrix of type '<class 'numpy.float64'>'
|
with 3 stored elements in COOrdinate format>
|
>>> A.todense()
|
matrix([[0., 0., 1., 3.],
|
[3., 0., 0., 0.],
|
[0., 0., 0., 0.]])
|
|
>>> rows
|
[(1, 1), (1, 2), (2, 1)]
|
>>> columns
|
[('a', 0), ('a', 1), ('b', 0), ('b', 1)]
|
r )Úsparse_series_to_coor@ )r9 rB r )r Z
|
row_levelsZ column_levelsrA rB r; ÚrowsÚcolumnsr r r r/ n s K ÿ zSparseAccessor.to_coor c C s, ddl m} || jj ¡ | jj| jjddS )aà
|
Convert a Series from sparse values to dense.
|
|
Returns
|
-------
|
Series:
|
A Series with the same values, stored as a dense array.
|
|
Examples
|
--------
|
>>> series = pd.Series(pd.arrays.SparseArray([0, 1, 0]))
|
>>> series
|
0 0
|
1 1
|
2 0
|
dtype: Sparse[int64, 0]
|
|
>>> series.sparse.to_dense()
|
0 0
|
1 1
|
2 0
|
dtype: int64
|
r r4 F)r6 r* r7 )r8 r r r( Úto_denser6 r* )r r r r r rE À s
|
üzSparseAccessor.to_denseN)F)r= r> F) r r r Ú__doc__r r- r1 Ú classmethodr. r/ rE r r r r r# % s 1Rr# c @ s` e Zd ZdZdd ZedddddZddd d
|
Zd d Ze d dddZ
|
e dd Z dS )ÚSparseFrameAccessorz-
|
DataFrame accessor for sparse data.
|
c C s& |j }tdd |D s"t| jd S )Nc s s | ]}t |tV qd S r )r$ r )Ú.0Útr r r Ú <genexpr>é s z0SparseFrameAccessor._validate.<locals>.<genexpr>)ÚdtypesÚallr& r )r r rL r r r r ç s z SparseFrameAccessor._validateNr
|
r c C sÊ ddl m} ddlm} | ¡ }| |||¡\}}|j\}}| ¡ |j}|j } |j
|
}
|
t |
|
j d} g } t |D ]H} t| | | | d }|||| dd}t |
|
| || ¡}| |¡ qn|j| ||ddS )aè
|
Create a new DataFrame from a scipy sparse matrix.
|
|
Parameters
|
----------
|
data : scipy.sparse.spmatrix
|
Must be convertible to csc format.
|
index, columns : Index, optional
|
Row and column labels to use for the resulting DataFrame.
|
Defaults to a RangeIndex.
|
|
Returns
|
-------
|
DataFrame
|
Each column of the DataFrame is stored as a
|
:class:`arrays.SparseArray`.
|
|
Examples
|
--------
|
>>> import scipy.sparse
|
>>> mat = scipy.sparse.eye(3)
|
>>> pd.DataFrame.sparse.from_spmatrix(mat)
|
0 1 2
|
0 1.0 0.0 0.0
|
1 0.0 1.0 0.0
|
2 0.0 0.0 1.0
|
r )ÚIntIndex©r
|
r? F)Zcheck_integrity)rD r6 Zverify_integrity)Zpandas._libs.sparserN r8 r
|
ZtocscÚ _prep_indexÚshapeZ sort_indicesÚindicesÚindptrr r r% ÚrangeÚslicer Z _simple_newÚappendZ _from_arrays)r: r r6 rD rN r
|
Zn_rowsZ n_columnsrR rS Z
|
array_datar% ZarraysÚiÚslÚidxZarrr r r Ú from_spmatrixì s,
|
ÿz!SparseFrameAccessor.from_spmatrixc C s6 ddl m} dd | j ¡ D }||| jj| jjdS )ay
|
Convert a DataFrame with sparse values to dense.
|
|
Returns
|
-------
|
DataFrame
|
A DataFrame with the same values stored as dense arrays.
|
|
Examples
|
--------
|
>>> df = pd.DataFrame({"A": pd.arrays.SparseArray([0, 1, 0])})
|
>>> df.sparse.to_dense()
|
A
|
0 0
|
1 1
|
2 0
|
r rO c S s i | ]\}}||j ¡ qS r )r( rE )rI ÚkÚvr r r Ú
|
<dictcomp>7 s z0SparseFrameAccessor.to_dense.<locals>.<dictcomp>)r6 rD )r8 r
|
r Úitemsr6 rD )r r
|
r r r r rE # s z SparseFrameAccessor.to_densec C sì t d ddlm} t| jj ¡ }t|tr4|j }g g g }}}t
|
| j ¡ D ]b\}\}}|j } | j dkrvtd| jj}
|
| t |t|
|
¡¡ | |
|
¡ | | jj|dd¡ qRt |¡}t |¡}t |¡}||||ff| jjdS )aÍ
|
Return the contents of the frame as a sparse SciPy COO matrix.
|
|
Returns
|
-------
|
scipy.sparse.spmatrix
|
If the caller is heterogeneous and contains booleans or objects,
|
the result will be of dtype=object. See Notes.
|
|
Notes
|
-----
|
The dtype will be the lowest-common-denominator type (implicit
|
upcasting); that is to say if the dtypes (even of numeric types)
|
are mixed, the one that accommodates all will be chosen.
|
|
e.g. If the dtypes are float16 and float32, dtype will be upcast to
|
float32. By numpy.find_common_type convention, mixing int64 and
|
and uint64 will result in a float64 dtype.
|
Zscipyr )Ú
|
coo_matrixz2fill value must be 0 when converting to COO matrixF)r7 )rQ )r Z scipy.sparser_ r r rL Zto_listr$ r ÚsubtypeÚ enumerater^ r( r r0 Zsp_indexrR rV ÚnpÚrepeatÚlenr ZastypeZ concatenaterQ ) r r_ r% ÚcolsrC r ÚcolÚ_ZserZsp_arrÚrowr r r r/ : s$
|
|
|
|
|
|
zSparseFrameAccessor.to_cooÚfloatc C s t dd | j ¡ D ¡}|S )zJ
|
Ratio of non-sparse points to total (dense) data points.
|
c S s g | ]\}}|j jqS r )r( r )rI rg Úcolumnr r r Ú
|
<listcomp>j s z/SparseFrameAccessor.density.<locals>.<listcomp>)rb Zmeanr r^ )r Útmpr r r r e s zSparseFrameAccessor.densityc C s ddl m}m} | j\}}|d kr,||}n||}|d krF||}n||}t||krrtdt| d| t||krtdt| d| ||fS )Nr )Ú default_indexÚ ensure_indexzColumn length mismatch: z vs. zIndex length mismatch: )Zpandas.core.indexes.apirm rn rQ rd r0 )r r6 rD rm rn ÚNÚKr r r rP m s
|
|
|
z SparseFrameAccessor._prep_index)NN) r r r rF r rG rZ rE r/ r! r Ú staticmethodrP r r r r rH â s 6+rH )rF Ú
|
__future__r Útypingr Únumpyrb Zpandas.compat._optionalr Zpandas.core.dtypes.castr Zpandas.core.accessorr r Z pandas.core.arrays.sparse.arrayr Z pandas.core.arrays.sparse.dtyper r8 r
|
r r r# rH r r r r Ú<module> s&
|
ÿ ;
|
