2iD/JdZddlmZddlmZmZmZddlZddlm Z ddl m Z ddl m Z ddlmZdd lmZdd lmZdd lmZmZmZmZdd lmZmZmZmZdd lm Z ddl!m"cm#Z$ddl%m&Z&erddl'm(Z(m)Z)ddlm*Z*ddl+m,Z,dZ-ddZ.dZ/ddZ0ddZ1 d ddZ2ddZ3y)zH Table Schema builders https://specs.frictionlessdata.io/table-schema/ ) annotations) TYPE_CHECKINGAnycastN)option_context)lib) ujson_loads) timezones)find_stack_level) _registry) is_bool_dtypeis_integer_dtypeis_numeric_dtypeis_string_dtype)CategoricalDtypeDatetimeTZDtypeExtensionDtype PeriodDtype) DataFrame) to_offset)DtypeObjJSONSerializable)Series) MultiIndexz1.4.0ct|ryt|ryt|rytj|dst |t tfrytj|dryt|ryy ) a Convert a NumPy / pandas type to its corresponding json_table. Parameters ---------- x : np.dtype or ExtensionDtype Returns ------- str the Table Schema data types Notes ----- This table shows the relationship between NumPy / pandas dtypes, and Table Schema dtypes. ============== ================= Pandas type Table Schema type ============== ================= int64 integer float64 number bool boolean datetime64[ns] datetime timedelta64[ns] duration object str categorical any =============== ================= integerbooleannumberMdatetimemdurationstringany) rr rr is_np_dtype isinstancerrr)xs S/var/www/html/acx/venv/lib/python3.12/site-packages/pandas/io/json/_table_schema.pyas_json_table_typer)7sc< q  !  C Jq?K2P$Q C   ctj|jjr|jj}t |dk(r:|jj dk(r!t jdt|St |dkDr1td|Drt jdt|S|jd}|jjdkDr:tj|jj|j_|S|jj xsd|j_|S) z?Sets index names to 'index' for regular, or 'level_x' for Multiindexz-Index name of 'index' is not round-trippable.) stacklevelc3>K|]}|jdyw)level_N) startswith).0r's r( z$set_default_names..ns!FQ!,,x"8!Fsz *!JJj Lr*c |d}|dk(r|jddS|dk(r|jddS|dk(r|jddS|d k(r|jdd S|d k(ry |d k(rU|jdr d|ddS|jdr)t|d}t|j}d|dSy|dk(r;d|vrd|vrt |dd|dSd|vrt j |dSytd|)a  Converts a JSON field descriptor into its corresponding NumPy / pandas type Parameters ---------- field A JSON field descriptor Returns ------- dtype Raises ------ ValueError If the type of the provided field is unknown or currently unsupported Examples -------- >>> convert_json_field_to_pandas_type({"name": "an_int", "type": "integer"}) 'int64' >>> convert_json_field_to_pandas_type( ... { ... "name": "a_categorical", ... "type": "any", ... "constraints": {"enum": ["a", "b", "c"]}, ... "ordered": True, ... } ... ) CategoricalDtype(categories=['a', 'b', 'c'], ordered=True, categories_dtype=str) >>> convert_json_field_to_pandas_type({"name": "a_datetime", "type": "datetime"}) 'datetime64[ns]' >>> convert_json_field_to_pandas_type( ... {"name": "a_datetime_with_tz", "type": "datetime", "tz": "US/Central"} ... ) 'datetime64[ns, US/Central]' rDr#rKNrint64rfloat64rboolr" timedelta64r rJzdatetime64[ns, ]rHzperiod[zdatetime64[ns]r$rFrGrE)rMrGobjectz#Unsupported or invalid field type: )getrr_freqstrrregistryfind ValueError)rTtypoffsetrHs r(!convert_json_field_to_pandas_typerfsHR -C hyyT** yyW-- yyY// yyV,,   99T?$U4[M3 3 YYv uV}-Fv&//DTF!$ $#  E !i5&8# /7yAQ 5 ==z!23 3 :3%@ AAr*cV|dur t|}i}g}|r|jjdkDr{td|j|_t |jj |jj dD]&\}}t|}||d<|j|(n$|jt|j|jdkDr3|jD]\} } |jt| !n|jt|||d<|rf|jjrP|N|jjdk(r|jjg|d<n!|jj |d<n|||d<|r t|d<|S) a Create a Table schema from ``data``. This method is a utility to generate a JSON-serializable schema representation of a pandas Series or DataFrame, compatible with the Table Schema specification. It enables structured data to be shared and validated in various applications, ensuring consistency and interoperability. Parameters ---------- data : Series or DataFrame The input data for which the table schema is to be created. 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 A dictionary representing the Table schema. See Also -------- DataFrame.to_json : Convert the object to a JSON string. read_json : Convert a JSON string to pandas object. 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', 'extDtype': 'str'}, {'name': 'C', 'type': 'datetime'}], 'primaryKey': ['idx'], 'pandas_version': '1.4.0'} Tr,r)strictr9fields primaryKeypandas_version)rAr-r=rziplevelsr7rWappendndimitems is_uniquer9TABLE_SCHEMA_VERSION) r?r- primary_keyversionschemarilevelr9 new_fieldcolumnss r(build_table_schemarzswJ } &F F ::   !lDJJ7DJ"4::#4#4djj6F6FtT ) t=eD $( &! i( ) MM;DJJG H yy1} @IFA MM;A> ? @  7=>F8 %%+*= ::   "$(JJOO#4F< #'::#3#3F<  *|#7 Mr*ct||}|ddDcgc]}|d }}t|d||}|ddDcic]}|dt|}}d|jvr t dt d d 5|j |}d d d d |dvr|j|dd }t|jjd k(r,|jjdk(rd |j_ |S|jjDcgc]}|jdrd n|c}|j_ |Scc}wcc}w#1swYxYwcc}w)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_floatrurir9r?)columnsr\zrs # )))49  0 4+\0@IB\# f f ff f ! fR@r*