forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathtest_quantile.py
388 lines (306 loc) · 15.3 KB
/
test_quantile.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
# -*- coding: utf-8 -*-
from __future__ import print_function
import pytest
import numpy as np
from pandas import DataFrame, Series, Timestamp
import pandas as pd
from pandas.util.testing import assert_series_equal, assert_frame_equal
import pandas.util.testing as tm
from pandas.tests.frame.common import TestData
class TestDataFrameQuantile(TestData):
def test_quantile(self):
from numpy import percentile
q = self.tsframe.quantile(0.1, axis=0)
assert q['A'] == percentile(self.tsframe['A'], 10)
tm.assert_index_equal(q.index, self.tsframe.columns)
q = self.tsframe.quantile(0.9, axis=1)
assert (q['2000-01-17'] ==
percentile(self.tsframe.loc['2000-01-17'], 90))
tm.assert_index_equal(q.index, self.tsframe.index)
# test degenerate case
q = DataFrame({'x': [], 'y': []}).quantile(0.1, axis=0)
assert(np.isnan(q['x']) and np.isnan(q['y']))
# non-numeric exclusion
df = DataFrame({'col1': ['A', 'A', 'B', 'B'], 'col2': [1, 2, 3, 4]})
rs = df.quantile(0.5)
xp = df.median().rename(0.5)
assert_series_equal(rs, xp)
# axis
df = DataFrame({"A": [1, 2, 3], "B": [2, 3, 4]}, index=[1, 2, 3])
result = df.quantile(.5, axis=1)
expected = Series([1.5, 2.5, 3.5], index=[1, 2, 3], name=0.5)
assert_series_equal(result, expected)
result = df.quantile([.5, .75], axis=1)
expected = DataFrame({1: [1.5, 1.75], 2: [2.5, 2.75],
3: [3.5, 3.75]}, index=[0.5, 0.75])
assert_frame_equal(result, expected, check_index_type=True)
# We may want to break API in the future to change this
# so that we exclude non-numeric along the same axis
# See GH #7312
df = DataFrame([[1, 2, 3],
['a', 'b', 4]])
result = df.quantile(.5, axis=1)
expected = Series([3., 4.], index=[0, 1], name=0.5)
assert_series_equal(result, expected)
def test_quantile_axis_mixed(self):
# mixed on axis=1
df = DataFrame({"A": [1, 2, 3],
"B": [2., 3., 4.],
"C": pd.date_range('20130101', periods=3),
"D": ['foo', 'bar', 'baz']})
result = df.quantile(.5, axis=1)
expected = Series([1.5, 2.5, 3.5], name=0.5)
assert_series_equal(result, expected)
# must raise
with pytest.raises(TypeError):
df.quantile(.5, axis=1, numeric_only=False)
def test_quantile_axis_parameter(self):
# GH 9543/9544
df = DataFrame({"A": [1, 2, 3], "B": [2, 3, 4]}, index=[1, 2, 3])
result = df.quantile(.5, axis=0)
expected = Series([2., 3.], index=["A", "B"], name=0.5)
assert_series_equal(result, expected)
expected = df.quantile(.5, axis="index")
assert_series_equal(result, expected)
result = df.quantile(.5, axis=1)
expected = Series([1.5, 2.5, 3.5], index=[1, 2, 3], name=0.5)
assert_series_equal(result, expected)
result = df.quantile(.5, axis="columns")
assert_series_equal(result, expected)
pytest.raises(ValueError, df.quantile, 0.1, axis=-1)
pytest.raises(ValueError, df.quantile, 0.1, axis="column")
def test_quantile_interpolation(self):
# see gh-10174
from numpy import percentile
# interpolation = linear (default case)
q = self.tsframe.quantile(0.1, axis=0, interpolation='linear')
assert q['A'] == percentile(self.tsframe['A'], 10)
q = self.intframe.quantile(0.1)
assert q['A'] == percentile(self.intframe['A'], 10)
# test with and without interpolation keyword
q1 = self.intframe.quantile(0.1)
assert q1['A'] == np.percentile(self.intframe['A'], 10)
tm.assert_series_equal(q, q1)
# interpolation method other than default linear
df = DataFrame({"A": [1, 2, 3], "B": [2, 3, 4]}, index=[1, 2, 3])
result = df.quantile(.5, axis=1, interpolation='nearest')
expected = Series([1, 2, 3], index=[1, 2, 3], name=0.5)
tm.assert_series_equal(result, expected)
# cross-check interpolation=nearest results in original dtype
exp = np.percentile(np.array([[1, 2, 3], [2, 3, 4]]), .5,
axis=0, interpolation='nearest')
expected = Series(exp, index=[1, 2, 3], name=0.5, dtype='int64')
tm.assert_series_equal(result, expected)
# float
df = DataFrame({"A": [1., 2., 3.], "B": [2., 3., 4.]}, index=[1, 2, 3])
result = df.quantile(.5, axis=1, interpolation='nearest')
expected = Series([1., 2., 3.], index=[1, 2, 3], name=0.5)
tm.assert_series_equal(result, expected)
exp = np.percentile(np.array([[1., 2., 3.], [2., 3., 4.]]), .5,
axis=0, interpolation='nearest')
expected = Series(exp, index=[1, 2, 3], name=0.5, dtype='float64')
assert_series_equal(result, expected)
# axis
result = df.quantile([.5, .75], axis=1, interpolation='lower')
expected = DataFrame({1: [1., 1.], 2: [2., 2.],
3: [3., 3.]}, index=[0.5, 0.75])
assert_frame_equal(result, expected)
# test degenerate case
df = DataFrame({'x': [], 'y': []})
q = df.quantile(0.1, axis=0, interpolation='higher')
assert(np.isnan(q['x']) and np.isnan(q['y']))
# multi
df = DataFrame([[1, 1, 1], [2, 2, 2], [3, 3, 3]],
columns=['a', 'b', 'c'])
result = df.quantile([.25, .5], interpolation='midpoint')
# https://github.com/numpy/numpy/issues/7163
expected = DataFrame([[1.5, 1.5, 1.5], [2.0, 2.0, 2.0]],
index=[.25, .5], columns=['a', 'b', 'c'])
assert_frame_equal(result, expected)
def test_quantile_multi(self):
df = DataFrame([[1, 1, 1], [2, 2, 2], [3, 3, 3]],
columns=['a', 'b', 'c'])
result = df.quantile([.25, .5])
expected = DataFrame([[1.5, 1.5, 1.5], [2., 2., 2.]],
index=[.25, .5], columns=['a', 'b', 'c'])
assert_frame_equal(result, expected)
# axis = 1
result = df.quantile([.25, .5], axis=1)
expected = DataFrame([[1.5, 1.5, 1.5], [2., 2., 2.]],
index=[.25, .5], columns=[0, 1, 2])
# empty
result = DataFrame({'x': [], 'y': []}).quantile([0.1, .9], axis=0)
expected = DataFrame({'x': [np.nan, np.nan], 'y': [np.nan, np.nan]},
index=[.1, .9])
assert_frame_equal(result, expected)
def test_quantile_datetime(self):
df = DataFrame({'a': pd.to_datetime(['2010', '2011']), 'b': [0, 5]})
# exclude datetime
result = df.quantile(.5)
expected = Series([2.5], index=['b'])
# datetime
result = df.quantile(.5, numeric_only=False)
expected = Series([Timestamp('2010-07-02 12:00:00'), 2.5],
index=['a', 'b'],
name=0.5)
assert_series_equal(result, expected)
# datetime w/ multi
result = df.quantile([.5], numeric_only=False)
expected = DataFrame([[Timestamp('2010-07-02 12:00:00'), 2.5]],
index=[.5], columns=['a', 'b'])
assert_frame_equal(result, expected)
# axis = 1
df['c'] = pd.to_datetime(['2011', '2012'])
result = df[['a', 'c']].quantile(.5, axis=1, numeric_only=False)
expected = Series([Timestamp('2010-07-02 12:00:00'),
Timestamp('2011-07-02 12:00:00')],
index=[0, 1],
name=0.5)
assert_series_equal(result, expected)
result = df[['a', 'c']].quantile([.5], axis=1, numeric_only=False)
expected = DataFrame([[Timestamp('2010-07-02 12:00:00'),
Timestamp('2011-07-02 12:00:00')]],
index=[0.5], columns=[0, 1])
assert_frame_equal(result, expected)
# empty when numeric_only=True
# FIXME (gives empty frame in 0.18.1, broken in 0.19.0)
# result = df[['a', 'c']].quantile(.5)
# result = df[['a', 'c']].quantile([.5])
def test_quantile_invalid(self):
msg = 'percentiles should all be in the interval \\[0, 1\\]'
for invalid in [-1, 2, [0.5, -1], [0.5, 2]]:
with pytest.raises(ValueError, match=msg):
self.tsframe.quantile(invalid)
def test_quantile_box(self):
df = DataFrame({'A': [pd.Timestamp('2011-01-01'),
pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-03')],
'B': [pd.Timestamp('2011-01-01', tz='US/Eastern'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timestamp('2011-01-03', tz='US/Eastern')],
'C': [pd.Timedelta('1 days'),
pd.Timedelta('2 days'),
pd.Timedelta('3 days')]})
res = df.quantile(0.5, numeric_only=False)
exp = pd.Series([pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timedelta('2 days')],
name=0.5, index=['A', 'B', 'C'])
tm.assert_series_equal(res, exp)
res = df.quantile([0.5], numeric_only=False)
exp = pd.DataFrame([[pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timedelta('2 days')]],
index=[0.5], columns=['A', 'B', 'C'])
tm.assert_frame_equal(res, exp)
# DatetimeBlock may be consolidated and contain NaT in different loc
df = DataFrame({'A': [pd.Timestamp('2011-01-01'),
pd.NaT,
pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-03')],
'a': [pd.Timestamp('2011-01-01'),
pd.Timestamp('2011-01-02'),
pd.NaT,
pd.Timestamp('2011-01-03')],
'B': [pd.Timestamp('2011-01-01', tz='US/Eastern'),
pd.NaT,
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timestamp('2011-01-03', tz='US/Eastern')],
'b': [pd.Timestamp('2011-01-01', tz='US/Eastern'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.NaT,
pd.Timestamp('2011-01-03', tz='US/Eastern')],
'C': [pd.Timedelta('1 days'),
pd.Timedelta('2 days'),
pd.Timedelta('3 days'),
pd.NaT],
'c': [pd.NaT,
pd.Timedelta('1 days'),
pd.Timedelta('2 days'),
pd.Timedelta('3 days')]},
columns=list('AaBbCc'))
res = df.quantile(0.5, numeric_only=False)
exp = pd.Series([pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timedelta('2 days'),
pd.Timedelta('2 days')],
name=0.5, index=list('AaBbCc'))
tm.assert_series_equal(res, exp)
res = df.quantile([0.5], numeric_only=False)
exp = pd.DataFrame([[pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timedelta('2 days'),
pd.Timedelta('2 days')]],
index=[0.5], columns=list('AaBbCc'))
tm.assert_frame_equal(res, exp)
def test_quantile_nan(self):
# GH 14357 - float block where some cols have missing values
df = DataFrame({'a': np.arange(1, 6.0), 'b': np.arange(1, 6.0)})
df.iloc[-1, 1] = np.nan
res = df.quantile(0.5)
exp = Series([3.0, 2.5], index=['a', 'b'], name=0.5)
tm.assert_series_equal(res, exp)
res = df.quantile([0.5, 0.75])
exp = DataFrame({'a': [3.0, 4.0], 'b': [2.5, 3.25]}, index=[0.5, 0.75])
tm.assert_frame_equal(res, exp)
res = df.quantile(0.5, axis=1)
exp = Series(np.arange(1.0, 6.0), name=0.5)
tm.assert_series_equal(res, exp)
res = df.quantile([0.5, 0.75], axis=1)
exp = DataFrame([np.arange(1.0, 6.0)] * 2, index=[0.5, 0.75])
tm.assert_frame_equal(res, exp)
# full-nan column
df['b'] = np.nan
res = df.quantile(0.5)
exp = Series([3.0, np.nan], index=['a', 'b'], name=0.5)
tm.assert_series_equal(res, exp)
res = df.quantile([0.5, 0.75])
exp = DataFrame({'a': [3.0, 4.0], 'b': [np.nan, np.nan]},
index=[0.5, 0.75])
tm.assert_frame_equal(res, exp)
def test_quantile_nat(self):
# full NaT column
df = DataFrame({'a': [pd.NaT, pd.NaT, pd.NaT]})
res = df.quantile(0.5, numeric_only=False)
exp = Series([pd.NaT], index=['a'], name=0.5)
tm.assert_series_equal(res, exp)
res = df.quantile([0.5], numeric_only=False)
exp = DataFrame({'a': [pd.NaT]}, index=[0.5])
tm.assert_frame_equal(res, exp)
# mixed non-null / full null column
df = DataFrame({'a': [pd.Timestamp('2012-01-01'),
pd.Timestamp('2012-01-02'),
pd.Timestamp('2012-01-03')],
'b': [pd.NaT, pd.NaT, pd.NaT]})
res = df.quantile(0.5, numeric_only=False)
exp = Series([pd.Timestamp('2012-01-02'), pd.NaT], index=['a', 'b'],
name=0.5)
tm.assert_series_equal(res, exp)
res = df.quantile([0.5], numeric_only=False)
exp = DataFrame([[pd.Timestamp('2012-01-02'), pd.NaT]], index=[0.5],
columns=['a', 'b'])
tm.assert_frame_equal(res, exp)
def test_quantile_empty(self):
# floats
df = DataFrame(columns=['a', 'b'], dtype='float64')
res = df.quantile(0.5)
exp = Series([np.nan, np.nan], index=['a', 'b'], name=0.5)
tm.assert_series_equal(res, exp)
res = df.quantile([0.5])
exp = DataFrame([[np.nan, np.nan]], columns=['a', 'b'], index=[0.5])
tm.assert_frame_equal(res, exp)
# FIXME (gives empty frame in 0.18.1, broken in 0.19.0)
# res = df.quantile(0.5, axis=1)
# res = df.quantile([0.5], axis=1)
# ints
df = DataFrame(columns=['a', 'b'], dtype='int64')
# FIXME (gives empty frame in 0.18.1, broken in 0.19.0)
# res = df.quantile(0.5)
# datetimes
df = DataFrame(columns=['a', 'b'], dtype='datetime64[ns]')
# FIXME (gives NaNs instead of NaT in 0.18.1 or 0.19.0)
# res = df.quantile(0.5, numeric_only=False)