`Vg(5ddlmZddlmZddlZddlmZddlm Z ddl m Z ddl Z ddlmZmZddlmZdd lmZmZmZmZdd lmZmZmZmZej:ej<ej>ej@ejBejDejDd Z#ej>ejHdfejDejJe fej:ejLdfej<ejLdfej@ejLdfejNejJd fejBejPdfiZ)ejLd ejHdejJdiZ*GddeZ+y)) annotations)AnyN) infer_dtype)iNaT)cache_readonly)is_categorical_dtypeis_string_dtype) PandasBuffer)Column ColumnBuffersColumnNullType DtypeKind) ArrowCTypes EndiannessNoBufferPresentdtype_to_arrow_c_fmt)iufbUMmzThis column is non-nullablezThis column uses NaN as nullz!This column uses a sentinel valueceZdZdZdddZddZeddZeddZ ddZ edZ edZ edd Z edd Zdd Zddd ZddZ ddZddZddZy ) 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. ct|tjstdt |d||_||_y)zu Note: doesn't deal with extension arrays yet, just assume a regular Series/ndarray for now. zColumns of type  not handled yetN) isinstancepdSeriesNotImplementedErrortype_col _allow_copy)selfcolumn allow_copys _/var/www/html/hubwallet-dev/venv/lib/python3.12/site-packages/pandas/core/interchange/column.py__init__zPandasColumn.__init__Hs= &")),%(8fFV&WX X %c.|jjS)z2 Size of the column, in elements. )r$sizer&s r)r-zPandasColumn.sizeTsyy~~r+cy)z7 Offset of first element. Always zero. rr.s r)offsetzPandasColumn.offsetZs r+c|jj}t|rb|jjj}|j |j\}}}}t j||tjfSt|rNt|jdk(r+t jdt|tjfStd|j |S)Nstringz.Non-string object dtypes are not supported yet)r$dtypervaluescodes_dtype_from_pandasdtyper CATEGORICALrNATIVEr rSTRINGrr")r&r5r7_bitwidthc_arrow_dtype_f_strs r)r5zPandasColumn.dtypebs   &II$$**E ,,U[[9  #%%#!!   U #499%1$$(/%%  &&VW W//6 6r+ctj|jd}|td|d||jdzt ||j fS)z/ See `self.dtype` for details. N Data type z& not supported by interchange protocolr4) _NP_KINDSgetkind ValueErroritemsizer byteorder)r&r5rCs r)r8z$PandasColumn._dtype_from_pandasdtypesT}}UZZ. <z%0VWX XU^^a')=e)DeooUUr+c|jdtjk(s td|jj j dttj|jj jdS)a: If the dtype is categorical, there are two options: - There are only values in the data buffer. - There is a separate non-categorical Column encoding for categorical values. Raises TypeError if the dtype is not categorical Content of returned dict: - "is_ordered" : bool, whether the ordering of dictionary indices is semantically meaningful. - "is_dictionary" : bool, whether a dictionary-style mapping of categorical values to other objects exists - "categories" : Column representing the (implicit) mapping of indices to category values (e.g. an array of cat1, cat2, ...). None if not a dictionary-style categorical. rzCdescribe_categorical only works on a column with categorical dtype!T) is_ordered is_dictionary categories) r5rr9 TypeErrorr$catorderedrr r!rJr.s r)describe_categoricalz!PandasColumn.describe_categoricalsi$zz!} 5 55U  ))--//!&ryy1I1I'JK  r+cz|jd} t|\}}||fS#t$rtd|dwxYw)Nrr@z not yet supported)r5_NULL_DESCRIPTIONKeyErrorr")r&rCnullvalues r) describe_nullzPandasColumn.describe_nullsWzz!} M+D1KD%U{ M% 4&8J&KL L Ms !:cn|jjjjS)zB Number of null elements. Should always be known. )r$isnasumitemr.s r) null_countzPandasColumn.null_counts' yy~~##%**,,r+c2d|jjiS)z8 Store specific metadata of the column. z pandas.index)r$indexr.s r)metadatazPandasColumn.metadatas  00r+cy)zE Return the number of chunks the column consists of. r0r.s r) num_chunkszPandasColumn.num_chunkssr+Nc#K|rt|dkDrot|j}||z}||zdk7r|dz }td||z|D]4}t|jj|||z|j 6y|yw)zy Return an iterator yielding the chunks. See `DataFrame.get_chunks` for details on ``n_chunks``. r^rN)lenr$rangerilocr%)r&n_chunksr-stepstarts r) get_chunkszPandasColumn.get_chunkss 1 tyy>D8#Dh!# q$/48 "IINN554<8$:J:J  JsAc|jddd} |j|d< |j|d<|S#t$rY!wxYw#t$rY|SwxYw)a` Return a dictionary containing the underlying buffers. The returned dictionary has the following contents: - "data": a two-element tuple whose first element is a buffer containing the data and whose second element is the data buffer's associated dtype. - "validity": a two-element tuple whose first element is a buffer containing mask values indicating missing data and whose second element is the mask value buffer's associated dtype. None if the null representation is not a bit or byte mask. - "offsets": a two-element tuple whose first element is a buffer containing the offset values for variable-size binary data (e.g., variable-length strings) and whose second element is the offsets buffer's associated dtype. None if the data buffer does not have an associated offsets buffer. N)datavalidityoffsetsrjrk)_get_data_buffer_get_validity_bufferr_get_offsets_buffer)r&bufferss r) get_bufferszPandasColumn.get_bufferss())+"   "&";";"=GJ  !%!9!9!;GI        s ?A A  A  AAc |jdtjtjtjtj tj fvr?t|jj|j}|j}||fS|jdtjk(rV|jjj}t||j}|j|j}||fS|jdtjk(r|jj}t!}|D]4}t#|t$s|j'|j)d6tt+j,|d}tjdt.jt0j2f}||fSt5d|jjd ) zZ Return the buffer containing the data and the buffer's associated dtype. r)r(utf-8encodinguint8)r5r4r@r)r5rINTUINTFLOATBOOLDATETIMEr r$to_numpyr%r9r6_codesr8r; bytearrayrstrextendencodenp frombufferrrr:r")r&bufferr5r7bufrobjs r)rlzPandasColumn._get_data_buffers ::a= MM NN OO NN      "$))"4"4"64CSCSTFJJE:u}9ZZ]i33 3II$$++E!%D4D4DEF00=E2u}1ZZ]i.. .))$$&C A ;c3'HHSZZZ9: ; ""--"ABF  ""!! Eu}& 499??2CCS&TU Ur+c4|j\}}|jdtjk(r|jj }|dk(}| }t jt|ft j}t|D]\}}t|tr|n|||<t|}tjdtjt j"f} || fS t$|dz} t+| #t&$r t)dwxYw)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. rshaper5r4z! so does not have a separate maskzSee self.describe_null)rTr5rr;r$r{rzerosrabool_ enumeraterr~r ryrrr:_NO_VALIDITY_BUFFERrQr"r) r&rRinvalidrvalidmaskrrrr5msgs r)rmz!PandasColumn._get_validity_buffer-s ** g ::a=I,, ,))$$&CqLEiG883s8+RXX>D#C. E3#-c3#7%WQ E "$'F^^Q (8(8*:K:KLE5=  @%d+.QQC c""  @%&>? ? @s + DDc|jdtjk(r|jj }d}t j t|dzft j}t|D]=\}}t|tr |jd}|t|z }|||dz<?t|}tjdtj t"j$f}||fSt'd)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. rr^rrrrs@zJThis column has a fixed-length dtype so it does not have an offsets buffer)r5rr;r$r{rrraint64rrr~rr rvrINT64rr:r) r&r6ptrrkrvrrr5s r)rnz PandasColumn._get_offsets_bufferSs ::a=I,, ,YY'')FChhc&kAo%7rxxHG!&) %1a%'2A3q6MC!$A %"'*F !!!! Eu} "5 r+)T)r'z pd.Seriesr(boolreturnNone)rint)rztuple[DtypeKind, int, str, str])rzdict[str, pd.Index])N)rdz int | None)rr )rztuple[PandasBuffer, Any])__name__ __module__ __qualname____doc__r*r-propertyr1rr5r8rNrTrYr\r_rgrprlrmrnr0r+r)rr<s  & 77: V  8-- 11  "#J+ !+Z$#L&r+r), __future__rtypingrnumpyrpandas._libs.librpandas._libs.tslibsrpandas.util._decoratorsrpandasr pandas.api.typesrr pandas.core.interchange.bufferr *pandas.core.interchange.dataframe_protocolr r r rpandas.core.interchange.utilsrrrrrvrwrxryr;rzrAUSE_NAN USE_SENTINEL NON_NULLABLEr9 USE_BYTEMASKrPrrr0r+r)rsR"($28                OOn,,d3 44d; MMN//6 NN^00$7 NN^00$7N77< ~22A6 !>:!D}6}r+