Wh*ddlmZddlmZmZmZddlmZmZddl m Z ddl m Z erddl mZddlmZddlmZdd lmZGd d e Zdd Zdd ZddZddZddZddZddZ d ddZgdZy)) annotations) TYPE_CHECKINGAnyNoReturn) ExprMetadatacombine_metadata)flatten)Expr)Iterable)timezone)DType)TimeUnitcDeZdZd dZd dZd dZd dZd dZd dZd dZ y) SelectorcBt|j|jSN)r _to_compliant_expr _metadata)selfs L/var/www/html/jupyter_env/lib/python3.12/site-packages/narwhals/selectors.py_to_exprzSelector._to_exprsD++T^^<<cbt|tr d}t||j|zS)Nz=unsupported operand type(s) for op: ('Selector' + 'Selector')) isinstancer TypeErrorr)rothermsgs r__add__zSelector.__add__s, eX &QCC. }}&&rc ttr$jfdtdddSj zS)NcJj|j|zSrrplxrrs rz!Selector.__or__..#D33C85;S;STW;XXrFT str_as_litallow_multi_outputto_single_outputrr __class__rrrrs``r__or__zSelector.__or__K eX &>>X $'+%*   }}&&rc ttr$jfdtdddSj zS)NcJj|j|zSrr!r"s rr$z"Selector.__and__..,r%rFTr&r*r,s``r__and__zSelector.__and__)r.rctrNotImplementedErrorr,s r__rsub__zSelector.__rsub__7!!rctrr3r,s r__rand__zSelector.__rand__:r6rctrr3r,s r__ror__zSelector.__ror__=r6rN)returnr )rrr;r )rrr;r) __name__ __module__ __qualname__rrr-r1r5r8r:rrrrs%=' ' '"""rrc\t|tfdtjS)aSelect columns based on their dtype. Arguments: dtypes: one or data types to select Returns: A new expression. Examples: >>> import pyarrow as pa >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pa.table({"a": [1, 2], "b": ["x", "y"], "c": [4.1, 2.3]}) >>> df = nw.from_native(df_native) Let's select int64 and float64 dtypes and multiply each value by 2: >>> df.select(ncs.by_dtype(nw.Int64, nw.Float64) * 2).to_native() pyarrow.Table a: int64 c: double ---- a: [[2,4]] c: [[8.2,4.6]] c:|jjSr) selectorsby_dtype)r# flatteneds rr$zby_dtype..]sCMM**95r)r rrselector_multi_unnamed)dtypesrDs @rrCrCAs*4I 5++- rcFtfdtjS)aSelect all columns that match the given regex pattern. Arguments: pattern: A valid regular expression pattern. Returns: A new expression. 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 c:|jjSr)rBmatches)r#patterns rr$zmatches..|sCMM))'2rrrrE)rJs`rrIrIbs 2 2L4W4W4Y rc@tdtjS)uSelect numeric columns. Returns: A new expression. Examples: >>> import polars as pl >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pl.DataFrame({"a": [1, 2], "b": ["x", "y"], "c": [4.1, 2.3]}) >>> df = nw.from_native(df_native) Let's select numeric dtypes and multiply each value by 2: >>> df.select(ncs.numeric() * 2).to_native() shape: (2, 2) ┌─────┬─────┐ │ a ┆ c │ │ --- ┆ --- │ │ i64 ┆ f64 │ ╞═════╪═════╡ │ 2 ┆ 8.2 │ │ 4 ┆ 4.6 │ └─────┴─────┘ c6|jjSr)rBnumericr#s rr$znumeric..CMM))+rrKr?rrrNrNs4 +\-P-P-R rc@tdtjS)uSelect boolean columns. Returns: A new expression. 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 │ | | ╞═══════╡ | | │ false │ | | │ true │ | | └───────┘ | └──────────────────┘ c6|jjSr)rBbooleanrOs rr$zboolean..rPrrKr?rrrSrSs< +\-P-P-R rc@tdtjS)uoSelect string columns. Returns: A new expression. Examples: >>> import polars as pl >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pl.DataFrame({"a": [1, 2], "b": ["x", "y"], "c": [False, True]}) >>> df = nw.from_native(df_native) Let's select string dtypes: >>> df.select(ncs.string()).to_native() shape: (2, 1) ┌─────┐ │ b │ │ --- │ │ str │ ╞═════╡ │ x │ │ y │ └─────┘ c6|jjSr)rBstringrOs rr$zstring..sCMM((*rrKr?rrrVrVs4 *L,O,O,Q rc@tdtjS)uSelect categorical columns. Returns: A new expression. 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 │ ╞═════╡ │ x │ │ y │ └─────┘ c6|jjSr)rB categoricalrOs rr$zcategorical..sCMM--/rrKr?rrrYrYs8 /1T1T1V rc@tdtjS)aSelect all columns. Returns: A new expression. Examples: >>> import pandas as pd >>> import narwhals as nw >>> import narwhals.selectors as ncs >>> df_native = pd.DataFrame({"a": [1, 2], "b": ["x", "y"], "c": [False, True]}) >>> df = nw.from_native(df_native) Let's select all dtypes: >>> df.select(ncs.all()).to_native() a b c 0 1 x False 1 2 y True c6|jjSr)rBallrOs rr$zall..sCMM%%'rrKr?rrr\r\s( ')L)L)N rNcJtfdtjS)aSelect 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. Returns: A new expression. 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]] c>|jjS)N time_unit time_zone)rBdatetime)r#r`ras rr$zdatetime..SsCMM**Y)*TrrKr_s``rrbrbs"n T++- r)r\rSrCrYrbrIrNrV)rFz3DType | type[DType] | Iterable[DType | type[DType]]r;r)rJstrr;r)r;r)N)*N)r`z$TimeUnit | Iterable[TimeUnit] | Noneraz7str | timezone | Iterable[str | timezone | None] | Noner;r) __future__rtypingrrrnarwhals._expression_parsingrrnarwhals._utilsr narwhals.exprr collections.abcr rbr narwhals.dtypesr narwhals.typingrrrCrIrNrSrVrYr\__all__r?rrrns"//G#(!%(-"t-"`B<> F>B47;IT:3:F::z r