forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_sql.py
1911 lines (1532 loc) · 68.5 KB
/
test_sql.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
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
"""SQL io tests
The SQL tests are broken down in different classes:
- `PandasSQLTest`: base class with common methods for all test classes
- Tests for the public API (only tests with sqlite3)
- `_TestSQLApi` base class
- `TestSQLApi`: test the public API with sqlalchemy engine
- `TesySQLLegacyApi`: test the public API with DBAPI connection
- Tests for the different SQL flavors (flavor specific type conversions)
- Tests for the sqlalchemy mode: `_TestSQLAlchemy` is the base class with
common methods, the different tested flavors (sqlite3, MySQL, PostgreSQL)
derive from the base class
- Tests for the legacy mode (`TestSQLiteLegacy` and `TestMySQLLegacy`)
"""
from __future__ import print_function
import unittest
import sqlite3
import csv
import os
import sys
import nose
import warnings
import numpy as np
from datetime import datetime
from pandas import DataFrame, Series, Index, MultiIndex, isnull
from pandas import date_range, to_datetime, to_timedelta
import pandas.compat as compat
from pandas.compat import StringIO, range, lrange, string_types
from pandas.core.datetools import format as date_format
import pandas.io.sql as sql
import pandas.util.testing as tm
from pandas import _np_version_under1p7
try:
import sqlalchemy
SQLALCHEMY_INSTALLED = True
except ImportError:
SQLALCHEMY_INSTALLED = False
SQL_STRINGS = {
'create_iris': {
'sqlite': """CREATE TABLE iris (
"SepalLength" REAL,
"SepalWidth" REAL,
"PetalLength" REAL,
"PetalWidth" REAL,
"Name" TEXT
)""",
'mysql': """CREATE TABLE iris (
`SepalLength` DOUBLE,
`SepalWidth` DOUBLE,
`PetalLength` DOUBLE,
`PetalWidth` DOUBLE,
`Name` VARCHAR(200)
)""",
'postgresql': """CREATE TABLE iris (
"SepalLength" DOUBLE PRECISION,
"SepalWidth" DOUBLE PRECISION,
"PetalLength" DOUBLE PRECISION,
"PetalWidth" DOUBLE PRECISION,
"Name" VARCHAR(200)
)"""
},
'insert_iris': {
'sqlite': """INSERT INTO iris VALUES(?, ?, ?, ?, ?)""",
'mysql': """INSERT INTO iris VALUES(%s, %s, %s, %s, "%s");""",
'postgresql': """INSERT INTO iris VALUES(%s, %s, %s, %s, %s);"""
},
'create_test_types': {
'sqlite': """CREATE TABLE types_test_data (
"TextCol" TEXT,
"DateCol" TEXT,
"IntDateCol" INTEGER,
"FloatCol" REAL,
"IntCol" INTEGER,
"BoolCol" INTEGER,
"IntColWithNull" INTEGER,
"BoolColWithNull" INTEGER
)""",
'mysql': """CREATE TABLE types_test_data (
`TextCol` TEXT,
`DateCol` DATETIME,
`IntDateCol` INTEGER,
`FloatCol` DOUBLE,
`IntCol` INTEGER,
`BoolCol` BOOLEAN,
`IntColWithNull` INTEGER,
`BoolColWithNull` BOOLEAN
)""",
'postgresql': """CREATE TABLE types_test_data (
"TextCol" TEXT,
"DateCol" TIMESTAMP,
"IntDateCol" INTEGER,
"FloatCol" DOUBLE PRECISION,
"IntCol" INTEGER,
"BoolCol" BOOLEAN,
"IntColWithNull" INTEGER,
"BoolColWithNull" BOOLEAN
)"""
},
'insert_test_types': {
'sqlite': """
INSERT INTO types_test_data
VALUES(?, ?, ?, ?, ?, ?, ?, ?)
""",
'mysql': """
INSERT INTO types_test_data
VALUES("%s", %s, %s, %s, %s, %s, %s, %s)
""",
'postgresql': """
INSERT INTO types_test_data
VALUES(%s, %s, %s, %s, %s, %s, %s, %s)
"""
},
'read_parameters': {
'sqlite': "SELECT * FROM iris WHERE Name=? AND SepalLength=?",
'mysql': 'SELECT * FROM iris WHERE `Name`="%s" AND `SepalLength`=%s',
'postgresql': 'SELECT * FROM iris WHERE "Name"=%s AND "SepalLength"=%s'
},
'read_named_parameters': {
'sqlite': """
SELECT * FROM iris WHERE Name=:name AND SepalLength=:length
""",
'mysql': """
SELECT * FROM iris WHERE
`Name`="%(name)s" AND `SepalLength`=%(length)s
""",
'postgresql': """
SELECT * FROM iris WHERE
"Name"=%(name)s AND "SepalLength"=%(length)s
"""
}
}
class PandasSQLTest(unittest.TestCase):
"""
Base class with common private methods for SQLAlchemy and fallback cases.
"""
def drop_table(self, table_name):
self._get_exec().execute("DROP TABLE IF EXISTS %s" % table_name)
def _get_exec(self):
if hasattr(self.conn, 'execute'):
return self.conn
else:
return self.conn.cursor()
def _load_iris_data(self):
import io
iris_csv_file = os.path.join(tm.get_data_path(), 'iris.csv')
self.drop_table('iris')
self._get_exec().execute(SQL_STRINGS['create_iris'][self.flavor])
with io.open(iris_csv_file, mode='r', newline=None) as iris_csv:
r = csv.reader(iris_csv)
next(r) # skip header row
ins = SQL_STRINGS['insert_iris'][self.flavor]
for row in r:
self._get_exec().execute(ins, row)
def _check_iris_loaded_frame(self, iris_frame):
pytype = iris_frame.dtypes[0].type
row = iris_frame.iloc[0]
self.assertTrue(
issubclass(pytype, np.floating), 'Loaded frame has incorrect type')
tm.equalContents(row.values, [5.1, 3.5, 1.4, 0.2, 'Iris-setosa'])
def _load_test1_data(self):
columns = ['index', 'A', 'B', 'C', 'D']
data = [(
'2000-01-03 00:00:00', 0.980268513777, 3.68573087906, -0.364216805298, -1.15973806169),
('2000-01-04 00:00:00', 1.04791624281, -
0.0412318367011, -0.16181208307, 0.212549316967),
('2000-01-05 00:00:00', 0.498580885705,
0.731167677815, -0.537677223318, 1.34627041952),
('2000-01-06 00:00:00', 1.12020151869, 1.56762092543, 0.00364077397681, 0.67525259227)]
self.test_frame1 = DataFrame(data, columns=columns)
def _load_test2_data(self):
df = DataFrame(dict(A=[4, 1, 3, 6],
B=['asd', 'gsq', 'ylt', 'jkl'],
C=[1.1, 3.1, 6.9, 5.3],
D=[False, True, True, False],
E=['1990-11-22', '1991-10-26', '1993-11-26', '1995-12-12']))
df['E'] = to_datetime(df['E'])
self.test_frame3 = df
def _load_test3_data(self):
columns = ['index', 'A', 'B']
data = [(
'2000-01-03 00:00:00', 2 ** 31 - 1, -1.987670),
('2000-01-04 00:00:00', -29, -0.0412318367011),
('2000-01-05 00:00:00', 20000, 0.731167677815),
('2000-01-06 00:00:00', -290867, 1.56762092543)]
self.test_frame3 = DataFrame(data, columns=columns)
def _load_raw_sql(self):
self.drop_table('types_test_data')
self._get_exec().execute(SQL_STRINGS['create_test_types'][self.flavor])
ins = SQL_STRINGS['insert_test_types'][self.flavor]
data = [(
'first', '2000-01-03 00:00:00', 535852800, 10.10, 1, False, 1, False),
('first', '2000-01-04 00:00:00', 1356998400, 10.10, 1, False, None, None)]
for d in data:
self._get_exec().execute(ins, d)
def _count_rows(self, table_name):
result = self._get_exec().execute(
"SELECT count(*) AS count_1 FROM %s" % table_name).fetchone()
return result[0]
def _read_sql_iris(self):
iris_frame = self.pandasSQL.read_sql("SELECT * FROM iris")
self._check_iris_loaded_frame(iris_frame)
def _read_sql_iris_parameter(self):
query = SQL_STRINGS['read_parameters'][self.flavor]
params = ['Iris-setosa', 5.1]
iris_frame = self.pandasSQL.read_sql(query, params=params)
self._check_iris_loaded_frame(iris_frame)
def _read_sql_iris_named_parameter(self):
query = SQL_STRINGS['read_named_parameters'][self.flavor]
params = {'name': 'Iris-setosa', 'length': 5.1}
iris_frame = self.pandasSQL.read_sql(query, params=params)
self._check_iris_loaded_frame(iris_frame)
def _to_sql(self):
self.drop_table('test_frame1')
self.pandasSQL.to_sql(self.test_frame1, 'test_frame1')
self.assertTrue(self.pandasSQL.has_table(
'test_frame1'), 'Table not written to DB')
# Nuke table
self.drop_table('test_frame1')
def _to_sql_fail(self):
self.drop_table('test_frame1')
self.pandasSQL.to_sql(
self.test_frame1, 'test_frame1', if_exists='fail')
self.assertTrue(self.pandasSQL.has_table(
'test_frame1'), 'Table not written to DB')
self.assertRaises(ValueError, self.pandasSQL.to_sql,
self.test_frame1, 'test_frame1', if_exists='fail')
self.drop_table('test_frame1')
def _to_sql_replace(self):
self.drop_table('test_frame1')
self.pandasSQL.to_sql(
self.test_frame1, 'test_frame1', if_exists='fail')
# Add to table again
self.pandasSQL.to_sql(
self.test_frame1, 'test_frame1', if_exists='replace')
self.assertTrue(self.pandasSQL.has_table(
'test_frame1'), 'Table not written to DB')
num_entries = len(self.test_frame1)
num_rows = self._count_rows('test_frame1')
self.assertEqual(
num_rows, num_entries, "not the same number of rows as entries")
self.drop_table('test_frame1')
def _to_sql_append(self):
# Nuke table just in case
self.drop_table('test_frame1')
self.pandasSQL.to_sql(
self.test_frame1, 'test_frame1', if_exists='fail')
# Add to table again
self.pandasSQL.to_sql(
self.test_frame1, 'test_frame1', if_exists='append')
self.assertTrue(self.pandasSQL.has_table(
'test_frame1'), 'Table not written to DB')
num_entries = 2 * len(self.test_frame1)
num_rows = self._count_rows('test_frame1')
self.assertEqual(
num_rows, num_entries, "not the same number of rows as entries")
self.drop_table('test_frame1')
def _roundtrip(self):
self.drop_table('test_frame_roundtrip')
self.pandasSQL.to_sql(self.test_frame1, 'test_frame_roundtrip')
result = self.pandasSQL.read_sql('SELECT * FROM test_frame_roundtrip')
result.set_index('level_0', inplace=True)
# result.index.astype(int)
result.index.name = None
tm.assert_frame_equal(result, self.test_frame1)
def _execute_sql(self):
# drop_sql = "DROP TABLE IF EXISTS test" # should already be done
iris_results = self.pandasSQL.execute("SELECT * FROM iris")
row = iris_results.fetchone()
tm.equalContents(row, [5.1, 3.5, 1.4, 0.2, 'Iris-setosa'])
#------------------------------------------------------------------------------
#--- Testing the public API
class _TestSQLApi(PandasSQLTest):
"""
Base class to test the public API.
From this two classes are derived to run these tests for both the
sqlalchemy mode (`TestSQLApi`) and the legacy mode (`TestSQLLegacyApi`).
These tests are run with sqlite3. Specific tests for the different
sql flavours are included in `_TestSQLAlchemy`.
Notes:
flavor can always be passed even in SQLAlchemy mode,
should be correctly ignored.
we don't use drop_table because that isn't part of the public api
"""
flavor = 'sqlite'
def setUp(self):
self.conn = self.connect()
self._load_iris_data()
self._load_test1_data()
self._load_test2_data()
self._load_test3_data()
self._load_raw_sql()
def test_read_sql_iris(self):
iris_frame = sql.read_sql_query(
"SELECT * FROM iris", self.conn)
self._check_iris_loaded_frame(iris_frame)
def test_legacy_read_frame(self):
with tm.assert_produces_warning(FutureWarning):
iris_frame = sql.read_frame(
"SELECT * FROM iris", self.conn)
self._check_iris_loaded_frame(iris_frame)
def test_to_sql(self):
sql.to_sql(self.test_frame1, 'test_frame1', self.conn, flavor='sqlite')
self.assertTrue(
sql.has_table('test_frame1', self.conn, flavor='sqlite'), 'Table not written to DB')
def test_to_sql_fail(self):
sql.to_sql(self.test_frame1, 'test_frame2',
self.conn, flavor='sqlite', if_exists='fail')
self.assertTrue(
sql.has_table('test_frame2', self.conn, flavor='sqlite'), 'Table not written to DB')
self.assertRaises(ValueError, sql.to_sql, self.test_frame1,
'test_frame2', self.conn, flavor='sqlite', if_exists='fail')
def test_to_sql_replace(self):
sql.to_sql(self.test_frame1, 'test_frame3',
self.conn, flavor='sqlite', if_exists='fail')
# Add to table again
sql.to_sql(self.test_frame1, 'test_frame3',
self.conn, flavor='sqlite', if_exists='replace')
self.assertTrue(
sql.has_table('test_frame3', self.conn, flavor='sqlite'),
'Table not written to DB')
num_entries = len(self.test_frame1)
num_rows = self._count_rows('test_frame3')
self.assertEqual(
num_rows, num_entries, "not the same number of rows as entries")
def test_to_sql_append(self):
sql.to_sql(self.test_frame1, 'test_frame4',
self.conn, flavor='sqlite', if_exists='fail')
# Add to table again
sql.to_sql(self.test_frame1, 'test_frame4',
self.conn, flavor='sqlite', if_exists='append')
self.assertTrue(
sql.has_table('test_frame4', self.conn, flavor='sqlite'),
'Table not written to DB')
num_entries = 2 * len(self.test_frame1)
num_rows = self._count_rows('test_frame4')
self.assertEqual(
num_rows, num_entries, "not the same number of rows as entries")
def test_to_sql_type_mapping(self):
sql.to_sql(self.test_frame3, 'test_frame5',
self.conn, flavor='sqlite', index=False)
result = sql.read_sql("SELECT * FROM test_frame5", self.conn)
tm.assert_frame_equal(self.test_frame3, result)
def test_to_sql_series(self):
s = Series(np.arange(5, dtype='int64'), name='series')
sql.to_sql(s, "test_series", self.conn, flavor='sqlite', index=False)
s2 = sql.read_sql_query("SELECT * FROM test_series", self.conn)
tm.assert_frame_equal(s.to_frame(), s2)
def test_to_sql_panel(self):
panel = tm.makePanel()
self.assertRaises(NotImplementedError, sql.to_sql, panel,
'test_panel', self.conn, flavor='sqlite')
def test_legacy_write_frame(self):
# Assume that functionality is already tested above so just do
# quick check that it basically works
with tm.assert_produces_warning(FutureWarning):
sql.write_frame(self.test_frame1, 'test_frame_legacy', self.conn,
flavor='sqlite')
self.assertTrue(
sql.has_table('test_frame_legacy', self.conn, flavor='sqlite'),
'Table not written to DB')
def test_roundtrip(self):
sql.to_sql(self.test_frame1, 'test_frame_roundtrip',
con=self.conn, flavor='sqlite')
result = sql.read_sql_query(
'SELECT * FROM test_frame_roundtrip',
con=self.conn)
# HACK!
result.index = self.test_frame1.index
result.set_index('level_0', inplace=True)
result.index.astype(int)
result.index.name = None
tm.assert_frame_equal(result, self.test_frame1)
def test_execute_sql(self):
# drop_sql = "DROP TABLE IF EXISTS test" # should already be done
iris_results = sql.execute("SELECT * FROM iris", con=self.conn)
row = iris_results.fetchone()
tm.equalContents(row, [5.1, 3.5, 1.4, 0.2, 'Iris-setosa'])
def test_date_parsing(self):
# Test date parsing in read_sq
# No Parsing
df = sql.read_sql_query("SELECT * FROM types_test_data", self.conn)
self.assertFalse(
issubclass(df.DateCol.dtype.type, np.datetime64),
"DateCol loaded with incorrect type")
df = sql.read_sql_query("SELECT * FROM types_test_data", self.conn,
parse_dates=['DateCol'])
self.assertTrue(
issubclass(df.DateCol.dtype.type, np.datetime64),
"DateCol loaded with incorrect type")
df = sql.read_sql_query("SELECT * FROM types_test_data", self.conn,
parse_dates={'DateCol': '%Y-%m-%d %H:%M:%S'})
self.assertTrue(
issubclass(df.DateCol.dtype.type, np.datetime64),
"DateCol loaded with incorrect type")
df = sql.read_sql_query("SELECT * FROM types_test_data", self.conn,
parse_dates=['IntDateCol'])
self.assertTrue(issubclass(df.IntDateCol.dtype.type, np.datetime64),
"IntDateCol loaded with incorrect type")
df = sql.read_sql_query("SELECT * FROM types_test_data", self.conn,
parse_dates={'IntDateCol': 's'})
self.assertTrue(issubclass(df.IntDateCol.dtype.type, np.datetime64),
"IntDateCol loaded with incorrect type")
def test_date_and_index(self):
# Test case where same column appears in parse_date and index_col
df = sql.read_sql_query("SELECT * FROM types_test_data", self.conn,
index_col='DateCol',
parse_dates=['DateCol', 'IntDateCol'])
self.assertTrue(issubclass(df.index.dtype.type, np.datetime64),
"DateCol loaded with incorrect type")
self.assertTrue(issubclass(df.IntDateCol.dtype.type, np.datetime64),
"IntDateCol loaded with incorrect type")
def test_timedelta(self):
# see #6921
tm._skip_if_not_numpy17_friendly()
df = to_timedelta(Series(['00:00:01', '00:00:03'], name='foo')).to_frame()
with tm.assert_produces_warning(UserWarning):
df.to_sql('test_timedelta', self.conn)
result = sql.read_sql_query('SELECT * FROM test_timedelta', self.conn)
tm.assert_series_equal(result['foo'], df['foo'].astype('int64'))
def test_to_sql_index_label(self):
temp_frame = DataFrame({'col1': range(4)})
# no index name, defaults to 'index'
sql.to_sql(temp_frame, 'test_index_label', self.conn)
frame = sql.read_sql_query('SELECT * FROM test_index_label', self.conn)
self.assertEqual(frame.columns[0], 'index')
# specifying index_label
sql.to_sql(temp_frame, 'test_index_label', self.conn,
if_exists='replace', index_label='other_label')
frame = sql.read_sql_query('SELECT * FROM test_index_label', self.conn)
self.assertEqual(frame.columns[0], 'other_label',
"Specified index_label not written to database")
# using the index name
temp_frame.index.name = 'index_name'
sql.to_sql(temp_frame, 'test_index_label', self.conn,
if_exists='replace')
frame = sql.read_sql_query('SELECT * FROM test_index_label', self.conn)
self.assertEqual(frame.columns[0], 'index_name',
"Index name not written to database")
# has index name, but specifying index_label
sql.to_sql(temp_frame, 'test_index_label', self.conn,
if_exists='replace', index_label='other_label')
frame = sql.read_sql_query('SELECT * FROM test_index_label', self.conn)
self.assertEqual(frame.columns[0], 'other_label',
"Specified index_label not written to database")
def test_to_sql_index_label_multiindex(self):
temp_frame = DataFrame({'col1': range(4)},
index=MultiIndex.from_product([('A0', 'A1'), ('B0', 'B1')]))
# no index name, defaults to 'level_0' and 'level_1'
sql.to_sql(temp_frame, 'test_index_label', self.conn)
frame = sql.read_sql_query('SELECT * FROM test_index_label', self.conn)
self.assertEqual(frame.columns[0], 'level_0')
self.assertEqual(frame.columns[1], 'level_1')
# specifying index_label
sql.to_sql(temp_frame, 'test_index_label', self.conn,
if_exists='replace', index_label=['A', 'B'])
frame = sql.read_sql_query('SELECT * FROM test_index_label', self.conn)
self.assertEqual(frame.columns[:2].tolist(), ['A', 'B'],
"Specified index_labels not written to database")
# using the index name
temp_frame.index.names = ['A', 'B']
sql.to_sql(temp_frame, 'test_index_label', self.conn,
if_exists='replace')
frame = sql.read_sql_query('SELECT * FROM test_index_label', self.conn)
self.assertEqual(frame.columns[:2].tolist(), ['A', 'B'],
"Index names not written to database")
# has index name, but specifying index_label
sql.to_sql(temp_frame, 'test_index_label', self.conn,
if_exists='replace', index_label=['C', 'D'])
frame = sql.read_sql_query('SELECT * FROM test_index_label', self.conn)
self.assertEqual(frame.columns[:2].tolist(), ['C', 'D'],
"Specified index_labels not written to database")
# wrong length of index_label
self.assertRaises(ValueError, sql.to_sql, temp_frame,
'test_index_label', self.conn, if_exists='replace',
index_label='C')
def test_integer_col_names(self):
df = DataFrame([[1, 2], [3, 4]], columns=[0, 1])
sql.to_sql(df, "test_frame_integer_col_names", self.conn,
if_exists='replace')
def test_get_schema(self):
create_sql = sql.get_schema(self.test_frame1, 'test', 'sqlite',
con=self.conn)
self.assertTrue('CREATE' in create_sql)
class TestSQLApi(_TestSQLApi):
"""
Test the public API as it would be used directly
Tests for `read_sql_table` are included here, as this is specific for the
sqlalchemy mode.
"""
flavor = 'sqlite'
def connect(self):
if SQLALCHEMY_INSTALLED:
return sqlalchemy.create_engine('sqlite:///:memory:')
else:
raise nose.SkipTest('SQLAlchemy not installed')
def test_read_table_columns(self):
# test columns argument in read_table
sql.to_sql(self.test_frame1, 'test_frame', self.conn)
cols = ['A', 'B']
result = sql.read_sql_table('test_frame', self.conn, columns=cols)
self.assertEqual(result.columns.tolist(), cols,
"Columns not correctly selected")
def test_read_table_index_col(self):
# test columns argument in read_table
sql.to_sql(self.test_frame1, 'test_frame', self.conn)
result = sql.read_sql_table('test_frame', self.conn, index_col="index")
self.assertEqual(result.index.names, ["index"],
"index_col not correctly set")
result = sql.read_sql_table('test_frame', self.conn, index_col=["A", "B"])
self.assertEqual(result.index.names, ["A", "B"],
"index_col not correctly set")
result = sql.read_sql_table('test_frame', self.conn, index_col=["A", "B"],
columns=["C", "D"])
self.assertEqual(result.index.names, ["A", "B"],
"index_col not correctly set")
self.assertEqual(result.columns.tolist(), ["C", "D"],
"columns not set correctly whith index_col")
def test_read_sql_delegate(self):
iris_frame1 = sql.read_sql_query(
"SELECT * FROM iris", self.conn)
iris_frame2 = sql.read_sql(
"SELECT * FROM iris", self.conn)
tm.assert_frame_equal(iris_frame1, iris_frame2,
"read_sql and read_sql_query have not the same"
" result with a query")
iris_frame1 = sql.read_sql_table('iris', self.conn)
iris_frame2 = sql.read_sql('iris', self.conn)
tm.assert_frame_equal(iris_frame1, iris_frame2)
def test_not_reflect_all_tables(self):
# create invalid table
qry = """CREATE TABLE invalid (x INTEGER, y UNKNOWN);"""
self.conn.execute(qry)
qry = """CREATE TABLE other_table (x INTEGER, y INTEGER);"""
self.conn.execute(qry)
with warnings.catch_warnings(record=True) as w:
# Cause all warnings to always be triggered.
warnings.simplefilter("always")
# Trigger a warning.
sql.read_sql_table('other_table', self.conn)
sql.read_sql_query('SELECT * FROM other_table', self.conn)
# Verify some things
self.assertEqual(len(w), 0, "Warning triggered for other table")
class TestSQLLegacyApi(_TestSQLApi):
"""
Test the public legacy API
"""
flavor = 'sqlite'
def connect(self, database=":memory:"):
return sqlite3.connect(database)
def test_sql_open_close(self):
# Test if the IO in the database still work if the connection closed
# between the writing and reading (as in many real situations).
with tm.ensure_clean() as name:
conn = self.connect(name)
sql.to_sql(self.test_frame3, "test_frame3_legacy", conn,
flavor="sqlite", index=False)
conn.close()
conn = self.connect(name)
result = sql.read_sql_query("SELECT * FROM test_frame3_legacy;",
conn)
conn.close()
tm.assert_frame_equal(self.test_frame3, result)
def test_read_sql_delegate(self):
iris_frame1 = sql.read_sql_query("SELECT * FROM iris", self.conn)
iris_frame2 = sql.read_sql("SELECT * FROM iris", self.conn)
tm.assert_frame_equal(iris_frame1, iris_frame2,
"read_sql and read_sql_query have not the same"
" result with a query")
self.assertRaises(sql.DatabaseError, sql.read_sql, 'iris', self.conn)
def test_safe_names_warning(self):
# GH 6798
df = DataFrame([[1, 2], [3, 4]], columns=['a', 'b ']) # has a space
# warns on create table with spaces in names
with tm.assert_produces_warning():
sql.to_sql(df, "test_frame3_legacy", self.conn,
flavor="sqlite", index=False)
def test_get_schema2(self):
# without providing a connection object (available for backwards comp)
create_sql = sql.get_schema(self.test_frame1, 'test', 'sqlite')
self.assertTrue('CREATE' in create_sql)
def test_tquery(self):
with tm.assert_produces_warning(FutureWarning):
iris_results = sql.tquery("SELECT * FROM iris", con=self.conn)
row = iris_results[0]
tm.equalContents(row, [5.1, 3.5, 1.4, 0.2, 'Iris-setosa'])
def test_uquery(self):
with tm.assert_produces_warning(FutureWarning):
rows = sql.uquery("SELECT * FROM iris LIMIT 1", con=self.conn)
self.assertEqual(rows, -1)
#------------------------------------------------------------------------------
#--- Database flavor specific tests
class _TestSQLAlchemy(PandasSQLTest):
"""
Base class for testing the sqlalchemy backend.
Subclasses for specific database types are created below. Tests that
deviate for each flavor are overwritten there.
"""
flavor = None
def setUp(self):
self.setup_import()
self.setup_driver()
self.setup_connect()
self._load_iris_data()
self._load_raw_sql()
self._load_test1_data()
def setup_import(self):
# Skip this test if SQLAlchemy not available
if not SQLALCHEMY_INSTALLED:
raise nose.SkipTest('SQLAlchemy not installed')
def setup_driver(self):
raise NotImplementedError()
def connect(self):
raise NotImplementedError()
def setup_connect(self):
try:
self.conn = self.connect()
self.pandasSQL = sql.PandasSQLAlchemy(self.conn)
# to test if connection can be made:
self.conn.connect()
except sqlalchemy.exc.OperationalError:
raise nose.SkipTest("Can't connect to {0} server".format(self.flavor))
def tearDown(self):
raise NotImplementedError()
def test_aread_sql(self):
self._read_sql_iris()
def test_read_sql_parameter(self):
self._read_sql_iris_parameter()
def test_read_sql_named_parameter(self):
self._read_sql_iris_named_parameter()
def test_to_sql(self):
self._to_sql()
def test_to_sql_fail(self):
self._to_sql_fail()
def test_to_sql_replace(self):
self._to_sql_replace()
def test_to_sql_append(self):
self._to_sql_append()
def test_create_table(self):
temp_conn = self.connect()
temp_frame = DataFrame(
{'one': [1., 2., 3., 4.], 'two': [4., 3., 2., 1.]})
pandasSQL = sql.PandasSQLAlchemy(temp_conn)
pandasSQL.to_sql(temp_frame, 'temp_frame')
self.assertTrue(
temp_conn.has_table('temp_frame'), 'Table not written to DB')
def test_drop_table(self):
temp_conn = self.connect()
temp_frame = DataFrame(
{'one': [1., 2., 3., 4.], 'two': [4., 3., 2., 1.]})
pandasSQL = sql.PandasSQLAlchemy(temp_conn)
pandasSQL.to_sql(temp_frame, 'temp_frame')
self.assertTrue(
temp_conn.has_table('temp_frame'), 'Table not written to DB')
pandasSQL.drop_table('temp_frame')
self.assertFalse(
temp_conn.has_table('temp_frame'), 'Table not deleted from DB')
def test_roundtrip(self):
self._roundtrip()
def test_execute_sql(self):
self._execute_sql()
def test_read_table(self):
iris_frame = sql.read_sql_table("iris", con=self.conn)
self._check_iris_loaded_frame(iris_frame)
def test_read_table_columns(self):
iris_frame = sql.read_sql_table(
"iris", con=self.conn, columns=['SepalLength', 'SepalLength'])
tm.equalContents(
iris_frame.columns.values, ['SepalLength', 'SepalLength'])
def test_read_table_absent(self):
self.assertRaises(
ValueError, sql.read_sql_table, "this_doesnt_exist", con=self.conn)
def test_default_type_conversion(self):
df = sql.read_sql_table("types_test_data", self.conn)
self.assertTrue(issubclass(df.FloatCol.dtype.type, np.floating),
"FloatCol loaded with incorrect type")
self.assertTrue(issubclass(df.IntCol.dtype.type, np.integer),
"IntCol loaded with incorrect type")
self.assertTrue(issubclass(df.BoolCol.dtype.type, np.bool_),
"BoolCol loaded with incorrect type")
# Int column with NA values stays as float
self.assertTrue(issubclass(df.IntColWithNull.dtype.type, np.floating),
"IntColWithNull loaded with incorrect type")
# Bool column with NA values becomes object
self.assertTrue(issubclass(df.BoolColWithNull.dtype.type, np.object),
"BoolColWithNull loaded with incorrect type")
def test_bigint(self):
# int64 should be converted to BigInteger, GH7433
df = DataFrame(data={'i64':[2**62]})
df.to_sql('test_bigint', self.conn, index=False)
result = sql.read_sql_table('test_bigint', self.conn)
tm.assert_frame_equal(df, result)
def test_default_date_load(self):
df = sql.read_sql_table("types_test_data", self.conn)
# IMPORTANT - sqlite has no native date type, so shouldn't parse, but
# MySQL SHOULD be converted.
self.assertTrue(issubclass(df.DateCol.dtype.type, np.datetime64),
"DateCol loaded with incorrect type")
def test_date_parsing(self):
# No Parsing
df = sql.read_sql_table("types_test_data", self.conn)
df = sql.read_sql_table("types_test_data", self.conn,
parse_dates=['DateCol'])
self.assertTrue(issubclass(df.DateCol.dtype.type, np.datetime64),
"DateCol loaded with incorrect type")
df = sql.read_sql_table("types_test_data", self.conn,
parse_dates={'DateCol': '%Y-%m-%d %H:%M:%S'})
self.assertTrue(issubclass(df.DateCol.dtype.type, np.datetime64),
"DateCol loaded with incorrect type")
df = sql.read_sql_table("types_test_data", self.conn, parse_dates={
'DateCol': {'format': '%Y-%m-%d %H:%M:%S'}})
self.assertTrue(issubclass(df.DateCol.dtype.type, np.datetime64),
"IntDateCol loaded with incorrect type")
df = sql.read_sql_table(
"types_test_data", self.conn, parse_dates=['IntDateCol'])
self.assertTrue(issubclass(df.IntDateCol.dtype.type, np.datetime64),
"IntDateCol loaded with incorrect type")
df = sql.read_sql_table(
"types_test_data", self.conn, parse_dates={'IntDateCol': 's'})
self.assertTrue(issubclass(df.IntDateCol.dtype.type, np.datetime64),
"IntDateCol loaded with incorrect type")
df = sql.read_sql_table(
"types_test_data", self.conn, parse_dates={'IntDateCol': {'unit': 's'}})
self.assertTrue(issubclass(df.IntDateCol.dtype.type, np.datetime64),
"IntDateCol loaded with incorrect type")
def test_datetime(self):
if self.driver == 'pymysql':
raise nose.SkipTest('writing datetime not working with pymysql')
df = DataFrame({'A': date_range('2013-01-01 09:00:00', periods=3),
'B': np.arange(3.0)})
df.to_sql('test_datetime', self.conn)
# with read_table -> type information from schema used
result = sql.read_sql_table('test_datetime', self.conn)
result = result.drop('index', axis=1)
tm.assert_frame_equal(result, df)
# with read_sql -> no type information -> sqlite has no native
result = sql.read_sql_query('SELECT * FROM test_datetime', self.conn)
result = result.drop('index', axis=1)
if self.flavor == 'sqlite':
self.assertTrue(isinstance(result.loc[0, 'A'], string_types))
result['A'] = to_datetime(result['A'])
tm.assert_frame_equal(result, df)
else:
tm.assert_frame_equal(result, df)
def test_datetime_NaT(self):
# status:
# - postgresql: gives error on inserting "0001-255-255T00:00:00"
# - sqlite3: works, but reading it with query returns '-001--1--1 -1:-1:-1.-00001'
if self.driver == 'pymysql':
raise nose.SkipTest('writing datetime not working with pymysql')
if self.driver == 'psycopg2':
raise nose.SkipTest('writing datetime NaT not working with psycopg2')
if self.flavor == 'sqlite':
raise nose.SkipTest('reading datetime NaT not working with sqlite')
df = DataFrame({'A': date_range('2013-01-01 09:00:00', periods=3),
'B': np.arange(3.0)})
df.loc[1, 'A'] = np.nan
df.to_sql('test_datetime', self.conn, index=False)
# with read_table -> type information from schema used
result = sql.read_sql_table('test_datetime', self.conn)
tm.assert_frame_equal(result, df)
# with read_sql -> no type information -> sqlite has no native
result = sql.read_sql_query('SELECT * FROM test_datetime', self.conn)
if self.flavor == 'sqlite':
self.assertTrue(isinstance(result.loc[0, 'A'], string_types))
result['A'] = to_datetime(result['A'], coerce=True)
tm.assert_frame_equal(result, df)
else:
tm.assert_frame_equal(result, df)
def test_mixed_dtype_insert(self):
# see GH6509
s1 = Series(2**25 + 1,dtype=np.int32)
s2 = Series(0.0,dtype=np.float32)
df = DataFrame({'s1': s1, 's2': s2})
# write and read again
df.to_sql("test_read_write", self.conn, index=False)
df2 = sql.read_sql_table("test_read_write", self.conn)
tm.assert_frame_equal(df, df2, check_dtype=False, check_exact=True)
def test_nan_numeric(self):
if self.driver == 'pymysql':
raise nose.SkipTest('writing NaNs not working with pymysql')
# NaNs in numeric float column
df = DataFrame({'A':[0, 1, 2], 'B':[0.2, np.nan, 5.6]})
df.to_sql('test_nan', self.conn, index=False)
# with read_table
result = sql.read_sql_table('test_nan', self.conn)
tm.assert_frame_equal(result, df)
# with read_sql
result = sql.read_sql_query('SELECT * FROM test_nan', self.conn)
tm.assert_frame_equal(result, df)
def test_nan_fullcolumn(self):
if self.driver == 'pymysql':
raise nose.SkipTest('writing NaNs not working with pymysql')