U
|
¬ý°d¶6 ã @ sD d dl mZ d dlmZ d dlZd dlmZ d dlm Z d dl
|
m Z d dl m Z d dlZd dlmZmZ d d lmZ d d
|
lmZmZmZmZ d d lmZm Z m Z ej ej ej ej!ej"ej#ej#d Z$ej ej%dfej#ej&e fej ej'dfej ej'dfej!ej'dfej(ej&d fej"ej)d fiZ*ej'dej%dej&diZ+G dd deZ,dS )é )Ú annotations)ÚAnyN)Ú infer_dtype)ÚiNaT)ÚNoBufferPresent)Úcache_readonly)Úis_categorical_dtypeÚis_string_dtype)Ú PandasBuffer)ÚColumnÚ ColumnBuffersÚColumnNullTypeÚ DtypeKind)Ú ArrowCTypesÚ
|
EndiannessÚdtype_to_arrow_c_fmt)ÚiÚuÚfÚbÚUÚMÚméÿÿÿÿzThis column is non-nullablez This column uses NaN as nullz!This column uses a sentinel valuec @ sö e Zd ZdZd.ddddddZd d
|
d d Zed d
|
d dZedd
|
ddZ dd
|
ddZ
|
edd Z edd Z ed d
|
ddZ edd
|
dd Zd d
|
d d Zd/d d!d"d#Zd$d
|
d%d&Zd'd
|
d(d)Zd'd
|
d*d+Zd'd
|
d,d-Zd S )0Ú PandasColumnaö
|
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.
|
Tz pd.SeriesÚboolÚNone)ÚcolumnÚ
|
allow_copyÚreturnc C s0 t |tjs tdt| d|| _|| _dS )zu
|
Note: doesn't deal with extension arrays yet, just assume a regular
|
Series/ndarray for now.
|
zColumns of type ú not handled yetN)Ú
|
isinstanceÚpdÚSeriesÚNotImplementedErrorÚtypeÚ_colÚ _allow_copy)Úselfr r © r) úUd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/core/interchange/column.pyÚ__init__H s zPandasColumn.__init__Úint)r c C s | j jS )z2
|
Size of the column, in elements.
|
)r& Úsize©r( r) r) r* r- T s zPandasColumn.sizec C s dS )z7
|
Offset of first element. Always zero.
|
r r) r. r) r) r* ÚoffsetZ s zPandasColumn.offsetz tuple[DtypeKind, int, str, str]c C s | j j}t|r>| j jj}| |j¡\}}}}tj||tj fS t
|
|rrt | j dkrhtj dt |tj fS tdn
|
| |¡S d S )NÚstringé z.Non-string object dtypes are not supported yet)r& Údtyper ÚvaluesÚcodesÚ_dtype_from_pandasdtyper Ú CATEGORICALr ÚNATIVEr r ÚSTRINGr r$ )r( r2 r4 Ú_ZbitwidthZc_arrow_dtype_f_strr) r) r* r2 b s.
|
|
ûüü
|
zPandasColumn.dtypec C s> t |jd¡}|dkr&td| d||jd t||jfS )z/
|
See `self.dtype` for details.
|
Nú
|
Data type z& not supported by interchange protocolr1 )Ú _NP_KINDSÚgetÚkindÚ
|
ValueErrorÚitemsizer Ú byteorder)r( r2 r= r) r) r* r5 s z$PandasColumn._dtype_from_pandasdtypec C s: | j d tjkstd| jjjdtt | jjj
|
¡dS )a:
|
If the dtype is categorical, there are two options:
|
- There are only values in the data buffer.
|
- There is a separate non-categorical Column encoding for categorical values.
|
|
Raises TypeError if the dtype is not categorical
|
|
Content of returned dict:
|
- "is_ordered" : bool, whether the ordering of dictionary indices is
|
semantically meaningful.
|
- "is_dictionary" : bool, whether a dictionary-style mapping of
|
categorical values to other objects exists
|
- "categories" : Column representing the (implicit) mapping of indices to
|
category values (e.g. an array of cat1, cat2, ...).
|
None if not a dictionary-style categorical.
|
r zCdescribe_categorical only works on a column with categorical dtype!T)Z
|
is_orderedZ is_dictionaryÚ
|
categories) r2 r r6 Ú TypeErrorr& ÚcatZorderedr r" r# rA r. r) r) r* Údescribe_categorical s ÿýz!PandasColumn.describe_categoricalc C sH | j d }zt| \}}W n$ tk
|
r> td| dY nX ||fS )Nr r: z not yet supported)r2 Ú_NULL_DESCRIPTIONÚKeyErrorr$ )r( r= ÚnullÚvaluer) r) r* Ú describe_null¬ s
|
zPandasColumn.describe_nullc C s | j ¡ ¡ ¡ S )zB
|
Number of null elements. Should always be known.
|
)r& ZisnaÚsumÚitemr. r) r) r* Ú
|
null_count¶ s zPandasColumn.null_countzdict[str, pd.Index]c C s d| j jiS )z8
|
Store specific metadata of the column.
|
z pandas.index)r& Úindexr. r) r) r* Úmetadata½ s zPandasColumn.metadatac C s dS )zE
|
Return the number of chunks the column consists of.
|
é r) r. r) r) r* Ú
|
num_chunksÄ s zPandasColumn.num_chunksNz
|
int | None)Ún_chunksc c sr |rh|dkrht | j}|| }|| dkr2|d7 }td|| |D ]"}t| jj|||
| jV qBn| V dS )zy
|
Return an iterator yielding the chunks.
|
See `DataFrame.get_chunks` for details on ``n_chunks``.
|
rO r N)Úlenr& Úranger Zilocr' )r( rQ r- ÚstepÚstartr) r) r* Ú
|
get_chunksÊ s
|
ÿ
|
zPandasColumn.get_chunksr c C s` | ¡ ddd}z| ¡ |d< W n tk
|
r4 Y nX z| ¡ |d< W n tk
|
rZ Y nX |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)ÚdataÚvalidityÚoffsetsrX rY )Ú_get_data_bufferÚ_get_validity_bufferr Ú_get_offsets_buffer)r( Úbuffersr) r) r* Ú get_buffersÛ s ýzPandasColumn.get_buffersztuple[PandasBuffer, Any]c C sü | j d tjtjtjtjtjfkr>t| j ¡ | j
|
d}| j }n¶| j d tj krt| jj j }t|| j
|
d}| |j ¡}n| j d tjkrà| j ¡ }t }|D ] }t|tr| |jdd¡ qttj|dd}tjdtjtjf}ntd| jj d ||fS )
|
zZ
|
Return the buffer containing the data and the buffer's associated dtype.
|
r )r úutf-8©ÚencodingZuint8)r2 r1 r: r )r2 r ÚINTÚUINTÚFLOATÚBOOLÚDATETIMEr
|
r& Úto_numpyr' r6 r3 Ú_codesr5 r8 Ú bytearrayr! ÚstrÚextendÚencodeÚnpZ
|
frombufferr r r7 r$ )r( Úbufferr2 r4 Úbufr Úobjr) r) r* rZ s6 û
|
|
|
üz PandasColumn._get_data_bufferc C sÎ | j \}}| jd tjkr| j ¡ }|dk}| }tjt|ftj d}t
|
|D ] \}}t |t rf|n|||< qPt |}tjdtjtjf} || fS zt| d}
|
W n tk
|
rÀ tdY nX t|
|
dS )zÒ
|
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.
|
r ©Úshaper2 r1 z! so does not have a separate maskzSee self.describe_nullN)rI r2 r r8 r& rg rm ÚzerosrR Zbool_Ú enumerater! rj r
|
re r r r7 Ú_NO_VALIDITY_BUFFERrF r$ r ) r( rG Úinvalidro ZvalidÚmaskr rp rn r2 Úmsgr) r) r* r[ - s
|
|
z!PandasColumn._get_validity_bufferc C s¤ | j d tjkr| j ¡ }d}tjt|d ftjd}t |D ]6\}}t
|
|t rj|j dd}|t|7 }|||d < q@t |}tjdtjtjf}ntd||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.
|
r rO rq r_ r` é@ zJThis column has a fixed-length dtype so it does not have an offsets buffer)r2 r r8 r& rg rm rs rR Úint64rt r! rj rl r
|
rb r ZINT64r r7 r ) r( r3 ÚptrrY r Úvr rn r2 r) r) r* r\ S s&
|
|
üÿz PandasColumn._get_offsets_buffer)T)N)Ú__name__Ú
|
__module__Ú __qualname__Ú__doc__r+ r- Úpropertyr/ r r2 r5 rD rI rL rN rP rV r^ rZ r[ r\ r) r) r) r* r < s,
|
|
%-&r )-Ú
|
__future__r Útypingr Únumpyrm Zpandas._libs.libr Zpandas._libs.tslibsr Z pandas.errorsr Zpandas.util._decoratorsr Zpandasr" Zpandas.api.typesr r Z pandas.core.interchange.bufferr
|
Z*pandas.core.interchange.dataframe_protocolr r r r Z pandas.core.interchange.utilsr r r rb rc rd re r8 rf r; ZUSE_NANZ USE_SENTINELZ NON_NULLABLEr6 Z USE_BYTEMASKrE ru r r) r) r) r* Ú<module> sT ù ö ý
|
