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
| import numpy as np
| import pytest
|
| import pandas as pd
| import pandas._testing as tm
|
|
| def test_data_frame_value_counts_unsorted():
| df = pd.DataFrame(
| {"num_legs": [2, 4, 4, 6], "num_wings": [2, 0, 0, 0]},
| index=["falcon", "dog", "cat", "ant"],
| )
|
| result = df.value_counts(sort=False)
| expected = pd.Series(
| data=[1, 2, 1],
| index=pd.MultiIndex.from_arrays(
| [(2, 4, 6), (2, 0, 0)], names=["num_legs", "num_wings"]
| ),
| name="count",
| )
|
| tm.assert_series_equal(result, expected)
|
|
| def test_data_frame_value_counts_ascending():
| df = pd.DataFrame(
| {"num_legs": [2, 4, 4, 6], "num_wings": [2, 0, 0, 0]},
| index=["falcon", "dog", "cat", "ant"],
| )
|
| result = df.value_counts(ascending=True)
| expected = pd.Series(
| data=[1, 1, 2],
| index=pd.MultiIndex.from_arrays(
| [(2, 6, 4), (2, 0, 0)], names=["num_legs", "num_wings"]
| ),
| name="count",
| )
|
| tm.assert_series_equal(result, expected)
|
|
| def test_data_frame_value_counts_default():
| df = pd.DataFrame(
| {"num_legs": [2, 4, 4, 6], "num_wings": [2, 0, 0, 0]},
| index=["falcon", "dog", "cat", "ant"],
| )
|
| result = df.value_counts()
| expected = pd.Series(
| data=[2, 1, 1],
| index=pd.MultiIndex.from_arrays(
| [(4, 2, 6), (0, 2, 0)], names=["num_legs", "num_wings"]
| ),
| name="count",
| )
|
| tm.assert_series_equal(result, expected)
|
|
| def test_data_frame_value_counts_normalize():
| df = pd.DataFrame(
| {"num_legs": [2, 4, 4, 6], "num_wings": [2, 0, 0, 0]},
| index=["falcon", "dog", "cat", "ant"],
| )
|
| result = df.value_counts(normalize=True)
| expected = pd.Series(
| data=[0.5, 0.25, 0.25],
| index=pd.MultiIndex.from_arrays(
| [(4, 2, 6), (0, 2, 0)], names=["num_legs", "num_wings"]
| ),
| name="proportion",
| )
|
| tm.assert_series_equal(result, expected)
|
|
| def test_data_frame_value_counts_single_col_default():
| df = pd.DataFrame({"num_legs": [2, 4, 4, 6]})
|
| result = df.value_counts()
| expected = pd.Series(
| data=[2, 1, 1],
| index=pd.MultiIndex.from_arrays([[4, 2, 6]], names=["num_legs"]),
| name="count",
| )
|
| tm.assert_series_equal(result, expected)
|
|
| def test_data_frame_value_counts_empty():
| df_no_cols = pd.DataFrame()
|
| result = df_no_cols.value_counts()
| expected = pd.Series(
| [], dtype=np.int64, name="count", index=np.array([], dtype=np.intp)
| )
|
| tm.assert_series_equal(result, expected)
|
|
| def test_data_frame_value_counts_empty_normalize():
| df_no_cols = pd.DataFrame()
|
| result = df_no_cols.value_counts(normalize=True)
| expected = pd.Series(
| [], dtype=np.float64, name="proportion", index=np.array([], dtype=np.intp)
| )
|
| tm.assert_series_equal(result, expected)
|
|
| def test_data_frame_value_counts_dropna_true(nulls_fixture):
| # GH 41334
| df = pd.DataFrame(
| {
| "first_name": ["John", "Anne", "John", "Beth"],
| "middle_name": ["Smith", nulls_fixture, nulls_fixture, "Louise"],
| },
| )
| result = df.value_counts()
| expected = pd.Series(
| data=[1, 1],
| index=pd.MultiIndex.from_arrays(
| [("Beth", "John"), ("Louise", "Smith")], names=["first_name", "middle_name"]
| ),
| name="count",
| )
|
| tm.assert_series_equal(result, expected)
|
|
| def test_data_frame_value_counts_dropna_false(nulls_fixture):
| # GH 41334
| df = pd.DataFrame(
| {
| "first_name": ["John", "Anne", "John", "Beth"],
| "middle_name": ["Smith", nulls_fixture, nulls_fixture, "Louise"],
| },
| )
|
| result = df.value_counts(dropna=False)
| expected = pd.Series(
| data=[1, 1, 1, 1],
| index=pd.MultiIndex(
| levels=[
| pd.Index(["Anne", "Beth", "John"]),
| pd.Index(["Louise", "Smith", nulls_fixture]),
| ],
| codes=[[0, 1, 2, 2], [2, 0, 1, 2]],
| names=["first_name", "middle_name"],
| ),
| name="count",
| )
|
| tm.assert_series_equal(result, expected)
|
|
| @pytest.mark.parametrize("columns", (["first_name", "middle_name"], [0, 1]))
| def test_data_frame_value_counts_subset(nulls_fixture, columns):
| # GH 50829
| df = pd.DataFrame(
| {
| columns[0]: ["John", "Anne", "John", "Beth"],
| columns[1]: ["Smith", nulls_fixture, nulls_fixture, "Louise"],
| },
| )
| result = df.value_counts(columns[0])
| expected = pd.Series(
| data=[2, 1, 1],
| index=pd.Index(["John", "Anne", "Beth"], name=columns[0]),
| name="count",
| )
|
| tm.assert_series_equal(result, expected)
|
|
