Ë
|
nñúh - ã óJ d Z ddlmZ ddlmZmZmZ ddlZddlm Z ddl
|
m Z ddl m Z ddlmZ dd lmZ dd
|
lmZ dd lmZmZmZmZ dd lmZm Z m Z m Z dd l m Z ddl!m"c m#Z$ ddl%m&Z& erddl'm(Z(m)Z) ddl m*Z* ddl+m,Z, dZ-ddZ.d Z/ddZ0ddZ1 d d dZ2d dZ3y) zH
|
Table Schema builders
|
|
https://specs.frictionlessdata.io/table-schema/
|
é )Ú annotations)Ú TYPE_CHECKINGÚAnyÚcastN)Úlib)Ú ujson_loads)Ú timezones)Úfreq_to_period_freqstr)Úfind_stack_level)Ú _registry)Ú is_bool_dtypeÚis_integer_dtypeÚis_numeric_dtypeÚis_string_dtype)ÚCategoricalDtypeÚDatetimeTZDtypeÚExtensionDtypeÚ PeriodDtype)Ú DataFrame)Ú to_offset)ÚDtypeObjÚJSONSerializable)ÚSeries)Ú
|
MultiIndexz1.4.0c óì t | « ryt | « ryt | « ryt j | d« st | t t f« ryt j | d« ryt | « ryy )
|
a
|
Convert a NumPy / pandas type to its corresponding json_table.
|
|
Parameters
|
----------
|
x : np.dtype or ExtensionDtype
|
|
Returns
|
-------
|
str
|
the Table Schema data types
|
|
Notes
|
-----
|
This table shows the relationship between NumPy / pandas dtypes,
|
and Table Schema dtypes.
|
|
============== =================
|
Pandas type Table Schema type
|
============== =================
|
int64 integer
|
float64 number
|
bool boolean
|
datetime64[ns] datetime
|
timedelta64[ns] duration
|
object str
|
categorical any
|
=============== =================
|
ÚintegerÚbooleanÚnumberÚMÚdatetimeÚmÚdurationÚstringÚany) r r r r Ú is_np_dtypeÚ
|
isinstancer r r )Úxs úOH:\Change_password\venv_build\Lib\site-packages\pandas/io/json/_table_schema.pyÚas_json_table_typer) 5 sc ô< ÔØÜ qÔ ØÜ !Ô ØÜ CÔ ¤J¨q´?ÄKÐ2PÔ$QØÜ CÔ ØÜ Ô Øàó c ó¨ t j | j j r| j j }t |« dk( r:| j j
|
dk( r!t j dt « ¬« | S t |« dkD r1t d |D « « r t j dt « ¬« | S | j « } | j j dkD r:t j | j j « | j _ | S | j j
|
xs d| j _ | S )z?Sets index names to 'index' for regular, or 'level_x' for Multié Úindexz-Index name of 'index' is not round-trippable.)Ú
|
stacklevelc 3 ó> K | ] }|j d « yw)Úlevel_N)Ú
|
startswith)Ú.0r' s r( ú <genexpr>z$set_default_names.<locals>.<genexpr>l s è ø Ò!F¸Q !§,¡,¨x×"8Ñ!Fùs z<Index names beginning with 'level_' are not round-trippable.) ÚcomÚ all_not_noner- ÚnamesÚlenÚnameÚwarningsÚwarnr r$ ÚcopyÚnlevelsÚfill_missing_names)ÚdataÚnmss r( Úset_default_namesr@ c sù ä
|
×Ñ×)Ñ)Ñ*Øjj× Ñ Ü s8q=TZZ__°Ò 7Ü MMØ?Ü+Ó-õ ð ô X\cÑ!FÀ#Ô!FÔ FÜ MMØNÜ+Ó-õ ð à 99;DØ zz×ÑAÒ Ü ×1Ñ1°$·*±*×2BÑ2BÓC
|
|
Ôð Kð **//Ò4¨W
|
|
Ø Kr* c ó$ | j }| j d}n | j }|t |« d}t |t « r/|j
|
}|j }dt |« i|d< ||d< |S t |t « r|j j |d< |S t |t « rAt j |j « rd|d< |S |j j |d< |S t |t « r|j |d < |S )
|
NÚvalues)r8 ÚtypeÚenumÚ constraintsÚorderedÚfreqÚUTCÚtzÚextDtype)Údtyper8 r) r& r Ú
|
categoriesrF Úlistr rG Úfreqstrr r Úis_utcrI Úzoner )ÚarrrK r8 ÚfieldÚcatsrF s r( Ú!convert_pandas_type_to_json_fieldrT { s Ø IIEà
|
xxÐØàxxàÜ" 5Ó)ñ*Eô
|
%Ô)Ô*Ø× Ñ Ø--à &¬¨T«
|
Ð 3mÑ Ø"iÑð Lô
|
E;Ô 'Ø
|
|
×*Ñ*f ð Lô
|
E?Ô +Ü × Ñ EHHÔ %à E$Kð Lð ((--E$Kð Lô
|
E>Ô *Ø !JJjÑØ Lr* c ó> | d }|dk( r| j dd« S |dk( r| j dd« S |dk( r| j dd« S |d k( r| j dd
|
« S |d k( ry |d k( rd| j d« r d| d dS | j d« r8t | d « }|j |j }}t ||« }d| dS y|dk( r;d| v rd| v rt | d d | d ¬« S d| v rt j | d « S yt d| « )a
|
Converts a JSON field descriptor into its corresponding NumPy / pandas type
|
|
Parameters
|
----------
|
field
|
A JSON field descriptor
|
|
Returns
|
-------
|
dtype
|
|
Raises
|
------
|
ValueError
|
If the type of the provided field is unknown or currently unsupported
|
|
Examples
|
--------
|
>>> convert_json_field_to_pandas_type({"name": "an_int", "type": "integer"})
|
'int64'
|
|
>>> convert_json_field_to_pandas_type(
|
... {
|
... "name": "a_categorical",
|
... "type": "any",
|
... "constraints": {"enum": ["a", "b", "c"]},
|
... "ordered": True,
|
... }
|
... )
|
CategoricalDtype(categories=['a', 'b', 'c'], ordered=True, categories_dtype=object)
|
|
>>> convert_json_field_to_pandas_type({"name": "a_datetime", "type": "datetime"})
|
'datetime64[ns]'
|
|
>>> convert_json_field_to_pandas_type(
|
... {"name": "a_datetime_with_tz", "type": "datetime", "tz": "US/Central"}
|
... )
|
'datetime64[ns, US/Central]'
|
rC r# rJ Nr Úint64r Úfloat64r Úboolr" Ú timedelta64r rI zdatetime64[ns, ú]rG zperiod[zdatetime64[ns]r$ rE rF rD )rL rF Úobjectz#Unsupported or invalid field type: ) Úgetr Únr8 r
|
r ÚregistryÚfindÚ
|
ValueError)rR ÚtypÚoffsetÚfreq_nÚ freq_namerG s r( Ú!convert_json_field_to_pandas_typere sU ðR -CØ
|
hØyy TÓ*Ð*Ø Ò Øyy WÓ-Ð-Ø Øyy YÓ/Ð/Ø Ò Øyy VÓ,Ð,Ø
|
Ò Ø Ø
|
Ò Ø 99T?Ø$ U¨4¡[ M°Ð3Ð 3Ø YYvÔ ä u V}Ó-FØ &§¡¨&¯+©+IFÜ)¨&°)Ó<Dà TF !Ð$Ð $à#Ø Ø EÑ ! i°5Ñ&8Ü#Ø Ñ/°Ñ7ÀÀyÑAQôð ð 5Ñ Ü== zÑ!2Ó3Ð 3àä
|
Ð:¸3¸%Ð@Ó
|
AÐAr* c óR |du r t | « } i }g }|r¶| j j dkD ryt d| j « | _ t | j j
|
| j j « D ]& \ }}t |« }||d< |j |« ( n$|j t | j « « | j dkD r3| j « D ] \ } }
|
|j t |
|
« « ! n|j t | « « ||d< |rf| j j rP|N| j j dk( r| j j g|d< n!| j j |d< n|||d< |r t |d< |S )a
|
Create a Table schema from ``data``.
|
|
Parameters
|
----------
|
data : Series, DataFrame
|
index : bool, default True
|
Whether to include ``data.index`` in the schema.
|
primary_key : bool or None, default True
|
Column names to designate as the primary key.
|
The default `None` will set `'primaryKey'` to the index
|
level or levels if the index is unique.
|
version : bool, default True
|
Whether to include a field `pandas_version` with the version
|
of pandas that last revised the table schema. This version
|
can be different from the installed pandas version.
|
|
Returns
|
-------
|
dict
|
|
Notes
|
-----
|
See `Table Schema
|
<https://pandas.pydata.org/docs/user_guide/io.html#table-schema>`__ for
|
conversion types.
|
Timedeltas as converted to ISO8601 duration format with
|
9 decimal places after the seconds field for nanosecond precision.
|
|
Categoricals are converted to the `any` dtype, and use the `enum` field
|
constraint to list the allowed values. The `ordered` attribute is included
|
in an `ordered` field.
|
|
Examples
|
--------
|
>>> from pandas.io.json._table_schema import build_table_schema
|
>>> df = pd.DataFrame(
|
... {'A': [1, 2, 3],
|
... 'B': ['a', 'b', 'c'],
|
... 'C': pd.date_range('2016-01-01', freq='d', periods=3),
|
... }, index=pd.Index(range(3), name='idx'))
|
>>> build_table_schema(df)
|
{'fields': [{'name': 'idx', 'type': 'integer'}, {'name': 'A', 'type': 'integer'}, {'name': 'B', 'type': 'string'}, {'name': 'C', 'type': 'datetime'}], 'primaryKey': ['idx'], 'pandas_version': '1.4.0'}
|
Tr, r r8 ÚfieldsÚ
|
primaryKeyÚpandas_version)r@ r- r< r ÚzipÚlevelsr6 rT ÚappendÚndimÚitemsÚ is_uniquer8 ÚTABLE_SCHEMA_VERSION) r> r- Ú primary_keyÚversionÚschemarg Úlevelr8 Ú new_fieldÚcolumnÚss r( Úbuild_table_schemarx è su ðp }Ü Ó&à FØ Fá Ø ::× Ñ Ò !Ü l¨D¯J©JÓ7DJÜ " 4§:¡:×#4Ñ#4°d·j±j×6FÑ6FÓ Gò ) tÜ =¸eÓ D Ø$( &Ñ!Ø iÕ(ñ )ð
|
MMÔ;¸D¿J¹JÓGÔ Hà yy1}Ø ò @IFAØ MMÔ;¸AÓ>Õ ?ñ @ð Ô7¸Ó=Ô>à F8ÑÙ ×%Ò%¨+Ð*=Ø ::× Ñ Ò "Ø$(§J¡J§O¡OÐ#4F<Ò à#'§:¡:×#3Ñ#3F<Ò Ø Ð Ø *|Ñ áÜ#7Ð Ñ Ø Mr* c ó t | |¬« }|d d D cg c] }|d }}t |d |¬« | }|d d D ci c] }|d t |« }}d|j « v r t d« |j |« }d |d v r«|j |d d « }t |j j « d
|
k( r,|j j d k( rd |j _
|
|S |j j D cg c] }|j d « rd n| c}|j _ |S c c}w c c}w c c}w )a
|
Builds a DataFrame from a given schema
|
|
Parameters
|
----------
|
json :
|
A JSON table schema
|
precise_float : bool
|
Flag controlling precision when decoding string to double values, as
|
dictated by ``read_json``
|
|
Returns
|
-------
|
df : DataFrame
|
|
Raises
|
------
|
NotImplementedError
|
If the JSON table schema contains either timezone or timedelta data
|
|
Notes
|
-----
|
Because :func:`DataFrame.to_json` uses the string 'index' to denote a
|
name-less :class:`Index`, this function sets the name of the returned
|
:class:`DataFrame` to ``None`` when said string is encountered with a
|
normal :class:`Index`. For a :class:`MultiIndex`, the same limitation
|
applies to any strings beginning with 'level_'. Therefore, an
|
:class:`Index` name of 'index' and :class:`MultiIndex` names starting
|
with 'level_' are not supported.
|
|
See Also
|
--------
|
build_table_schema : Inverse function.
|
pandas.read_json
|
)Ú precise_floatrs rg r8 r> )ÚcolumnsrY z<table="orient" can not yet read ISO-formatted Timedelta datarh r, r- Nr0 ) r r re rB ÚNotImplementedErrorÚastypeÚ set_indexr7 r- r6 r8 r1 )Újsonrz ÚtablerR Ú col_orderÚdfÚdtypesr' s r( Úparse_table_schemar D sU ôH ¨MÔ :EØ,1°(©O¸HÑ,EÖF 5v ÐFIÐFÜ 5=¨)Ô 4°YÑ ?Bð 8_ XÑ.öà ð f Ô8¸Ó?Ñ?ðFð ð Ñ'Ü!Ø Jó
|
ð
|
ð
|
6Ó BàuXÑ&Ø \\% /¨,Ñ7Ó 8Ü rxx~~Ó !Ò #Øxx}} Ò'Ø $ ð Ið @B¿x¹x¿~¹~ö Ø:; XÔ.°AÑ5ò BHHNð Iùò5 Gùòùò& s D=ÁEÄ E)r' r ÚreturnÚstr)r
údict[str, JSONSerializable])r
zstr | CategoricalDtype)TNT)
|
r> zDataFrame | Seriesr- rX rq z bool | Nonerr rX r
r )rz rX r
r )4Ú__doc__Ú
|
__future__r Útypingr r r r9 Ú pandas._libsr Úpandas._libs.jsonr Úpandas._libs.tslibsr Úpandas._libs.tslibs.dtypesr
|
Úpandas.util._exceptionsr Úpandas.core.dtypes.baser r^ Úpandas.core.dtypes.commonr r r r Úpandas.core.dtypes.dtypesr r r r Úpandasr Úpandas.core.commonÚcoreÚcommonr4 Úpandas.tseries.frequenciesr Úpandas._typingr r r Úpandas.core.indexes.multir rp r) r@ rT re rx r © r* r( ú<module>r sÍ ðñõ
|
#÷ñ ó
|
å Ý )Ý )Ý =Ý 4å 9÷ó ÷ ó õ ß Ð å 0á÷õ
|
Ý4ð Ð ó+ò\ó0 ó@JBð^ Ø #Øð YØ
|
ðYà ðYð ðYð ð Yð
|
!ó Yôx?r*
|
