forked from pandas-dev/pandas
/
test_quantile.py
184 lines (139 loc) · 5.9 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
# coding=utf-8
# pylint: disable-msg=E1101,W0612
import numpy as np
import pandas as pd
from pandas import Index, Series
from pandas.core.indexes.datetimes import Timestamp
from pandas.core.dtypes.common import is_integer
import pandas.util.testing as tm
from .common import TestData
class TestSeriesQuantile(TestData):
def test_quantile(self):
q = self.ts.quantile(0.1)
assert q == np.percentile(self.ts.dropna(), 10)
q = self.ts.quantile(0.9)
assert q == np.percentile(self.ts.dropna(), 90)
# object dtype
q = Series(self.ts, dtype=object).quantile(0.9)
assert q == np.percentile(self.ts.dropna(), 90)
# datetime64[ns] dtype
dts = self.ts.index.to_series()
q = dts.quantile(.2)
assert q == Timestamp('2000-01-10 19:12:00')
# timedelta64[ns] dtype
tds = dts.diff()
q = tds.quantile(.25)
assert q == pd.to_timedelta('24:00:00')
# GH7661
result = Series([np.timedelta64('NaT')]).sum()
assert result == pd.Timedelta(0)
msg = 'percentiles should all be in the interval \\[0, 1\\]'
for invalid in [-1, 2, [0.5, -1], [0.5, 2]]:
with tm.assert_raises_regex(ValueError, msg):
self.ts.quantile(invalid)
def test_quantile_multi(self):
qs = [.1, .9]
result = self.ts.quantile(qs)
expected = pd.Series([np.percentile(self.ts.dropna(), 10),
np.percentile(self.ts.dropna(), 90)],
index=qs, name=self.ts.name)
tm.assert_series_equal(result, expected)
dts = self.ts.index.to_series()
dts.name = 'xxx'
result = dts.quantile((.2, .2))
expected = Series([Timestamp('2000-01-10 19:12:00'),
Timestamp('2000-01-10 19:12:00')],
index=[.2, .2], name='xxx')
tm.assert_series_equal(result, expected)
result = self.ts.quantile([])
expected = pd.Series([], name=self.ts.name, index=Index(
[], dtype=float))
tm.assert_series_equal(result, expected)
def test_quantile_interpolation(self):
# see gh-10174
# interpolation = linear (default case)
q = self.ts.quantile(0.1, interpolation='linear')
assert q == np.percentile(self.ts.dropna(), 10)
q1 = self.ts.quantile(0.1)
assert q1 == np.percentile(self.ts.dropna(), 10)
# test with and without interpolation keyword
assert q == q1
def test_quantile_interpolation_dtype(self):
# GH #10174
# interpolation = linear (default case)
q = pd.Series([1, 3, 4]).quantile(0.5, interpolation='lower')
assert q == np.percentile(np.array([1, 3, 4]), 50)
assert is_integer(q)
q = pd.Series([1, 3, 4]).quantile(0.5, interpolation='higher')
assert q == np.percentile(np.array([1, 3, 4]), 50)
assert is_integer(q)
def test_quantile_nan(self):
# GH 13098
s = pd.Series([1, 2, 3, 4, np.nan])
result = s.quantile(0.5)
expected = 2.5
assert result == expected
# all nan/empty
cases = [Series([]), Series([np.nan, np.nan])]
for s in cases:
res = s.quantile(0.5)
assert np.isnan(res)
res = s.quantile([0.5])
tm.assert_series_equal(res, pd.Series([np.nan], index=[0.5]))
res = s.quantile([0.2, 0.3])
tm.assert_series_equal(res, pd.Series([np.nan, np.nan],
index=[0.2, 0.3]))
def test_quantile_box(self):
cases = [[pd.Timestamp('2011-01-01'), pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-03')],
[pd.Timestamp('2011-01-01', tz='US/Eastern'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timestamp('2011-01-03', tz='US/Eastern')],
[pd.Timedelta('1 days'), pd.Timedelta('2 days'),
pd.Timedelta('3 days')],
# NaT
[pd.Timestamp('2011-01-01'), pd.Timestamp('2011-01-02'),
pd.Timestamp('2011-01-03'), pd.NaT],
[pd.Timestamp('2011-01-01', tz='US/Eastern'),
pd.Timestamp('2011-01-02', tz='US/Eastern'),
pd.Timestamp('2011-01-03', tz='US/Eastern'), pd.NaT],
[pd.Timedelta('1 days'), pd.Timedelta('2 days'),
pd.Timedelta('3 days'), pd.NaT]]
for case in cases:
s = pd.Series(case, name='XXX')
res = s.quantile(0.5)
assert res == case[1]
res = s.quantile([0.5])
exp = pd.Series([case[1]], index=[0.5], name='XXX')
tm.assert_series_equal(res, exp)
def test_datetime_timedelta_quantiles(self):
# covers #9694
assert pd.isna(Series([], dtype='M8[ns]').quantile(.5))
assert pd.isna(Series([], dtype='m8[ns]').quantile(.5))
def test_quantile_nat(self):
res = Series([pd.NaT, pd.NaT]).quantile(0.5)
assert res is pd.NaT
res = Series([pd.NaT, pd.NaT]).quantile([0.5])
tm.assert_series_equal(res, pd.Series([pd.NaT], index=[0.5]))
def test_quantile_empty(self):
# floats
s = Series([], dtype='float64')
res = s.quantile(0.5)
assert np.isnan(res)
res = s.quantile([0.5])
exp = Series([np.nan], index=[0.5])
tm.assert_series_equal(res, exp)
# int
s = Series([], dtype='int64')
res = s.quantile(0.5)
assert np.isnan(res)
res = s.quantile([0.5])
exp = Series([np.nan], index=[0.5])
tm.assert_series_equal(res, exp)
# datetime
s = Series([], dtype='datetime64[ns]')
res = s.quantile(0.5)
assert res is pd.NaT
res = s.quantile([0.5])
exp = Series([pd.NaT], index=[0.5])
tm.assert_series_equal(res, exp)