Ë
|
nñúh?6 ã óØ d Z ddlmZ ddlmZmZ ddlmZmZ ddl m
|
Z
|
m Z ddl m Z e
|
sddlZddlmZ ddlmZ erdd lmZ dd
|
lmZmZ G d d e¬ « Z G d de« Z G d de« Z y)z Accessors for arrow-backed data.é )Ú annotations)ÚABCMetaÚabstractmethod)Ú TYPE_CHECKINGÚcast)Úpa_version_under10p1Úpa_version_under11p0)Ú is_list_likeN)Ú
|
ArrowDtype)ÚIterator)Ú DataFrameÚSeriesc óF e Zd Zedd« Zedd« Zd Zed « Zy)Ú ArrowAccessorc óB || _ || _ | j |« y ©N)Ú_dataÚ_validation_msgÚ _validate)ÚselfÚdataÚvalidation_msgs úUH:\Change_password\venv_build\Lib\site-packages\pandas/core/arrays/arrow/accessors.pyÚ__init__zArrowAccessor.__init__% s à
|
Ø -Ô Ø tÕ ó c ó y r © ©r Ú pyarrow_dtypes r Ú_is_valid_pyarrow_dtypez%ArrowAccessor._is_valid_pyarrow_dtype+ s à r c ó |j }t st |t « s%t | j
|
j |¬« « | j |j « s%t | j
|
j |¬« « y )N©Údtype) r# r Ú
|
isinstancer ÚAttributeErrorr Úformatr r )r r r# s r r zArrowAccessor._validate/ so Ø
|
|
Ý ¤z°%¼Ô'Dä ×!5Ñ!5×!<Ñ!<À5Ð!<Ó!IÓJÐ Jà×+Ñ+¨E×,?Ñ,?Ô@ä ×!5Ñ!5×!<Ñ!<À5Ð!<Ó!IÓJÐ Jð Ar c óB | j j j S r )r ÚarrayÚ _pa_array©r s r r) zArrowAccessor._pa_array9 s àzz× Ñ ×)Ñ)Ð)r N)r ÚstrÚreturnÚNone©r, Úbool) Ú__name__Ú
|
__module__Ú __qualname__r r r r Úpropertyr) r r r r r $ sB Øò ó ð ð
|
ò ó ð òKð ñ*ó ñ*r r )Ú metaclassc óN e Zd ZdZdd fd Zd
|
dZd dZd dZd dZd dZ xZ
|
S )Ú ListAccessorz¤
|
Accessor object for list data properties of the Series values.
|
|
Parameters
|
----------
|
data : Series
|
Series containing Arrow list data.
|
c ó( t | |d¬« y )NzJCan only use the '.list' accessor with 'list[pyarrow]' dtype, not {dtype}.©r ©Úsuperr ©r r Ú __class__s r r zListAccessor.__init__H s ø Ü ÑØ ð 2ð õ
|
r c óÄ t j j |« xs@ t j j |« xs t j j |« S r )ÚpaÚtypesÚis_listÚis_fixed_size_listÚ is_large_listr s r r z$ListAccessor._is_valid_pyarrow_dtypeO sG ä HH× Ñ ]Ó +ò 5Üxx×*Ñ*¨=Ó9ò 5äxx×%Ñ% mÓ4ð
|
r c ó ddl m} t j | j « } ||t |j « ¬« S )a
|
Return the length of each list in the Series.
|
|
Returns
|
-------
|
pandas.Series
|
The length of each list.
|
|
Examples
|
--------
|
>>> import pyarrow as pa
|
>>> s = pd.Series(
|
... [
|
... [1, 2, 3],
|
... [3],
|
... ],
|
... dtype=pd.ArrowDtype(pa.list_(
|
... pa.int64()
|
... ))
|
... )
|
>>> s.list.len()
|
0 3
|
1 1
|
dtype: int32[pyarrow]
|
r ©r r" )Úpandasr ÚpcÚlist_value_lengthr) r Útype)r r Ú value_lengthss r ÚlenzListAccessor.lenV s3 õ4 "ä×,Ñ,¨T¯^©^Ó< Ùm¬:°m×6HÑ6HÓ+IÔJÐJr c ó& ddl m} t |t « r=t j
|
| j |« } ||t |j « ¬« S t |t « rt r t dt j d« |j |j |j }}}|d}|d}t j" | j |||« } ||t |j « ¬« S t% dt |« j& « )a
|
Index or slice lists in the Series.
|
|
Parameters
|
----------
|
key : int | slice
|
Index or slice of indices to access from each list.
|
|
Returns
|
-------
|
pandas.Series
|
The list at requested index.
|
|
Examples
|
--------
|
>>> import pyarrow as pa
|
>>> s = pd.Series(
|
... [
|
... [1, 2, 3],
|
... [3],
|
... ],
|
... dtype=pd.ArrowDtype(pa.list_(
|
... pa.int64()
|
... ))
|
... )
|
>>> s.list[0]
|
0 1
|
1 3
|
dtype: int64[pyarrow]
|
r rD r" z$List slice not supported by pyarrow ú.é z!key must be an int or slice, got )rE r r$ ÚintrF Ú list_elementr) r rH Úslicer ÚNotImplementedErrorr> Ú __version__ÚstartÚstopÚstepÚ
|
list_sliceÚ
|
ValueErrorr0 )r Úkeyr ÚelementrS rT rU Úsliceds r Ú __getitem__zListAccessor.__getitem__u så õ> "ä c3Ô ô
|
oo d§n¡n°cÓ:GÙ'¬°G·L±LÓ)AÔBÐ BÜ UÔ #Ý#Ü)Ø:¼2¿>¹>Ð:JÈ!ÐLóð ð !$§ ¡ ¨3¯8©8°S·X±X4EØ}ð Ø|ØÜ]] 4§>¡>°5¸$ÀÓEFÙ&¬
|
°6·;±;Ó(?Ô@Ð @ä Ð @ÄÀcÃ×ASÑASÐ@TÐ UÓVÐ Vr c óF t dt | « j d« )Nú'z' object is not iterable)Ú TypeErrorrH r0 r* s r Ú__iter__zListAccessor.__iter__² s" Ü!D J× /Ñ /Ð0Ð0HÐIÓJÐJr c ó ddl m} t j | j « } ||t |j « ¬« S )a;
|
Flatten list values.
|
|
Returns
|
-------
|
pandas.Series
|
The data from all lists in the series flattened.
|
|
Examples
|
--------
|
>>> import pyarrow as pa
|
>>> s = pd.Series(
|
... [
|
... [1, 2, 3],
|
... [3],
|
... ],
|
... dtype=pd.ArrowDtype(pa.list_(
|
... pa.int64()
|
... ))
|
... )
|
>>> s.list.flatten()
|
0 1
|
1 2
|
2 3
|
3 3
|
dtype: int64[pyarrow]
|
r rD r" )rE r rF Ú list_flattenr) r rH )r r Ú flatteneds r ÚflattenzListAccessor.flattenµ s/ õ8 "äOO D§N¡NÓ3 Ùi¤z°)·.±.Ó'AÔBÐBr r ©r, r- r. ©r, r )rX z int | slicer, r )r, r ) r0 r1 r2 Ú__doc__r r rJ r[ r_ rc Ú __classcell__©r< s @r r6 r6 > s+ ø ñö
|
ó
|
ó Kó>;WózK÷ Cr r6 c óX e Zd ZdZdd fd Zd dZed
|
d« Z d dZd dZ xZ
|
S ) ÚStructAccessorz¬
|
Accessor object for structured data properties of the Series values.
|
|
Parameters
|
----------
|
data : Series
|
Series containing Arrow struct data.
|
c ó( t | |d¬« y )NzNCan only use the '.struct' accessor with 'struct[pyarrow]' dtype, not {dtype}.r8 r9 r; s r r zStructAccessor.__init__á s ø Ü ÑØ ð&ð õ
|
r c ó@ t j j |« S r )r> r? Ú is_structr s r r z&StructAccessor._is_valid_pyarrow_dtypeê s Üxx×!Ñ! -Ó0Ð0r c óü ddl m}m} | j j j
|
}|D cg c] }t |j « }}|D cg c] }|j }} || ||« ¬« S c c}w c c}w )að
|
Return the dtype object of each child field of the struct.
|
|
Returns
|
-------
|
pandas.Series
|
The data type of each child field.
|
|
Examples
|
--------
|
>>> import pyarrow as pa
|
>>> s = pd.Series(
|
... [
|
... {"version": 1, "project": "pandas"},
|
... {"version": 2, "project": "pandas"},
|
... {"version": 1, "project": "numpy"},
|
... ],
|
... dtype=pd.ArrowDtype(pa.struct(
|
... [("version", pa.int64()), ("project", pa.string())]
|
... ))
|
... )
|
>>> s.struct.dtypes
|
version int64[pyarrow]
|
project string[pyarrow]
|
dtype: object
|
r )ÚIndexr )Úindex) rE ro r r r# r r rH Úname)r ro r Úpa_typeÚstructr? Únamess r ÚdtypeszStructAccessor.dtypesí sk ÷8
|
ð
|
**×"Ñ"×0Ñ0Ø7>Ö?¨VFKKÕ(Ð?Ð?Ø+2Ö3 Ð3Ð3Ùe¡5¨£<Ô0Ð0ùò @ùÚ3s A4ÁA9c ó ddl m} dfd | j j j } ||« }t j ||« } ||t |j « | j j |¬« S )aÃ
|
Extract a child field of a struct as a Series.
|
|
Parameters
|
----------
|
name_or_index : str | bytes | int | expression | list
|
Name or index of the child field to extract.
|
|
For list-like inputs, this will index into a nested
|
struct.
|
|
Returns
|
-------
|
pandas.Series
|
The data corresponding to the selected child field.
|
|
See Also
|
--------
|
Series.struct.explode : Return all child fields as a DataFrame.
|
|
Notes
|
-----
|
The name of the resulting Series will be set using the following
|
rules:
|
|
- For string, bytes, or integer `name_or_index` (or a list of these, for
|
a nested selection), the Series name is set to the selected
|
field's name.
|
- For a :class:`pyarrow.compute.Expression`, this is set to
|
the string form of the expression.
|
- For list-like `name_or_index`, the name will be set to the
|
name of the final field selected.
|
|
Examples
|
--------
|
>>> import pyarrow as pa
|
>>> s = pd.Series(
|
... [
|
... {"version": 1, "project": "pandas"},
|
... {"version": 2, "project": "pandas"},
|
... {"version": 1, "project": "numpy"},
|
... ],
|
... dtype=pd.ArrowDtype(pa.struct(
|
... [("version", pa.int64()), ("project", pa.string())]
|
... ))
|
... )
|
|
Extract by field name.
|
|
>>> s.struct.field("project")
|
0 pandas
|
1 pandas
|
2 numpy
|
Name: project, dtype: string[pyarrow]
|
|
Extract by field index.
|
|
>>> s.struct.field(0)
|
0 1
|
1 2
|
2 1
|
Name: version, dtype: int64[pyarrow]
|
|
Or an expression
|
|
>>> import pyarrow.compute as pc
|
>>> s.struct.field(pc.field("project"))
|
0 pandas
|
1 pandas
|
2 numpy
|
Name: project, dtype: string[pyarrow]
|
|
For nested struct types, you can pass a list of values to index
|
multiple levels:
|
|
>>> version_type = pa.struct([
|
... ("major", pa.int64()),
|
... ("minor", pa.int64()),
|
... ])
|
>>> s = pd.Series(
|
... [
|
... {"version": {"major": 1, "minor": 5}, "project": "pandas"},
|
... {"version": {"major": 2, "minor": 1}, "project": "pandas"},
|
... {"version": {"major": 1, "minor": 26}, "project": "numpy"},
|
... ],
|
... dtype=pd.ArrowDtype(pa.struct(
|
... [("version", version_type), ("project", pa.string())]
|
... ))
|
... )
|
>>> s.struct.field(["version", "minor"])
|
0 5
|
1 1
|
2 26
|
Name: minor, dtype: int64[pyarrow]
|
>>> s.struct.field([0, 0])
|
0 1
|
1 2
|
2 1
|
Name: major, dtype: int64[pyarrow]
|
r rD c ó, t | t « r'|j j | « j }|S t | t
|
t f« r| }|S t | t j « r t | « }|S t | « rt t | « « } |}| rlt t | « } | j « } ||« }|j j |j j |« « }|j }| rlS t d« )NzVname_or_index must be an int, str, bytes, pyarrow.compute.Expression, or list of those)r$ rN rH Úfieldrq r+ ÚbytesrF Ú
|
Expressionr
|
ÚlistÚreversedr ÚpopÚget_field_indexrW )Úlevel_name_or_indexr rq ÚselectedÚ name_or_indexÚget_names r r z&StructAccessor.field.<locals>.get_name s ø ô Ð-¬sÔ3ØyyÐ':Ó;×@Ñ@ð0 Kô/ Ð /´#´u° Ô>Ø*ð, Kô+ Ð /´· ± Ô?ÜÐ.Ó/ð( Kô' Ð 1Ô2ô '+¬8Ð4GÓ+HÓ&IÐ#Ø Ù)ô +/¬tÐ5HÓ*IÐ'Ø$7×$;Ñ$;Ó$=MÙ# M°8Ó<DØ '}}× 2Ñ 2°8·=±=×3PÑ3PÐQUÓ3VÓ WHØ#==Dò *ð Kô !ðCóð r )r# rp rq )r úGlist[str] | list[bytes] | list[int] | pc.Expression | bytes | str | intr zpa.ChunkedArray)
|
rE r r r( r) rF Ú struct_fieldr rH rp )r r r Úpa_arrrq Ú field_arrr s @r rx zStructAccessor.field s ø õ\ "ð# ð"ð# ð "õ# ðJ ×!Ñ!×+Ñ+Ù vÓ.ÜOO F¨MÓ: áØ Ü Y^^Ó,Ø**×"Ñ"Øô
|
ð
|
r c ó¸ ddl m} | j j } |t |j
|
« D cg c] }| j |« c}d¬« S c c}w )at
|
Extract all child fields of a struct as a DataFrame.
|
|
Returns
|
-------
|
pandas.DataFrame
|
The data corresponding to all child fields.
|
|
See Also
|
--------
|
Series.struct.field : Return a single child field as a Series.
|
|
Examples
|
--------
|
>>> import pyarrow as pa
|
>>> s = pd.Series(
|
... [
|
... {"version": 1, "project": "pandas"},
|
... {"version": 2, "project": "pandas"},
|
... {"version": 1, "project": "numpy"},
|
... ],
|
... dtype=pd.ArrowDtype(pa.struct(
|
... [("version", pa.int64()), ("project", pa.string())]
|
... ))
|
... )
|
|
>>> s.struct.explode()
|
version project
|
0 1 pandas
|
1 2 pandas
|
2 1 numpy
|
r )ÚconcatÚcolumns)Úaxis)rE r r) rH ÚrangeÚ
|
num_fieldsrx )r r rr Úis r ÚexplodezStructAccessor.explode³ sJ õB "à..×%Ñ%ÙÜ$)¨'×*<Ñ*<Ó$=Ö >qTZZ]Ò >ÀYô
|
ð
|
ùÚ >s ¶Ar rd r. re )r r r, r )r, r ) r0 r1 r2 rf r r r3 ru rx r rg rh s @r rj rj × sI ø ñö
|
ó1ð ò#1ó ð#1ðJ^
|
ðð^
|
ð
|
ó^
|
÷@&
|
r rj ) rf Ú
|
__future__r Úabcr r Útypingr r Ú pandas.compatr r Úpandas.core.dtypes.commonr
|
Úpyarrowr> Úpyarrow.computeÚcomputerF Úpandas.core.dtypes.dtypesr Úcollections.abcr rE r r r r6 rj r r r ú<module>r sa ðÙ &å "÷÷÷
|
õ
|
3áÛÝ å4áÝ(÷ô *gõ *ô4VC=ô VCôrB
|
]õ B
|
r
|
