-
Notifications
You must be signed in to change notification settings - Fork 28.2k
/
test_num_ops.py
633 lines (549 loc) · 27.3 KB
/
test_num_ops.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
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
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You 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 datetime
import unittest
from distutils.version import LooseVersion
import pandas as pd
import numpy as np
from pandas.api.types import CategoricalDtype
from pyspark import pandas as ps
from pyspark.pandas.config import option_context
from pyspark.pandas.tests.data_type_ops.testing_utils import TestCasesUtils
from pyspark.pandas.typedef.typehints import (
extension_dtypes_available,
extension_float_dtypes_available,
)
from pyspark.sql.types import DecimalType, IntegralType
from pyspark.testing.pandasutils import PandasOnSparkTestCase
class NumOpsTest(PandasOnSparkTestCase, TestCasesUtils):
"""Unit tests for arithmetic operations of numeric data types.
A few test cases are disabled because pandas-on-Spark returns float64 whereas pandas
returns float32.
The underlying reason is the respective Spark operations return DoubleType always.
"""
@property
def float_pser(self):
return pd.Series([1, 2, 3], dtype=float)
@property
def float_psser(self):
return ps.from_pandas(self.float_pser)
def test_add(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(pser + pser, psser + psser)
self.assert_eq(pser + 1, psser + 1)
# self.assert_eq(pser + 0.1, psser + 0.1)
self.assert_eq(pser + pser.astype(bool), psser + psser.astype(bool))
self.assert_eq(pser + True, psser + True)
self.assert_eq(pser + False, psser + False)
for n_col in self.non_numeric_df_cols:
if n_col == "bool":
self.assert_eq(pser + pdf[n_col], psser + psdf[n_col])
else:
self.assertRaises(TypeError, lambda: psser + psdf[n_col])
def test_sub(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(pser - pser, psser - psser)
self.assert_eq(pser - 1, psser - 1)
# self.assert_eq(pser - 0.1, psser - 0.1)
self.assert_eq(pser - pser.astype(bool), psser - psser.astype(bool))
self.assert_eq(pser - True, psser - True)
self.assert_eq(pser - False, psser - False)
for n_col in self.non_numeric_df_cols:
if n_col == "bool":
self.assert_eq(pser - pdf[n_col], psser - psdf[n_col])
else:
self.assertRaises(TypeError, lambda: psser - psdf[n_col])
def test_mul(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(pser * pser, psser * psser)
self.assert_eq(pser * pser.astype(bool), psser * psser.astype(bool))
self.assert_eq(pser * True, psser * True)
self.assert_eq(pser * False, psser * False)
if psser.dtype in [int, np.int32]:
self.assert_eq(pser * pdf["string"], psser * psdf["string"])
else:
self.assertRaises(TypeError, lambda: psser * psdf["string"])
self.assert_eq(pser * pdf["bool"], psser * psdf["bool"])
self.assertRaises(TypeError, lambda: psser * psdf["datetime"])
self.assertRaises(TypeError, lambda: psser * psdf["date"])
self.assertRaises(TypeError, lambda: psser * psdf["categorical"])
def test_truediv(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
if psser.dtype in [float, int, np.int32]:
self.assert_eq(pser / pser, psser / psser)
self.assert_eq(pser / pser.astype(bool), psser / psser.astype(bool))
self.assert_eq(pser / True, psser / True)
self.assert_eq(pser / False, psser / False)
for n_col in self.non_numeric_df_cols:
if n_col == "bool":
self.assert_eq(pdf["float"] / pdf[n_col], psdf["float"] / psdf[n_col])
else:
self.assertRaises(TypeError, lambda: psser / psdf[n_col])
def test_floordiv(self):
pdf, psdf = self.pdf, self.psdf
pser, psser = pdf["float"], psdf["float"]
self.assert_eq(pser // pser, psser // psser)
self.assert_eq(pser // pser.astype(bool), psser // psser.astype(bool))
self.assert_eq(pser // True, psser // True)
self.assert_eq(pser // False, psser // False)
for n_col in self.non_numeric_df_cols:
if n_col == "bool":
if LooseVersion(pd.__version__) >= LooseVersion("0.25.3"):
self.assert_eq(
pdf["float"] // pdf["bool"],
psdf["float"] // psdf["bool"],
)
else:
self.assert_eq(
pd.Series([1.0, 2.0, np.inf]),
psdf["float"] // psdf["bool"],
)
else:
for col in self.numeric_df_cols:
psser = psdf[col]
self.assertRaises(TypeError, lambda: psser // psdf[n_col])
def test_mod(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(pser % pser, psser % psser)
self.assert_eq(pser % pser.astype(bool), psser % psser.astype(bool))
self.assert_eq(pser % True, psser % True)
if col in ["int", "int32"]:
self.assert_eq(
pd.Series([np.nan, np.nan, np.nan], dtype=float, name=col), psser % False
)
else:
self.assert_eq(
pd.Series([np.nan, np.nan, np.nan], dtype=pser.dtype, name=col), psser % False
)
for n_col in self.non_numeric_df_cols:
if n_col == "bool":
self.assert_eq(pdf["float"] % pdf[n_col], psdf["float"] % psdf[n_col])
else:
self.assertRaises(TypeError, lambda: psser % psdf[n_col])
def test_pow(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
if col == "float":
self.assert_eq(pser ** pser, psser ** psser)
self.assert_eq(pser ** pser.astype(bool), psser ** psser.astype(bool))
self.assert_eq(pser ** True, psser ** True)
self.assert_eq(pser ** False, psser ** False)
for n_col in self.non_numeric_df_cols:
if n_col == "bool":
self.assert_eq(pdf["float"] ** pdf[n_col], psdf["float"] ** psdf[n_col])
else:
self.assertRaises(TypeError, lambda: psser ** psdf[n_col])
# TODO(SPARK-36031): Merge test_pow_with_nan into test_pow
def test_pow_with_float_nan(self):
for col in self.numeric_w_nan_df_cols:
if col == "float_w_nan":
pser, psser = self.numeric_w_nan_pdf[col], self.numeric_w_nan_psdf[col]
self.assert_eq(pser ** pser, psser ** psser)
self.assert_eq(pser ** pser.astype(bool), psser ** psser.astype(bool))
self.assert_eq(pser ** True, psser ** True)
self.assert_eq(pser ** False, psser ** False)
self.assert_eq(pser ** 1, psser ** 1)
self.assert_eq(pser ** 0, psser ** 0)
def test_radd(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(1 + pser, 1 + psser)
# self.assert_eq(0.1 + pser, 0.1 + psser)
self.assertRaises(TypeError, lambda: "x" + psser)
self.assert_eq(True + pser, True + psser)
self.assert_eq(False + pser, False + psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) + psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) + psser)
def test_rsub(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(1 - pser, 1 - psser)
# self.assert_eq(0.1 - pser, 0.1 - psser)
self.assertRaises(TypeError, lambda: "x" - psser)
self.assert_eq(True - pser, True - psser)
self.assert_eq(False - pser, False - psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) - psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) - psser)
def test_rmul(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(1 * pser, 1 * psser)
# self.assert_eq(0.1 * pser, 0.1 * psser)
self.assertRaises(TypeError, lambda: "x" * psser)
self.assert_eq(True * pser, True * psser)
self.assert_eq(False * pser, False * psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) * psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) * psser)
def test_rtruediv(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
# self.assert_eq(5 / pser, 5 / psser)
# self.assert_eq(0.1 / pser, 0.1 / psser)
self.assertRaises(TypeError, lambda: "x" / psser)
self.assert_eq((True / pser).astype(float), True / psser, check_exact=False)
self.assert_eq((False / pser).astype(float), False / psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) / psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) / psser)
def test_rfloordiv(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
# self.assert_eq(5 // pser, 5 // psser)
# self.assert_eq(0.1 // pser, 0.1 // psser)
self.assertRaises(TypeError, lambda: "x" // psser)
self.assert_eq((True // pser).astype(float), True // psser)
self.assert_eq((False // pser).astype(float), False // psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) // psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) // psser)
def test_rpow(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
# self.assert_eq(1 ** pser, 1 ** psser)
# self.assert_eq(0.1 ** pser, 0.1 ** psser)
self.assertRaises(TypeError, lambda: "x" ** psser)
self.assert_eq((True ** pser).astype(float), True ** psser)
self.assert_eq((False ** pser).astype(float), False ** psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) ** psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) ** psser)
def test_rmod(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(1 % pser, 1 % psser)
# self.assert_eq(0.1 % pser, 0.1 % psser)
self.assert_eq(True % pser, True % psser)
self.assert_eq(False % pser, False % psser)
self.assertRaises(TypeError, lambda: datetime.date(1994, 1, 1) % psser)
self.assertRaises(TypeError, lambda: datetime.datetime(1994, 1, 1) % psser)
def test_and(self):
psdf = self.psdf
for col in self.numeric_df_cols:
psser = psdf[col]
self.assertRaises(TypeError, lambda: psser & True)
self.assertRaises(TypeError, lambda: psser & False)
self.assertRaises(TypeError, lambda: psser & psser)
def test_rand(self):
psdf = self.psdf
for col in self.numeric_df_cols:
psser = psdf[col]
self.assertRaises(TypeError, lambda: True & psser)
self.assertRaises(TypeError, lambda: False & psser)
def test_or(self):
psdf = self.psdf
for col in self.numeric_df_cols:
psser = psdf[col]
self.assertRaises(TypeError, lambda: psser | True)
self.assertRaises(TypeError, lambda: psser | False)
self.assertRaises(TypeError, lambda: psser | psser)
def test_ror(self):
psdf = self.psdf
for col in self.numeric_df_cols:
psser = psdf[col]
self.assertRaises(TypeError, lambda: True | psser)
self.assertRaises(TypeError, lambda: False | psser)
def test_from_to_pandas(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(pser, psser.to_pandas())
self.assert_eq(ps.from_pandas(pser), psser)
def test_isnull(self):
pdf, psdf = self.numeric_w_nan_pdf, self.numeric_w_nan_psdf
for col in self.numeric_w_nan_df_cols:
self.assert_eq(pdf[col].isnull(), psdf[col].isnull())
def test_astype(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(pser.astype(int), psser.astype(int))
self.assert_eq(pser.astype(float), psser.astype(float))
self.assert_eq(pser.astype(np.float32), psser.astype(np.float32))
self.assert_eq(pser.astype(np.int32), psser.astype(np.int32))
self.assert_eq(pser.astype(np.int16), psser.astype(np.int16))
self.assert_eq(pser.astype(np.int8), psser.astype(np.int8))
self.assert_eq(pser.astype(str), psser.astype(str))
self.assert_eq(pser.astype(bool), psser.astype(bool))
self.assert_eq(pser.astype("category"), psser.astype("category"))
cat_type = CategoricalDtype(categories=[2, 1, 3])
self.assert_eq(pser.astype(cat_type), psser.astype(cat_type))
self.assertRaisesRegex(
ValueError,
"Cannot convert fractions with missing values to integer",
lambda: self.float_withnan_psser.astype(int),
)
self.assertRaisesRegex(
ValueError,
"Cannot convert fractions with missing values to integer",
lambda: self.float_withnan_psser.astype(np.int32),
)
self.assert_eq(self.float_withnan_psser.astype(str), self.float_withnan_psser.astype(str))
self.assert_eq(self.float_withnan_psser.astype(bool), self.float_withnan_psser.astype(bool))
self.assert_eq(
self.float_withnan_psser.astype("category"), self.float_withnan_psser.astype("category")
)
def test_neg(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
self.assert_eq(-pdf[col], -psdf[col])
def test_abs(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
self.assert_eq(abs(pdf[col]), abs(psdf[col]))
def test_invert(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
if isinstance(psser.spark.data_type, IntegralType):
self.assert_eq(~pser, ~psser)
else:
self.assertRaises(TypeError, lambda: ~psser)
def test_eq(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
self.assert_eq(pdf[col] == pdf[col], psdf[col] == psdf[col])
def test_ne(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
self.assert_eq(pdf[col] != pdf[col], psdf[col] != psdf[col])
def test_lt(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
if isinstance(psser.spark.data_type, DecimalType):
self.assertRaisesRegex(TypeError, "< can not be applied to", lambda: psser < psser)
else:
self.assert_eq(pser < pser, psser < psser)
def test_le(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
if isinstance(psser.spark.data_type, DecimalType):
self.assertRaisesRegex(
TypeError, "<= can not be applied to", lambda: psser <= psser
)
else:
self.assert_eq(pser <= pser, psser <= psser)
def test_gt(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
if isinstance(psser.spark.data_type, DecimalType):
self.assertRaisesRegex(TypeError, "> can not be applied to", lambda: psser > psser)
else:
self.assert_eq(pser > pser, psser > psser)
def test_ge(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
if isinstance(psser.spark.data_type, DecimalType):
self.assertRaisesRegex(
TypeError, ">= can not be applied to", lambda: psser >= psser
)
else:
self.assert_eq(pser >= pser, psser >= psser)
@unittest.skipIf(not extension_dtypes_available, "pandas extension dtypes are not available")
class IntegralExtensionOpsTest(PandasOnSparkTestCase, TestCasesUtils):
@property
def intergral_extension_psers(self):
return [pd.Series([1, 2, 3, None], dtype=dtype) for dtype in self.integral_extension_dtypes]
@property
def intergral_extension_pssers(self):
return [ps.from_pandas(pser) for pser in self.intergral_extension_psers]
@property
def intergral_extension_pser_psser_pairs(self):
return zip(self.intergral_extension_psers, self.intergral_extension_pssers)
def test_from_to_pandas(self):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(pser, psser.to_pandas())
self.check_extension(ps.from_pandas(pser), psser)
def test_isnull(self):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.assert_eq(pser.isnull(), psser.isnull())
def test_astype(self):
for pser, psser in self.intergral_extension_pser_psser_pairs:
for dtype in self.extension_dtypes:
if dtype in self.string_extension_dtype:
if LooseVersion(pd.__version__) >= LooseVersion("1.1.0"):
# Limit pandas version due to
# https://github.com/pandas-dev/pandas/issues/31204
self.check_extension(pser.astype(dtype), psser.astype(dtype))
else:
self.check_extension(pser.astype(dtype), psser.astype(dtype))
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.assert_eq(pser.astype(float), psser.astype(float))
self.assert_eq(pser.astype(np.float32), psser.astype(np.float32))
self.assertRaisesRegex(
ValueError,
"Cannot convert integrals with missing values to bool",
lambda: psser.astype(bool),
)
self.assertRaisesRegex(
ValueError,
"Cannot convert integrals with missing values to integer",
lambda: psser.astype(int),
)
self.assertRaisesRegex(
ValueError,
"Cannot convert integrals with missing values to integer",
lambda: psser.astype(np.int32),
)
def test_neg(self):
for pser, psser in self.intergral_extension_pser_psser_pairs:
if LooseVersion(pd.__version__) < LooseVersion("1.1.3"):
# pandas < 1.1.0: object dtype is returned after negation
# pandas 1.1.1 and 1.1.2:
# a TypeError "bad operand type for unary -: 'IntegerArray'" is raised
# Please refer to https://github.com/pandas-dev/pandas/issues/36063.
self.check_extension(pd.Series([-1, -2, -3, None], dtype=pser.dtype), -psser)
else:
self.check_extension(-pser, -psser)
def test_abs(self):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(abs(pser), abs(psser))
def test_invert(self):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(~pser, ~psser)
def test_eq(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(pser == pser, (psser == psser).sort_index())
def test_ne(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(pser != pser, (psser != psser).sort_index())
def test_lt(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(pser < pser, (psser < psser).sort_index())
def test_le(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(pser <= pser, (psser <= psser).sort_index())
def test_gt(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(pser > pser, (psser > psser).sort_index())
def test_ge(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.intergral_extension_pser_psser_pairs:
self.check_extension(pser >= pser, (psser >= psser).sort_index())
@unittest.skipIf(
not extension_float_dtypes_available, "pandas extension float dtypes are not available"
)
class FractionalExtensionOpsTest(PandasOnSparkTestCase, TestCasesUtils):
@property
def fractional_extension_psers(self):
return [
pd.Series([0.1, 0.2, 0.3, None], dtype=dtype)
for dtype in self.fractional_extension_dtypes
]
@property
def fractional_extension_pssers(self):
return [ps.from_pandas(pser) for pser in self.fractional_extension_psers]
@property
def fractional_extension_pser_psser_pairs(self):
return zip(self.fractional_extension_psers, self.fractional_extension_pssers)
def test_from_to_pandas(self):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(pser, psser.to_pandas())
self.check_extension(ps.from_pandas(pser), psser)
def test_isnull(self):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.assert_eq(pser.isnull(), psser.isnull())
def test_astype(self):
for pser, psser in self.fractional_extension_pser_psser_pairs:
for dtype in self.extension_dtypes:
self.check_extension(pser.astype(dtype), psser.astype(dtype))
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.assert_eq(pser.astype(float), psser.astype(float))
self.assert_eq(pser.astype(np.float32), psser.astype(np.float32))
self.assertRaisesRegex(
ValueError,
"Cannot convert fractions with missing values to bool",
lambda: psser.astype(bool),
)
self.assertRaisesRegex(
ValueError,
"Cannot convert fractions with missing values to integer",
lambda: psser.astype(int),
)
self.assertRaisesRegex(
ValueError,
"Cannot convert fractions with missing values to integer",
lambda: psser.astype(np.int32),
)
def test_neg(self):
# pandas raises "TypeError: bad operand type for unary -: 'FloatingArray'"
for dtype in self.fractional_extension_dtypes:
self.assert_eq(
ps.Series([-0.1, -0.2, -0.3, None], dtype=dtype),
-ps.Series([0.1, 0.2, 0.3, None], dtype=dtype),
)
def test_abs(self):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(abs(pser), abs(psser))
def test_invert(self):
for psser in self.fractional_extension_pssers:
self.assertRaises(TypeError, lambda: ~psser)
def test_eq(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(pser == pser, (psser == psser).sort_index())
def test_ne(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(pser != pser, (psser != psser).sort_index())
def test_lt(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(pser < pser, (psser < psser).sort_index())
def test_le(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(pser <= pser, (psser <= psser).sort_index())
def test_gt(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(pser > pser, (psser > psser).sort_index())
def test_ge(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(pser >= pser, (psser >= psser).sort_index())
if __name__ == "__main__":
from pyspark.pandas.tests.data_type_ops.test_num_ops import * # noqa: F401
try:
import xmlrunner # type: ignore[import]
testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
except ImportError:
testRunner = None
unittest.main(testRunner=testRunner, verbosity=2)