o i!@slUddlmZddlZddlmZddlmZddlmZm Z m Z ddl m Z ddl mZddlmZmZmZdd lmZdd lmZdd lmZeedd lmZmZmZWdn1scwYerdd lmZddlm Z ddl!Z"ddl#m$Z$m%Z%ddl m&Z&nddl'm!Z"d ddZ(ee)efZ*eeBe BZ+de,d<dgZ-d!ddZ.Gddde*Z/dS)") annotationsN) OrderedDict)Mapping) TYPE_CHECKINGLiteraloverload)PythonDataType)unstable)DataType DataTypeClassis_polars_dtype)parse_into_dtype)DuplicateError) CompatLevel)&init_polars_schema_from_arrow_c_schema'polars_schema_field_from_arrow_c_schemapolars_schema_to_pycapsule)Iterable) TypeAlias DataFrame LazyFrame)ArrowSchemaExportable)pyarrowtpr returnboolcCs t|jSN)r__annotations__)rrD/home/app/Keep/.python/lib/python3.10/site-packages/polars/schema.py_required_init_args"s r!rSchemaInitDataTypeSchemaDataType | DataTypeClassr cCs>t|ts|s|st|rd|}t||}|S)Nz%dtypes must be fully-specified, got: ) isinstancer Z is_nestedZ is_decimalr! TypeError)rmsgrrr _check_dtype,s  r(cseZdZdZ d9ddd:fd d Zd;ddZd;ddZd<fdd Zed=ddZ d>ddZ d?dd Z edd!d@d%d&Z e dAd*d+Ze d,d-dBd0d+Zdd-dCd2d+ZdDd4d5ZdEd7d8ZZS)Fr#aA Ordered mapping of column names to their data type. Parameters ---------- schema The schema definition given by column names and their associated Polars data type. Accepts a mapping, or an iterable of tuples, or any object implementing the `__arrow_c_schema__` PyCapsule interface (e.g. pyarrow schemas). Examples -------- Define a schema by passing instantiated data types. >>> schema = pl.Schema( ... { ... "foo": pl.String(), ... "bar": pl.Duration("us"), ... "baz": pl.Array(pl.Int8, 4), ... } ... ) >>> schema Schema({'foo': String, 'bar': Duration(time_unit='us'), 'baz': Array(Int8, shape=(4,))}) Access the data type associated with a specific column name. >>> schema["baz"] Array(Int8, shape=(4,)) Access various schema properties using the `names`, `dtypes`, and `len` methods. >>> schema.names() ['foo', 'bar', 'baz'] >>> schema.dtypes() [String, Duration(time_unit='us'), Array(Int8, shape=(4,))] >>> schema.len() 3 Import a pyarrow schema. >>> import pyarrow as pa >>> pl.Schema(pa.schema([pa.field("x", pa.int32())])) Schema({'x': Int32}) Export a schema to pyarrow. >>> pa.schema(pl.Schema({"x": pl.Int32})) x: int32 NT) check_dtypesschemaMapping[str, SchemaInitDataType] | Iterable[tuple[str, SchemaInitDataType] | ArrowSchemaExportable] | ArrowSchemaExportable | Noner)rrNonecst|drt|tst||dSt|tr|n|pd}|D]>}t|dr0t|ts0t|n|\}}||vrBd|d}t||sLt ||q t |rZt |t |q |||<q dS)N__arrow_c_schema__rz7iterable passed to pl.Schema contained duplicate name '') hasattrr%r#rritemsr rrsuper __setitem__r r()selfr*r)inputvnamerr' __class__rr __init__js(    zSchema.__init__otherobjectcCsft|tsdSt|t|krdSt||ddD]\\}}\}}||ks-||s0dSqdS)NFT)strict)r%rlenzipr0is_)r3r:Znm1Ztp1Znm2Ztp2rrr __eq__s &z Schema.__eq__cCs || Sr)r@)r3r:rrr __ne__s z Schema.__ne__r6strdtype)DataType | DataTypeClass | PythonDataTypecstt|}t||dSr)r(r r1r2)r3r6rCr7rr r2s zSchema.__setitem__cCst|tjS)z Export a Schema via the Arrow PyCapsule Interface. https://arrow.apache.org/docs/dev/format/CDataInterface/PyCapsuleInterface.html )rrnewest_versionr3rrr r-szSchema.__arrow_c_schema__ list[str]cC t|S)z Get the column names of the schema. Examples -------- >>> s = pl.Schema({"x": pl.Float64(), "y": pl.Datetime(time_zone="UTC")}) >>> s.names() ['x', 'y'] )listkeysrGrrr names z Schema.nameslist[DataType]cCrI)z Get the data types of the schema. Examples -------- >>> s = pl.Schema({"x": pl.UInt8(), "y": pl.List(pl.UInt8)}) >>> s.dtypes() [UInt8, List(UInt8)] )rJvaluesrGrrr dtypesrMz Schema.dtypes) compat_levelrQCompatLevel | None pa.SchemacCs2Gddd}t|||durtS|S)aI Convert the schema to a pyarrow schema. Parameters ---------- compat_level Use a specific compatibility level when exporting Polars' internal data types. Examples -------- >>> pl.Schema({"x": pl.String}).to_arrow() x: string_view c@s eZdZd ddZdd d Zd S)z.Schema.to_arrow..SchemaCapsuleProviderr*r#rQrrr,cSs||_||_dSr)r*rQ)r3r*rQrrr r9s z7Schema.to_arrow..SchemaCapsuleProvider.__init__r;cSst|j|jjSr)rr*rQrFrGrrr r-s zASchema.to_arrow..SchemaCapsuleProvider.__arrow_c_schema__N)r*r#rQrrr,rr;)__name__ __module__ __qualname__r9r-rrrr SchemaCapsuleProviders rXN)par*rrE)r3rQrXrrr to_arrows zSchema.to_arroweagerLiteral[False]rcCdSrrr3r[rrr to_framezSchema.to_frame.)r[ Literal[True]rcCr]rrr^rrr r_r`DataFrame | LazyFramecCs(ddlm}m}|r||dS||dS)u Create an empty DataFrame (or LazyFrame) from this Schema. Parameters ---------- eager If True, create a DataFrame; otherwise, create a LazyFrame. Examples -------- >>> s = pl.Schema({"x": pl.Int32(), "y": pl.String()}) >>> s.to_frame() shape: (0, 2) ┌─────┬─────┐ │ x ┆ y │ │ --- ┆ --- │ │ i32 ┆ str │ ╞═════╪═════╡ └─────┴─────┘ >>> s.to_frame(eager=False) # doctest: +IGNORE_RESULT rr)r*)polarsrr)r3r[rrrrr r_sintcCst|S)z Get the number of schema entries. Examples -------- >>> s = pl.Schema({"x": pl.Int32(), "y": pl.List(pl.String)}) >>> s.len() 2 >>> len(s) 2 )r=rGrrr r=s z Schema.lendict[str, type]cCsdd|DS)a Return a dictionary of column names and Python types. Examples -------- >>> s = pl.Schema( ... { ... "x": pl.Int8(), ... "y": pl.String(), ... "z": pl.Duration("us"), ... } ... ) >>> s.to_python() {'x': , 'y': , 'z': } cSsi|] \}}||qSr) to_python).0r6rrrr sz$Schema.to_python..)r0rGrrr rfszSchema.to_pythonr)r*r+r)rrr,)r:r;rr)r6rBrCrDrr,rT)rrH)rrN)rQrRrrS)r[r\rr)r[rarr)r[rrrb)rrd)rre)rUrVrW__doc__r9r@rAr2r r-rLrPrZrr_r=rf __classcell__rrr7r r#6s,:  "       )rr rr)rr$rr )0 __future__r contextlib collectionsrcollections.abcrtypingrrrZpolars._typingrZpolars._utils.unstabler Zpolars.datatypesr r r Zpolars.datatypes._parser Zpolars.exceptionsrZpolars.interchange.protocolrsuppress ImportErrorZ polars._plrrrrrrrrYrcrrrZpolars._dependenciesr!rBZ BaseSchemar"r__all__r(r#rrrr s6