iDBddlmZddlmZmZddlZddlmZddl m Z ddl m Z ddl mZddlmZddlZdd lmZmZdd lmZdd lmZmZdd lmZmZmZmZdd lm Z m!Z!m"Z"erddlm#Z#ej$ej%ej&ej'ej(ej)ej)dZ*ej&ej+dfej)ej,e fej$ej-dfej%ej-dfej'ej-dfej.ej,dfej(ej/dfiZ0ej-dej+dej,diZ1GddeZ2dS)) annotations) TYPE_CHECKINGAnyN) infer_dtype)iNaT)NoBufferPresent)cache_readonly)BaseMaskedDtype) ArrowDtypeDatetimeTZDtype)is_string_dtype) PandasBufferPandasBufferPyarrow)Column ColumnBuffersColumnNullType DtypeKind) ArrowCTypes Endiannessdtype_to_arrow_c_fmt)Buffer)iufbUMmzThis column is non-nullablezThis column uses NaN as nullz!This column uses a sentinel valueceZdZdZd"d#d Zd$d Zed$d Zed%dZ d%dZ edZ edZ ed$dZ ed&dZd$dZd'd(dZd)dZd*dZd+dZd,d!ZdS)- PandasColumna A column object, with only the methods and properties required by the interchange protocol defined. A column can contain one or more chunks. Each chunk can contain up to three buffers - a data buffer, a mask buffer (depending on null representation), and an offsets buffer (if variable-size binary; e.g., variable-length strings). Note: this Column object can only be produced by ``__dataframe__``, so doesn't need its own version or ``__column__`` protocol. Tcolumn pd.Series allow_copyboolreturnNonect|tjrtd|jdt|tjs t dt|d||_||_ dS)zu Note: doesn't deal with extension arrays yet, just assume a regular Series/ndarray for now. zExpected a Series, got a DataFrame. This likely happened because you called __dataframe__ on a DataFrame which, after converting column names to string, resulted in duplicated names: zD. Please rename these columns before using the interchange protocol.zColumns of type  not handled yetN) isinstancepd DataFrame TypeErrorcolumnsSeriesNotImplementedErrortype_col _allow_copy)selfr"r$s V/srv/django_bis/venv311/lib/python3.11/site-packages/pandas/core/interchange/column.py__init__zPandasColumn.__init__Ts fbl + + 2!.222 &"),, Y%&Wf&W&W&WXX X %intc|jjS)z2 Size of the column, in elements. )r2sizer4s r5r:zPandasColumn.sizehsy~r7cdS)z7 Offset of first element. Always zero. rr;s r5offsetzPandasColumn.offsetns qr7tuple[DtypeKind, int, str, str]c|jj}t|tjrJ|jjj}||j\}}}}tj ||tj fSt|rLt|jdvr'tjdt|tj fSt!d||S)N)stringemptyz.Non-string object dtypes are not supported yet)r2dtyper*r+CategoricalDtypevaluescodes_dtype_from_pandasdtyper CATEGORICALrNATIVEr rSTRINGrr0)r4rDrG_bitwidthc_arrow_dtype_f_strs r5rDzPandasColumn.dtypevs  eR0 1 1 7I$*E ,,U[99  #%#!   U # # 749%%)<<<$(//%  &&VWW W//66 6r7ct|jd}|td|dt |t r |jj}nKt |tr |j j}n)t |tr |jj}n|j}|dkr||j tj |fS||j dzt||fS)z/ See `self.dtype` for details. N Data type z& not supported by interchange protocolz bool[pyarrow]rC) _NP_KINDSgetkind ValueErrorr*r numpy_dtype byteorderr baser itemsizerBOOLr)r4rDrSrVs r5rHz$PandasColumn._dtype_from_pandasdtypes}}UZ.. <W%WWWXX X eZ ( ( ()3II  / / ( ,II  / / ()3III O # #   U^a')=e)D)DiOOr7c|jdtjkstd|jjjdttj |jjj dS)a: If the dtype is categorical, there are two options: - There are only values in the data buffer. - There is a separate non-categorical Column encoding for categorical values. Raises TypeError if the dtype is not categorical Content of returned dict: - "is_ordered" : bool, whether the ordering of dictionary indices is semantically meaningful. - "is_dictionary" : bool, whether a dictionary-style mapping of categorical values to other objects exists - "categories" : Column representing the (implicit) mapping of indices to category values (e.g. an array of cat1, cat2, ...). None if not a dictionary-style categorical. rzCdescribe_categorical only works on a column with categorical dtype!T) is_ordered is_dictionary categories) rDrrIr-r2catorderedr!r+r/r]r;s r5describe_categoricalz!PandasColumn.describe_categoricalsg$z!} 555U  )-/!&ry1I'J'JKK   r7ct|jjtrtj}d}||fSt|jjt rP|jjjj d dtj dfStj dfS|jd} t|\}}n!#t$rtd|dwxYw||fS)NrrPz not yet supported)r*r2rDr r USE_BYTEMASKr array _pa_arraychunksbuffers NON_NULLABLE USE_BITMASK_NULL_DESCRIPTIONKeyErrorr0)r4column_null_dtype null_valuerSnullvalues r5 describe_nullzPandasColumn.describe_nulls dio 7 7 1 . ; J$j0 0 dioz 2 2 1y(/2::<>D8#Dh!## q$/488  "IN554<#78$:J   JJJJJr7rc|ddd} ||d<n#t$rYnwxYw ||d<n#t$rYnwxYw|S)a` Return a dictionary containing the underlying buffers. The returned dictionary has the following contents: - "data": a two-element tuple whose first element is a buffer containing the data and whose second element is the data buffer's associated dtype. - "validity": a two-element tuple whose first element is a buffer containing mask values indicating missing data and whose second element is the mask value buffer's associated dtype. None if the null representation is not a bit or byte mask. - "offsets": a two-element tuple whose first element is a buffer containing the offset values for variable-size binary data (e.g., variable-length strings) and whose second element is the offsets buffer's associated dtype. None if the data buffer does not have an associated offsets buffer. N)datavalidityoffsetsrr)_get_data_buffer_get_validity_bufferr_get_offsets_buffer)r4rgs r5 get_bufferszPandasColumn.get_buffers s())++" "   "&";";"="=GJ      D  !%!9!9!;!;GI      D s2 ??A A('A(.tuple[Buffer, tuple[DtypeKind, int, str, str]]cJ|jdtjtjtjtjtjfvr/|j}|jdtjkrPt|jddkr2|jj d }n|jj }t|jjtr|j}nrt|jjt rL|jjd}t'|dt|}||fS|j}t-||j}n*|jdtjkrB|jjj}t-||j}||j}n|jdtjkr|j }t;}|D]@}t|t<r)|| d At-tCj"|d }|j}ntGd |jjd ||fS)zZ Return the buffer containing the data and the buffer's associated dtype. rNrblength)r$utf-8encodinguint8)rDrPr))$rDrINTUINTFLOATrYDATETIMErr2dt tz_convertto_numpyrdr*r _datar rerfrrg_ndarrayrr3rIrF_codesrHrK bytearraystrextendencodenp frombufferr0) r4rDnp_arrarrbufferrGbufrobjs r5rzPandasColumn._get_data_buffer0sH :a= M N O N      JEz!} 222s4:a=7I7IA7M7M0066??AAiodio?? * YFF << *-.q1C0 a("3xxF"5=( \F!&T5EFFFFF Z]i3 3 3I$+E!%D4DEEEF00==EE Z]i. . .)$$&&C A ; ;c3'';HHSZZZ99:::""-"A"A"ABBF JEE%&T49?&T&T&TUU Uu}r7tuple[Buffer, Any] | Nonecp|j\}}t|jjtr|jjjjd}tj dtj tj f}| ddSt| dt|}||fSt|jjt rH|jjj}t%|}tj dtj tj f}||fS|jdtjkr|j}|dk}| }t+jt|ft*j}t1|D]!\} } t| t2r|n||| <"t%|}tj dtj tj f}||fS t4|d} n#t6$rt9dwxYwt;| ) z Return the buffer containing the mask values indicating missing data and the buffer's associated dtype. Raises NoBufferPresent if null representation is not a bit or byte mask. rrbNrrCshaperDz! so does not have a separate maskzSee self.describe_null)rpr*r2rDr rdrerfrrYrrrJrgrrr _maskrrKrrzerosbool_ enumerater_NO_VALIDITY_BUFFERrkr0r) r4rninvalidrrDrmaskrvalidrrmsgs r5rz!PandasColumn._get_validity_bufferns * g dioz 2 2 !)/+215C^Q (8*:KLE{{}}Q't( a 3xxF5= dio 7 7 !9?(D!$''F^Q (8*:KLE5= :a=I, , ,)$$&&CqLEiG83s88+RX>>>D#C.. E E3#-c3#7#7D%%WQ"$''F^Q (8*:KLE5=  @(.QQQCC @ @ @%&>?? ? @c"""s ;H H&tuple[PandasBuffer, Any]c|jdtjkr|j}d}t jt|dzft j}t|D]J\}}t|tr(| d}|t|z }|||dz<Kt|}tjdtjt"jf}nt'd||fS)a Return the buffer containing the offset values for variable-size binary data (e.g., variable-length strings) and the buffer's associated dtype. Raises NoBufferPresent if the data buffer does not have an associated offsets buffer. rrbrrr@zJThis column has a fixed-length dtype so it does not have an offsets buffer)rDrrKr2rrrrint64rr*rrrrrINT64rrJr) r4rFptrrrvrrrDs r5rz PandasColumn._get_offsets_buffers :a=I, , ,Y''))FChc&kkAo%7rxHHHG!&)) % %1a%%"'22A3q66MC!$A"'**F !! EE"5  u}r7)T)r"r#r$r%r&r')r&r8)r&r?)r&rv)N)r|r})r&r)r&r)r&r)r&r)__name__ __module__ __qualname____doc__r6r:propertyr>r rDrHr`rpruryr{rrrrrr=r7r5r!r!Hs  &&&&&( X777^7:PPPPB  X 8X&---^- 111X1  "####J<<<<|7#7#7#7#r&&&&&&r7r!)3 __future__rtypingrrnumpyrpandas._libs.librpandas._libs.tslibsr pandas.errorsrpandas.util._decoratorsr pandas.core.dtypes.dtypesr pandasr+r r pandas.api.typesr pandas.core.interchange.bufferrr*pandas.core.interchange.dataframe_protocolrrrrpandas.core.interchange.utilsrrrrrrrrYrKrrQUSE_NAN USE_SENTINELrhrIrcrjrr!r=r7r5rs"""""" (((((($$$$$$))))))222222555555-,,,,,  BAAAAAA             On,d3 4d; MN/6 N^0$7 N^0$7N7< ~2A6 !>:!DEEEEE6EEEEEr7