a OfJ-@s^dZddlmZddlmZmZmZddlZddlm Z ddl m Z ddl m Z ddlmZdd lmZdd lmZdd lmZmZmZmZdd lmZmZmZmZdd lm Z ddl!m"m#Z$ddl%m&Z&erddl'm(Z(m)Z)ddlm*Z*ddl+m,Z,dZ-dddddZ.ddZ/ddddZ0dddd Z1d,d"d#d$d#dd%d&d'Z2d#d(d)d*d+Z3dS)-zH Table Schema builders https://specs.frictionlessdata.io/table-schema/ ) annotations) TYPE_CHECKINGAnycastN)lib) ujson_loads) timezones)freq_to_period_freqstr)find_stack_level) _registry) is_bool_dtypeis_integer_dtypeis_numeric_dtypeis_string_dtype)CategoricalDtypeDatetimeTZDtypeExtensionDtype PeriodDtype) DataFrame) to_offset)DtypeObjJSONSerializable)Series) MultiIndexz1.4.0rstr)xreturncCstt|r dSt|rdSt|r$dSt|ds>t|ttfrBdSt|drRdSt|tr`dSt |rld SdSd S) a Convert a NumPy / pandas type to its corresponding json_table. Parameters ---------- x : np.dtype or ExtensionDtype Returns ------- str the Table Schema data types Notes ----- This table shows the relationship between NumPy / pandas dtypes, and Table Schema dtypes. ============== ================= Pandas type Table Schema type ============== ================= int64 integer float64 number bool boolean datetime64[ns] datetime timedelta64[ns] duration object str categorical any =============== ================= integerbooleannumberMdatetimemdurationanystringN) r r rrZ is_np_dtype isinstancerrrr)rr'U/var/www/ai-form-bot/venv/lib/python3.9/site-packages/pandas/io/json/_table_schema.pyas_json_table_type5s  r)cCstj|jjrr|jj}t|dkr@|jjdkr@tjdtdn.t|dkrnt dd|Drntjdtd|S| }|jj dkrt |jj|j_n|jjpd|j_|S)z?Sets index names to 'index' for regular, or 'level_x' for Multiindexz-Index name of 'index' is not round-trippable.) stacklevelcss|]}|dVqdSZlevel_N startswith.0rr'r'r( nz$set_default_names..z>> 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]' r?r%objectrrFZint64rZfloat64rboolr# timedelta64r!rEzdatetime64[ns, ]rCzperiod[zdatetime64[ns]r$rArBr@)rHrBz#Unsupported or invalid field type: N) getrnr7r rregistryfind ValueError)rKtypoffsetZfreq_nZ freq_namerCr'r'r(!convert_json_field_to_pandas_types:)          rXTzDataFrame | SeriesrNz bool | None)r<r+ primary_keyversionrc Cs"|durt|}i}g}|r~|jjdkrntd|j|_t|jj|jjD]"\}}t|}||d<||qHn|t|j|j dkr| D]\} } |t| qn|t|||d<|r|jj r|dur|jjdkr|jj g|d<n |jj|d<n|dur||d<|rt |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 `__ 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*rr7fieldsN primaryKeyZpandas_version)r=r+r;rzipZlevelsr5rLappendndimitemsZ is_uniquer7TABLE_SCHEMA_VERSION) r<r+rYrZschemar[levelr7Z new_fieldcolumnsr'r'r(build_table_schemas48    rfr) precise_floatrcCst||d}dd|ddD}t|d|d|}dd |ddD}d |vr`td ||}d |dvr||dd }t|jjd kr|jj dkrd|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 )rgcSsg|] }|dqSr7r'r1rKr'r'r( kr3z&parse_table_schema..rbr[r<)columnscSsi|]}|dt|qSrh)rXrir'r'r( nsz&parse_table_schema..rOzNotImplementedErrorZastypeZ set_indexr6r+r5r7)jsonrgtableZ col_orderZdfZdtypesr'r'r(parse_table_schemaFs($        rp)TNT)4__doc__ __future__rtypingrrrr8Z pandas._libsrZpandas._libs.jsonrZpandas._libs.tslibsrZpandas._libs.tslibs.dtypesr Zpandas.util._exceptionsr Zpandas.core.dtypes.baser rSZpandas.core.dtypes.commonr r rrZpandas.core.dtypes.dtypesrrrrZpandasrZpandas.core.commoncorecommonr4Zpandas.tseries.frequenciesrZpandas._typingrrrZpandas.core.indexes.multirrar)r=rLrXrfrpr'r'r'r(s8           0 O\