U
|
¬ý°d@- ã @ s> d Z ddlmZ ddlmZmZmZ ddlZddlm Z ddl
|
m Z ddl m Z mZ ddlmZ dd lmZ dd
|
lmZmZmZmZmZmZmZm Z m Z m Z dd l m Z dd l!m"Z" ddl#m$ m%Z& erâdd l!m'Z' ddl(m)Z) dZ*dddddZ+dd Z,ddddZ-ddd d Z.d'd d d!d dd"d#d$Z/d%d& Z0dS )(zH
|
Table Schema builders
|
|
https://specs.frictionlessdata.io/table-schema/
|
é )Ú annotations)Ú TYPE_CHECKINGÚAnyÚcastN)Úloads)Ú timezones)ÚDtypeObjÚJSONSerializable)Úfind_stack_level)Ú _registry)
|
Ú is_bool_dtypeÚis_categorical_dtypeÚis_datetime64_dtypeÚis_datetime64tz_dtypeÚis_extension_array_dtypeÚis_integer_dtypeÚis_numeric_dtypeÚis_period_dtypeÚis_string_dtypeÚis_timedelta64_dtype)ÚCategoricalDtype)Ú DataFrame)ÚSeries)Ú
|
MultiIndexz1.4.0r Ústr)ÚxÚreturnc C sx t | r dS t| rdS t| r$dS t| s<t| s<t| r@dS t| rLdS t| rXdS t| rddS t | rpdS dS dS ) 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
|
=============== =================
|
ÚintegerÚbooleanÚnumberÚdatetimeÚdurationÚanyÚstringN)
|
r r r r r r r r r r )r © r$ úSd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/io/json/_table_schema.pyÚas_json_table_type1 s" r& c C s® t j| jj rr| jj}t|dkr@| jjdkr@tjdt d n.t|dkrnt dd |D rntjdt d | S |
|
¡ } | jj dkrt | jj¡| j_n| jjp¤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 s s | ]}| d ¡V qdS ©Zlevel_N©Ú
|
startswith©Ú.0r r$ r$ r% Ú <genexpr>l s z$set_default_names.<locals>.<genexpr>z<Index names beginning with 'level_' are not round-trippable.) ÚcomZ all_not_noner( ÚnamesÚlenÚnameÚwarningsÚwarnr
|
r" ÚcopyÚnlevelsZfill_missing_names)ÚdataZnmsr$ r$ r% Úset_default_namesc s$ þ þ r9 zdict[str, JSONSerializable])r c C s° | j }| jd krd}n| j}|t|d}t|rX|j}|j}dt|i|d< ||d< nTt|rn|jj |d< n>t
|
|rt |j ¡rd|d< q¬|j j|d< nt|r¬|j|d < |S )
|
NÚvalues)r3 ÚtypeÚenumÚ constraintsÚorderedÚfreqÚUTCÚtzÚextDtype)Údtyper3 r& r Ú
|
categoriesr> Úlistr r? Zfreqstrr r Zis_utcrA Úzoner )ZarrrC r3 ÚfieldZcatsr> r$ r$ r% Ú!convert_pandas_type_to_json_field{ s*
|
þ
|
|
|
rH zstr | CategoricalDtypec C sú | d }|dkrdS |dkr(| dd¡S |dkr<| dd¡S |d krP| dd
|
¡S |d kr\d S |d kr| d¡r~d| d dS | d¡rd| d dS dS nJ|dkrèd| krÎd| krÎt| d d | d dS d| krät | d ¡S dS td| dS )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)
|
|
>>> 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]'
|
r; r# Úobjectr rB Úint64r Úfloat64r Úboolr! Ú timedelta64r rA zdatetime64[ns, ú]r? zperiod[zdatetime64[ns]r" r= r> r< )rD r> z#Unsupported or invalid field type: N)Úgetr ÚregistryÚfindÚ
|
ValueError)rG Útypr$ r$ r% Ú!convert_json_field_to_pandas_type s6 )
|
|
|
ÿrT TzDataFrame | SeriesrL z bool | None)r8 r( Ú primary_keyÚversionr c C s" |dkrt | } i }g }|r~| jjdkrntd| j| _t| jj| jjD ]"\}}t|}||d< | |¡ qHn| t| j¡ | j dkrª|
|
¡ D ]\} }
|
| t|
|
¡ qn| t| ¡ ||d< |rþ| jj rþ|dkrþ| jjdkrð| jj g|d< n | jj|d< n|dk r||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 r3 ÚfieldsNÚ
|
primaryKeyZpandas_version)r9 r( r7 r ÚzipÚlevelsr1 rH ÚappendÚndimÚitemsZ is_uniquer3 ÚTABLE_SCHEMA_VERSION) r8 r( rU rV ÚschemarW Úlevelr3 Z new_fieldÚcolumnÚsr$ r$ r% Úbuild_table_schemaã s4 8
|
|
rc c C sÈ t | |d}dd |d d D }t|d |d| }dd |d d D }d
|
| ¡ kr`td | |¡}d |d krÄ| |d d ¡}t|jjd kr®|jj dkrÄd|j_ ndd |jjD |j_|S )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_floatc S s g | ] }|d qS ©r3 r$ ©r. rG r$ r$ r% Ú
|
<listcomp>d s z&parse_table_schema.<locals>.<listcomp>r_ rW r8 )Úcolumnsc S s i | ]}|d t |qS re )rT rf r$ r$ r% Ú
|
<dictcomp>g s ÿ z&parse_table_schema.<locals>.<dictcomp>rM z<table="orient" can not yet read ISO-formatted Timedelta datarX r' r( Nc S s g | ]}| d ¡rdn|qS r* r+ r- r$ r$ r% rg z s )
|
r r r: ÚNotImplementedErrorZastypeZ set_indexr2 r( r1 r3 )Újsonrd ÚtableZ col_orderZdfZdtypesr$ r$ r% Úparse_table_schema? s( $
|
þ ÿ
|
|
ÿ
|
rm )TNT)1Ú__doc__Ú
|
__future__r Útypingr r r r4 Zpandas._libs.jsonr Zpandas._libs.tslibsr Zpandas._typingr r Zpandas.util._exceptionsr
|
Zpandas.core.dtypes.baser rP Zpandas.core.dtypes.commonr r r r r r r r r r Zpandas.core.dtypes.dtypesr Zpandasr Zpandas.core.commonÚcoreÚcommonr0 r Zpandas.core.indexes.multir r^ r& r9 rH rT rc rm r$ r$ r$ r% Ú<module> s2 0 2 K ü\
|
