-
-
Notifications
You must be signed in to change notification settings - Fork 18.4k
/
Copy pathtest_format.py
1729 lines (1458 loc) · 58.7 KB
/
test_format.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
# -*- coding: utf-8 -*-
try:
from StringIO import StringIO
except:
from io import StringIO
import os
import sys
import unittest
from textwrap import dedent
import warnings
from numpy import nan
from numpy.random import randn
import numpy as np
from pandas import DataFrame, Series, Index
from pandas.util.py3compat import lzip
import pandas.core.format as fmt
import pandas.util.testing as tm
from pandas.util.terminal import get_terminal_size
import pandas
import pandas as pd
from pandas.core.config import (set_option, get_option,
option_context, reset_option)
_frame = DataFrame(tm.getSeriesData())
def curpath():
pth, _ = os.path.split(os.path.abspath(__file__))
return pth
def has_info_repr(df):
r = repr(df)
return r.split('\n')[0].startswith("<class")
def has_expanded_repr(df):
r = repr(df)
for line in r.split('\n'):
if line.endswith('\\'):
return True
return False
class TestDataFrameFormatting(unittest.TestCase):
_multiprocess_can_split_ = True
def setUp(self):
self.warn_filters = warnings.filters
warnings.filterwarnings('ignore',
category=FutureWarning,
module=".*format")
self.frame = _frame.copy()
def tearDown(self):
warnings.filters = self.warn_filters
def test_repr_embedded_ndarray(self):
arr = np.empty(10, dtype=[('err', object)])
for i in range(len(arr)):
arr['err'][i] = np.random.randn(i)
df = DataFrame(arr)
repr(df['err'])
repr(df)
df.to_string()
def test_eng_float_formatter(self):
self.frame.ix[5] = 0
fmt.set_eng_float_format()
result = repr(self.frame)
fmt.set_eng_float_format(use_eng_prefix=True)
repr(self.frame)
fmt.set_eng_float_format(accuracy=0)
repr(self.frame)
fmt.reset_printoptions()
def test_repr_tuples(self):
buf = StringIO()
df = DataFrame({'tups': zip(range(10), range(10))})
repr(df)
df.to_string(col_space=10, buf=buf)
def test_repr_truncation(self):
max_len = 20
with option_context("display.max_colwidth", max_len):
df = DataFrame({'A': np.random.randn(10),
'B': [tm.rands(np.random.randint(max_len - 1,
max_len + 1)) for i in range(10)]})
r = repr(df)
r = r[r.find('\n') + 1:]
_strlen = fmt._strlen_func()
for line, value in zip(r.split('\n'), df['B']):
if _strlen(value) + 1 > max_len:
self.assert_('...' in line)
else:
self.assert_('...' not in line)
with option_context("display.max_colwidth", 999999):
self.assert_('...' not in repr(df))
with option_context("display.max_colwidth", max_len + 2):
self.assert_('...' not in repr(df))
def test_repr_chop_threshold(self):
df = DataFrame([[0.1, 0.5],[0.5, -0.1]])
pd.reset_option("display.chop_threshold") # default None
self.assertEqual(repr(df), ' 0 1\n0 0.1 0.5\n1 0.5 -0.1')
with option_context("display.chop_threshold", 0.2 ):
self.assertEqual(repr(df), ' 0 1\n0 0.0 0.5\n1 0.5 0.0')
with option_context("display.chop_threshold", 0.6 ):
self.assertEqual(repr(df), ' 0 1\n0 0 0\n1 0 0')
with option_context("display.chop_threshold", None ):
self.assertEqual(repr(df), ' 0 1\n0 0.1 0.5\n1 0.5 -0.1')
def test_repr_obeys_max_seq_limit(self):
import pandas.core.common as com
#unlimited
reset_option("display.max_seq_items")
self.assertTrue(len(com.pprint_thing(range(1000)))> 2000)
with option_context("display.max_seq_items",5):
self.assertTrue(len(com.pprint_thing(range(1000)))< 100)
def test_repr_should_return_str(self):
# http://docs.python.org/py3k/reference/datamodel.html#object.__repr__
# http://docs.python.org/reference/datamodel.html#object.__repr__
# "...The return value must be a string object."
# (str on py2.x, str (unicode) on py3)
data = [8, 5, 3, 5]
index1 = [u"\u03c3", u"\u03c4", u"\u03c5", u"\u03c6"]
cols = [u"\u03c8"]
df = DataFrame(data, columns=cols, index=index1)
self.assertTrue(type(df.__repr__() == str)) # both py2 / 3
def test_repr_no_backslash(self):
with option_context('mode.sim_interactive', True):
df = DataFrame(np.random.randn(10, 4))
self.assertTrue('\\' not in repr(df))
def test_expand_frame_repr(self):
df_small = DataFrame('hello', [0], [0])
df_wide = DataFrame('hello', [0], range(10))
df_tall = DataFrame('hello', range(30), range(5))
with option_context('mode.sim_interactive', True):
with option_context('display.width', 50,
'display.height', 20):
with option_context('display.expand_frame_repr', True):
self.assertFalse(has_info_repr(df_small))
self.assertFalse(has_expanded_repr(df_small))
self.assertFalse(has_info_repr(df_wide))
self.assertTrue(has_expanded_repr(df_wide))
self.assertTrue(has_info_repr(df_tall))
self.assertFalse(has_expanded_repr(df_tall))
with option_context('display.expand_frame_repr', False):
self.assertFalse(has_info_repr(df_small))
self.assertFalse(has_expanded_repr(df_small))
self.assertTrue(has_info_repr(df_wide))
self.assertFalse(has_expanded_repr(df_wide))
self.assertTrue(has_info_repr(df_tall))
self.assertFalse(has_expanded_repr(df_tall))
def test_repr_non_interactive(self):
# in non interactive mode, there can be no dependency on the
# result of terminal auto size detection
df = DataFrame('hello', range(1000), range(5))
with option_context('mode.sim_interactive', False,
'display.width', 0,
'display.height', 0,
'display.max_rows',5000):
self.assertFalse(has_info_repr(df))
self.assertFalse(has_expanded_repr(df))
def test_repr_max_columns_max_rows(self):
term_width, term_height = get_terminal_size()
if term_width < 10 or term_height < 10:
raise nose.SkipTest
def mkframe(n):
index = ['%05d' % i for i in range(n)]
return DataFrame(0, index, index)
df6 = mkframe(6)
df10 = mkframe(10)
with option_context('mode.sim_interactive', True):
with option_context('display.width', term_width * 2):
with option_context('display.max_rows', 5,
'display.max_columns', 5):
self.assertFalse(has_expanded_repr(mkframe(4)))
self.assertFalse(has_expanded_repr(mkframe(5)))
self.assertFalse(has_expanded_repr(df6))
self.assertTrue(has_info_repr(df6))
with option_context('display.max_rows', 20,
'display.max_columns', 5):
# Out off max_columns boundary, but no extending
# since not exceeding width
self.assertFalse(has_expanded_repr(df6))
self.assertFalse(has_info_repr(df6))
with option_context('display.max_rows', 9,
'display.max_columns', 10):
# out vertical bounds can not result in exanded repr
self.assertFalse(has_expanded_repr(df10))
self.assertTrue(has_info_repr(df10))
with option_context('display.max_columns', 0,
'display.max_rows', term_width * 20,
'display.width', 0):
df = mkframe((term_width // 7) - 2)
self.assertFalse(has_expanded_repr(df))
df = mkframe((term_width // 7) + 2)
self.assertTrue(has_expanded_repr(df))
def test_to_string_repr_unicode(self):
buf = StringIO()
unicode_values = [u'\u03c3'] * 10
unicode_values = np.array(unicode_values, dtype=object)
df = DataFrame({'unicode': unicode_values})
df.to_string(col_space=10, buf=buf)
# it works!
repr(df)
idx = Index(['abc', u'\u03c3a', 'aegdvg'])
ser = Series(np.random.randn(len(idx)), idx)
rs = repr(ser).split('\n')
line_len = len(rs[0])
for line in rs[1:]:
try:
line = line.decode(get_option("display.encoding"))
except:
pass
if not line.startswith('dtype:'):
self.assert_(len(line) == line_len)
# it works even if sys.stdin in None
_stdin= sys.stdin
try:
sys.stdin = None
repr(df)
finally:
sys.stdin = _stdin
def test_to_string_unicode_columns(self):
df = DataFrame({u'\u03c3': np.arange(10.)})
buf = StringIO()
df.to_string(buf=buf)
buf.getvalue()
buf = StringIO()
df.info(buf=buf)
buf.getvalue()
result = self.frame.to_string()
self.assert_(isinstance(result, unicode))
def test_to_string_utf8_columns(self):
n = u"\u05d0".encode('utf-8')
with option_context('display.max_rows', 1):
df = pd.DataFrame([1, 2], columns=[n])
repr(df)
def test_to_string_unicode_two(self):
dm = DataFrame({u'c/\u03c3': []})
buf = StringIO()
dm.to_string(buf)
def test_to_string_unicode_three(self):
dm = DataFrame(['\xc2'])
buf = StringIO()
dm.to_string(buf)
def test_to_string_with_formatters(self):
df = DataFrame({'int': [1, 2, 3],
'float': [1.0, 2.0, 3.0],
'object': [(1, 2), True, False]},
columns=['int', 'float', 'object'])
formatters = [('int', lambda x: '0x%x' % x),
('float', lambda x: '[% 4.1f]' % x),
('object', lambda x: '-%s-' % str(x))]
result = df.to_string(formatters=dict(formatters))
result2 = df.to_string(formatters=lzip(*formatters)[1])
self.assertEqual(result, (' int float object\n'
'0 0x1 [ 1.0] -(1, 2)-\n'
'1 0x2 [ 2.0] -True-\n'
'2 0x3 [ 3.0] -False-'))
self.assertEqual(result, result2)
def test_to_string_with_formatters_unicode(self):
df = DataFrame({u'c/\u03c3': [1, 2, 3]})
result = df.to_string(formatters={u'c/\u03c3': lambda x: '%s' % x})
self.assertEqual(result, (u' c/\u03c3\n'
'0 1\n'
'1 2\n'
'2 3'))
def test_to_string_buffer_all_unicode(self):
buf = StringIO()
empty = DataFrame({u'c/\u03c3': Series()})
nonempty = DataFrame({u'c/\u03c3': Series([1, 2, 3])})
print >>buf, empty
print >>buf, nonempty
# this should work
buf.getvalue()
def test_to_string_with_col_space(self):
df = DataFrame(np.random.random(size=(1, 3)))
c10 = len(df.to_string(col_space=10).split("\n")[1])
c20 = len(df.to_string(col_space=20).split("\n")[1])
c30 = len(df.to_string(col_space=30).split("\n")[1])
self.assertTrue(c10 < c20 < c30)
def test_to_html_with_col_space(self):
def check_with_width(df, col_space):
import re
# check that col_space affects HTML generation
# and be very brittle about it.
html = df.to_html(col_space=col_space)
hdrs = [x for x in html.split("\n") if re.search("<th[>\s]", x)]
self.assertTrue(len(hdrs) > 0)
for h in hdrs:
self.assertTrue("min-width" in h)
self.assertTrue(str(col_space) in h)
df = DataFrame(np.random.random(size=(1, 3)))
check_with_width(df, 30)
check_with_width(df, 50)
def test_to_html_unicode(self):
# it works!
df = DataFrame({u'\u03c3': np.arange(10.)})
df.to_html()
df = DataFrame({'A': [u'\u03c3']})
df.to_html()
def test_to_html_escaped(self):
a = 'str<ing1 &'
b = 'stri>ng2 &'
test_dict = {'co<l1': {a: "<type 'str'>",
b: "<type 'str'>"},
'co>l2':{a: "<type 'str'>",
b: "<type 'str'>"}}
rs = pd.DataFrame(test_dict).to_html()
xp = """<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>co<l1</th>
<th>co>l2</th>
</tr>
</thead>
<tbody>
<tr>
<th>str<ing1 &amp;</th>
<td> <type 'str'></td>
<td> <type 'str'></td>
</tr>
<tr>
<th>stri>ng2 &amp;</th>
<td> <type 'str'></td>
<td> <type 'str'></td>
</tr>
</tbody>
</table>"""
self.assertEqual(xp, rs)
def test_to_html_escape_disabled(self):
a = 'str<ing1 &'
b = 'stri>ng2 &'
test_dict = {'co<l1': {a: "<b>bold</b>",
b: "<b>bold</b>"},
'co>l2': {a: "<b>bold</b>",
b: "<b>bold</b>"}}
rs = pd.DataFrame(test_dict).to_html(escape=False)
xp = """<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>co<l1</th>
<th>co>l2</th>
</tr>
</thead>
<tbody>
<tr>
<th>str<ing1 &</th>
<td> <b>bold</b></td>
<td> <b>bold</b></td>
</tr>
<tr>
<th>stri>ng2 &</th>
<td> <b>bold</b></td>
<td> <b>bold</b></td>
</tr>
</tbody>
</table>"""
self.assertEqual(xp, rs)
def test_to_html_multiindex_sparsify(self):
index = pd.MultiIndex.from_arrays([[0, 0, 1, 1], [0, 1, 0, 1]],
names=['foo', None])
df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]], index=index)
result = df.to_html()
expected = """<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th></th>
<th>0</th>
<th>1</th>
</tr>
<tr>
<th>foo</th>
<th></th>
<th></th>
<th></th>
</tr>
</thead>
<tbody>
<tr>
<th rowspan="2" valign="top">0</th>
<th>0</th>
<td> 0</td>
<td> 1</td>
</tr>
<tr>
<th>1</th>
<td> 2</td>
<td> 3</td>
</tr>
<tr>
<th rowspan="2" valign="top">1</th>
<th>0</th>
<td> 4</td>
<td> 5</td>
</tr>
<tr>
<th>1</th>
<td> 6</td>
<td> 7</td>
</tr>
</tbody>
</table>"""
self.assertEquals(result, expected)
df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]],
columns=index[::2], index=index)
result = df.to_html()
expected = """\
<table border="1" class="dataframe">
<thead>
<tr>
<th></th>
<th>foo</th>
<th>0</th>
<th>1</th>
</tr>
<tr>
<th></th>
<th></th>
<th>0</th>
<th>0</th>
</tr>
<tr>
<th>foo</th>
<th></th>
<th></th>
<th></th>
</tr>
</thead>
<tbody>
<tr>
<th rowspan="2" valign="top">0</th>
<th>0</th>
<td> 0</td>
<td> 1</td>
</tr>
<tr>
<th>1</th>
<td> 2</td>
<td> 3</td>
</tr>
<tr>
<th rowspan="2" valign="top">1</th>
<th>0</th>
<td> 4</td>
<td> 5</td>
</tr>
<tr>
<th>1</th>
<td> 6</td>
<td> 7</td>
</tr>
</tbody>
</table>"""
self.assertEquals(result, expected)
def test_to_html_index_formatter(self):
df = DataFrame([[0, 1], [2, 3], [4, 5], [6, 7]],
columns=['foo', None], index=range(4))
f = lambda x: 'abcd'[x]
result = df.to_html(formatters={'__index__': f})
expected = """\
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>foo</th>
<th></th>
</tr>
</thead>
<tbody>
<tr>
<th>a</th>
<td> 0</td>
<td> 1</td>
</tr>
<tr>
<th>b</th>
<td> 2</td>
<td> 3</td>
</tr>
<tr>
<th>c</th>
<td> 4</td>
<td> 5</td>
</tr>
<tr>
<th>d</th>
<td> 6</td>
<td> 7</td>
</tr>
</tbody>
</table>"""
self.assertEquals(result, expected)
def test_nonunicode_nonascii_alignment(self):
df = DataFrame([["aa\xc3\xa4\xc3\xa4", 1], ["bbbb", 2]])
rep_str = df.to_string()
lines = rep_str.split('\n')
self.assert_(len(lines[1]) == len(lines[2]))
def test_unicode_problem_decoding_as_ascii(self):
dm = DataFrame({u'c/\u03c3': Series({'test': np.NaN})})
unicode(dm.to_string())
def test_string_repr_encoding(self):
filepath = tm.get_data_path('unicode_series.csv')
df = pandas.read_csv(filepath, header=None, encoding='latin1')
repr(df)
repr(df[1])
def test_repr_corner(self):
# representing infs poses no problems
df = DataFrame({'foo': np.inf * np.empty(10)})
foo = repr(df)
def test_frame_info_encoding(self):
index = ['\'Til There Was You (1997)',
'ldum klaka (Cold Fever) (1994)']
fmt.set_printoptions(max_rows=1)
df = DataFrame(columns=['a', 'b', 'c'], index=index)
repr(df)
repr(df.T)
fmt.set_printoptions(max_rows=200)
def test_large_frame_repr(self):
def wrap_rows_options(f):
def _f(*args, **kwargs):
old_max_rows = pd.get_option('display.max_rows')
old_max_info_rows = pd.get_option('display.max_info_rows')
o = f(*args, **kwargs)
pd.set_option('display.max_rows', old_max_rows)
pd.set_option('display.max_info_rows', old_max_info_rows)
return o
return _f
@wrap_rows_options
def test_setting(value, nrows=3, ncols=2):
if value is None:
expected_difference = 0
elif isinstance(value, int):
expected_difference = ncols
else:
raise ValueError("'value' must be int or None")
with option_context('mode.sim_interactive', True):
pd.set_option('display.max_rows', nrows - 1)
pd.set_option('display.max_info_rows', value)
smallx = DataFrame(np.random.rand(nrows, ncols))
repr_small = repr(smallx)
bigx = DataFrame(np.random.rand(nrows + 1, ncols))
repr_big = repr(bigx)
diff = len(repr_small.splitlines()) - len(repr_big.splitlines())
# the difference in line count is the number of columns
self.assertEqual(diff, expected_difference)
test_setting(None)
test_setting(3)
self.assertRaises(ValueError, test_setting, 'string')
def test_wide_repr(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option('display.expand_frame_repr')
def test_wide_repr_wide_columns(self):
with option_context('mode.sim_interactive', True):
df = DataFrame(randn(5, 3), columns=['a' * 90, 'b' * 90, 'c' * 90])
rep_str = repr(df)
self.assert_(len(rep_str.splitlines()) == 20)
def test_wide_repr_named(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
df.index.name = 'DataFrame Index'
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.width', 150):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
for line in wide_repr.splitlines()[1::13]:
self.assert_('DataFrame Index' in line)
reset_option('display.expand_frame_repr')
def test_wide_repr_multiindex(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays([np.array(col(10, 5)),
np.array(col(10, 5))])
df = DataFrame([col(20, 25) for _ in range(10)],
index=midx)
df.index.names = ['Level 0', 'Level 1']
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.width', 150):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
for line in wide_repr.splitlines()[1::13]:
self.assert_('Level 0 Level 1' in line)
reset_option('display.expand_frame_repr')
def test_wide_repr_multiindex_cols(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays([np.array(col(10, 5)),
np.array(col(10, 5))])
mcols = pandas.MultiIndex.from_arrays([np.array(col(20, 3)),
np.array(col(20, 3))])
df = DataFrame([col(20, 25) for _ in range(10)],
index=midx, columns=mcols)
df.index.names = ['Level 0', 'Level 1']
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.width', 150):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option('display.expand_frame_repr')
def test_wide_repr_unicode(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.randu(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.width', 150):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option('display.expand_frame_repr')
def test_wide_repr_wide_long_columns(self):
with option_context('mode.sim_interactive', True):
df = DataFrame(
{'a': ['a' * 30, 'b' * 30], 'b': ['c' * 70, 'd' * 80]})
result = repr(df)
self.assertTrue('ccccc' in result)
self.assertTrue('ddddd' in result)
def test_long_series(self):
n = 1000
s = Series(np.random.randint(-50,50,n),index=['s%04d' % x for x in xrange(n)], dtype='int64')
import re
str_rep = str(s)
nmatches = len(re.findall('dtype',str_rep))
self.assert_(nmatches == 1)
def test_index_with_nan(self):
# GH 2850
df = DataFrame({'id1': {0: '1a3', 1: '9h4'}, 'id2': {0: np.nan, 1: 'd67'},
'id3': {0: '78d', 1: '79d'}, 'value': {0: 123, 1: 64}})
# multi-index
y = df.set_index(['id1', 'id2', 'id3'])
result = y.to_string()
expected = u' value\nid1 id2 id3 \n1a3 NaN 78d 123\n9h4 d67 79d 64'
self.assert_(result == expected)
# index
y = df.set_index('id2')
result = y.to_string()
expected = u' id1 id3 value\nid2 \nNaN 1a3 78d 123\nd67 9h4 79d 64'
self.assert_(result == expected)
# all-nan in mi
df2 = df.copy()
df2.ix[:,'id2'] = np.nan
y = df2.set_index('id2')
result = y.to_string()
expected = u' id1 id3 value\nid2 \nNaN 1a3 78d 123\nNaN 9h4 79d 64'
self.assert_(result == expected)
# partial nan in mi
df2 = df.copy()
df2.ix[:,'id2'] = np.nan
y = df2.set_index(['id2','id3'])
result = y.to_string()
expected = u' id1 value\nid2 id3 \nNaN 78d 1a3 123\n 79d 9h4 64'
self.assert_(result == expected)
df = DataFrame({'id1': {0: np.nan, 1: '9h4'}, 'id2': {0: np.nan, 1: 'd67'},
'id3': {0: np.nan, 1: '79d'}, 'value': {0: 123, 1: 64}})
y = df.set_index(['id1','id2','id3'])
result = y.to_string()
expected = u' value\nid1 id2 id3 \nNaN NaN NaN 123\n9h4 d67 79d 64'
self.assert_(result == expected)
def test_to_string(self):
from pandas import read_table
import re
# big mixed
biggie = DataFrame({'A': randn(200),
'B': tm.makeStringIndex(200)},
index=range(200))
biggie['A'][:20] = nan
biggie['B'][:20] = nan
s = biggie.to_string()
buf = StringIO()
retval = biggie.to_string(buf=buf)
self.assert_(retval is None)
self.assertEqual(buf.getvalue(), s)
self.assert_(isinstance(s, basestring))
# print in right order
result = biggie.to_string(columns=['B', 'A'], col_space=17,
float_format='%.5f'.__mod__)
lines = result.split('\n')
header = lines[0].strip().split()
joined = '\n'.join([re.sub('\s+', ' ', x).strip() for x in lines[1:]])
recons = read_table(StringIO(joined), names=header,
header=None, sep=' ')
tm.assert_series_equal(recons['B'], biggie['B'])
self.assertEqual(recons['A'].count(), biggie['A'].count())
self.assert_((np.abs(recons['A'].dropna() -
biggie['A'].dropna()) < 0.1).all())
# expected = ['B', 'A']
# self.assertEqual(header, expected)
result = biggie.to_string(columns=['A'], col_space=17)
header = result.split('\n')[0].strip().split()
expected = ['A']
self.assertEqual(header, expected)
biggie.to_string(columns=['B', 'A'],
formatters={'A': lambda x: '%.1f' % x})
biggie.to_string(columns=['B', 'A'], float_format=str)
biggie.to_string(columns=['B', 'A'], col_space=12,
float_format=str)
frame = DataFrame(index=np.arange(200))
frame.to_string()
def test_to_string_no_header(self):
df = DataFrame({'x': [1, 2, 3],
'y': [4, 5, 6]})
df_s = df.to_string(header=False)
expected = "0 1 4\n1 2 5\n2 3 6"
assert(df_s == expected)
def test_to_string_no_index(self):
df = DataFrame({'x': [1, 2, 3],
'y': [4, 5, 6]})
df_s = df.to_string(index=False)
expected = " x y\n 1 4\n 2 5\n 3 6"
assert(df_s == expected)
def test_to_string_float_formatting(self):
fmt.reset_printoptions()
fmt.set_printoptions(precision=6, column_space=12,
notebook_repr_html=False)
df = DataFrame({'x': [0, 0.25, 3456.000, 12e+45, 1.64e+6,
1.7e+8, 1.253456, np.pi, -1e6]})
df_s = df.to_string()
# Python 2.5 just wants me to be sad. And debian 32-bit
# sys.version_info[0] == 2 and sys.version_info[1] < 6:
if _three_digit_exp():
expected = (' x\n0 0.00000e+000\n1 2.50000e-001\n'
'2 3.45600e+003\n3 1.20000e+046\n4 1.64000e+006\n'
'5 1.70000e+008\n6 1.25346e+000\n7 3.14159e+000\n'
'8 -1.00000e+006')
else:
expected = (' x\n0 0.00000e+00\n1 2.50000e-01\n'
'2 3.45600e+03\n3 1.20000e+46\n4 1.64000e+06\n'
'5 1.70000e+08\n6 1.25346e+00\n7 3.14159e+00\n'
'8 -1.00000e+06')
assert(df_s == expected)
df = DataFrame({'x': [3234, 0.253]})
df_s = df.to_string()
expected = (' x\n'
'0 3234.000\n'
'1 0.253')
assert(df_s == expected)
fmt.reset_printoptions()
self.assertEqual(get_option("display.precision"), 7)
df = DataFrame({'x': [1e9, 0.2512]})
df_s = df.to_string()
# Python 2.5 just wants me to be sad. And debian 32-bit
# sys.version_info[0] == 2 and sys.version_info[1] < 6:
if _three_digit_exp():
expected = (' x\n'
'0 1.000000e+009\n'
'1 2.512000e-001')
else:
expected = (' x\n'
'0 1.000000e+09\n'
'1 2.512000e-01')
assert(df_s == expected)
def test_to_string_small_float_values(self):
df = DataFrame({'a': [1.5, 1e-17, -5.5e-7]})
result = df.to_string()
# sadness per above
if '%.4g' % 1.7e8 == '1.7e+008':
expected = (' a\n'
'0 1.500000e+000\n'
'1 1.000000e-017\n'
'2 -5.500000e-007')
else:
expected = (' a\n'
'0 1.500000e+00\n'
'1 1.000000e-17\n'
'2 -5.500000e-07')
self.assertEqual(result, expected)
# but not all exactly zero
df = df * 0
result = df.to_string()
expected = (' 0\n'
'0 0\n'
'1 0\n'
'2 -0')
def test_to_string_float_index(self):
index = Index([1.5, 2, 3, 4, 5])
df = DataFrame(range(5), index=index)
result = df.to_string()
expected = (' 0\n'
'1.5 0\n'
'2 1\n'
'3 2\n'
'4 3\n'
'5 4')
self.assertEqual(result, expected)
def test_to_string_ascii_error(self):
data = [('0 ',
u' .gitignore ',
u' 5 ',
' \xe2\x80\xa2\xe2\x80\xa2\xe2\x80'
'\xa2\xe2\x80\xa2\xe2\x80\xa2')]
df = DataFrame(data)
# it works!
repr(df)
def test_to_string_int_formatting(self):
df = DataFrame({'x': [-15, 20, 25, -35]})
self.assert_(issubclass(df['x'].dtype.type, np.integer))
output = df.to_string()
expected = (' x\n'
'0 -15\n'
'1 20\n'
'2 25\n'
'3 -35')
self.assertEqual(output, expected)
def test_to_string_index_formatter(self):
df = DataFrame([range(5), range(5, 10), range(10, 15)])
rs = df.to_string(formatters={'__index__': lambda x: 'abc'[x]})
xp = """\
0 1 2 3 4
a 0 1 2 3 4
b 5 6 7 8 9
c 10 11 12 13 14\
"""
self.assertEqual(rs, xp)
def test_to_string_left_justify_cols(self):
fmt.reset_printoptions()
df = DataFrame({'x': [3234, 0.253]})
df_s = df.to_string(justify='left')
expected = (' x \n'