OwgD*ddlmZddlmZmZddlZddlmZddl m Z ddl m Z ddl mZddlmZddlZdd lmZmZdd lmZdd lmZmZdd lmZmZmZmZdd lm Z m!Z!m"Z"erddlm#Z#ejHejJejLejNejPejRejRdZ*ejLejVdfejRejXe fejHejZdfejJejZdfejNejZdfej\ejXdfejPej^dfiZ0ejZdejVdejXdiZ1GddeZ2y)) 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 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|tjrtd|jdt|tj st dt|d||_||_ y)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)selfcolumn allow_copys U/var/www/horilla/myenv/lib/python3.12/site-packages/pandas/core/interchange/column.py__init__zPandasColumn.__init__Tsu fbll +!..)*22 &")),%(8fFV&WX X %c.|jjS)z2 Size of the column, in elements. )r,sizer.s r1r5zPandasColumn.sizehsyy~~r3cy)z7 Offset of first element. Always zero. rr6s r1offsetzPandasColumn.offsetns r3c|jj}t|tjrb|jj j }|j|j\}}}}tj||tjfSt|rMt|jdvr+tjdt|tjfSt!d|j|S)N)stringemptyz.Non-string object dtypes are not supported yet)r,dtyper$r%CategoricalDtypevaluescodes_dtype_from_pandasdtyper CATEGORICALrNATIVEr rSTRINGrr*)r.r>rA_bitwidthc_arrow_dtype_f_strs r1r>zPandasColumn.dtypevs  eR00 1II$$**E ,,U[[9  #%%#!!   U #499%)<<$$(/%%  &&VW W//6 6r3ctj|jd}|td|dt |t r|j j}nZt |tr|jj}n3t |tr|j j}n |j}|dk(r||jtj|fS||jdzt||fS)z/ See `self.dtype` for details. N Data type z& not supported by interchange protocolz bool[pyarrow]r=) _NP_KINDSgetkind ValueErrorr$r numpy_dtype byteorderr baser itemsizerBOOLr)r.r>rMrPs r1rBz$PandasColumn._dtype_from_pandasdtypes}}UZZ. <z%0VWX X eZ ())33I  / ,,I  /))33II O #    U^^a')=e)DiOOr3c|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) r>rrCr'r,catorderedr!r%r)rWr6s r1describe_categoricalz!PandasColumn.describe_categoricalsi$zz!} 5 55U  ))--//!&ryy1I1I'JK  r3ct|jjtrtj }d}||fSt|jjt rb|jjjjdjdtjdfStjdfS|jd} t|\}}||fS#t$rtd|dwxYw)NrrJz not yet supported)r$r,r>r r USE_BYTEMASKr array _pa_arraychunksbuffers NON_NULLABLE USE_BITMASK_NULL_DESCRIPTIONKeyErrorr*)r.column_null_dtype null_valuerMnullvalues r1 describe_nullzPandasColumn.describe_nulls diioo 7 . ; ; J$j0 0 diiooz 2yy((//2::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)datavalidityoffsetsrr)_get_data_buffer_get_validity_bufferr_get_offsets_buffer)r.ras r1 get_bufferszPandasColumn.get_buffers s())+"   "&";";"=GJ  !%!9!9!;GI        s ?A A  A  AAc|jdtjtjtjtj tj fvrQ|j}|jdtj k(rOt|jddkDr4|jjjdj}n|jj}t|jjtr |j}ntt|jjt rD|j"j$d}t'|j)dt|}||fS|j*}t-||j.}||fS|jdtj0k(rV|jj2j4}t-||j.}|j7|j}||fS|jdtj8k(r|jj}t;}|D]4}t|t<s|j?|jAd 6t-tCjD|d }|j}||fStGd |jjd )zZ Return the buffer containing the data and the buffer's associated dtype. rNr\length)r0utf-8encodinguint8)r>rJr#)$r>rINTUINTFLOATrSDATETIMErvr,dt tz_convertto_numpyr^r$r _datar r_r`rra_ndarrayrr-rCr@_codesrBrE bytearraystrextendencodenp frombufferr*) r.r>np_arrarrbufferrAbufrobjs r1rzPandasColumn._get_data_buffer0sF ::a= MM NN OO NN      JJEzz!} 2 22s4::a=7IA7M006??Aiioodiioo? YYF <--..q1C0 a("3xF"5=( \\F!&T5E5EFF4u}3ZZ]i33 3II$$++E!%D4D4DEF00=E,u}+ZZ]i.. .))$$&C A ;c3'HHSZZZ9: ; ""--"ABF JJEu}& 499??2CCS&TU Ur3c|j\}}t|jjtr|jj j jd}tjdtjtjf}|jdyt|jdt|}||fSt|jjt r_|jj j"}t%|}tjdtjtjf}||fS|jdtj&k(r|jj)}|dk(}| }t+j,t|ft*j.}t1|D]\} } t| t2r|n||| <t%|}tjdtjtjf}||fS t4|d} t;| #t6$r t9dwxYw) z Return the buffer containing the mask values indicating missing data and the buffer's associated dtype. Raises NoBufferPresent if null representation is not a bit or byte mask. rr\Nrr=shaper>z! so does not have a separate maskzSee self.describe_null)rjr$r,r>r r^r_r`rrSrrrDrarrvr _maskrrErrzerosbool_ enumerater_NO_VALIDITY_BUFFERrer*r) r.rhinvalidrr>rmaskrvalidrrmsgs r1rz!PandasColumn._get_validity_bufferns ** g diiooz 2))//++2215C^^Q (8(8*:K:KLE{{}Q'( a 3xF5= diioo 799??((D!$'F^^Q (8(8*:K:KLE5= ::a=I,, ,))$$&CqLEiG883s8+RXX>D#C. E3#-c3#7%WQ E "$'F^^Q (8(8*:K:KLE5=  @(.//PQC c""  @%&>? ? @s . IIc|jdtjk(r|jj }d}t j t|dzft j}t|D]=\}}t|tr |jd}|t|z }|||dz<?t|}tjdtj t"j$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\rrr@zJThis column has a fixed-length dtype so it does not have an offsets buffer)r>rrEr,rrrrvint64rr$rrrrrINT64rrDr) r.r@ptrrrvrrr>s r1rz PandasColumn._get_offsets_buffers ::a=I,, ,YY'')FChhc&kAo%7rxxHG!&) %1a%'2A3q6MC!$A %"'*F !!!! Eu} "5 r3)T)r/z pd.Seriesr0boolreturnNone)rint)rztuple[DtypeKind, int, str, str])rzdict[str, pd.Index])N)ryz int | None)rr)rz.tuple[Buffer, tuple[DtypeKind, int, str, str]])rztuple[Buffer, Any] | None)rztuple[PandasBuffer, Any])__name__ __module__ __qualname____doc__r2r5propertyr9r r>rBrZrjrorrrtr|rrrrr8r3r1r!r!Hs &( 77:PB  8&-- 11  "#J< 7<|7#r&r3r!)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.utilsrrrrrrrrSrErrKUSE_NAN USE_SENTINELrbrCr]rdrr!r8r3r1rsi" ($)25-  A               OOn,,d3 44d; MMN//6 NN^00$7 NN^00$7N77< ~22A6 !>:!DE6Er3