forked from data-apis/dataframe-api
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdataframe_object.py
525 lines (426 loc) · 12.7 KB
/
dataframe_object.py
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
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
from __future__ import annotations
from typing import Sequence, Union, TYPE_CHECKING
if TYPE_CHECKING:
from .column_object import Column
from .groupby_object import GroupBy
from ._types import Scalar
__all__ = ["DataFrame"]
class DataFrame:
@property
def dataframe(self) -> object:
"""
Return underlying (not-necessarily-Standard-compliant) DataFrame.
If a library only implements the Standard, then this can return `self`.
"""
...
def groupby(self, keys: Sequence[str], /) -> GroupBy:
"""
Group the DataFrame by the given columns.
Parameters
----------
keys : Sequence[str]
Returns
-------
GroupBy
Raises
------
KeyError
If any of the requested keys are not present.
Notes
-----
Downstream operations from this function, like aggregations, return
results for which row order is not guaranteed and is implementation
defined.
"""
...
def get_column_by_name(self, name: str, /) -> Column:
"""
Select a column by name.
Parameters
----------
name : str
Returns
-------
Column
Raises
------
KeyError
If the key is not present.
"""
...
def get_columns_by_name(self, names: Sequence[str], /) -> DataFrame:
"""
Select multiple columns by name.
Parameters
----------
names : Sequence[str]
Returns
-------
DataFrame
Raises
------
KeyError
If the any requested key is not present.
"""
...
def get_rows(self, indices: Sequence[int]) -> DataFrame:
"""
Select a subset of rows, similar to `ndarray.take`.
Parameters
----------
indices : Sequence[int]
Positions of rows to select.
Returns
-------
DataFrame
Notes
-----
Some discussion participants prefer a stricter type Column[int] for
indices in order to make it easier to implement in a performant manner
on GPUs.
"""
...
def slice_rows(
self, start: int | None, stop: int | None, step: int | None
) -> DataFrame:
"""
Select a subset of rows corresponding to a slice.
Parameters
----------
start : int or None
stop : int or None
step : int or None
Returns
-------
DataFrame
"""
...
def get_rows_by_mask(self, mask: "Column[bool]") -> DataFrame:
"""
Select a subset of rows corresponding to a mask.
Parameters
----------
mask : Column[bool]
Returns
-------
DataFrame
Notes
-----
Some participants preferred a weaker type Arraylike[bool] for mask,
where 'Arraylike' denotes an object adhering to the Array API standard.
"""
...
def insert(self, loc: int, label: str, value: Column) -> DataFrame:
"""
Insert column into DataFrame at specified location.
Parameters
----------
loc : int
Insertion index. Must verify 0 <= loc <= len(columns).
label : str
Label of the inserted column.
value : Column
"""
...
def drop_column(self, label: str) -> DataFrame:
"""
Drop the specified column.
Parameters
----------
label : str
Returns
-------
DataFrame
Raises
------
KeyError
If the label is not present.
"""
...
def set_column(self, label: str, value: Column) -> DataFrame:
"""
Add or replace a column.
Parameters
----------
label : str
value : Column
Returns
-------
DataFrame
"""
...
def __eq__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Compare for equality.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __ne__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Compare for non-equality.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __ge__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Compare for "greater than or equal to" `other`.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __gt__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Compare for "greater than" `other`.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __le__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Compare for "less than or equal to" `other`.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __lt__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Compare for "less than" `other`.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __add__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Add `other` dataframe or scalar to this dataframe.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __sub__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Subtract `other` dataframe or scalar from this dataframe.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __mul__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Multiply `other` dataframe or scalar with this dataframe.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __truediv__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Divide this dataframe by `other` dataframe or scalar. True division, returns floats.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __floordiv__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Floor-divide (returns integers) this dataframe by `other` dataframe or scalar.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __pow__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Raise this dataframe to the power of `other`.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __mod__(self, other: DataFrame | Scalar) -> DataFrame:
"""
Return modulus of this dataframe by `other` (`%` operator).
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
DataFrame
"""
...
def __divmod__(self, other: DataFrame | Scalar) -> tuple[DataFrame, DataFrame]:
"""
Return quotient and remainder of integer division. See `divmod` builtin function.
Parameters
----------
other : DataFrame or Scalar
If DataFrame, must have same length and matching columns.
"Scalar" here is defined implicitly by what scalar types are allowed
for the operation by the underling dtypes.
Returns
-------
A tuple of two DataFrame's
"""
...
def any(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def all(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def min(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def max(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def sum(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def prod(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def median(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def mean(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def std(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def var(self, skipna: bool = True) -> DataFrame:
"""
Reduction returns a 1-row DataFrame.
"""
...
def isnull(self) -> DataFrame:
"""
Check for 'missing' or 'null' entries.
Returns
-------
DataFrame
See also
--------
isnan
Notes
-----
Does *not* include NaN-like entries.
"""
...
def isnan(self) -> DataFrame:
"""
Check for nan-like entries.
Returns
-------
DataFrame
See also
--------
isnull
Notes
-----
Includes anything with NaN-like semantics, e.g. np.datetime64("NaT").
Does *not* include 'missing' or 'null' entries.
"""
...