o $&]i«'ã@sîddlmZddlmZmZmZddlmZmZddl m Z ddl m Z er>ddl mZddlmZddlmZdd lmZGd d „d e ƒZd(dd„Zd)dd„Zd*dd„Zd*dd„Zd*dd„Zd*dd„Zd*dd„Z  d+d,d%d&„Zgd'¢ZdS)-é)Ú annotations)Ú TYPE_CHECKINGÚAnyÚNoReturn)ÚExprKindÚExprNode)Úflatten)ÚExpr)ÚIterable)Útimezone)ÚDType)ÚTimeUnitc@sReZdZddd„Zddd„Zdd d „Zdd d „Zddd„Zddd„Zddd„Z dS)ÚSelectorÚreturnr cCs t|jŽS©N)r Ú_nodes)Úself©rúP/var/www/html/IGF-ODF-V3/venv/lib/python3.10/site-packages/narwhals/selectors.pyÚ_to_exprs zSelector._to_exprÚotherrcCs2t|tƒr d}t|ƒ‚| ¡ ttjd|dd¡S)Nz=unsupported operand type(s) for op: ('Selector' + 'Selector')Ú__add__T©Ú str_as_lit)Ú isinstancerÚ TypeErrorrÚ _append_noderrÚ ELEMENTWISE)rrÚmsgrrrrs ÿzSelector.__add__c Có@t|tƒr| ttjd|ddd¡S| ¡ ttjd|dd¡S)NÚ__or__T©rÚallow_multi_outputr©rrrrrrr©rrrrrr ó ûÿ ÿzSelector.__or__c Cr)NÚ__and__Tr!rr#r$rrrr&,r%zSelector.__and__rcCót‚r©ÚNotImplementedErrorr$rrrÚ__rsub__;ózSelector.__rsub__cCr'rr(r$rrrÚ__rand__>r+zSelector.__rand__cCr'rr(r$rrrÚ__ror__Ar+zSelector.__ror__N)rr )rrrr )rrrr) Ú__name__Ú __module__Ú __qualname__rrr r&r*r,r-rrrrrs      rÚdtypesú3DType | type[DType] | Iterable[DType | type[DType]]rcGst|ƒ}tttjd|dƒS)ajSelect columns based on their dtype. Arguments: dtypes: one or data types to select Examples: >>> import pyarrow as pa >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pa.table({"a": [1, 2], "b": ["x", "y"], "c": [4.1, 2.3]}) >>> df = nw.from_native(df_native) Let's select int64 and float64 dtypes and multiply each value by 2: >>> df.select(ncs.by_dtype(nw.Int64, nw.Float64) * 2).to_native() pyarrow.Table a: int64 c: double ---- a: [[2,4]] c: [[8.2,4.6]] zselectors.by_dtype)r1)rrrrÚSELECTOR)r1Ú flattenedrrrÚby_dtypeEsr5ÚpatternÚstrcCstttjd|dƒS)awSelect all columns that match the given regex pattern. Arguments: pattern: A valid regular expression pattern. Examples: >>> import pandas as pd >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pd.DataFrame( ... {"bar": [123, 456], "baz": [2.0, 5.5], "zap": [0, 1]} ... ) >>> df = nw.from_native(df_native) Let's select column names containing an 'a', preceded by a character that is not 'z': >>> df.select(ncs.matches("[^z]a")).to_native() bar baz 0 123 2.0 1 456 5.5 zselectors.matches©r6©rrrr3r8rrrÚmatches`sr:cCótttjdƒƒS)uÆSelect numeric columns. Examples: >>> import polars as pl >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pl.DataFrame({"a": [1, 2], "b": ["x", "y"], "c": [4.1, 2.3]}) >>> df = nw.from_native(df_native) Let's select numeric dtypes and multiply each value by 2: >>> df.select(ncs.numeric() * 2).to_native() shape: (2, 2) ┌─────┬─────┠│ a ┆ c │ │ --- ┆ --- │ │ i64 ┆ f64 │ â•žâ•â•â•â•â•â•ªâ•â•â•â•â•â•¡ │ 2 ┆ 8.2 │ │ 4 ┆ 4.6 │ └─────┴─────┘ zselectors.numericr9rrrrÚnumericyór<cCr;)u}Select boolean columns. Examples: >>> import polars as pl >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pl.DataFrame({"a": [1, 2], "b": ["x", "y"], "c": [False, True]}) >>> df = nw.from_native(df_native) Let's select boolean dtypes: >>> df.select(ncs.boolean()) ┌──────────────────┠|Narwhals DataFrame| |------------------| | shape: (2, 1) | | ┌───────┠| | │ c │ | | │ --- │ | | │ bool │ | | â•žâ•â•â•â•â•â•â•â•¡ | | │ false │ | | │ true │ | | └───────┘ | └──────────────────┘ zselectors.booleanr9rrrrÚboolean“sr>cCr;)uGSelect string columns. Examples: >>> import polars as pl >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pl.DataFrame({"a": [1, 2], "b": ["x", "y"], "c": [False, True]}) >>> df = nw.from_native(df_native) Let's select string dtypes: >>> df.select(ncs.string()).to_native() shape: (2, 1) ┌─────┠│ b │ │ --- │ │ str │ â•žâ•â•â•â•â•â•¡ │ x │ │ y │ └─────┘ zselectors.stringr9rrrrÚstring±r=r?cCr;)uÓSelect categorical columns. Examples: >>> import polars as pl >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pl.DataFrame({"a": [1, 2], "b": ["x", "y"], "c": [False, True]}) Let's convert column "b" to categorical, and then select categorical dtypes: >>> df = nw.from_native(df_native).with_columns( ... b=nw.col("b").cast(nw.Categorical()) ... ) >>> df.select(ncs.categorical()).to_native() shape: (2, 1) ┌─────┠│ b │ │ --- │ │ cat │ â•žâ•â•â•â•â•â•¡ │ x │ │ y │ └─────┘ zselectors.categoricalr9rrrrÚ categoricalËsr@cCr;)a¯Select all columns. Examples: >>> import pandas as pd >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pd.DataFrame({"a": [1, 2], "b": ["x", "y"], "c": [False, True]}) >>> df = nw.from_native(df_native) Let's select all dtypes: >>> df.select(ncs.all()).to_native() a b c 0 1 x False 1 2 y True z selectors.allr9rrrrÚallçsrAN©Ú*NÚ time_unitú$TimeUnit | Iterable[TimeUnit] | NoneÚ time_zoneú7str | timezone | Iterable[str | timezone | None] | NonecCstttjd||dƒS)aéSelect all datetime columns, optionally filtering by time unit/zone. Arguments: time_unit: One (or more) of the allowed timeunit precision strings, "ms", "us", "ns" and "s". Omit to select columns with any valid timeunit. time_zone: Specify which timezone(s) to select * One or more timezone strings, as defined in zoneinfo (to see valid options run `import zoneinfo; zoneinfo.available_timezones()` for a full list). * Set `None` to select Datetime columns that do not have a timezone. * Set `"*"` to select Datetime columns that have *any* timezone. Examples: >>> from datetime import datetime, timezone >>> import pyarrow as pa >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> >>> utc_tz = timezone.utc >>> data = { ... "tstamp_utc": [ ... datetime(2023, 4, 10, 12, 14, 16, 999000, tzinfo=utc_tz), ... datetime(2025, 8, 25, 14, 18, 22, 666000, tzinfo=utc_tz), ... ], ... "tstamp": [ ... datetime(2000, 11, 20, 18, 12, 16, 600000), ... datetime(2020, 10, 30, 10, 20, 25, 123000), ... ], ... "numeric": [3.14, 6.28], ... } >>> df_native = pa.table(data) >>> df_nw = nw.from_native(df_native) >>> df_nw.select(ncs.datetime()).to_native() pyarrow.Table tstamp_utc: timestamp[us, tz=UTC] tstamp: timestamp[us] ---- tstamp_utc: [[2023-04-10 12:14:16.999000Z,2025-08-25 14:18:22.666000Z]] tstamp: [[2000-11-20 18:12:16.600000,2020-10-30 10:20:25.123000]] Select only datetime columns that have any time_zone specification: >>> df_nw.select(ncs.datetime(time_zone="*")).to_native() pyarrow.Table tstamp_utc: timestamp[us, tz=UTC] ---- tstamp_utc: [[2023-04-10 12:14:16.999000Z,2025-08-25 14:18:22.666000Z]] zselectors.datetime©rDrFr9rHrrrÚdatetimeûs4üÿrI)rAr>r5r@rIr:r<r?)r1r2rr)r6r7rr)rr)NrB)rDrErFrGrr)Ú __future__rÚtypingrrrÚnarwhals._expression_parsingrrÚnarwhals._utilsrÚ narwhals.exprr Úcollections.abcr rIr Únarwhals.dtypesr Únarwhals.typingr rr5r:r<r>r?r@rAÚ__all__rrrrÚs,        4       þ >