a oEb)@s&dZddlmZddlmZmZmZddlZddlm m Z ddl m Z m Z ddlmZddlmZmZmZmZmZmZmZmZmZmZddlmZdd lmZddl m!m"Z#erdd lm$Z$dd l%m&Z&e j'Z'd Z(d ddddZ)ddZ*ddZ+ddZ,d"ddddddddZ-d d!Z.dS)#zM Table Schema builders https://specs.frictionlessdata.io/json-table-schema/ ) annotations) TYPE_CHECKINGAnycastN)DtypeObjJSONSerializable) _registry) is_bool_dtypeis_categorical_dtypeis_datetime64_dtypeis_datetime64tz_dtypeis_extension_array_dtypeis_integer_dtypeis_numeric_dtypeis_period_dtypeis_string_dtypeis_timedelta64_dtype)CategoricalDtype) DataFrame)Series) MultiIndexz1.4.0rstr)xreturncCsxt|r dSt|rdSt|r$dSt|shz$set_default_names..zt|rn|jj |d<n(t |r|j j |d<nt |r|j|d<|S) Nvalues)r0typeenum constraintsorderedfreqtzextDtype)dtyper0r#r categoriesr;listrr<Zfreqstrr r=zoner )Zarrr?r0fieldZcatsr;r!r!r"!convert_pandas_type_to_json_fieldvs&   rDcCs|d}|dkrdS|dkr dS|dkr,dS|dkr8d S|d krDd S|d krl|d rfd|d dSdSnJ|dkrd|vrd|vrt|dd|ddSd|vrt|dSdStd|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]' r8r objectrZint64rZfloat64rboolr timedelta64rr=zdatetime64[ns, ]zdatetime64[ns]rr:r;r9)r@r;r>z#Unsupported or invalid field type: N)getrregistryfind ValueError)rCtypr!r!r"!convert_json_field_to_pandas_types0) rNTzDataFrame | SeriesrFz bool | Nonezdict[str, JSONSerializable])r5r% 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) aG 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 ------- schema : 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 -------- >>> 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$rr0fieldsN primaryKeyZpandas_version)r6r%r4rzipZlevelsr.rDappendndimitemsZ is_uniquer0TABLE_SCHEMA_VERSION) r5r%rOrPschemarQlevelr0Z new_fieldcolumnsr!r!r"build_table_schemas47    r\cCst||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 ) precise_floatcSsg|] }|dqSr0r!r*rCr!r!r" Vr,z&parse_table_schema..rXrQr5)columnscSsi|]}|dt|qSr^)rNr_r!r!r" Ysz&parse_table_schema..rGzs0  0    2H[