forked from googleapis/python-bigquery-dataframes
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_dataframe.py
More file actions
5400 lines (4253 loc) · 173 KB
/
Copy pathtest_dataframe.py
File metadata and controls
5400 lines (4253 loc) · 173 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.
import io
import operator
import sys
import tempfile
import typing
from typing import Dict, List, Tuple
import geopandas as gpd # type: ignore
import numpy as np
import pandas as pd
import pandas.testing
import pyarrow as pa # type: ignore
import pytest
import bigframes
import bigframes._config.display_options as display_options
import bigframes.core.indexes as bf_indexes
import bigframes.dataframe as dataframe
import bigframes.pandas as bpd
import bigframes.series as series
from tests.system.utils import (
assert_dfs_equivalent,
assert_pandas_df_equal,
assert_series_equal,
assert_series_equivalent,
skip_legacy_pandas,
)
def test_df_construct_copy(scalars_dfs):
columns = ["int64_col", "string_col", "float64_col"]
scalars_df, scalars_pandas_df = scalars_dfs
# Make the mapping from label to col_id non-trivial
bf_df = scalars_df.copy()
bf_df["int64_col"] = bf_df["int64_col"] / 2
pd_df = scalars_pandas_df.copy()
pd_df["int64_col"] = pd_df["int64_col"] / 2
bf_result = dataframe.DataFrame(bf_df, columns=columns).to_pandas()
pd_result = pd.DataFrame(pd_df, columns=columns)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_df_construct_pandas_default(scalars_dfs):
# This should trigger the inlined codepath
columns = [
"int64_too",
"int64_col",
"float64_col",
"bool_col",
"string_col",
"date_col",
"datetime_col",
"numeric_col",
"float64_col",
"time_col",
"timestamp_col",
]
_, scalars_pandas_df = scalars_dfs
bf_result = dataframe.DataFrame(scalars_pandas_df, columns=columns).to_pandas()
pd_result = pd.DataFrame(scalars_pandas_df, columns=columns)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_df_construct_large_strings():
data = [["hello", "w" + "o" * 50000 + "rld"]]
bf_result = dataframe.DataFrame(data).to_pandas()
pd_result = pd.DataFrame(data, dtype=pd.StringDtype(storage="pyarrow"))
pandas.testing.assert_frame_equal(bf_result, pd_result, check_index_type=False)
def test_df_construct_pandas_load_job(scalars_dfs_maybe_ordered):
# This should trigger the inlined codepath
columns = [
"int64_too",
"int64_col",
"float64_col",
"bool_col",
"string_col",
"date_col",
"datetime_col",
"numeric_col",
"float64_col",
"time_col",
"timestamp_col",
"geography_col",
]
_, scalars_pandas_df = scalars_dfs_maybe_ordered
bf_result = dataframe.DataFrame(scalars_pandas_df, columns=columns)
pd_result = pd.DataFrame(scalars_pandas_df, columns=columns)
assert_dfs_equivalent(pd_result, bf_result)
def test_df_construct_structs(session):
pd_frame = pd.Series(
[
{"version": 1, "project": "pandas"},
{"version": 2, "project": "pandas"},
{"version": 1, "project": "numpy"},
]
).to_frame()
bf_series = session.read_pandas(pd_frame)
pd.testing.assert_frame_equal(
bf_series.to_pandas(), pd_frame, check_index_type=False, check_dtype=False
)
def test_df_construct_pandas_set_dtype(scalars_dfs):
columns = [
"int64_too",
"int64_col",
"float64_col",
"bool_col",
]
_, scalars_pandas_df = scalars_dfs
bf_result = dataframe.DataFrame(
scalars_pandas_df, columns=columns, dtype="Float64"
).to_pandas()
pd_result = pd.DataFrame(scalars_pandas_df, columns=columns, dtype="Float64")
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_df_construct_from_series(scalars_dfs_maybe_ordered):
scalars_df, scalars_pandas_df = scalars_dfs_maybe_ordered
bf_result = dataframe.DataFrame(
{"a": scalars_df["int64_col"], "b": scalars_df["string_col"]},
dtype="string[pyarrow]",
)
pd_result = pd.DataFrame(
{"a": scalars_pandas_df["int64_col"], "b": scalars_pandas_df["string_col"]},
dtype="string[pyarrow]",
)
assert_dfs_equivalent(pd_result, bf_result)
def test_df_construct_from_dict():
input_dict = {
"Animal": ["Falcon", "Falcon", "Parrot", "Parrot"],
# With a space in column name. We use standardized SQL schema ids to solve the problem that BQ schema doesn't support column names with spaces. b/296751058
"Max Speed": [380.0, 370.0, 24.0, 26.0],
}
bf_result = dataframe.DataFrame(input_dict).to_pandas()
pd_result = pd.DataFrame(input_dict)
pandas.testing.assert_frame_equal(
bf_result, pd_result, check_dtype=False, check_index_type=False
)
def test_df_construct_inline_respects_location():
# Note: This starts a thread-local session.
with bpd.option_context("bigquery.location", "europe-west1"):
df = bpd.DataFrame([[1, 2, 3], [4, 5, 6]])
repr(df)
assert df.query_job is not None
table = bpd.get_global_session().bqclient.get_table(df.query_job.destination)
assert table.location == "europe-west1"
def test_df_construct_dtype():
data = {
"int_col": [1, 2, 3],
"string_col": ["1.1", "2.0", "3.5"],
"float_col": [1.0, 2.0, 3.0],
}
dtype = pd.StringDtype(storage="pyarrow")
bf_result = dataframe.DataFrame(data, dtype=dtype)
pd_result = pd.DataFrame(data, dtype=dtype)
pd_result.index = pd_result.index.astype("Int64")
pandas.testing.assert_frame_equal(bf_result.to_pandas(), pd_result)
def test_get_column(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
col_name = "int64_col"
series = scalars_df[col_name]
bf_result = series.to_pandas()
pd_result = scalars_pandas_df[col_name]
assert_series_equal(bf_result, pd_result)
def test_get_column_nonstring(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
series = scalars_df.rename(columns={"int64_col": 123.1})[123.1]
bf_result = series.to_pandas()
pd_result = scalars_pandas_df.rename(columns={"int64_col": 123.1})[123.1]
assert_series_equal(bf_result, pd_result)
def test_hasattr(scalars_dfs):
scalars_df, _ = scalars_dfs
assert hasattr(scalars_df, "int64_col")
assert hasattr(scalars_df, "head")
assert not hasattr(scalars_df, "not_exist")
@pytest.mark.parametrize(
("ordered"),
[
(True),
(False),
],
)
def test_head_with_custom_column_labels(
scalars_df_index, scalars_pandas_df_index, ordered
):
rename_mapping = {
"int64_col": "Integer Column",
"string_col": "言語列",
}
bf_df = scalars_df_index.rename(columns=rename_mapping).head(3)
bf_result = bf_df.to_pandas(ordered=ordered)
pd_result = scalars_pandas_df_index.rename(columns=rename_mapping).head(3)
assert_pandas_df_equal(bf_result, pd_result, ignore_order=not ordered)
def test_tail_with_custom_column_labels(scalars_df_index, scalars_pandas_df_index):
rename_mapping = {
"int64_col": "Integer Column",
"string_col": "言語列",
}
bf_df = scalars_df_index.rename(columns=rename_mapping).tail(3)
bf_result = bf_df.to_pandas()
pd_result = scalars_pandas_df_index.rename(columns=rename_mapping).tail(3)
pandas.testing.assert_frame_equal(bf_result, pd_result)
@pytest.mark.parametrize(
("keep",),
[
("first",),
("last",),
("all",),
],
)
def test_df_nlargest(scalars_df_index, scalars_pandas_df_index, keep):
bf_result = scalars_df_index.nlargest(3, ["bool_col", "int64_too"], keep=keep)
pd_result = scalars_pandas_df_index.nlargest(
3, ["bool_col", "int64_too"], keep=keep
)
pd.testing.assert_frame_equal(
bf_result.to_pandas(),
pd_result,
)
@pytest.mark.parametrize(
("keep",),
[
("first",),
("last",),
("all",),
],
)
def test_df_nsmallest(scalars_df_index, scalars_pandas_df_index, keep):
bf_result = scalars_df_index.nsmallest(6, ["bool_col"], keep=keep)
pd_result = scalars_pandas_df_index.nsmallest(6, ["bool_col"], keep=keep)
pd.testing.assert_frame_equal(
bf_result.to_pandas(),
pd_result,
)
def test_get_column_by_attr(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
series = scalars_df.int64_col
bf_result = series.to_pandas()
pd_result = scalars_pandas_df.int64_col
assert_series_equal(bf_result, pd_result)
def test_get_columns(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
col_names = ["bool_col", "float64_col", "int64_col"]
df_subset = scalars_df.get(col_names)
df_pandas = df_subset.to_pandas()
pd.testing.assert_index_equal(
df_pandas.columns, scalars_pandas_df[col_names].columns
)
def test_get_columns_default(scalars_dfs):
scalars_df, _ = scalars_dfs
col_names = ["not", "column", "names"]
result = scalars_df.get(col_names, "default_val")
assert result == "default_val"
@pytest.mark.parametrize(
("loc", "column", "value", "allow_duplicates"),
[
(0, 666, 2, False),
(5, "float64_col", 2.2, True),
(13, "rowindex_2", [8, 7, 6, 5, 4, 3, 2, 1, 0], True),
pytest.param(
14,
"test",
2,
False,
marks=pytest.mark.xfail(
raises=IndexError,
),
),
pytest.param(
12,
"int64_col",
2,
False,
marks=pytest.mark.xfail(
raises=ValueError,
),
),
],
)
def test_insert(scalars_dfs, loc, column, value, allow_duplicates):
scalars_df, scalars_pandas_df = scalars_dfs
# insert works inplace, so will influence other tests.
# make a copy to avoid inplace changes.
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
bf_df.insert(loc, column, value, allow_duplicates)
pd_df.insert(loc, column, value, allow_duplicates)
pd.testing.assert_frame_equal(bf_df.to_pandas(), pd_df, check_dtype=False)
def test_where_series_cond(scalars_df_index, scalars_pandas_df_index):
# Condition is dataframe, other is None (as default).
cond_bf = scalars_df_index["int64_col"] > 0
cond_pd = scalars_pandas_df_index["int64_col"] > 0
bf_result = scalars_df_index.where(cond_bf).to_pandas()
pd_result = scalars_pandas_df_index.where(cond_pd)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_mask_series_cond(scalars_df_index, scalars_pandas_df_index):
cond_bf = scalars_df_index["int64_col"] > 0
cond_pd = scalars_pandas_df_index["int64_col"] > 0
bf_df = scalars_df_index[["int64_too", "int64_col", "float64_col"]]
pd_df = scalars_pandas_df_index[["int64_too", "int64_col", "float64_col"]]
bf_result = bf_df.mask(cond_bf, bf_df + 1).to_pandas()
pd_result = pd_df.mask(cond_pd, pd_df + 1)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_where_series_multi_index(scalars_df_index, scalars_pandas_df_index):
# Test when a dataframe has multi-index or multi-columns.
columns = ["int64_col", "float64_col"]
dataframe_bf = scalars_df_index[columns]
dataframe_bf.columns = pd.MultiIndex.from_tuples(
[("str1", 1), ("str2", 2)], names=["STR", "INT"]
)
cond_bf = dataframe_bf["str1"] > 0
with pytest.raises(NotImplementedError) as context:
dataframe_bf.where(cond_bf).to_pandas()
assert (
str(context.value)
== "The dataframe.where() method does not support multi-index and/or multi-column."
)
def test_where_series_cond_const_other(scalars_df_index, scalars_pandas_df_index):
# Condition is a series, other is a constant.
columns = ["int64_col", "float64_col"]
dataframe_bf = scalars_df_index[columns]
dataframe_pd = scalars_pandas_df_index[columns]
dataframe_bf.columns.name = "test_name"
dataframe_pd.columns.name = "test_name"
cond_bf = dataframe_bf["int64_col"] > 0
cond_pd = dataframe_pd["int64_col"] > 0
other = 0
bf_result = dataframe_bf.where(cond_bf, other).to_pandas()
pd_result = dataframe_pd.where(cond_pd, other)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_where_series_cond_dataframe_other(scalars_df_index, scalars_pandas_df_index):
# Condition is a series, other is a dataframe.
columns = ["int64_col", "float64_col"]
dataframe_bf = scalars_df_index[columns]
dataframe_pd = scalars_pandas_df_index[columns]
cond_bf = dataframe_bf["int64_col"] > 0
cond_pd = dataframe_pd["int64_col"] > 0
other_bf = -dataframe_bf
other_pd = -dataframe_pd
bf_result = dataframe_bf.where(cond_bf, other_bf).to_pandas()
pd_result = dataframe_pd.where(cond_pd, other_pd)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_where_dataframe_cond(scalars_df_index, scalars_pandas_df_index):
# Condition is a dataframe, other is None.
columns = ["int64_col", "float64_col"]
dataframe_bf = scalars_df_index[columns]
dataframe_pd = scalars_pandas_df_index[columns]
cond_bf = dataframe_bf > 0
cond_pd = dataframe_pd > 0
bf_result = dataframe_bf.where(cond_bf, None).to_pandas()
pd_result = dataframe_pd.where(cond_pd, None)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_where_dataframe_cond_const_other(scalars_df_index, scalars_pandas_df_index):
# Condition is a dataframe, other is a constant.
columns = ["int64_col", "float64_col"]
dataframe_bf = scalars_df_index[columns]
dataframe_pd = scalars_pandas_df_index[columns]
cond_bf = dataframe_bf > 0
cond_pd = dataframe_pd > 0
other_bf = 10
other_pd = 10
bf_result = dataframe_bf.where(cond_bf, other_bf).to_pandas()
pd_result = dataframe_pd.where(cond_pd, other_pd)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_where_dataframe_cond_dataframe_other(
scalars_df_index, scalars_pandas_df_index
):
# Condition is a dataframe, other is a dataframe.
columns = ["int64_col", "float64_col"]
dataframe_bf = scalars_df_index[columns]
dataframe_pd = scalars_pandas_df_index[columns]
cond_bf = dataframe_bf > 0
cond_pd = dataframe_pd > 0
other_bf = dataframe_bf * 2
other_pd = dataframe_pd * 2
bf_result = dataframe_bf.where(cond_bf, other_bf).to_pandas()
pd_result = dataframe_pd.where(cond_pd, other_pd)
pandas.testing.assert_frame_equal(bf_result, pd_result)
def test_drop_column(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
col_name = "int64_col"
df_pandas = scalars_df.drop(columns=col_name).to_pandas()
pd.testing.assert_index_equal(
df_pandas.columns, scalars_pandas_df.drop(columns=col_name).columns
)
def test_drop_columns(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
col_names = ["int64_col", "geography_col", "time_col"]
df_pandas = scalars_df.drop(columns=col_names).to_pandas()
pd.testing.assert_index_equal(
df_pandas.columns, scalars_pandas_df.drop(columns=col_names).columns
)
def test_drop_labels_axis_1(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
labels = ["int64_col", "geography_col", "time_col"]
pd_result = scalars_pandas_df.drop(labels=labels, axis=1)
bf_result = scalars_df.drop(labels=labels, axis=1).to_pandas()
pd.testing.assert_frame_equal(pd_result, bf_result)
def test_drop_with_custom_column_labels(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
rename_mapping = {
"int64_col": "Integer Column",
"string_col": "言語列",
}
dropped_columns = [
"言語列",
"timestamp_col",
]
bf_df = scalars_df.rename(columns=rename_mapping).drop(columns=dropped_columns)
bf_result = bf_df.to_pandas()
pd_result = scalars_pandas_df.rename(columns=rename_mapping).drop(
columns=dropped_columns
)
assert_pandas_df_equal(bf_result, pd_result)
def test_df_memory_usage(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
pd_result = scalars_pandas_df.memory_usage()
bf_result = scalars_df.memory_usage()
pd.testing.assert_series_equal(pd_result, bf_result, rtol=1.5)
def test_df_info(scalars_dfs):
expected = (
"<class 'bigframes.dataframe.DataFrame'>\n"
"Index: 9 entries, 0 to 8\n"
"Data columns (total 13 columns):\n"
" # Column Non-Null Count Dtype\n"
"--- ------------- ---------------- ------------------------------\n"
" 0 bool_col 8 non-null boolean\n"
" 1 bytes_col 6 non-null binary[pyarrow]\n"
" 2 date_col 7 non-null date32[day][pyarrow]\n"
" 3 datetime_col 6 non-null timestamp[us][pyarrow]\n"
" 4 geography_col 4 non-null geometry\n"
" 5 int64_col 8 non-null Int64\n"
" 6 int64_too 9 non-null Int64\n"
" 7 numeric_col 6 non-null decimal128(38, 9)[pyarrow]\n"
" 8 float64_col 7 non-null Float64\n"
" 9 rowindex_2 9 non-null Int64\n"
" 10 string_col 8 non-null string\n"
" 11 time_col 6 non-null time64[us][pyarrow]\n"
" 12 timestamp_col 6 non-null timestamp[us, tz=UTC][pyarrow]\n"
"dtypes: Float64(1), Int64(3), binary[pyarrow](1), boolean(1), date32[day][pyarrow](1), decimal128(38, 9)[pyarrow](1), geometry(1), string(1), time64[us][pyarrow](1), timestamp[us, tz=UTC][pyarrow](1), timestamp[us][pyarrow](1)\n"
"memory usage: 1269 bytes\n"
)
scalars_df, _ = scalars_dfs
bf_result = io.StringIO()
scalars_df.info(buf=bf_result)
assert expected == bf_result.getvalue()
@pytest.mark.parametrize(
("include", "exclude"),
[
("Int64", None),
(["int"], None),
("number", None),
([pd.Int64Dtype(), pd.BooleanDtype()], None),
(None, [pd.Int64Dtype(), pd.BooleanDtype()]),
("Int64", ["boolean"]),
],
)
def test_select_dtypes(scalars_dfs, include, exclude):
scalars_df, scalars_pandas_df = scalars_dfs
pd_result = scalars_pandas_df.select_dtypes(include=include, exclude=exclude)
bf_result = scalars_df.select_dtypes(include=include, exclude=exclude).to_pandas()
pd.testing.assert_frame_equal(pd_result, bf_result)
def test_drop_index(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
pd_result = scalars_pandas_df.drop(index=[4, 1, 2])
bf_result = scalars_df.drop(index=[4, 1, 2]).to_pandas()
pd.testing.assert_frame_equal(pd_result, bf_result)
def test_drop_pandas_index(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
drop_index = scalars_pandas_df.iloc[[4, 1, 2]].index
pd_result = scalars_pandas_df.drop(index=drop_index)
bf_result = scalars_df.drop(index=drop_index).to_pandas()
pd.testing.assert_frame_equal(pd_result, bf_result)
def test_drop_bigframes_index(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
drop_index = scalars_df.loc[[4, 1, 2]].index
drop_pandas_index = scalars_pandas_df.loc[[4, 1, 2]].index
pd_result = scalars_pandas_df.drop(index=drop_pandas_index)
bf_result = scalars_df.drop(index=drop_index).to_pandas()
pd.testing.assert_frame_equal(pd_result, bf_result)
def test_drop_bigframes_index_with_na(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
scalars_df = scalars_df.copy()
scalars_pandas_df = scalars_pandas_df.copy()
scalars_df = scalars_df.set_index("bytes_col")
scalars_pandas_df = scalars_pandas_df.set_index("bytes_col")
drop_index = scalars_df.iloc[[3, 5]].index
drop_pandas_index = scalars_pandas_df.iloc[[3, 5]].index
pd_result = scalars_pandas_df.drop(index=drop_pandas_index) # drop_pandas_index)
bf_result = scalars_df.drop(index=drop_index).to_pandas()
pd.testing.assert_frame_equal(pd_result, bf_result)
@skip_legacy_pandas
def test_drop_bigframes_multiindex(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
scalars_df = scalars_df.copy()
scalars_pandas_df = scalars_pandas_df.copy()
sub_df = scalars_df.iloc[[4, 1, 2]]
sub_pandas_df = scalars_pandas_df.iloc[[4, 1, 2]]
sub_df = sub_df.set_index(["bytes_col", "numeric_col"])
sub_pandas_df = sub_pandas_df.set_index(["bytes_col", "numeric_col"])
drop_index = sub_df.index
drop_pandas_index = sub_pandas_df.index
scalars_df = scalars_df.set_index(["bytes_col", "numeric_col"])
scalars_pandas_df = scalars_pandas_df.set_index(["bytes_col", "numeric_col"])
bf_result = scalars_df.drop(index=drop_index).to_pandas()
pd_result = scalars_pandas_df.drop(index=drop_pandas_index)
pd.testing.assert_frame_equal(pd_result, bf_result)
def test_drop_labels_axis_0(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
pd_result = scalars_pandas_df.drop(labels=[4, 1, 2], axis=0)
bf_result = scalars_df.drop(labels=[4, 1, 2], axis=0).to_pandas()
pd.testing.assert_frame_equal(pd_result, bf_result)
def test_drop_index_and_columns(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
pd_result = scalars_pandas_df.drop(index=[4, 1, 2], columns="int64_col")
bf_result = scalars_df.drop(index=[4, 1, 2], columns="int64_col").to_pandas()
pd.testing.assert_frame_equal(pd_result, bf_result)
def test_rename(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
col_name_dict = {"bool_col": 1.2345}
df_pandas = scalars_df.rename(columns=col_name_dict).to_pandas()
pd.testing.assert_index_equal(
df_pandas.columns, scalars_pandas_df.rename(columns=col_name_dict).columns
)
def test_df_peek(scalars_dfs_maybe_ordered):
scalars_df, scalars_pandas_df = scalars_dfs_maybe_ordered
peek_result = scalars_df.peek(n=3, force=False)
pd.testing.assert_index_equal(scalars_pandas_df.columns, peek_result.columns)
assert len(peek_result) == 3
def test_df_peek_filtered(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
peek_result = scalars_df[scalars_df.int64_col != 0].peek(n=3, force=False)
pd.testing.assert_index_equal(scalars_pandas_df.columns, peek_result.columns)
assert len(peek_result) == 3
def test_df_peek_exception(scalars_dfs):
scalars_df, _ = scalars_dfs
with pytest.raises(ValueError):
# Window ops aren't compatible with efficient peeking
scalars_df[["int64_col", "int64_too"]].cumsum().peek(n=3, force=False)
def test_df_peek_force_default(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
peek_result = scalars_df[["int64_col", "int64_too"]].cumsum().peek(n=3)
pd.testing.assert_index_equal(
scalars_pandas_df[["int64_col", "int64_too"]].columns, peek_result.columns
)
assert len(peek_result) == 3
def test_df_peek_reset_index(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
peek_result = (
scalars_df[["int64_col", "int64_too"]].reset_index(drop=True).peek(n=3)
)
pd.testing.assert_index_equal(
scalars_pandas_df[["int64_col", "int64_too"]].columns, peek_result.columns
)
assert len(peek_result) == 3
def test_repr_w_all_rows(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
# Remove columns with flaky formatting, like NUMERIC columns (which use the
# object dtype). Also makes a copy so that mutating the index name doesn't
# break other tests.
scalars_df = scalars_df.drop(columns=["numeric_col"])
scalars_pandas_df = scalars_pandas_df.drop(columns=["numeric_col"])
# When there are 10 or fewer rows, the outputs should be identical.
actual = repr(scalars_df.head(10))
with display_options.pandas_repr(bigframes.options.display):
expected = repr(scalars_pandas_df.head(10))
assert actual == expected
def test_join_repr(scalars_dfs_maybe_ordered):
scalars_df, scalars_pandas_df = scalars_dfs_maybe_ordered
scalars_df = (
scalars_df[["int64_col"]]
.join(scalars_df.set_index("int64_col")[["int64_too"]])
.sort_index()
)
scalars_pandas_df = (
scalars_pandas_df[["int64_col"]]
.join(scalars_pandas_df.set_index("int64_col")[["int64_too"]])
.sort_index()
)
# Pandas join result index name seems to depend on the index values in a way that bigframes can't match exactly
scalars_pandas_df.index.name = None
actual = repr(scalars_df)
with display_options.pandas_repr(bigframes.options.display):
expected = repr(scalars_pandas_df)
assert actual == expected
def test_repr_html_w_all_rows(scalars_dfs, session):
metrics = session._metrics
scalars_df, _ = scalars_dfs
# get a pandas df of the expected format
df, _ = scalars_df._block.to_pandas()
pandas_df = df.set_axis(scalars_df._block.column_labels, axis=1)
pandas_df.index.name = scalars_df.index.name
executions_pre = metrics.execution_count
# When there are 10 or fewer rows, the outputs should be identical except for the extra note.
actual = scalars_df.head(10)._repr_html_()
executions_post = metrics.execution_count
with display_options.pandas_repr(bigframes.options.display):
pandas_repr = pandas_df.head(10)._repr_html_()
expected = (
pandas_repr
+ f"[{len(pandas_df.index)} rows x {len(pandas_df.columns)} columns in total]"
)
assert actual == expected
assert (executions_post - executions_pre) <= 2
def test_df_column_name_with_space(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
col_name_dict = {"bool_col": "bool col"}
df_pandas = scalars_df.rename(columns=col_name_dict).to_pandas()
pd.testing.assert_index_equal(
df_pandas.columns, scalars_pandas_df.rename(columns=col_name_dict).columns
)
def test_df_column_name_duplicate(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
col_name_dict = {"int64_too": "int64_col"}
df_pandas = scalars_df.rename(columns=col_name_dict).to_pandas()
pd.testing.assert_index_equal(
df_pandas.columns, scalars_pandas_df.rename(columns=col_name_dict).columns
)
def test_get_df_column_name_duplicate(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
col_name_dict = {"int64_too": "int64_col"}
bf_result = scalars_df.rename(columns=col_name_dict)["int64_col"].to_pandas()
pd_result = scalars_pandas_df.rename(columns=col_name_dict)["int64_col"]
pd.testing.assert_index_equal(bf_result.columns, pd_result.columns)
def test_filter_df(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bf_bool_series = scalars_df["bool_col"]
bf_result = scalars_df[bf_bool_series].to_pandas()
pd_bool_series = scalars_pandas_df["bool_col"]
pd_result = scalars_pandas_df[pd_bool_series]
assert_pandas_df_equal(bf_result, pd_result)
def test_assign_new_column(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
kwargs = {"new_col": 2}
df = scalars_df.assign(**kwargs)
bf_result = df.to_pandas()
pd_result = scalars_pandas_df.assign(**kwargs)
# Convert default pandas dtypes `int64` to match BigQuery DataFrames dtypes.
pd_result["new_col"] = pd_result["new_col"].astype("Int64")
assert_pandas_df_equal(bf_result, pd_result)
def test_assign_new_column_w_loc(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
bf_df.loc[:, "new_col"] = 2
pd_df.loc[:, "new_col"] = 2
bf_result = bf_df.to_pandas()
pd_result = pd_df
# Convert default pandas dtypes `int64` to match BigQuery DataFrames dtypes.
pd_result["new_col"] = pd_result["new_col"].astype("Int64")
pd.testing.assert_frame_equal(bf_result, pd_result)
@pytest.mark.parametrize(
("scalar",),
[
(2.1,),
(None,),
],
)
def test_assign_new_column_w_setitem(scalars_dfs, scalar):
scalars_df, scalars_pandas_df = scalars_dfs
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
bf_df["new_col"] = scalar
pd_df["new_col"] = scalar
bf_result = bf_df.to_pandas()
pd_result = pd_df
# Convert default pandas dtypes `float64` to match BigQuery DataFrames dtypes.
pd_result["new_col"] = pd_result["new_col"].astype("Float64")
pd.testing.assert_frame_equal(bf_result, pd_result)
def test_assign_new_column_w_setitem_dataframe(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
bf_df["int64_col"] = bf_df["int64_too"].to_frame()
pd_df["int64_col"] = pd_df["int64_too"].to_frame()
# Convert default pandas dtypes `int64` to match BigQuery DataFrames dtypes.
pd_df["int64_col"] = pd_df["int64_col"].astype("Int64")
pd.testing.assert_frame_equal(bf_df.to_pandas(), pd_df)
def test_assign_new_column_w_setitem_dataframe_error(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
with pytest.raises(ValueError):
bf_df["impossible_col"] = bf_df[["int64_too", "string_col"]]
with pytest.raises(ValueError):
pd_df["impossible_col"] = pd_df[["int64_too", "string_col"]]
def test_assign_new_column_w_setitem_list(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
bf_df["new_col"] = [9, 8, 7, 6, 5, 4, 3, 2, 1]
pd_df["new_col"] = [9, 8, 7, 6, 5, 4, 3, 2, 1]
bf_result = bf_df.to_pandas()
pd_result = pd_df
# Convert default pandas dtypes `int64` to match BigQuery DataFrames dtypes.
pd_result["new_col"] = pd_result["new_col"].astype("Int64")
pd.testing.assert_frame_equal(bf_result, pd_result)
def test_assign_new_column_w_setitem_list_repeated(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
bf_df["new_col"] = [9, 8, 7, 6, 5, 4, 3, 2, 1]
pd_df["new_col"] = [9, 8, 7, 6, 5, 4, 3, 2, 1]
bf_df["new_col_2"] = [1, 3, 2, 5, 4, 7, 6, 9, 8]
pd_df["new_col_2"] = [1, 3, 2, 5, 4, 7, 6, 9, 8]
bf_result = bf_df.to_pandas()
pd_result = pd_df
# Convert default pandas dtypes `int64` to match BigQuery DataFrames dtypes.
pd_result["new_col"] = pd_result["new_col"].astype("Int64")
pd_result["new_col_2"] = pd_result["new_col_2"].astype("Int64")
pd.testing.assert_frame_equal(bf_result, pd_result)
def test_assign_new_column_w_setitem_list_custom_index(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
# set the custom index
pd_df = pd_df.set_index(["string_col", "int64_col"])
bf_df = bf_df.set_index(["string_col", "int64_col"])
bf_df["new_col"] = [9, 8, 7, 6, 5, 4, 3, 2, 1]
pd_df["new_col"] = [9, 8, 7, 6, 5, 4, 3, 2, 1]
bf_result = bf_df.to_pandas()
pd_result = pd_df
# Convert default pandas dtypes `int64` to match BigQuery DataFrames dtypes.
pd_result["new_col"] = pd_result["new_col"].astype("Int64")
pd.testing.assert_frame_equal(bf_result, pd_result)
def test_assign_new_column_w_setitem_list_error(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
bf_df = scalars_df.copy()
pd_df = scalars_pandas_df.copy()
with pytest.raises(ValueError):
pd_df["new_col"] = [1, 2, 3] # should be len 9, is 3
with pytest.raises(ValueError):
bf_df["new_col"] = [1, 2, 3]
def test_assign_existing_column(scalars_dfs):
scalars_df, scalars_pandas_df = scalars_dfs
kwargs = {"int64_col": 2}
df = scalars_df.assign(**kwargs)
bf_result = df.to_pandas()
pd_result = scalars_pandas_df.assign(**kwargs)
# Convert default pandas dtypes `int64` to match BigQuery DataFrames dtypes.
pd_result["int64_col"] = pd_result["int64_col"].astype("Int64")
assert_pandas_df_equal(bf_result, pd_result)
def test_assign_listlike_to_empty_df(session):
empty_df = dataframe.DataFrame(session=session)
empty_pandas_df = pd.DataFrame()
bf_result = empty_df.assign(new_col=[1, 2, 3])
pd_result = empty_pandas_df.assign(new_col=[1, 2, 3])
pd_result["new_col"] = pd_result["new_col"].astype("Int64")
pd_result.index = pd_result.index.astype("Int64")
assert_pandas_df_equal(bf_result.to_pandas(), pd_result)
def test_assign_to_empty_df_multiindex_error(session):
empty_df = dataframe.DataFrame(session=session)
empty_pandas_df = pd.DataFrame()
empty_df["empty_col_1"] = typing.cast(series.Series, [])
empty_df["empty_col_2"] = typing.cast(series.Series, [])
empty_pandas_df["empty_col_1"] = []
empty_pandas_df["empty_col_2"] = []
empty_df = empty_df.set_index(["empty_col_1", "empty_col_2"])
empty_pandas_df = empty_pandas_df.set_index(["empty_col_1", "empty_col_2"])
with pytest.raises(ValueError):
empty_df.assign(new_col=[1, 2, 3, 4, 5, 6, 7, 8, 9])
with pytest.raises(ValueError):
empty_pandas_df.assign(new_col=[1, 2, 3, 4, 5, 6, 7, 8, 9])
@pytest.mark.parametrize(
("ordered"),
[
(True),
(False),
],
)
def test_assign_series(scalars_dfs, ordered):
scalars_df, scalars_pandas_df = scalars_dfs
column_name = "int64_col"
df = scalars_df.assign(new_col=scalars_df[column_name])