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
|
"""Almost entirely complete, generic `selectors` implementation."""
from __future__ import annotations
import re
from functools import partial
from typing import (
TYPE_CHECKING,
Collection,
Iterable,
Iterator,
Protocol,
Sequence,
TypeVar,
overload,
)
from narwhals._compliant.expr import CompliantExpr
from narwhals._typing_compat import Protocol38
from narwhals._utils import (
_parse_time_unit_and_time_zone,
dtype_matches_time_unit_and_time_zone,
get_column_names,
is_compliant_dataframe,
)
if TYPE_CHECKING:
from datetime import timezone
from typing_extensions import Self, TypeAlias, TypeIs
from narwhals._compliant.expr import NativeExpr
from narwhals._compliant.typing import (
CompliantDataFrameAny,
CompliantExprAny,
CompliantFrameAny,
CompliantLazyFrameAny,
CompliantSeriesAny,
CompliantSeriesOrNativeExprAny,
EvalNames,
EvalSeries,
ScalarKwargs,
)
from narwhals._utils import Implementation, Version, _FullContext
from narwhals.dtypes import DType
from narwhals.typing import TimeUnit
__all__ = [
"CompliantSelector",
"CompliantSelectorNamespace",
"EagerSelectorNamespace",
"LazySelectorNamespace",
]
SeriesOrExprT = TypeVar("SeriesOrExprT", bound="CompliantSeriesOrNativeExprAny")
SeriesT = TypeVar("SeriesT", bound="CompliantSeriesAny")
ExprT = TypeVar("ExprT", bound="NativeExpr")
FrameT = TypeVar("FrameT", bound="CompliantFrameAny")
DataFrameT = TypeVar("DataFrameT", bound="CompliantDataFrameAny")
LazyFrameT = TypeVar("LazyFrameT", bound="CompliantLazyFrameAny")
SelectorOrExpr: TypeAlias = (
"CompliantSelector[FrameT, SeriesOrExprT] | CompliantExpr[FrameT, SeriesOrExprT]"
)
class CompliantSelectorNamespace(Protocol[FrameT, SeriesOrExprT]):
_implementation: Implementation
_backend_version: tuple[int, ...]
_version: Version
@classmethod
def from_namespace(cls, context: _FullContext, /) -> Self:
obj = cls.__new__(cls)
obj._implementation = context._implementation
obj._backend_version = context._backend_version
obj._version = context._version
return obj
@property
def _selector(self) -> type[CompliantSelector[FrameT, SeriesOrExprT]]: ...
def _iter_columns(self, df: FrameT, /) -> Iterator[SeriesOrExprT]: ...
def _iter_schema(self, df: FrameT, /) -> Iterator[tuple[str, DType]]: ...
def _iter_columns_dtypes(
self, df: FrameT, /
) -> Iterator[tuple[SeriesOrExprT, DType]]: ...
def _iter_columns_names(self, df: FrameT, /) -> Iterator[tuple[SeriesOrExprT, str]]:
yield from zip(self._iter_columns(df), df.columns)
def _is_dtype(
self: CompliantSelectorNamespace[FrameT, SeriesOrExprT], dtype: type[DType], /
) -> CompliantSelector[FrameT, SeriesOrExprT]:
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
return [
ser for ser, tp in self._iter_columns_dtypes(df) if isinstance(tp, dtype)
]
def names(df: FrameT) -> Sequence[str]:
return [name for name, tp in self._iter_schema(df) if isinstance(tp, dtype)]
return self._selector.from_callables(series, names, context=self)
def by_dtype(
self, dtypes: Collection[DType | type[DType]]
) -> CompliantSelector[FrameT, SeriesOrExprT]:
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
return [ser for ser, tp in self._iter_columns_dtypes(df) if tp in dtypes]
def names(df: FrameT) -> Sequence[str]:
return [name for name, tp in self._iter_schema(df) if tp in dtypes]
return self._selector.from_callables(series, names, context=self)
def matches(self, pattern: str) -> CompliantSelector[FrameT, SeriesOrExprT]:
p = re.compile(pattern)
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
if (
is_compliant_dataframe(df)
and not self._implementation.is_duckdb()
and not self._implementation.is_ibis()
):
return [df.get_column(col) for col in df.columns if p.search(col)]
return [ser for ser, name in self._iter_columns_names(df) if p.search(name)]
def names(df: FrameT) -> Sequence[str]:
return [col for col in df.columns if p.search(col)]
return self._selector.from_callables(series, names, context=self)
def numeric(self) -> CompliantSelector[FrameT, SeriesOrExprT]:
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
return [ser for ser, tp in self._iter_columns_dtypes(df) if tp.is_numeric()]
def names(df: FrameT) -> Sequence[str]:
return [name for name, tp in self._iter_schema(df) if tp.is_numeric()]
return self._selector.from_callables(series, names, context=self)
def categorical(self) -> CompliantSelector[FrameT, SeriesOrExprT]:
return self._is_dtype(self._version.dtypes.Categorical)
def string(self) -> CompliantSelector[FrameT, SeriesOrExprT]:
return self._is_dtype(self._version.dtypes.String)
def boolean(self) -> CompliantSelector[FrameT, SeriesOrExprT]:
return self._is_dtype(self._version.dtypes.Boolean)
def all(self) -> CompliantSelector[FrameT, SeriesOrExprT]:
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
return list(self._iter_columns(df))
return self._selector.from_callables(series, get_column_names, context=self)
def datetime(
self,
time_unit: TimeUnit | Iterable[TimeUnit] | None,
time_zone: str | timezone | Iterable[str | timezone | None] | None,
) -> CompliantSelector[FrameT, SeriesOrExprT]:
time_units, time_zones = _parse_time_unit_and_time_zone(time_unit, time_zone)
matches = partial(
dtype_matches_time_unit_and_time_zone,
dtypes=self._version.dtypes,
time_units=time_units,
time_zones=time_zones,
)
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
return [ser for ser, tp in self._iter_columns_dtypes(df) if matches(tp)]
def names(df: FrameT) -> Sequence[str]:
return [name for name, tp in self._iter_schema(df) if matches(tp)]
return self._selector.from_callables(series, names, context=self)
class EagerSelectorNamespace(
CompliantSelectorNamespace[DataFrameT, SeriesT], Protocol[DataFrameT, SeriesT]
):
def _iter_schema(self, df: DataFrameT, /) -> Iterator[tuple[str, DType]]:
for ser in self._iter_columns(df):
yield ser.name, ser.dtype
def _iter_columns(self, df: DataFrameT, /) -> Iterator[SeriesT]:
yield from df.iter_columns()
def _iter_columns_dtypes(self, df: DataFrameT, /) -> Iterator[tuple[SeriesT, DType]]:
for ser in self._iter_columns(df):
yield ser, ser.dtype
class LazySelectorNamespace(
CompliantSelectorNamespace[LazyFrameT, ExprT], Protocol[LazyFrameT, ExprT]
):
def _iter_schema(self, df: LazyFrameT) -> Iterator[tuple[str, DType]]:
yield from df.schema.items()
def _iter_columns(self, df: LazyFrameT) -> Iterator[ExprT]:
yield from df._iter_columns()
def _iter_columns_dtypes(self, df: LazyFrameT, /) -> Iterator[tuple[ExprT, DType]]:
yield from zip(self._iter_columns(df), df.schema.values())
class CompliantSelector(
CompliantExpr[FrameT, SeriesOrExprT], Protocol38[FrameT, SeriesOrExprT]
):
_call: EvalSeries[FrameT, SeriesOrExprT]
_window_function: None
_function_name: str
_depth: int
_implementation: Implementation
_backend_version: tuple[int, ...]
_version: Version
_scalar_kwargs: ScalarKwargs
@classmethod
def from_callables(
cls,
call: EvalSeries[FrameT, SeriesOrExprT],
evaluate_output_names: EvalNames[FrameT],
*,
context: _FullContext,
) -> Self:
obj = cls.__new__(cls)
obj._call = call
obj._window_function = None
obj._depth = 0
obj._function_name = "selector"
obj._evaluate_output_names = evaluate_output_names
obj._alias_output_names = None
obj._implementation = context._implementation
obj._backend_version = context._backend_version
obj._version = context._version
obj._scalar_kwargs = {}
return obj
@property
def selectors(self) -> CompliantSelectorNamespace[FrameT, SeriesOrExprT]:
return self.__narwhals_namespace__().selectors
def _to_expr(self) -> CompliantExpr[FrameT, SeriesOrExprT]: ...
def _is_selector(
self, other: Self | CompliantExpr[FrameT, SeriesOrExprT]
) -> TypeIs[CompliantSelector[FrameT, SeriesOrExprT]]:
return isinstance(other, type(self))
@overload
def __sub__(self, other: Self) -> Self: ...
@overload
def __sub__(
self, other: CompliantExpr[FrameT, SeriesOrExprT]
) -> CompliantExpr[FrameT, SeriesOrExprT]: ...
def __sub__(
self, other: SelectorOrExpr[FrameT, SeriesOrExprT]
) -> SelectorOrExpr[FrameT, SeriesOrExprT]:
if self._is_selector(other):
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
lhs_names, rhs_names = _eval_lhs_rhs(df, self, other)
return [
x for x, name in zip(self(df), lhs_names) if name not in rhs_names
]
def names(df: FrameT) -> Sequence[str]:
lhs_names, rhs_names = _eval_lhs_rhs(df, self, other)
return [x for x in lhs_names if x not in rhs_names]
return self.selectors._selector.from_callables(series, names, context=self)
return self._to_expr() - other
@overload
def __or__(self, other: Self) -> Self: ...
@overload
def __or__(
self, other: CompliantExpr[FrameT, SeriesOrExprT]
) -> CompliantExpr[FrameT, SeriesOrExprT]: ...
def __or__(
self, other: SelectorOrExpr[FrameT, SeriesOrExprT]
) -> SelectorOrExpr[FrameT, SeriesOrExprT]:
if self._is_selector(other):
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
lhs_names, rhs_names = _eval_lhs_rhs(df, self, other)
return [
*(x for x, name in zip(self(df), lhs_names) if name not in rhs_names),
*other(df),
]
def names(df: FrameT) -> Sequence[str]:
lhs_names, rhs_names = _eval_lhs_rhs(df, self, other)
return [*(x for x in lhs_names if x not in rhs_names), *rhs_names]
return self.selectors._selector.from_callables(series, names, context=self)
return self._to_expr() | other
@overload
def __and__(self, other: Self) -> Self: ...
@overload
def __and__(
self, other: CompliantExpr[FrameT, SeriesOrExprT]
) -> CompliantExpr[FrameT, SeriesOrExprT]: ...
def __and__(
self, other: SelectorOrExpr[FrameT, SeriesOrExprT]
) -> SelectorOrExpr[FrameT, SeriesOrExprT]:
if self._is_selector(other):
def series(df: FrameT) -> Sequence[SeriesOrExprT]:
lhs_names, rhs_names = _eval_lhs_rhs(df, self, other)
return [x for x, name in zip(self(df), lhs_names) if name in rhs_names]
def names(df: FrameT) -> Sequence[str]:
lhs_names, rhs_names = _eval_lhs_rhs(df, self, other)
return [x for x in lhs_names if x in rhs_names]
return self.selectors._selector.from_callables(series, names, context=self)
return self._to_expr() & other
def __invert__(self) -> CompliantSelector[FrameT, SeriesOrExprT]:
return self.selectors.all() - self
def _eval_lhs_rhs(
df: CompliantFrameAny, lhs: CompliantExprAny, rhs: CompliantExprAny
) -> tuple[Sequence[str], Sequence[str]]:
return lhs._evaluate_output_names(df), rhs._evaluate_output_names(df)
|
