1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
|
from __future__ import annotations
from typing import TYPE_CHECKING, Any, Iterable, NoReturn
from narwhals._expression_parsing import ExprMetadata, combine_metadata
from narwhals._utils import flatten
from narwhals.expr import Expr
if TYPE_CHECKING:
from datetime import timezone
from narwhals.dtypes import DType
from narwhals.typing import TimeUnit
class Selector(Expr):
def _to_expr(self) -> Expr:
return Expr(self._to_compliant_expr, self._metadata)
def __add__(self, other: Any) -> Expr: # type: ignore[override]
if isinstance(other, Selector):
msg = "unsupported operand type(s) for op: ('Selector' + 'Selector')"
raise TypeError(msg)
return self._to_expr() + other # type: ignore[no-any-return]
def __or__(self, other: Any) -> Expr: # type: ignore[override]
if isinstance(other, Selector):
return self.__class__(
lambda plx: self._to_compliant_expr(plx) | other._to_compliant_expr(plx),
combine_metadata(
self,
other,
str_as_lit=False,
allow_multi_output=True,
to_single_output=False,
),
)
return self._to_expr() | other # type: ignore[no-any-return]
def __and__(self, other: Any) -> Expr: # type: ignore[override]
if isinstance(other, Selector):
return self.__class__(
lambda plx: self._to_compliant_expr(plx) & other._to_compliant_expr(plx),
combine_metadata(
self,
other,
str_as_lit=False,
allow_multi_output=True,
to_single_output=False,
),
)
return self._to_expr() & other # type: ignore[no-any-return]
def __rsub__(self, other: Any) -> NoReturn:
raise NotImplementedError
def __rand__(self, other: Any) -> NoReturn:
raise NotImplementedError
def __ror__(self, other: Any) -> NoReturn:
raise NotImplementedError
def by_dtype(*dtypes: DType | type[DType] | Iterable[DType | type[DType]]) -> Selector:
"""Select 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]]
"""
flattened = flatten(dtypes)
return Selector(
lambda plx: plx.selectors.by_dtype(flattened),
ExprMetadata.selector_multi_unnamed(),
)
def matches(pattern: str) -> Selector:
"""Select 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
"""
return Selector(
lambda plx: plx.selectors.matches(pattern), ExprMetadata.selector_multi_unnamed()
)
def numeric() -> Selector:
"""Select 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 │
└─────┴─────┘
"""
return Selector(
lambda plx: plx.selectors.numeric(), ExprMetadata.selector_multi_unnamed()
)
def boolean() -> Selector:
"""Select 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 │ |
| └───────┘ |
└──────────────────┘
"""
return Selector(
lambda plx: plx.selectors.boolean(), ExprMetadata.selector_multi_unnamed()
)
def string() -> Selector:
"""Select 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 │
└─────┘
"""
return Selector(
lambda plx: plx.selectors.string(), ExprMetadata.selector_multi_unnamed()
)
def categorical() -> Selector:
"""Select 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 │
└─────┘
"""
return Selector(
lambda plx: plx.selectors.categorical(), ExprMetadata.selector_multi_unnamed()
)
def all() -> Selector:
"""Select 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
"""
return Selector(
lambda plx: plx.selectors.all(), ExprMetadata.selector_multi_unnamed()
)
def datetime(
time_unit: TimeUnit | Iterable[TimeUnit] | None = None,
time_zone: str | timezone | Iterable[str | timezone | None] | None = ("*", None),
) -> Selector:
"""Select 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]]
"""
return Selector(
lambda plx: plx.selectors.datetime(time_unit=time_unit, time_zone=time_zone),
ExprMetadata.selector_multi_unnamed(),
)
__all__ = [
"all",
"boolean",
"by_dtype",
"categorical",
"datetime",
"matches",
"numeric",
"string",
]
|
