forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 7
/
Copy pathtest_indexing.py
1501 lines (1149 loc) · 54.4 KB
/
test_indexing.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
# pylint: disable-msg=W0612,E1101
import unittest
import nose
import itertools
import warnings
from pandas.compat import range, lrange, StringIO, lmap, map
from numpy import random, nan
from numpy.random import randn
import numpy as np
from numpy.testing import assert_array_equal
import pandas as pd
import pandas.core.common as com
from pandas.core.api import (DataFrame, Index, Series, Panel, notnull, isnull,
MultiIndex, DatetimeIndex, Timestamp)
from pandas.util.testing import (assert_almost_equal, assert_series_equal,
assert_frame_equal, assert_panel_equal)
from pandas import compat, concat
import pandas.util.testing as tm
import pandas.lib as lib
from pandas import date_range
from numpy.testing.decorators import slow
_verbose = False
#-------------------------------------------------------------------------------
# Indexing test cases
def _generate_indices(f, values=False):
""" generate the indicies
if values is True , use the axis values
is False, use the range
"""
axes = f.axes
if values:
axes = [ lrange(len(a)) for a in axes ]
return itertools.product(*axes)
def _get_value(f, i, values=False):
""" return the value for the location i """
# check agains values
if values:
return f.values[i]
# this is equiv of f[col][row].....
#v = f
#for a in reversed(i):
# v = v.__getitem__(a)
#return v
return f.ix[i]
def _get_result(obj, method, key, axis):
""" return the result for this obj with this key and this axis """
if isinstance(key, dict):
key = key[axis]
# use an artifical conversion to map the key as integers to the labels
# so ix can work for comparisions
if method == 'indexer':
method = 'ix'
key = obj._get_axis(axis)[key]
# in case we actually want 0 index slicing
try:
xp = getattr(obj, method).__getitem__(_axify(obj,key,axis))
except:
xp = getattr(obj, method).__getitem__(key)
return xp
def _axify(obj, key, axis):
# create a tuple accessor
if axis is not None:
axes = [ slice(None) ] * obj.ndim
axes[axis] = key
return tuple(axes)
return k
class TestIndexing(unittest.TestCase):
_multiprocess_can_split_ = True
_objs = set(['series','frame','panel'])
_typs = set(['ints','labels','mixed','ts','floats','empty'])
def setUp(self):
import warnings
warnings.filterwarnings(action='ignore', category=FutureWarning)
self.series_ints = Series(np.random.rand(4), index=lrange(0,8,2))
self.frame_ints = DataFrame(np.random.randn(4, 4), index=lrange(0, 8, 2), columns=lrange(0,12,3))
self.panel_ints = Panel(np.random.rand(4,4,4), items=lrange(0,8,2),major_axis=lrange(0,12,3),minor_axis=lrange(0,16,4))
self.series_labels = Series(np.random.randn(4), index=list('abcd'))
self.frame_labels = DataFrame(np.random.randn(4, 4), index=list('abcd'), columns=list('ABCD'))
self.panel_labels = Panel(np.random.randn(4,4,4), items=list('abcd'), major_axis=list('ABCD'), minor_axis=list('ZYXW'))
self.series_mixed = Series(np.random.randn(4), index=[2, 4, 'null', 8])
self.frame_mixed = DataFrame(np.random.randn(4, 4), index=[2, 4, 'null', 8])
self.panel_mixed = Panel(np.random.randn(4,4,4), items=[2,4,'null',8])
self.series_ts = Series(np.random.randn(4), index=date_range('20130101', periods=4))
self.frame_ts = DataFrame(np.random.randn(4, 4), index=date_range('20130101', periods=4))
self.panel_ts = Panel(np.random.randn(4, 4, 4), items=date_range('20130101', periods=4))
#self.series_floats = Series(np.random.randn(4), index=[1.00, 2.00, 3.00, 4.00])
#self.frame_floats = DataFrame(np.random.randn(4, 4), columns=[1.00, 2.00, 3.00, 4.00])
#self.panel_floats = Panel(np.random.rand(4,4,4), items = [1.00,2.00,3.00,4.00])
self.frame_empty = DataFrame({})
self.series_empty = Series({})
self.panel_empty = Panel({})
# form agglomerates
for o in self._objs:
d = dict()
for t in self._typs:
d[t] = getattr(self,'%s_%s' % (o,t),None)
setattr(self,o,d)
def check_values(self, f, func, values = False):
if f is None: return
axes = f.axes
indicies = itertools.product(*axes)
for i in indicies:
result = getattr(f,func)[i]
# check agains values
if values:
expected = f.values[i]
else:
expected = f
for a in reversed(i):
expected = expected.__getitem__(a)
assert_almost_equal(result, expected)
def check_result(self, name, method1, key1, method2, key2, typs = None, objs = None, axes = None, fails = None):
def _eq(t, o, a, obj, k1, k2):
""" compare equal for these 2 keys """
if a is not None and a > obj.ndim-1:
return
def _print(result, error = None):
if error is not None:
error = str(error)
v = "%-16.16s [%-16.16s]: [typ->%-8.8s,obj->%-8.8s,key1->(%-4.4s),key2->(%-4.4s),axis->%s] %s" % (name,result,t,o,method1,method2,a,error or '')
if _verbose:
print(v)
try:
### good debug location ###
#if name == 'bool' and t == 'empty' and o == 'series' and method1 == 'loc':
# import pdb; pdb.set_trace()
rs = getattr(obj, method1).__getitem__(_axify(obj,k1,a))
try:
xp = _get_result(obj,method2,k2,a)
except:
result = 'no comp'
_print(result)
return
try:
if np.isscalar(rs) and np.isscalar(xp):
self.assert_(rs == xp)
elif xp.ndim == 1:
assert_series_equal(rs,xp)
elif xp.ndim == 2:
assert_frame_equal(rs,xp)
elif xp.ndim == 3:
assert_panel_equal(rs,xp)
result = 'ok'
except (AssertionError):
result = 'fail'
# reverse the checks
if fails is True:
if result == 'fail':
result = 'ok (fail)'
if not result.startswith('ok'):
raise AssertionError(_print(result))
_print(result)
except AssertionError:
raise
except TypeError:
raise AssertionError(_print('type error'))
except Exception as detail:
# if we are in fails, the ok, otherwise raise it
if fails is not None:
if isinstance(detail, fails):
result = 'ok (%s)' % type(detail).__name__
_print(result)
return
result = type(detail).__name__
raise AssertionError(_print(result, error = detail))
if typs is None:
typs = self._typs
if objs is None:
objs = self._objs
if axes is not None:
if not isinstance(axes,(tuple,list)):
axes = [ axes ]
else:
axes = list(axes)
else:
axes = [ 0, 1, 2]
# check
for o in objs:
if o not in self._objs:
continue
d = getattr(self,o)
for a in axes:
for t in typs:
if t not in self._typs:
continue
obj = d[t]
if obj is not None:
obj = obj.copy()
k2 = key2
_eq(t, o, a, obj, key1, k2)
def test_at_and_iat_get(self):
def _check(f, func, values = False):
if f is not None:
indicies = _generate_indices(f, values)
for i in indicies:
result = getattr(f,func)[i]
expected = _get_value(f,i,values)
assert_almost_equal(result, expected)
for o in self._objs:
d = getattr(self,o)
# iat
_check(d['ints'],'iat', values=True)
for f in [d['labels'],d['ts'],d['floats']]:
if f is not None:
self.assertRaises(ValueError, self.check_values, f, 'iat')
# at
_check(d['ints'], 'at')
_check(d['labels'],'at')
_check(d['ts'], 'at')
_check(d['floats'],'at')
def test_at_and_iat_set(self):
def _check(f, func, values = False):
if f is not None:
indicies = _generate_indices(f, values)
for i in indicies:
getattr(f,func)[i] = 1
expected = _get_value(f,i,values)
assert_almost_equal(expected, 1)
for t in self._objs:
d = getattr(self,t)
_check(d['ints'],'iat',values=True)
for f in [d['labels'],d['ts'],d['floats']]:
if f is not None:
self.assertRaises(ValueError, _check, f, 'iat')
# at
_check(d['ints'], 'at')
_check(d['labels'],'at')
_check(d['ts'], 'at')
_check(d['floats'],'at')
def test_at_timestamp(self):
# as timestamp is not a tuple!
dates = date_range('1/1/2000', periods=8)
df = DataFrame(randn(8, 4), index=dates, columns=['A', 'B', 'C', 'D'])
s = df['A']
result = s.at[dates[5]]
xp = s.values[5]
self.assert_(result == xp)
def test_iat_invalid_args(self):
pass
def test_iloc_getitem_int(self):
# integer
self.check_result('integer', 'iloc', 2, 'ix', { 0 : 4, 1: 6, 2: 8 }, typs = ['ints'])
self.check_result('integer', 'iloc', 2, 'indexer', 2, typs = ['labels','mixed','ts','floats','empty'], fails = IndexError)
def test_iloc_getitem_neg_int(self):
# neg integer
self.check_result('neg int', 'iloc', -1, 'ix', { 0 : 6, 1: 9, 2: 12 }, typs = ['ints'])
self.check_result('neg int', 'iloc', -1, 'indexer', -1, typs = ['labels','mixed','ts','floats','empty'], fails = IndexError)
def test_iloc_getitem_list_int(self):
# list of ints
self.check_result('list int', 'iloc', [0,1,2], 'ix', { 0 : [0,2,4], 1 : [0,3,6], 2: [0,4,8] }, typs = ['ints'])
self.check_result('list int', 'iloc', [0,1,2], 'indexer', [0,1,2], typs = ['labels','mixed','ts','floats','empty'], fails = IndexError)
def test_iloc_getitem_dups(self):
# no dups in panel (bug?)
self.check_result('list int (dups)', 'iloc', [0,1,1,3], 'ix', { 0 : [0,2,2,6], 1 : [0,3,3,9] }, objs = ['series','frame'], typs = ['ints'])
def test_iloc_getitem_array(self):
# array like
s = Series(index=lrange(1,4))
self.check_result('array like', 'iloc', s.index, 'ix', { 0 : [2,4,6], 1 : [3,6,9], 2: [4,8,12] }, typs = ['ints'])
def test_iloc_getitem_bool(self):
# boolean indexers
b = [True,False,True,False,]
self.check_result('bool', 'iloc', b, 'ix', b, typs = ['ints'])
self.check_result('bool', 'iloc', b, 'ix', b, typs = ['labels','mixed','ts','floats','empty'], fails = IndexError)
def test_iloc_getitem_slice(self):
# slices
self.check_result('slice', 'iloc', slice(1,3), 'ix', { 0 : [2,4], 1: [3,6], 2: [4,8] }, typs = ['ints'])
self.check_result('slice', 'iloc', slice(1,3), 'indexer', slice(1,3), typs = ['labels','mixed','ts','floats','empty'], fails = IndexError)
def test_iloc_getitem_slice_dups(self):
df1 = DataFrame(np.random.randn(10,4),columns=['A','A','B','B'])
df2 = DataFrame(np.random.randint(0,10,size=20).reshape(10,2),columns=['A','C'])
# axis=1
df = concat([df1,df2],axis=1)
assert_frame_equal(df.iloc[:,:4],df1)
assert_frame_equal(df.iloc[:,4:],df2)
df = concat([df2,df1],axis=1)
assert_frame_equal(df.iloc[:,:2],df2)
assert_frame_equal(df.iloc[:,2:],df1)
assert_frame_equal(df.iloc[:,0:3],concat([df2,df1.iloc[:,[0]]],axis=1))
# axis=0
df = concat([df,df],axis=0)
assert_frame_equal(df.iloc[0:10,:2],df2)
assert_frame_equal(df.iloc[0:10,2:],df1)
assert_frame_equal(df.iloc[10:,:2],df2)
assert_frame_equal(df.iloc[10:,2:],df1)
def test_iloc_getitem_out_of_bounds(self):
# out-of-bounds slice
self.assertRaises(IndexError, self.frame_ints.iloc.__getitem__, tuple([slice(None),slice(1,5,None)]))
self.assertRaises(IndexError, self.frame_ints.iloc.__getitem__, tuple([slice(None),slice(-5,3,None)]))
self.assertRaises(IndexError, self.frame_ints.iloc.__getitem__, tuple([slice(1,5,None)]))
self.assertRaises(IndexError, self.frame_ints.iloc.__getitem__, tuple([slice(-5,3,None)]))
def test_iloc_setitem(self):
df = self.frame_ints
df.iloc[1,1] = 1
result = df.iloc[1,1]
self.assert_(result == 1)
df.iloc[:,2:3] = 0
expected = df.iloc[:,2:3]
result = df.iloc[:,2:3]
assert_frame_equal(result, expected)
def test_iloc_multiindex(self):
df = DataFrame(np.random.randn(3, 3),
columns=[[2,2,4],[6,8,10]],
index=[[4,4,8],[8,10,12]])
rs = df.iloc[2]
xp = df.irow(2)
assert_series_equal(rs, xp)
rs = df.iloc[:,2]
xp = df.icol(2)
assert_series_equal(rs, xp)
rs = df.iloc[2,2]
xp = df.values[2,2]
self.assert_(rs == xp)
def test_loc_getitem_int(self):
# int label
self.check_result('int label', 'loc', 2, 'ix', 2, typs = ['ints'], axes = 0)
self.check_result('int label', 'loc', 3, 'ix', 3, typs = ['ints'], axes = 1)
self.check_result('int label', 'loc', 4, 'ix', 4, typs = ['ints'], axes = 2)
self.check_result('int label', 'loc', 2, 'ix', 2, typs = ['label'], fails = KeyError)
def test_loc_getitem_label(self):
# label
self.check_result('label', 'loc', 'c', 'ix', 'c', typs = ['labels'], axes=0)
self.check_result('label', 'loc', 'null', 'ix', 'null', typs = ['mixed'] , axes=0)
self.check_result('label', 'loc', 8, 'ix', 8, typs = ['mixed'] , axes=0)
self.check_result('label', 'loc', Timestamp('20130102'), 'ix', 1, typs = ['ts'], axes=0)
self.check_result('label', 'loc', 'c', 'ix', 'c', typs = ['empty'], fails = KeyError)
def test_loc_getitem_label_out_of_range(self):
# out of range label
self.check_result('label range', 'loc', 'f', 'ix', 'f', typs = ['ints','labels','mixed','ts','floats'], fails=KeyError)
def test_loc_getitem_label_list(self):
# list of labels
self.check_result('list lbl', 'loc', [0,2,4], 'ix', [0,2,4], typs = ['ints'], axes=0)
self.check_result('list lbl', 'loc', [3,6,9], 'ix', [3,6,9], typs = ['ints'], axes=1)
self.check_result('list lbl', 'loc', [4,8,12], 'ix', [4,8,12], typs = ['ints'], axes=2)
self.check_result('list lbl', 'loc', ['a','b','d'], 'ix', ['a','b','d'], typs = ['labels'], axes=0)
self.check_result('list lbl', 'loc', ['A','B','C'], 'ix', ['A','B','C'], typs = ['labels'], axes=1)
self.check_result('list lbl', 'loc', ['Z','Y','W'], 'ix', ['Z','Y','W'], typs = ['labels'], axes=2)
self.check_result('list lbl', 'loc', [2,8,'null'], 'ix', [2,8,'null'], typs = ['mixed'], axes=0)
self.check_result('list lbl', 'loc', [Timestamp('20130102'),Timestamp('20130103')], 'ix',
[Timestamp('20130102'),Timestamp('20130103')], typs = ['ts'], axes=0)
# fails
self.check_result('list lbl', 'loc', [0,1,2], 'indexer', [0,1,2], typs = ['empty'], fails = KeyError)
self.check_result('list lbl', 'loc', [0,2,3], 'ix', [0,2,3], typs = ['ints'], axes=0, fails = KeyError)
self.check_result('list lbl', 'loc', [3,6,7], 'ix', [3,6,9], typs = ['ints'], axes=1, fails = KeyError)
self.check_result('list lbl', 'loc', [4,8,10], 'ix', [4,8,12], typs = ['ints'], axes=2, fails = KeyError)
# array like
self.check_result('array like', 'loc', Series(index=[0,2,4]).index, 'ix', [0,2,4], typs = ['ints'], axes=0)
self.check_result('array like', 'loc', Series(index=[3,6,9]).index, 'ix', [3,6,9], typs = ['ints'], axes=1)
self.check_result('array like', 'loc', Series(index=[4,8,12]).index, 'ix', [4,8,12], typs = ['ints'], axes=2)
def test_loc_getitem_bool(self):
# boolean indexers
b = [True,False,True,False]
self.check_result('bool', 'loc', b, 'ix', b, typs = ['ints','labels','mixed','ts','floats'])
self.check_result('bool', 'loc', b, 'ix', b, typs = ['empty'], fails = KeyError)
def test_loc_getitem_int_slice(self):
# int slices in int
self.check_result('int slice1', 'loc', slice(2,4), 'ix', { 0 : [2,4], 1: [3,6], 2: [4,8] }, typs = ['ints'], fails=KeyError)
# ok
self.check_result('int slice2', 'loc', slice(2,4), 'ix', [2,4], typs = ['ints'], axes = 0)
self.check_result('int slice2', 'loc', slice(3,6), 'ix', [3,6], typs = ['ints'], axes = 1)
self.check_result('int slice2', 'loc', slice(4,8), 'ix', [4,8], typs = ['ints'], axes = 2)
# GH 3053
# loc should treat integer slices like label slices
from itertools import product
index = MultiIndex.from_tuples([t for t in product([6,7,8], ['a', 'b'])])
df = DataFrame(np.random.randn(6, 6), index, index)
result = df.loc[6:8,:]
expected = df.ix[6:8,:]
assert_frame_equal(result,expected)
index = MultiIndex.from_tuples([t for t in product([10, 20, 30], ['a', 'b'])])
df = DataFrame(np.random.randn(6, 6), index, index)
result = df.loc[20:30,:]
expected = df.ix[20:30,:]
assert_frame_equal(result,expected)
# doc examples
result = df.loc[10,:]
expected = df.ix[10,:]
assert_frame_equal(result,expected)
result = df.loc[:,10]
#expected = df.ix[:,10] (this fails)
expected = df[10]
assert_frame_equal(result,expected)
def test_loc_to_fail(self):
# GH3449
df = DataFrame(np.random.random((3, 3)),
index=['a', 'b', 'c'],
columns=['e', 'f', 'g'])
# raise a KeyError?
self.assertRaises(KeyError, df.loc.__getitem__, tuple([[1, 2], [1, 2]]))
def test_loc_getitem_label_slice(self):
# label slices (with ints)
self.check_result('lab slice', 'loc', slice(1,3), 'ix', slice(1,3), typs = ['labels','mixed','ts','floats','empty'], fails=KeyError)
# real label slices
self.check_result('lab slice', 'loc', slice('a','c'), 'ix', slice('a','c'), typs = ['labels'], axes=0)
self.check_result('lab slice', 'loc', slice('A','C'), 'ix', slice('A','C'), typs = ['labels'], axes=1)
self.check_result('lab slice', 'loc', slice('W','Z'), 'ix', slice('W','Z'), typs = ['labels'], axes=2)
self.check_result('ts slice', 'loc', slice('20130102','20130104'), 'ix', slice('20130102','20130104'), typs = ['ts'], axes=0)
self.check_result('ts slice', 'loc', slice('20130102','20130104'), 'ix', slice('20130102','20130104'), typs = ['ts'], axes=1, fails=KeyError)
self.check_result('ts slice', 'loc', slice('20130102','20130104'), 'ix', slice('20130102','20130104'), typs = ['ts'], axes=2, fails=KeyError)
self.check_result('mixed slice', 'loc', slice(2,8), 'ix', slice(2,8), typs = ['mixed'], axes=0, fails=KeyError)
self.check_result('mixed slice', 'loc', slice(2,8), 'ix', slice(2,8), typs = ['mixed'], axes=1, fails=KeyError)
self.check_result('mixed slice', 'loc', slice(2,8), 'ix', slice(2,8), typs = ['mixed'], axes=2, fails=KeyError)
self.check_result('mixed slice', 'loc', slice(2,4,2), 'ix', slice(2,4,2), typs = ['mixed'], axes=0)
def test_loc_general(self):
# GH 2922 (these are fails)
df = DataFrame(np.random.rand(4,4),columns=['A','B','C','D'])
self.assertRaises(KeyError, df.loc.__getitem__, tuple([slice(0,2),slice(0,2)]))
df = DataFrame(np.random.rand(4,4),columns=['A','B','C','D'], index=['A','B','C','D'])
self.assertRaises(KeyError, df.loc.__getitem__, tuple([slice(0,2),df.columns[0:2]]))
# want this to work
result = df.loc[:,"A":"B"].iloc[0:2,:]
self.assert_((result.columns == ['A','B']).all() == True)
self.assert_((result.index == ['A','B']).all() == True)
def test_loc_setitem_frame(self):
df = self.frame_labels
result = df.iloc[0,0]
df.loc['a','A'] = 1
result = df.loc['a','A']
self.assert_(result == 1)
result = df.iloc[0,0]
self.assert_(result == 1)
df.loc[:,'B':'D'] = 0
expected = df.loc[:,'B':'D']
result = df.ix[:,1:]
assert_frame_equal(result, expected)
def test_iloc_getitem_frame(self):
""" originally from test_frame.py"""
df = DataFrame(np.random.randn(10, 4), index=lrange(0, 20, 2), columns=lrange(0,8,2))
result = df.iloc[2]
exp = df.ix[4]
assert_series_equal(result, exp)
result = df.iloc[2,2]
exp = df.ix[4,4]
self.assert_(result == exp)
# slice
result = df.iloc[4:8]
expected = df.ix[8:14]
assert_frame_equal(result, expected)
result = df.iloc[:,2:3]
expected = df.ix[:,4:5]
assert_frame_equal(result, expected)
# list of integers
result = df.iloc[[0,1,3]]
expected = df.ix[[0,2,6]]
assert_frame_equal(result, expected)
result = df.iloc[[0,1,3],[0,1]]
expected = df.ix[[0,2,6],[0,2]]
assert_frame_equal(result, expected)
# neg indicies
result = df.iloc[[-1,1,3],[-1,1]]
expected = df.ix[[18,2,6],[6,2]]
assert_frame_equal(result, expected)
# dups indicies
result = df.iloc[[-1,-1,1,3],[-1,1]]
expected = df.ix[[18,18,2,6],[6,2]]
assert_frame_equal(result, expected)
# with index-like
s = Series(index=lrange(1,5))
result = df.iloc[s.index]
expected = df.ix[[2,4,6,8]]
assert_frame_equal(result, expected)
# out-of-bounds slice
self.assertRaises(IndexError, df.iloc.__getitem__, tuple([slice(None),slice(1,5,None)]))
self.assertRaises(IndexError, df.iloc.__getitem__, tuple([slice(None),slice(-5,3,None)]))
self.assertRaises(IndexError, df.iloc.__getitem__, tuple([slice(1,11,None)]))
self.assertRaises(IndexError, df.iloc.__getitem__, tuple([slice(-11,3,None)]))
# try with labelled frame
df = DataFrame(np.random.randn(10, 4), index=list('abcdefghij'), columns=list('ABCD'))
result = df.iloc[1,1]
exp = df.ix['b','B']
self.assert_(result == exp)
result = df.iloc[:,2:3]
expected = df.ix[:,['C']]
assert_frame_equal(result, expected)
# negative indexing
result = df.iloc[-1,-1]
exp = df.ix['j','D']
self.assert_(result == exp)
# out-of-bounds exception
self.assertRaises(IndexError, df.iloc.__getitem__, tuple([10,5]))
# trying to use a label
self.assertRaises(ValueError, df.iloc.__getitem__, tuple(['j','D']))
def test_iloc_setitem_series(self):
""" originally from test_series.py """
df = DataFrame(np.random.randn(10, 4), index=list('abcdefghij'), columns=list('ABCD'))
df.iloc[1,1] = 1
result = df.iloc[1,1]
self.assert_(result == 1)
df.iloc[:,2:3] = 0
expected = df.iloc[:,2:3]
result = df.iloc[:,2:3]
assert_frame_equal(result, expected)
def test_iloc_setitem_series(self):
s = Series(np.random.randn(10), index=lrange(0,20,2))
s.iloc[1] = 1
result = s.iloc[1]
self.assert_(result == 1)
s.iloc[:4] = 0
expected = s.iloc[:4]
result = s.iloc[:4]
assert_series_equal(result, expected)
def test_iloc_multiindex(self):
mi_labels = DataFrame(np.random.randn(4, 3), columns=[['i', 'i', 'j'],
['A', 'A', 'B']],
index=[['i', 'i', 'j', 'k'], ['X', 'X', 'Y','Y']])
mi_int = DataFrame(np.random.randn(3, 3),
columns=[[2,2,4],[6,8,10]],
index=[[4,4,8],[8,10,12]])
# the first row
rs = mi_int.iloc[0]
xp = mi_int.ix[4].ix[8]
assert_series_equal(rs, xp)
# 2nd (last) columns
rs = mi_int.iloc[:,2]
xp = mi_int.ix[:,2]
assert_series_equal(rs, xp)
# corner column
rs = mi_int.iloc[2,2]
xp = mi_int.ix[:,2].ix[2]
self.assert_(rs == xp)
# this is basically regular indexing
rs = mi_labels.iloc[2,2]
xp = mi_labels.ix['j'].ix[:,'j'].ix[0,0]
self.assert_(rs == xp)
def test_loc_multiindex(self):
mi_labels = DataFrame(np.random.randn(3, 3), columns=[['i', 'i', 'j'],
['A', 'A', 'B']],
index=[['i', 'i', 'j'], ['X', 'X', 'Y']])
mi_int = DataFrame(np.random.randn(3, 3),
columns=[[2,2,4],[6,8,10]],
index=[[4,4,8],[8,10,12]])
# the first row
rs = mi_labels.loc['i']
xp = mi_labels.ix['i']
assert_frame_equal(rs, xp)
# 2nd (last) columns
rs = mi_labels.loc[:,'j']
xp = mi_labels.ix[:,'j']
assert_frame_equal(rs, xp)
# corner column
rs = mi_labels.loc['j'].loc[:,'j']
xp = mi_labels.ix['j'].ix[:,'j']
assert_frame_equal(rs,xp)
# with a tuple
rs = mi_labels.loc[('i','X')]
xp = mi_labels.ix[('i','X')]
assert_frame_equal(rs,xp)
rs = mi_int.loc[4]
xp = mi_int.ix[4]
assert_frame_equal(rs,xp)
def test_ix_general(self):
# ix general issues
# GH 2817
data={'amount': {0: 700, 1: 600, 2: 222, 3: 333, 4: 444},
'col': {0: 3.5, 1: 3.5, 2: 4.0, 3: 4.0, 4: 4.0},
'year': {0: 2012, 1: 2011, 2: 2012, 3: 2012, 4: 2012}}
df = DataFrame(data).set_index(keys=['col','year'])
# this should raise correct error
self.assertRaises(KeyError, df.ix.__getitem__, tuple([4.0,2012]))
# this is ok
df.sortlevel(inplace=True)
df.ix[(4.0,2012)]
def test_ix_weird_slicing(self):
## http://stackoverflow.com/q/17056560/1240268
df = DataFrame({'one' : [1, 2, 3, np.nan, np.nan], 'two' : [1, 2, 3, 4, 5]})
df.ix[df['one']>1, 'two'] = -df['two']
expected = DataFrame({'one': {0: 1.0, 1: 2.0, 2: 3.0, 3: nan, 4: nan},
'two': {0: 1, 1: -2, 2: -3, 3: 4, 4: 5}})
assert_frame_equal(df, expected)
def test_xs_multiindex(self):
# GH2903
columns = MultiIndex.from_tuples([('a', 'foo'), ('a', 'bar'), ('b', 'hello'), ('b', 'world')], names=['lvl0', 'lvl1'])
df = DataFrame(np.random.randn(4, 4), columns=columns)
df.sortlevel(axis=1,inplace=True)
result = df.xs('a', level='lvl0', axis=1)
expected = df.iloc[:,0:2].loc[:,'a']
assert_frame_equal(result,expected)
result = df.xs('foo', level='lvl1', axis=1)
expected = df.iloc[:, 1:2].copy()
expected.columns = expected.columns.droplevel('lvl1')
assert_frame_equal(result, expected)
def test_setitem_dtype_upcast(self):
# GH3216
df = DataFrame([{"a": 1}, {"a": 3, "b": 2}])
df['c'] = np.nan
self.assert_(df['c'].dtype == np.float64)
df.ix[0,'c'] = 'foo'
expected = DataFrame([{"a": 1, "c" : 'foo'}, {"a": 3, "b": 2, "c" : np.nan}])
assert_frame_equal(df,expected)
def test_setitem_iloc(self):
# setitem with an iloc list
df = DataFrame(np.arange(9).reshape((3, 3)), index=["A", "B", "C"], columns=["A", "B", "C"])
df.iloc[[0,1],[1,2]]
df.iloc[[0,1],[1,2]] += 100
expected = DataFrame(np.array([0,101,102,3,104,105,6,7,8]).reshape((3, 3)), index=["A", "B", "C"], columns=["A", "B", "C"])
assert_frame_equal(df,expected)
def test_dups_fancy_indexing(self):
# GH 3455
from pandas.util.testing import makeCustomDataframe as mkdf
df= mkdf(10, 3)
df.columns = ['a','a','b']
cols = ['b','a']
result = df[['b','a']].columns
expected = Index(['b','a','a'])
self.assert_(result.equals(expected))
# across dtypes
df = DataFrame([[1,2,1.,2.,3.,'foo','bar']], columns=list('aaaaaaa'))
df.head()
str(df)
result = DataFrame([[1,2,1.,2.,3.,'foo','bar']])
result.columns = list('aaaaaaa')
df_v = df.iloc[:,4]
res_v = result.iloc[:,4]
assert_frame_equal(df,result)
# GH 3561, dups not in selected order
df = DataFrame({'test': [5,7,9,11]}, index=['A', 'A', 'B', 'C'])
rows = ['C', 'B']
expected = DataFrame({'test' : [11,9]},index=rows)
result = df.ix[rows]
assert_frame_equal(result, expected)
result = df.ix[Index(rows)]
assert_frame_equal(result, expected)
rows = ['C','B','E']
expected = DataFrame({'test' : [11,9,np.nan]},index=rows)
result = df.ix[rows]
assert_frame_equal(result, expected)
# inconsistent returns for unique/duplicate indices when values are missing
df = DataFrame(randn(4,3),index=list('ABCD'))
expected = df.ix[['E']]
dfnu = DataFrame(randn(5,3),index=list('AABCD'))
result = dfnu.ix[['E']]
assert_frame_equal(result, expected)
# GH 4619; duplicate indexer with missing label
df = DataFrame({"A": [0, 1, 2]})
result = df.ix[[0,8,0]]
expected = DataFrame({"A": [0, np.nan, 0]},index=[0,8,0])
assert_frame_equal(result,expected)
df = DataFrame({"A": list('abc')})
result = df.ix[[0,8,0]]
expected = DataFrame({"A": ['a', np.nan, 'a']},index=[0,8,0])
assert_frame_equal(result,expected)
# non unique with non unique selector
df = DataFrame({'test': [5,7,9,11]}, index=['A','A','B','C'])
expected = DataFrame({'test' : [5,7,5,7,np.nan]},index=['A','A','A','A','E'])
result = df.ix[['A','A','E']]
assert_frame_equal(result, expected)
def test_indexing_mixed_frame_bug(self):
# GH3492
df=DataFrame({'a':{1:'aaa',2:'bbb',3:'ccc'},'b':{1:111,2:222,3:333}})
# this works, new column is created correctly
df['test']=df['a'].apply(lambda x: '_' if x=='aaa' else x)
# this does not work, ie column test is not changed
idx=df['test']=='_'
temp=df.ix[idx,'a'].apply(lambda x: '-----' if x=='aaa' else x)
df.ix[idx,'test']=temp
self.assert_(df.iloc[0,2] == '-----')
#if I look at df, then element [0,2] equals '_'. If instead I type df.ix[idx,'test'], I get '-----', finally by typing df.iloc[0,2] I get '_'.
def test_set_index_nan(self):
# GH 3586
df = DataFrame({'PRuid': {17: 'nonQC', 18: 'nonQC', 19: 'nonQC', 20: '10', 21: '11', 22: '12', 23: '13',
24: '24', 25: '35', 26: '46', 27: '47', 28: '48', 29: '59', 30: '10'},
'QC': {17: 0.0, 18: 0.0, 19: 0.0, 20: nan, 21: nan, 22: nan, 23: nan, 24: 1.0, 25: nan,
26: nan, 27: nan, 28: nan, 29: nan, 30: nan},
'data': {17: 7.9544899999999998, 18: 8.0142609999999994, 19: 7.8591520000000008, 20: 0.86140349999999999,
21: 0.87853110000000001, 22: 0.8427041999999999, 23: 0.78587700000000005, 24: 0.73062459999999996,
25: 0.81668560000000001, 26: 0.81927080000000008, 27: 0.80705009999999999, 28: 0.81440240000000008,
29: 0.80140849999999997, 30: 0.81307740000000006},
'year': {17: 2006, 18: 2007, 19: 2008, 20: 1985, 21: 1985, 22: 1985, 23: 1985,
24: 1985, 25: 1985, 26: 1985, 27: 1985, 28: 1985, 29: 1985, 30: 1986}}).reset_index()
result = df.set_index(['year','PRuid','QC']).reset_index().reindex(columns=df.columns)
assert_frame_equal(result,df)
def test_multi_nan_indexing(self):
# GH 3588
df = DataFrame({"a":['R1', 'R2', np.nan, 'R4'], 'b':["C1", "C2", "C3" , "C4"], "c":[10, 15, np.nan , 20]})
result = df.set_index(['a','b'], drop=False)
expected = DataFrame({"a":['R1', 'R2', np.nan, 'R4'], 'b':["C1", "C2", "C3" , "C4"], "c":[10, 15, np.nan , 20]},
index = [Index(['R1','R2',np.nan,'R4'],name='a'),Index(['C1','C2','C3','C4'],name='b')])
assert_frame_equal(result,expected)
def test_iloc_panel_issue(self):
# GH 3617
p = Panel(randn(4, 4, 4))
self.assert_(p.iloc[:3, :3, :3].shape == (3,3,3))
self.assert_(p.iloc[1, :3, :3].shape == (3,3))
self.assert_(p.iloc[:3, 1, :3].shape == (3,3))
self.assert_(p.iloc[:3, :3, 1].shape == (3,3))
self.assert_(p.iloc[1, 1, :3].shape == (3,))
self.assert_(p.iloc[1, :3, 1].shape == (3,))
self.assert_(p.iloc[:3, 1, 1].shape == (3,))
def test_panel_getitem(self):
# GH4016, date selection returns a frame when a partial string selection
ind = date_range(start="2000", freq="D", periods=1000)
df = DataFrame(np.random.randn(len(ind), 5), index=ind, columns=list('ABCDE'))
panel = Panel(dict([ ('frame_'+c,df) for c in list('ABC') ]))
test2 = panel.ix[:, "2002":"2002-12-31"]
test1 = panel.ix[:, "2002"]
tm.assert_panel_equal(test1,test2)
def test_panel_assignment(self):
# GH3777
wp = Panel(randn(2, 5, 4), items=['Item1', 'Item2'], major_axis=date_range('1/1/2000', periods=5), minor_axis=['A', 'B', 'C', 'D'])
wp2 = Panel(randn(2, 5, 4), items=['Item1', 'Item2'], major_axis=date_range('1/1/2000', periods=5), minor_axis=['A', 'B', 'C', 'D'])
expected = wp.loc[['Item1', 'Item2'], :, ['A', 'B']]
def f():
wp.loc[['Item1', 'Item2'], :, ['A', 'B']] = wp2.loc[['Item1', 'Item2'], :, ['A', 'B']]
self.assertRaises(NotImplementedError, f)
#wp.loc[['Item1', 'Item2'], :, ['A', 'B']] = wp2.loc[['Item1', 'Item2'], :, ['A', 'B']]
#result = wp.loc[['Item1', 'Item2'], :, ['A', 'B']]
#tm.assert_panel_equal(result,expected)
def test_multiindex_assignment(self):
# GH3777 part 2
# mixed dtype
df = DataFrame(np.random.randint(5,10,size=9).reshape(3, 3),
columns=list('abc'),
index=[[4,4,8],[8,10,12]])
df['d'] = np.nan
arr = np.array([0.,1.])
df.ix[4,'d'] = arr
assert_series_equal(df.ix[4,'d'],Series(arr,index=[8,10],name='d'))
# single dtype
df = DataFrame(np.random.randint(5,10,size=9).reshape(3, 3),
columns=list('abc'),
index=[[4,4,8],[8,10,12]])
df.ix[4,'c'] = arr
assert_series_equal(df.ix[4,'c'],Series(arr,index=[8,10],name='c',dtype='int64'))
# scalar ok
df.ix[4,'c'] = 10
assert_series_equal(df.ix[4,'c'],Series(10,index=[8,10],name='c',dtype='int64'))
# invalid assignments
def f():
df.ix[4,'c'] = [0,1,2,3]
self.assertRaises(ValueError, f)
def f():
df.ix[4,'c'] = [0]
self.assertRaises(ValueError, f)
# groupby example
NUM_ROWS = 100
NUM_COLS = 10
col_names = ['A'+num for num in map(str,np.arange(NUM_COLS).tolist())]
index_cols = col_names[:5]
df = DataFrame(np.random.randint(5, size=(NUM_ROWS,NUM_COLS)), dtype=np.int64, columns=col_names)
df = df.set_index(index_cols).sort_index()
grp = df.groupby(level=index_cols[:4])
df['new_col'] = np.nan
f_index = np.arange(5)
def f(name,df2):
return Series(np.arange(df2.shape[0]),name=df2.index.values[0]).reindex(f_index)
new_df = pd.concat([ f(name,df2) for name, df2 in grp ],axis=1).T
for name, df2 in grp:
new_vals = np.arange(df2.shape[0])
df.ix[name, 'new_col'] = new_vals
def test_multi_assign(self):
# GH 3626, an assignement of a sub-df to a df
df = DataFrame({'FC':['a','b','a','b','a','b'],