forked from googleapis/python-bigquery-dataframes
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathseries.py
More file actions
1710 lines (1422 loc) · 63 KB
/
Copy pathseries.py
File metadata and controls
1710 lines (1422 loc) · 63 KB
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
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# Copyright 2023 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Series is a 1 dimensional data structure."""
from __future__ import annotations
import functools
import inspect
import itertools
import numbers
import textwrap
import typing
from typing import Any, cast, Literal, Mapping, Optional, Sequence, Tuple, Union
import bigframes_vendored.pandas.core.series as vendored_pandas_series
import google.cloud.bigquery as bigquery
import numpy
import pandas
import pandas.core.dtypes.common
import typing_extensions
import bigframes.constants as constants
import bigframes.core
from bigframes.core import log_adapter
import bigframes.core.block_transforms as block_ops
import bigframes.core.blocks as blocks
import bigframes.core.expression as ex
import bigframes.core.groupby as groupby
import bigframes.core.indexers
import bigframes.core.indexes as indexes
import bigframes.core.ordering as order
import bigframes.core.scalar as scalars
import bigframes.core.utils as utils
import bigframes.core.window
import bigframes.core.window_spec
import bigframes.dataframe
import bigframes.dtypes
import bigframes.formatting_helpers as formatter
import bigframes.operations as ops
import bigframes.operations.aggregations as agg_ops
import bigframes.operations.base
import bigframes.operations.datetimes as dt
import bigframes.operations.plotting as plotting
import bigframes.operations.strings as strings
import bigframes.operations.structs as structs
LevelType = typing.Union[str, int]
LevelsType = typing.Union[LevelType, typing.Sequence[LevelType]]
_remote_function_recommendation_message = (
"Your functions could not be applied directly to the Series."
" Try converting it to a remote function."
)
@log_adapter.class_logger
class Series(bigframes.operations.base.SeriesMethods, vendored_pandas_series.Series):
def __init__(self, *args, **kwargs):
self._query_job: Optional[bigquery.QueryJob] = None
super().__init__(*args, **kwargs)
@property
def dt(self) -> dt.DatetimeMethods:
return dt.DatetimeMethods(self._block)
@property
def dtype(self):
return self._dtype
@property
def dtypes(self):
return self._dtype
@property
def loc(self) -> bigframes.core.indexers.LocSeriesIndexer:
return bigframes.core.indexers.LocSeriesIndexer(self)
@property
def iloc(self) -> bigframes.core.indexers.IlocSeriesIndexer:
return bigframes.core.indexers.IlocSeriesIndexer(self)
@property
def iat(self) -> bigframes.core.indexers.IatSeriesIndexer:
return bigframes.core.indexers.IatSeriesIndexer(self)
@property
def at(self) -> bigframes.core.indexers.AtSeriesIndexer:
return bigframes.core.indexers.AtSeriesIndexer(self)
@property
def name(self) -> blocks.Label:
return self._name
@name.setter
def name(self, label: blocks.Label):
new_block = self._block.with_column_labels([label])
self._set_block(new_block)
@property
def shape(self) -> typing.Tuple[int]:
return (self._block.shape[0],)
@property
def size(self) -> int:
return self.shape[0]
@property
def ndim(self) -> int:
return 1
@property
def empty(self) -> bool:
return self.shape[0] == 0
@property
def hasnans(self) -> bool:
# Note, hasnans is actually a null check, and NaNs don't count for nullable float
return self.isnull().any()
@property
def values(self) -> numpy.ndarray:
return self.to_numpy()
@property
def index(self) -> indexes.Index:
return indexes.Index.from_frame(self)
@property
def query_job(self) -> Optional[bigquery.QueryJob]:
"""BigQuery job metadata for the most recent query.
Returns:
The most recent `QueryJob
<https://cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.job.QueryJob>`_.
"""
if self._query_job is None:
self._set_internal_query_job(self._compute_dry_run())
return self._query_job
@property
def struct(self) -> structs.StructAccessor:
return structs.StructAccessor(self._block)
@property
def T(self) -> Series:
return self.transpose()
@property
def _info_axis(self) -> indexes.Index:
return self.index
@property
def _session(self) -> bigframes.Session:
return self._get_block().expr.session
def transpose(self) -> Series:
return self
def _set_internal_query_job(self, query_job: bigquery.QueryJob):
self._query_job = query_job
def __len__(self):
return self.shape[0]
__len__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__len__)
def __iter__(self) -> typing.Iterator:
self._optimize_query_complexity()
return itertools.chain.from_iterable(
map(lambda x: x.squeeze(axis=1), self._block.to_pandas_batches())
)
def copy(self) -> Series:
return Series(self._block)
def rename(
self, index: Union[blocks.Label, Mapping[Any, Any]] = None, **kwargs
) -> Series:
if len(kwargs) != 0:
raise NotImplementedError(
f"rename does not currently support any keyword arguments. {constants.FEEDBACK_LINK}"
)
# rename the Series name
if index is None or isinstance(
index, str
): # Python 3.9 doesn't allow isinstance of Optional
index = typing.cast(Optional[str], index)
block = self._block.with_column_labels([index])
return Series(block)
# rename the index
if isinstance(index, Mapping):
index = typing.cast(Mapping[Any, Any], index)
block = self._block
for k, v in index.items():
new_idx_ids = []
for idx_id, idx_dtype in zip(block.index_columns, block.index.dtypes):
# Will throw if key type isn't compatible with index type, which leads to invalid SQL.
block.create_constant(k, dtype=idx_dtype)
# Will throw if value type isn't compatible with index type.
block, const_id = block.create_constant(v, dtype=idx_dtype)
block, cond_id = block.project_expr(
ops.ne_op.as_expr(idx_id, ex.const(k))
)
block, new_idx_id = block.apply_ternary_op(
idx_id, cond_id, const_id, ops.where_op
)
new_idx_ids.append(new_idx_id)
block = block.drop_columns([const_id, cond_id])
block = block.set_index(new_idx_ids, index_labels=block.index.names)
return Series(block)
# rename the Series name
if isinstance(index, typing.Hashable):
index = typing.cast(Optional[str], index)
block = self._block.with_column_labels([index])
return Series(block)
raise ValueError(f"Unsupported type of parameter index: {type(index)}")
def rename_axis(
self,
mapper: typing.Union[blocks.Label, typing.Sequence[blocks.Label]],
**kwargs,
) -> Series:
if len(kwargs) != 0:
raise NotImplementedError(
f"rename_axis does not currently support any keyword arguments. {constants.FEEDBACK_LINK}"
)
# limited implementation: the new index name is simply the 'mapper' parameter
if _is_list_like(mapper):
labels = mapper
else:
labels = [mapper]
return Series(self._block.with_index_labels(labels))
def equals(
self, other: typing.Union[Series, bigframes.dataframe.DataFrame]
) -> bool:
# Must be same object type, same column dtypes, and same label values
if not isinstance(other, Series):
return False
return block_ops.equals(self._block, other._block)
def reset_index(
self,
*,
name: typing.Optional[str] = None,
drop: bool = False,
) -> bigframes.dataframe.DataFrame | Series:
block = self._block.reset_index(drop)
if drop:
return Series(block)
else:
if name:
block = block.assign_label(self._value_column, name)
return bigframes.dataframe.DataFrame(block)
def __repr__(self) -> str:
# TODO(swast): Add a timeout here? If the query is taking a long time,
# maybe we just print the job metadata that we have so far?
# TODO(swast): Avoid downloading the whole series by using job
# metadata, like we do with DataFrame.
opts = bigframes.options.display
max_results = opts.max_rows
if opts.repr_mode == "deferred":
return formatter.repr_query_job(self.query_job)
self._cached()
pandas_df, _, query_job = self._block.retrieve_repr_request_results(max_results)
self._set_internal_query_job(query_job)
return repr(pandas_df.iloc[:, 0])
def astype(
self,
dtype: Union[bigframes.dtypes.DtypeString, bigframes.dtypes.Dtype],
) -> Series:
return self._apply_unary_op(bigframes.operations.AsTypeOp(to_type=dtype))
def to_pandas(
self,
max_download_size: Optional[int] = None,
sampling_method: Optional[str] = None,
random_state: Optional[int] = None,
*,
ordered: bool = True,
) -> pandas.Series:
"""Writes Series to pandas Series.
Args:
max_download_size (int, default None):
Download size threshold in MB. If max_download_size is exceeded when downloading data
(e.g., to_pandas()), the data will be downsampled if
bigframes.options.sampling.enable_downsampling is True, otherwise, an error will be
raised. If set to a value other than None, this will supersede the global config.
sampling_method (str, default None):
Downsampling algorithms to be chosen from, the choices are: "head": This algorithm
returns a portion of the data from the beginning. It is fast and requires minimal
computations to perform the downsampling; "uniform": This algorithm returns uniform
random samples of the data. If set to a value other than None, this will supersede
the global config.
random_state (int, default None):
The seed for the uniform downsampling algorithm. If provided, the uniform method may
take longer to execute and require more computation. If set to a value other than
None, this will supersede the global config.
ordered (bool, default True):
Determines whether the resulting pandas series will be deterministically ordered.
In some cases, unordered may result in a faster-executing query.
Returns:
pandas.Series: A pandas Series with all rows of this Series if the data_sampling_threshold_mb
is not exceeded; otherwise, a pandas Series with downsampled rows of the DataFrame.
"""
self._optimize_query_complexity()
df, query_job = self._block.to_pandas(
max_download_size=max_download_size,
sampling_method=sampling_method,
random_state=random_state,
ordered=ordered,
)
self._set_internal_query_job(query_job)
series = df.squeeze(axis=1)
series.name = self._name
return series
def _compute_dry_run(self) -> bigquery.QueryJob:
return self._block._compute_dry_run((self._value_column,))
def drop(
self,
labels: typing.Any = None,
*,
axis: typing.Union[int, str] = 0,
index: typing.Any = None,
columns: Union[blocks.Label, typing.Iterable[blocks.Label]] = None,
level: typing.Optional[LevelType] = None,
) -> Series:
if (labels is None) == (index is None):
raise ValueError("Must specify exactly one of 'labels' or 'index'")
if labels is not None:
index = labels
# ignore axis, columns params
block = self._block
level_id = self._resolve_levels(level or 0)[0]
if _is_list_like(index):
block, inverse_condition_id = block.apply_unary_op(
level_id, ops.IsInOp(values=tuple(index), match_nulls=True)
)
block, condition_id = block.apply_unary_op(
inverse_condition_id, ops.invert_op
)
else:
block, condition_id = block.project_expr(
ops.ne_op.as_expr(level_id, ex.const(index))
)
block = block.filter_by_id(condition_id, keep_null=True)
block = block.drop_columns([condition_id])
return Series(block.select_column(self._value_column))
def droplevel(self, level: LevelsType, axis: int | str = 0):
resolved_level_ids = self._resolve_levels(level)
return Series(self._block.drop_levels(resolved_level_ids))
def swaplevel(self, i: int = -2, j: int = -1):
level_i = self._block.index_columns[i]
level_j = self._block.index_columns[j]
mapping = {level_i: level_j, level_j: level_i}
reordering = [
mapping.get(index_id, index_id) for index_id in self._block.index_columns
]
return Series(self._block.reorder_levels(reordering))
def reorder_levels(self, order: LevelsType, axis: int | str = 0):
resolved_level_ids = self._resolve_levels(order)
return Series(self._block.reorder_levels(resolved_level_ids))
def _resolve_levels(self, level: LevelsType) -> typing.Sequence[str]:
return self._block.index.resolve_level(level)
def between(self, left, right, inclusive="both"):
if inclusive not in ["both", "neither", "left", "right"]:
raise ValueError(
"Must set 'inclusive' to one of 'both', 'neither', 'left', or 'right'"
)
left_op = ops.ge_op if (inclusive in ["left", "both"]) else ops.gt_op
right_op = ops.le_op if (inclusive in ["right", "both"]) else ops.lt_op
return self._apply_binary_op(left, left_op).__and__(
self._apply_binary_op(right, right_op)
)
def cumsum(self) -> Series:
return self._apply_window_op(
agg_ops.sum_op, bigframes.core.window_spec.WindowSpec(following=0)
)
def ffill(self, *, limit: typing.Optional[int] = None) -> Series:
window = bigframes.core.window_spec.WindowSpec(preceding=limit, following=0)
return self._apply_window_op(agg_ops.LastNonNullOp(), window)
pad = ffill
pad.__doc__ = inspect.getdoc(vendored_pandas_series.Series.ffill)
def bfill(self, *, limit: typing.Optional[int] = None) -> Series:
window = bigframes.core.window_spec.WindowSpec(preceding=0, following=limit)
return self._apply_window_op(agg_ops.FirstNonNullOp(), window)
def cummax(self) -> Series:
return self._apply_window_op(
agg_ops.max_op, bigframes.core.window_spec.WindowSpec(following=0)
)
def cummin(self) -> Series:
return self._apply_window_op(
agg_ops.min_op, bigframes.core.window_spec.WindowSpec(following=0)
)
def cumprod(self) -> Series:
return self._apply_window_op(
agg_ops.product_op, bigframes.core.window_spec.WindowSpec(following=0)
)
def shift(self, periods: int = 1) -> Series:
window = bigframes.core.window_spec.WindowSpec(
preceding=periods if periods > 0 else None,
following=-periods if periods < 0 else None,
)
return self._apply_window_op(agg_ops.ShiftOp(periods), window)
def diff(self, periods: int = 1) -> Series:
window = bigframes.core.window_spec.WindowSpec(
preceding=periods if periods > 0 else None,
following=-periods if periods < 0 else None,
)
return self._apply_window_op(agg_ops.DiffOp(periods), window)
def pct_change(self, periods: int = 1) -> Series:
# Future versions of pandas will not perfrom ffill automatically
series = self.ffill()
return Series(block_ops.pct_change(series._block, periods=periods))
def rank(
self,
axis=0,
method: str = "average",
numeric_only=False,
na_option: str = "keep",
ascending: bool = True,
) -> Series:
return Series(block_ops.rank(self._block, method, na_option, ascending))
def fillna(self, value=None) -> Series:
return self._apply_binary_op(value, ops.fillna_op)
def replace(
self, to_replace: typing.Any, value: typing.Any = None, *, regex: bool = False
):
if regex:
# No-op unless to_replace and series dtype are both string type
if not isinstance(to_replace, str) or not isinstance(
self.dtype, pandas.StringDtype
):
return self
return self._regex_replace(to_replace, value)
elif utils.is_dict_like(to_replace):
return self._mapping_replace(to_replace) # type: ignore
elif utils.is_list_like(to_replace):
replace_list = to_replace
else: # Scalar
replace_list = [to_replace]
replace_list = [
i for i in replace_list if bigframes.dtypes.is_compatible(i, self.dtype)
]
return self._simple_replace(replace_list, value) if replace_list else self
def _regex_replace(self, to_replace: str, value: str):
if not bigframes.dtypes.is_dtype(value, self.dtype):
raise NotImplementedError(
f"Cannot replace {self.dtype} elements with incompatible item {value} as mixed-type columns not supported. {constants.FEEDBACK_LINK}"
)
block, result_col = self._block.apply_unary_op(
self._value_column,
ops.RegexReplaceStrOp(to_replace, value),
result_label=self.name,
)
return Series(block.select_column(result_col))
def _simple_replace(self, to_replace_list: typing.Sequence, value):
result_type = bigframes.dtypes.is_compatible(value, self.dtype)
if not result_type:
raise NotImplementedError(
f"Cannot replace {self.dtype} elements with incompatible item {value} as mixed-type columns not supported. {constants.FEEDBACK_LINK}"
)
if result_type != self.dtype:
return self.astype(result_type)._simple_replace(to_replace_list, value)
block, cond = self._block.apply_unary_op(
self._value_column, ops.IsInOp(tuple(to_replace_list))
)
block, result_col = block.project_expr(
ops.where_op.as_expr(ex.const(value), cond, self._value_column), self.name
)
return Series(block.select_column(result_col))
def _mapping_replace(self, mapping: dict[typing.Hashable, typing.Hashable]):
tuples = []
lcd_types: list[typing.Optional[bigframes.dtypes.Dtype]] = []
for key, value in mapping.items():
lcd_type = bigframes.dtypes.is_compatible(key, self.dtype)
if not lcd_type:
continue
if not bigframes.dtypes.is_dtype(value, self.dtype):
raise NotImplementedError(
f"Cannot replace {self.dtype} elements with incompatible item {value} as mixed-type columns not supported. {constants.FEEDBACK_LINK}"
)
tuples.append((key, value))
lcd_types.append(lcd_type)
result_dtype = functools.reduce(
lambda t1, t2: bigframes.dtypes.lcd_type(t1, t2) if (t1 and t2) else None,
lcd_types,
)
if not result_dtype:
raise NotImplementedError(
f"Cannot replace {self.dtype} elements with incompatible mapping {mapping} as mixed-type columns not supported. {constants.FEEDBACK_LINK}"
)
block, result = self._block.apply_unary_op(
self._value_column, ops.MapOp(tuple(tuples))
)
return Series(block.select_column(result))
def interpolate(self, method: str = "linear") -> Series:
if method == "pad":
return self.ffill()
result = block_ops.interpolate(self._block, method)
return Series(result)
def dropna(
self,
*,
axis: int = 0,
inplace: bool = False,
how: typing.Optional[str] = None,
ignore_index: bool = False,
) -> Series:
if inplace:
raise NotImplementedError("'inplace'=True not supported")
result = block_ops.dropna(self._block, [self._value_column], how="any")
if ignore_index:
result = result.reset_index()
return Series(result)
def head(self, n: int = 5) -> Series:
return typing.cast(Series, self.iloc[0:n])
def tail(self, n: int = 5) -> Series:
return typing.cast(Series, self.iloc[-n:])
def nlargest(self, n: int = 5, keep: str = "first") -> Series:
if keep not in ("first", "last", "all"):
raise ValueError("'keep must be one of 'first', 'last', or 'all'")
return Series(
block_ops.nlargest(self._block, n, [self._value_column], keep=keep)
)
def nsmallest(self, n: int = 5, keep: str = "first") -> Series:
if keep not in ("first", "last", "all"):
raise ValueError("'keep must be one of 'first', 'last', or 'all'")
return Series(
block_ops.nsmallest(self._block, n, [self._value_column], keep=keep)
)
def isin(self, values) -> "Series" | None:
if not _is_list_like(values):
raise TypeError(
"only list-like objects are allowed to be passed to "
f"isin(), you passed a [{type(values).__name__}]"
)
return self._apply_unary_op(
ops.IsInOp(values=tuple(values), match_nulls=True)
).fillna(value=False)
def isna(self) -> "Series":
return self._apply_unary_op(ops.isnull_op)
isnull = isna
isnull.__doc__ = inspect.getdoc(vendored_pandas_series.Series.isna)
def notna(self) -> "Series":
return self._apply_unary_op(ops.notnull_op)
notnull = notna
notnull.__doc__ = inspect.getdoc(vendored_pandas_series.Series.notna)
def __and__(self, other: bool | int | Series) -> Series:
return self._apply_binary_op(other, ops.and_op)
__and__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__and__)
__rand__ = __and__
def __or__(self, other: bool | int | Series) -> Series:
return self._apply_binary_op(other, ops.or_op)
__or__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__or__)
__ror__ = __or__
def __add__(self, other: float | int | Series) -> Series:
return self.add(other)
__add__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__add__)
def __radd__(self, other: float | int | Series) -> Series:
return self.radd(other)
__radd__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__radd__)
def add(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.add_op)
def radd(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.add_op, reverse=True)
def __sub__(self, other: float | int | Series) -> Series:
return self.sub(other)
__sub__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__sub__)
def __rsub__(self, other: float | int | Series) -> Series:
return self.rsub(other)
__rsub__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__rsub__)
def sub(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.sub_op)
def rsub(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.sub_op, reverse=True)
subtract = sub
subtract.__doc__ = inspect.getdoc(vendored_pandas_series.Series.sub)
def __mul__(self, other: float | int | Series) -> Series:
return self.mul(other)
__mul__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__mul__)
def __rmul__(self, other: float | int | Series) -> Series:
return self.rmul(other)
__rmul__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__rmul__)
def mul(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.mul_op)
def rmul(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.mul_op, reverse=True)
multiply = mul
multiply.__doc__ = inspect.getdoc(vendored_pandas_series.Series.mul)
def __truediv__(self, other: float | int | Series) -> Series:
return self.truediv(other)
__truediv__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__truediv__)
def __rtruediv__(self, other: float | int | Series) -> Series:
return self.rtruediv(other)
__rtruediv__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__rtruediv__)
def truediv(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.div_op)
def rtruediv(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.div_op, reverse=True)
truediv.__doc__ = inspect.getdoc(vendored_pandas_series.Series.truediv)
div = divide = truediv
rdiv = rtruediv
rdiv.__doc__ = inspect.getdoc(vendored_pandas_series.Series.rtruediv)
def __floordiv__(self, other: float | int | Series) -> Series:
return self.floordiv(other)
__floordiv__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__floordiv__)
def __rfloordiv__(self, other: float | int | Series) -> Series:
return self.rfloordiv(other)
__rfloordiv__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__rfloordiv__)
def floordiv(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.floordiv_op)
def rfloordiv(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.floordiv_op, reverse=True)
def __pow__(self, other: float | int | Series) -> Series:
return self.pow(other)
__pow__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__pow__)
def __rpow__(self, other: float | int | Series) -> Series:
return self.rpow(other)
__rpow__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__rpow__)
def pow(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.pow_op)
def rpow(self, other: float | int | Series) -> Series:
return self._apply_binary_op(other, ops.pow_op, reverse=True)
def __lt__(self, other: float | int | Series) -> Series: # type: ignore
return self.lt(other)
def __le__(self, other: float | int | Series) -> Series: # type: ignore
return self.le(other)
def lt(self, other) -> Series:
return self._apply_binary_op(other, ops.lt_op)
def le(self, other) -> Series:
return self._apply_binary_op(other, ops.le_op)
def __gt__(self, other: float | int | Series) -> Series: # type: ignore
return self.gt(other)
def __ge__(self, other: float | int | Series) -> Series: # type: ignore
return self.ge(other)
def gt(self, other) -> Series:
return self._apply_binary_op(other, ops.gt_op)
def ge(self, other) -> Series:
return self._apply_binary_op(other, ops.ge_op)
def __mod__(self, other) -> Series: # type: ignore
return self.mod(other)
__mod__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__mod__)
def __rmod__(self, other) -> Series: # type: ignore
return self.rmod(other)
__rmod__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__rmod__)
def mod(self, other) -> Series: # type: ignore
return self._apply_binary_op(other, ops.mod_op)
def rmod(self, other) -> Series: # type: ignore
return self._apply_binary_op(other, ops.mod_op, reverse=True)
def divmod(self, other) -> Tuple[Series, Series]: # type: ignore
# TODO(huanc): when self and other both has dtype int and other contains zeros,
# the output should be dtype float, both floordiv and mod returns dtype int in this case.
return (self.floordiv(other), self.mod(other))
def rdivmod(self, other) -> Tuple[Series, Series]: # type: ignore
# TODO(huanc): when self and other both has dtype int and self contains zeros,
# the output should be dtype float, both floordiv and mod returns dtype int in this case.
return (self.rfloordiv(other), self.rmod(other))
def dot(self, other):
return (self * other).sum()
def __matmul__(self, other):
return self.dot(other)
__matmul__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__matmul__)
def __rmatmul__(self, other):
return self.dot(other)
__rmatmul__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__rmatmul__)
def combine_first(self, other: Series) -> Series:
result = self._apply_binary_op(other, ops.coalesce_op)
result.name = self.name
return result
def update(self, other: Union[Series, Sequence, Mapping]) -> None:
result = self._apply_binary_op(
other, ops.coalesce_op, reverse=True, alignment="left"
)
self._set_block(result._get_block())
def abs(self) -> Series:
return self._apply_unary_op(ops.abs_op)
def round(self, decimals=0) -> "Series":
return self._apply_binary_op(decimals, ops.round_op)
def corr(self, other: Series, method="pearson", min_periods=None) -> float:
# TODO(tbergeron): Validate early that both are numeric
# TODO(tbergeron): Handle partially-numeric columns
if method != "pearson":
raise NotImplementedError(
f"Only Pearson correlation is currently supported. {constants.FEEDBACK_LINK}"
)
if min_periods:
raise NotImplementedError(
f"min_periods not yet supported. {constants.FEEDBACK_LINK}"
)
return self._apply_binary_aggregation(other, agg_ops.CorrOp())
def autocorr(self, lag: int = 1) -> float:
return self.corr(self.shift(lag))
def cov(self, other: Series) -> float:
return self._apply_binary_aggregation(other, agg_ops.CovOp())
def all(self) -> bool:
return typing.cast(bool, self._apply_aggregation(agg_ops.all_op))
def any(self) -> bool:
return typing.cast(bool, self._apply_aggregation(agg_ops.any_op))
def count(self) -> int:
return typing.cast(int, self._apply_aggregation(agg_ops.count_op))
def nunique(self) -> int:
return typing.cast(int, self._apply_aggregation(agg_ops.nunique_op))
def max(self) -> scalars.Scalar:
return self._apply_aggregation(agg_ops.max_op)
def min(self) -> scalars.Scalar:
return self._apply_aggregation(agg_ops.min_op)
def std(self) -> float:
return typing.cast(float, self._apply_aggregation(agg_ops.std_op))
def var(self) -> float:
return typing.cast(float, self._apply_aggregation(agg_ops.var_op))
def _central_moment(self, n: int) -> float:
"""Useful helper for calculating central moment statistics"""
# Nth central moment is mean((x-mean(x))^n)
# See: https://en.wikipedia.org/wiki/Moment_(mathematics)
mean_deltas = self - self.mean()
delta_powers = mean_deltas**n
return delta_powers.mean()
def agg(self, func: str | typing.Sequence[str]) -> scalars.Scalar | Series:
if _is_list_like(func):
if self.dtype not in bigframes.dtypes.NUMERIC_BIGFRAMES_TYPES_PERMISSIVE:
raise NotImplementedError(
f"Multiple aggregations only supported on numeric series. {constants.FEEDBACK_LINK}"
)
aggregations = [agg_ops.lookup_agg_func(f) for f in func]
return Series(
self._block.summarize(
[self._value_column],
aggregations,
)
)
else:
return self._apply_aggregation(
agg_ops.lookup_agg_func(typing.cast(str, func))
)
aggregate = agg
aggregate.__doc__ = inspect.getdoc(vendored_pandas_series.Series.agg)
def skew(self):
count = self.count()
if count < 3:
return pandas.NA
moment3 = self._central_moment(3)
moment2 = self.var() * (count - 1) / count # Convert sample var to pop var
# See G1 estimator:
# https://en.wikipedia.org/wiki/Skewness#Sample_skewness
numerator = moment3
denominator = moment2 ** (3 / 2)
adjustment = (count * (count - 1)) ** 0.5 / (count - 2)
return (numerator / denominator) * adjustment
def kurt(self):
count = self.count()
if count < 4:
return pandas.NA
moment4 = self._central_moment(4)
moment2 = self.var() * (count - 1) / count # Convert sample var to pop var
# Kurtosis is often defined as the second standardize moment: moment(4)/moment(2)**2
# Pandas however uses Fisher’s estimator, implemented below
numerator = (count + 1) * (count - 1) * moment4
denominator = (count - 2) * (count - 3) * moment2**2
adjustment = 3 * (count - 1) ** 2 / ((count - 2) * (count - 3))
return (numerator / denominator) - adjustment
kurtosis = kurt
kurtosis.__doc__ = inspect.getdoc(vendored_pandas_series.Series.kurt)
def mode(self) -> Series:
block = self._block
# Approach: Count each value, return each value for which count(x) == max(counts))
block, agg_ids = block.aggregate(
by_column_ids=[self._value_column],
aggregations=((self._value_column, agg_ops.count_op),),
)
value_count_col_id = agg_ids[0]
block, max_value_count_col_id = block.apply_window_op(
value_count_col_id,
agg_ops.max_op,
window_spec=bigframes.core.window_spec.WindowSpec(),
)
block, is_mode_col_id = block.apply_binary_op(
value_count_col_id,
max_value_count_col_id,
ops.eq_op,
)
block = block.filter_by_id(is_mode_col_id)
# use temporary name for reset_index to avoid collision, restore after dropping extra columns
block = (
block.with_index_labels(["mode_temp_internal"])
.order_by([order.ascending_over(self._value_column)])
.reset_index(drop=False)
)
block = block.select_column(self._value_column).with_column_labels([self.name])
mode_values_series = Series(block.select_column(self._value_column))
return typing.cast(Series, mode_values_series)
def mean(self) -> float:
return typing.cast(float, self._apply_aggregation(agg_ops.mean_op))
def median(self, *, exact: bool = True) -> float:
if exact:
return typing.cast(float, self.quantile(0.5))
else:
return typing.cast(float, self._apply_aggregation(agg_ops.median_op))
def quantile(self, q: Union[float, Sequence[float]] = 0.5) -> Union[Series, float]:
qs = tuple(q) if utils.is_list_like(q) else (q,)
result = block_ops.quantile(self._block, (self._value_column,), qs=qs)
if utils.is_list_like(q):
result = result.stack()
result = result.drop_levels([result.index_columns[0]])
return Series(result)
else:
return cast(float, Series(result).to_pandas().squeeze())
def sum(self) -> float:
return typing.cast(float, self._apply_aggregation(agg_ops.sum_op))
def prod(self) -> float:
return typing.cast(float, self._apply_aggregation(agg_ops.product_op))
product = prod
product.__doc__ = inspect.getdoc(vendored_pandas_series.Series.prod)
def __eq__(self, other: object) -> Series: # type: ignore
return self.eq(other)
def __ne__(self, other: object) -> Series: # type: ignore
return self.ne(other)
def __invert__(self) -> Series:
return self._apply_unary_op(ops.invert_op)
__invert__.__doc__ = inspect.getdoc(vendored_pandas_series.Series.__invert__)
def eq(self, other: object) -> Series:
# TODO: enforce stricter alignment
return self._apply_binary_op(other, ops.eq_op)
def ne(self, other: object) -> Series: