ó šxŠ\c@sådZddlZddljjZddlmZmZmZm Z m Z m Z m Z m Z mZddlmZddlmZddljjZejZd„Zd„Zdd„Zd „Zeded „Zd „ZdS( sL Table Schema builders http://specs.frictionlessdata.io/json-table-schema/ iÿÿÿÿN( t is_bool_dtypetis_categorical_dtypetis_datetime64_dtypetis_datetime64tz_dtypetis_integer_dtypetis_numeric_dtypetis_period_dtypetis_string_dtypetis_timedelta64_dtype(t DataFrame(tCategoricalDtypecCst|ƒrdSt|ƒr dSt|ƒr0dSt|ƒsTt|ƒsTt|ƒrXdSt|ƒrhdSt|ƒrxdSt|ƒrˆdSdSdS( s” Convert a NumPy / pandas type to its corresponding json_table. Parameters ---------- x : array or dtype Returns ------- t : 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 =============== ================= tintegertbooleantnumbertdatetimetdurationtanytstringN( RRRRRRRRR(tx((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pytas_json_table_types        cCs tj|jjŒr‘|jj}t|ƒdkrU|jjdkrUtjdƒn8t|ƒdkrtd„|Dƒƒrtjdƒn|S|j ƒ}|jj dkrgt |jjƒD]-\}}|dk rà|n dj |ƒ^qÂ}||j_n|jjpd|j_|S(s?Sets index names to 'index' for regular, or 'level_x' for Multiitindexs,Index name of 'index' is not round-trippablecss|]}|jdƒVqdS(tlevel_N(t startswith(t.0R((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pys Mss;Index names beginning with 'level_' are not round-trippableslevel_{}N(tcomt _all_not_noneRtnamestlentnametwarningstwarnRtcopytnlevelst enumeratetNonetformat(tdatatnmstiRR((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pytset_default_namesGs $( CcCs|p |j}|jdkr'd}n |j}i|d6t|ƒd6}t|ƒr¶t|dƒrz|j}|j}n|jj}|jj}it |ƒd6|d<||d>> convert_json_field_to_pandas_type({'name': 'an_int', 'type': 'integer'}) 'int64' >>> convert_json_field_to_pandas_type({'name': 'a_categorical', 'type': 'any', 'contraints': {'enum': [ 'a', 'b', 'c']}, 'ordered': True}) 'CategoricalDtype(categories=['a', 'b', 'c'], ordered=True)' >>> convert_json_field_to_pandas_type({'name': 'a_datetime', 'type': 'datetime'}) 'datetime64[ns]' >>> convert_json_field_to_pandas_type({'name': 'a_datetime_with_tz', 'type': 'datetime', 'tz': 'US/Central'}) 'datetime64[ns, US/Central]' R)RtobjectR tint64R tfloat64R tboolRt timedelta64RR0sdatetime64[ns, {tz}]sdatetime64[ns]RR,R-R*R+s%Unsupported or invalid field type: {}N(tgetR#R t ValueError(R8ttyp((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pyt!convert_json_field_to_pandas_typexs*%         c Csm|tkrt|ƒ}ni}g}|r…|jjdkrlx@|jjD]}|jt|ƒƒqLWq…|jt|jƒƒn|jdkrÇxC|jƒD]\}}|jt|ƒƒq¡Wn|jt|ƒƒ||d<|r=|jj r=|dkr=|jjdkr*|jj g|d>> df = pd.DataFrame( ... {'A': [1, 2, 3], ... 'B': ['a', 'b', 'c'], ... 'C': pd.date_range('2016-01-01', freq='d', periods=3), ... }, index=pd.Index(range(3), name='idx')) >>> build_table_schema(df) {'fields': [{'name': 'idx', 'type': 'integer'}, {'name': 'A', 'type': 'integer'}, {'name': 'B', 'type': 'string'}, {'name': 'C', 'type': 'datetime'}], 'pandas_version': '0.20.0', 'primaryKey': ['idx']} itfieldst primaryKeys0.20.0tpandas_versionN( tTrueR'RR tlevelstappendR:tndimt iteritemst is_uniqueR"RR( R$Rt primary_keytversiontschemaRDtleveltcolumnts((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pytbuild_table_schema·s..     cCsht|d|ƒ}g|ddD]}|d^q!}t|dd|ƒ|}d„|ddDƒ}td„|jƒDƒƒr”td ƒ‚nd |jƒkrµtd ƒ‚n|j|ƒ}d |dkrd|j|dd ƒ}t|jj ƒd kr'|jj dkrad|j_ qaqdg|jj D]!}|j dƒrOdn|^q4|j_ n|S(s 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 t precise_floatRORDRR$tcolumnscSs#i|]}t|ƒ|d“qS(R(RC(RR8((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pys .s css$|]}t|ƒjdƒVqdS(sdatetime64[ns, N(tstrR(RR((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pys 2ss-table="orient" can not yet read timezone dataR?s<table="orient" can not yet read ISO-formatted Timedelta dataREiRRN( tloadsR RR(tNotImplementedErrortastypet set_indexRRRRR"R(tjsonRTttableR8t col_ordertdftdtypesR((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pytparse_table_schemas$$%:( t__doc__Rtpandas._libs.jsont_libsR[tpandas.core.dtypes.commonRRRRRRRRRtpandasR tpandas.api.typesR tpandas.core.commontcoretcommonRRWRR'R"R:RCRGRSR`(((s:lib/python2.7/site-packages/pandas/io/json/table_schema.pyts @  1   ?O