o 5c(5@s<ddlmZddlmZddlZddlmZddlm Z ddl m Z ddl Z ddlmZmZddlmZdd lmZmZmZmZdd lmZmZmZmZejejejej ej!ej"ej"d Z#ejej$dfej"ej%e fejej&dfejej&dfej ej&dfej'ej%d fej!ej(dfiZ)ej&d ej$dej%diZ*GdddeZ+dS)) 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 valuec@seZdZdZd/d0d d Zd1d d Zed1ddZed2ddZ d2ddZ eddZ eddZ ed1ddZ ed3ddZd1ddZd4d5d#d$Zd6d&d'Zd7d)d*Zd7d+d,Zd7d-d.Zd S)8 PandasColumna A column object, with only the methods and properties required by the interchange protocol defined. A column can contain one or more chunks. Each chunk can contain up to three buffers - a data buffer, a mask buffer (depending on null representation), and an offsets buffer (if variable-size binary; e.g., variable-length strings). Note: this Column object can only be produced by ``__dataframe__``, so doesn't need its own version or ``__column__`` protocol. Tcolumn pd.Series allow_copyboolreturnNonecCs0t|tjstdt|d||_||_dS)zu Note: doesn't deal with extension arrays yet, just assume a regular Series/ndarray for now. zColumns of type  not handled yetN) isinstancepdSeriesNotImplementedErrortype_col _allow_copy)selfrrr*T/var/www/html/gps/gps/lib/python3.10/site-packages/pandas/core/interchange/column.py__init__Hs  zPandasColumn.__init__intcCs|jjS)z2 Size of the column, in elements. )r'sizer)r*r*r+r.TszPandasColumn.sizecCdS)z7 Offset of first element. Always zero. rr*r/r*r*r+offsetZszPandasColumn.offsettuple[DtypeKind, int, str, str]cCsz|jj}t|r|jjj}||j\}}}}tj||tj fSt |r8t |jdkr4tj dt |tj fStd||S)Nstringz.Non-string object dtypes are not supported yet)r'dtypervaluescodes_dtype_from_pandasdtyper CATEGORICALrNATIVErrSTRINGrr%)r)r5r7_bitwidthc_arrow_dtype_f_strr*r*r+r5bs.   zPandasColumn.dtypecCs>t|jd}|durtd|d||jdt||jfS)z/ See `self.dtype` for details. N Data type z& not supported by interchange protocolr4) _NP_KINDSgetkind ValueErroritemsizer byteorder)r)r5rBr*r*r+r8sz$PandasColumn._dtype_from_pandasdtypecCs:|jdtjks td|jjjdtt |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) r5r r9 TypeErrorr'catorderedrr#r$rHr/r*r*r+describe_categoricalsz!PandasColumn.describe_categoricalcCs@|jd}z t|\}}W||fStytd|dw)Nrr?z not yet supported)r5_NULL_DESCRIPTIONKeyErrorr%)r)rBnullvaluer*r*r+ describe_nulls  zPandasColumn.describe_nullcCs|jS)zB Number of null elements. Should always be known. )r'isnasumitemr/r*r*r+ null_countszPandasColumn.null_countdict[str, pd.Index]cCs d|jjiS)z8 Store specific metadata of the column. z pandas.index)r'indexr/r*r*r+metadatas zPandasColumn.metadatacCr0)zE Return the number of chunks the column consists of. r*r/r*r*r+ num_chunksszPandasColumn.num_chunksNn_chunks int | Noneccsv|r6|dkr6t|j}||}||dkr|d7}td|||D]}t|jj||||jVq"dS|VdS)zy Return an iterator yielding the chunks. See `DataFrame.get_chunks` for details on ``n_chunks``. rYrN)lenr'rangerilocr()r)r[r.stepstartr*r*r+ get_chunkss    zPandasColumn.get_chunksr cCs\|ddd}z||d<Wn tyYnwz ||d<W|Sty-Y|Sw)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)datavalidityoffsetsrdre)_get_data_buffer_get_validity_bufferr_get_offsets_buffer)r)buffersr*r*r+ get_bufferss   zPandasColumn.get_bufferstuple[PandasBuffer, Any]cCs|jdtjtjtjtjtjfvr"t|j |j d}|j}||fS|jdtj kr@|jj j }t||j d}||j}||fS|jdtjkry|j }t}|D]}t|trb||jddqRttj|dd}tjdtjtjf}||fStd|jjd ) zZ Return the buffer containing the data and the buffer's associated dtype. r)rutf-8encodinguint8)r5r4r?r!)r5r INTUINTFLOATBOOLDATETIMEr r'to_numpyr(r9r6_codesr8r; bytearrayr"strextendencodenp frombufferrrr:r%)r)bufferr5r7bufrobjr*r*r+rfs<     zPandasColumn._get_data_bufferc Cs|j\}}|jdtjkrI|j}|dk}| }tjt|ftj d}t |D]\}}t |t r3|n|||<q(t |}tjdtjtjf} || fSz t|d} Wt| ty_tdw)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)rQr5r r;r'rur{zerosr]bool8 enumerater"rxr rsrrr:_NO_VALIDITY_BUFFERrNr%r) r)rOinvalidr~validmaskrrr}r5msgr*r*r+rg-s"   z!PandasColumn._get_validity_bufferc Cs|jdtjkrM|j}d}tjt|dftjd}t |D]\}}t |t r5|j dd}|t|7}|||d<q t |}tjdtjtjf}||fStd)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. rrYrrlrm@zJThis column has a fixed-length dtype so it does not have an offsets buffer)r5r r;r'rur{rr]int64rr"rxrzr rprINT64rr:r) r)r6ptrrervrr}r5r*r*r+rhSs&     z PandasColumn._get_offsets_buffer)T)rrrrrr )rr-)rr2)rrV)N)r[r\)rr )rrk)__name__ __module__ __qualname____doc__r,r.propertyr1rr5r8rLrQrUrXrZrbrjrfrgrhr*r*r*r+r<s.            % -&r), __future__rtypingrnumpyr{pandas._libs.librpandas._libs.tslibsrpandas.util._decoratorsrpandasr#pandas.api.typesrrpandas.core.interchange.bufferr *pandas.core.interchange.dataframe_protocolr r r r pandas.core.interchange.utilsrrrrrprqrrrsr;rtr@USE_NAN USE_SENTINEL NON_NULLABLEr9 USE_BYTEMASKrMrrr*r*r*r+s@