3 Ud?)@sdZddlmZmZmZmZmZddlZddlj j Z ddl m Z m Z mZddlmZmZmZmZmZmZmZmZmZddlmZddlmZddljjZ erddl!m"Z"e j#Z#e e$d d d Z%d d Z&ddZ'ddZ(de e)ee)e)ee$efdddZ*ddZ+dS)zM Table Schema builders https://specs.frictionlessdata.io/json-table-schema/ ) TYPE_CHECKINGAnyDictOptionalcastN)DtypeObj FrameOrSeriesJSONSerializable) is_bool_dtypeis_categorical_dtypeis_datetime64_dtypeis_datetime64tz_dtypeis_integer_dtypeis_numeric_dtypeis_period_dtypeis_string_dtypeis_timedelta64_dtype)CategoricalDtype) DataFrame) MultiIndex)xreturncCslt|r dSt|rdSt|r$dSt|sXsz$set_default_names..z;Index names beginning with 'level_' are not round-trippablecSs&g|]\}}|dk r|nd|qS)Nr$r)r&inamerrr _sz%set_default_names..) comZ all_not_noner#nameslenr)warningswarnrcopynlevels enumerate)dataZnmsr,rrr set_default_namesRs    r4cCs|j}|jdkrd}n|j}|t|d}t|rX|j}|j}dt|i|d<||d<n*t|rn|jj |d<nt |r|j j |d<|S)Nvalues)r)typeenum constraintsorderedfreqtz) dtyper)r!r categoriesr9listrr:Zfreqstrr r;zone)Zarrr<r)fieldZcatsr9rrr !convert_pandas_type_to_json_fieldhs     rAcCs|d}|dkrdS|dkr dS|dkr,dS|dkr8d S|d krDd S|d krl|jd rfd|d dSdSn4|dkrd|krd|krt|dd|ddSdStd|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]' r6robjectrZint64rZfloat64rboolr timedelta64rr;zdatetime64[ns, ]zdatetime64[ns]rr8r9r7)r=r9z#Unsupported or invalid field type: N)getr ValueError)r@typrrr !convert_json_field_to_pandas_types*% rIT)r3r# primary_keyversionrc Cs,|dkrt|}i}g}|r|jjdkrrtd|j|_xJt|jj|jjD]"\}}t|}||d<|j|qJWn|jt|j|j dkrx2|j D]\} } |jt| qWn|jt|||d<|o|jj o|dkr|jjdkr|jj g|d<n |jj|d<n|dk r||d<|r(d|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 generated the schema. 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'}], 'pandas_version': '0.20.0', 'primaryKey': ['idx']} Tr"rr)fieldsN primaryKeyz0.20.0Zpandas_version) r4r#r1rzipZlevelsr,rAappendndimitemsZ is_uniquer)) r3r#rJrKschemarLlevelr)Z new_fieldcolumnsrrr build_table_schemas45    rVcCst||d}dd|ddD}t|d|d|}dd |ddD}td d |jDrjtd d |jkr~td|j|}d|dkr|j|dd}t|jj dkr|jj dkrd|j_ ndd|jj D|j_ |S)a Builds a DataFrame from a given schema Parameters ---------- json : A JSON table schema precise_float : boolean 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|] }|dqS)r)r)r&r@rrr r*>sz&parse_table_schema..rRrLr3)columnscSsi|]}t||dqS)r))rI)r&r@rrr Asz&parse_table_schema..css|]}t|jdVqdS)zdatetime64[ns, N)strr%)r&rrrr r'Gsz%parse_table_schema..z-table="orient" can not yet read timezone datarDzs( ,    0BT