forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_value_counts.py
205 lines (169 loc) · 7.95 KB
/
test_value_counts.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
import numpy as np
import pytest
import pandas as pd
from pandas import Categorical, CategoricalIndex, Series
import pandas._testing as tm
class TestSeriesValueCounts:
def test_value_counts_datetime(self):
# most dtypes are tested in tests/base
values = [
pd.Timestamp("2011-01-01 09:00"),
pd.Timestamp("2011-01-01 10:00"),
pd.Timestamp("2011-01-01 11:00"),
pd.Timestamp("2011-01-01 09:00"),
pd.Timestamp("2011-01-01 09:00"),
pd.Timestamp("2011-01-01 11:00"),
]
exp_idx = pd.DatetimeIndex(
["2011-01-01 09:00", "2011-01-01 11:00", "2011-01-01 10:00"]
)
exp = pd.Series([3, 2, 1], index=exp_idx, name="xxx")
ser = pd.Series(values, name="xxx")
tm.assert_series_equal(ser.value_counts(), exp)
# check DatetimeIndex outputs the same result
idx = pd.DatetimeIndex(values, name="xxx")
tm.assert_series_equal(idx.value_counts(), exp)
# normalize
exp = pd.Series(np.array([3.0, 2.0, 1]) / 6.0, index=exp_idx, name="xxx")
tm.assert_series_equal(ser.value_counts(normalize=True), exp)
tm.assert_series_equal(idx.value_counts(normalize=True), exp)
def test_value_counts_datetime_tz(self):
values = [
pd.Timestamp("2011-01-01 09:00", tz="US/Eastern"),
pd.Timestamp("2011-01-01 10:00", tz="US/Eastern"),
pd.Timestamp("2011-01-01 11:00", tz="US/Eastern"),
pd.Timestamp("2011-01-01 09:00", tz="US/Eastern"),
pd.Timestamp("2011-01-01 09:00", tz="US/Eastern"),
pd.Timestamp("2011-01-01 11:00", tz="US/Eastern"),
]
exp_idx = pd.DatetimeIndex(
["2011-01-01 09:00", "2011-01-01 11:00", "2011-01-01 10:00"],
tz="US/Eastern",
)
exp = pd.Series([3, 2, 1], index=exp_idx, name="xxx")
ser = pd.Series(values, name="xxx")
tm.assert_series_equal(ser.value_counts(), exp)
idx = pd.DatetimeIndex(values, name="xxx")
tm.assert_series_equal(idx.value_counts(), exp)
exp = pd.Series(np.array([3.0, 2.0, 1]) / 6.0, index=exp_idx, name="xxx")
tm.assert_series_equal(ser.value_counts(normalize=True), exp)
tm.assert_series_equal(idx.value_counts(normalize=True), exp)
def test_value_counts_period(self):
values = [
pd.Period("2011-01", freq="M"),
pd.Period("2011-02", freq="M"),
pd.Period("2011-03", freq="M"),
pd.Period("2011-01", freq="M"),
pd.Period("2011-01", freq="M"),
pd.Period("2011-03", freq="M"),
]
exp_idx = pd.PeriodIndex(["2011-01", "2011-03", "2011-02"], freq="M")
exp = pd.Series([3, 2, 1], index=exp_idx, name="xxx")
ser = pd.Series(values, name="xxx")
tm.assert_series_equal(ser.value_counts(), exp)
# check DatetimeIndex outputs the same result
idx = pd.PeriodIndex(values, name="xxx")
tm.assert_series_equal(idx.value_counts(), exp)
# normalize
exp = pd.Series(np.array([3.0, 2.0, 1]) / 6.0, index=exp_idx, name="xxx")
tm.assert_series_equal(ser.value_counts(normalize=True), exp)
tm.assert_series_equal(idx.value_counts(normalize=True), exp)
def test_value_counts_categorical_ordered(self):
# most dtypes are tested in tests/base
values = pd.Categorical([1, 2, 3, 1, 1, 3], ordered=True)
exp_idx = pd.CategoricalIndex([1, 3, 2], categories=[1, 2, 3], ordered=True)
exp = pd.Series([3, 2, 1], index=exp_idx, name="xxx")
ser = pd.Series(values, name="xxx")
tm.assert_series_equal(ser.value_counts(), exp)
# check CategoricalIndex outputs the same result
idx = pd.CategoricalIndex(values, name="xxx")
tm.assert_series_equal(idx.value_counts(), exp)
# normalize
exp = pd.Series(np.array([3.0, 2.0, 1]) / 6.0, index=exp_idx, name="xxx")
tm.assert_series_equal(ser.value_counts(normalize=True), exp)
tm.assert_series_equal(idx.value_counts(normalize=True), exp)
def test_value_counts_categorical_not_ordered(self):
values = pd.Categorical([1, 2, 3, 1, 1, 3], ordered=False)
exp_idx = pd.CategoricalIndex([1, 3, 2], categories=[1, 2, 3], ordered=False)
exp = pd.Series([3, 2, 1], index=exp_idx, name="xxx")
ser = pd.Series(values, name="xxx")
tm.assert_series_equal(ser.value_counts(), exp)
# check CategoricalIndex outputs the same result
idx = pd.CategoricalIndex(values, name="xxx")
tm.assert_series_equal(idx.value_counts(), exp)
# normalize
exp = pd.Series(np.array([3.0, 2.0, 1]) / 6.0, index=exp_idx, name="xxx")
tm.assert_series_equal(ser.value_counts(normalize=True), exp)
tm.assert_series_equal(idx.value_counts(normalize=True), exp)
def test_value_counts_categorical(self):
# GH#12835
cats = Categorical(list("abcccb"), categories=list("cabd"))
ser = Series(cats, name="xxx")
res = ser.value_counts(sort=False)
exp_index = CategoricalIndex(list("cabd"), categories=cats.categories)
exp = Series([3, 1, 2, 0], name="xxx", index=exp_index)
tm.assert_series_equal(res, exp)
res = ser.value_counts(sort=True)
exp_index = CategoricalIndex(list("cbad"), categories=cats.categories)
exp = Series([3, 2, 1, 0], name="xxx", index=exp_index)
tm.assert_series_equal(res, exp)
# check object dtype handles the Series.name as the same
# (tested in tests/base)
ser = Series(["a", "b", "c", "c", "c", "b"], name="xxx")
res = ser.value_counts()
exp = Series([3, 2, 1], name="xxx", index=["c", "b", "a"])
tm.assert_series_equal(res, exp)
def test_value_counts_categorical_with_nan(self):
# see GH#9443
# sanity check
ser = Series(["a", "b", "a"], dtype="category")
exp = Series([2, 1], index=CategoricalIndex(["a", "b"]))
res = ser.value_counts(dropna=True)
tm.assert_series_equal(res, exp)
res = ser.value_counts(dropna=True)
tm.assert_series_equal(res, exp)
# same Series via two different constructions --> same behaviour
series = [
Series(["a", "b", None, "a", None, None], dtype="category"),
Series(
Categorical(["a", "b", None, "a", None, None], categories=["a", "b"])
),
]
for ser in series:
# None is a NaN value, so we exclude its count here
exp = Series([2, 1], index=CategoricalIndex(["a", "b"]))
res = ser.value_counts(dropna=True)
tm.assert_series_equal(res, exp)
# we don't exclude the count of None and sort by counts
exp = Series([3, 2, 1], index=CategoricalIndex([np.nan, "a", "b"]))
res = ser.value_counts(dropna=False)
tm.assert_series_equal(res, exp)
# When we aren't sorting by counts, and np.nan isn't a
# category, it should be last.
exp = Series([2, 1, 3], index=CategoricalIndex(["a", "b", np.nan]))
res = ser.value_counts(dropna=False, sort=False)
tm.assert_series_equal(res, exp)
@pytest.mark.parametrize(
"ser, dropna, exp",
[
(
pd.Series([False, True, True, pd.NA]),
False,
pd.Series([2, 1, 1], index=[True, False, pd.NA]),
),
(
pd.Series([False, True, True, pd.NA]),
True,
pd.Series([2, 1], index=[True, False]),
),
(
pd.Series(range(3), index=[True, False, np.nan]).index,
False,
pd.Series([1, 1, 1], index=[True, False, pd.NA]),
),
],
)
def test_value_counts_bool_with_nan(self, ser, dropna, exp):
# GH32146
out = ser.value_counts(dropna=dropna)
tm.assert_series_equal(out, exp)