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
| import numpy as np
| import pytest
|
| from pandas.compat import is_numpy_dev
|
| from pandas.core.dtypes.common import (
| is_complex_dtype,
| is_extension_array_dtype,
| )
|
| from pandas import (
| NA,
| Period,
| Series,
| Timedelta,
| Timestamp,
| date_range,
| )
| import pandas._testing as tm
|
|
| class TestSeriesDescribe:
| def test_describe_ints(self):
| ser = Series([0, 1, 2, 3, 4], name="int_data")
| result = ser.describe()
| expected = Series(
| [5, 2, ser.std(), 0, 1, 2, 3, 4],
| name="int_data",
| index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
| )
| tm.assert_series_equal(result, expected)
|
| def test_describe_bools(self):
| ser = Series([True, True, False, False, False], name="bool_data")
| result = ser.describe()
| expected = Series(
| [5, 2, False, 3], name="bool_data", index=["count", "unique", "top", "freq"]
| )
| tm.assert_series_equal(result, expected)
|
| def test_describe_strs(self):
| ser = Series(["a", "a", "b", "c", "d"], name="str_data")
| result = ser.describe()
| expected = Series(
| [5, 4, "a", 2], name="str_data", index=["count", "unique", "top", "freq"]
| )
| tm.assert_series_equal(result, expected)
|
| def test_describe_timedelta64(self):
| ser = Series(
| [
| Timedelta("1 days"),
| Timedelta("2 days"),
| Timedelta("3 days"),
| Timedelta("4 days"),
| Timedelta("5 days"),
| ],
| name="timedelta_data",
| )
| result = ser.describe()
| expected = Series(
| [5, ser[2], ser.std(), ser[0], ser[1], ser[2], ser[3], ser[4]],
| name="timedelta_data",
| index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
| )
| tm.assert_series_equal(result, expected)
|
| def test_describe_period(self):
| ser = Series(
| [Period("2020-01", "M"), Period("2020-01", "M"), Period("2019-12", "M")],
| name="period_data",
| )
| result = ser.describe()
| expected = Series(
| [3, 2, ser[0], 2],
| name="period_data",
| index=["count", "unique", "top", "freq"],
| )
| tm.assert_series_equal(result, expected)
|
| def test_describe_empty_object(self):
| # https://github.com/pandas-dev/pandas/issues/27183
| s = Series([None, None], dtype=object)
| result = s.describe()
| expected = Series(
| [0, 0, np.nan, np.nan],
| dtype=object,
| index=["count", "unique", "top", "freq"],
| )
| tm.assert_series_equal(result, expected)
|
| result = s[:0].describe()
| tm.assert_series_equal(result, expected)
| # ensure NaN, not None
| assert np.isnan(result.iloc[2])
| assert np.isnan(result.iloc[3])
|
| def test_describe_with_tz(self, tz_naive_fixture):
| # GH 21332
| tz = tz_naive_fixture
| name = str(tz_naive_fixture)
| start = Timestamp(2018, 1, 1)
| end = Timestamp(2018, 1, 5)
| s = Series(date_range(start, end, tz=tz), name=name)
| result = s.describe()
| expected = Series(
| [
| 5,
| Timestamp(2018, 1, 3).tz_localize(tz),
| start.tz_localize(tz),
| s[1],
| s[2],
| s[3],
| end.tz_localize(tz),
| ],
| name=name,
| index=["count", "mean", "min", "25%", "50%", "75%", "max"],
| )
| tm.assert_series_equal(result, expected)
|
| def test_describe_with_tz_numeric(self):
| name = tz = "CET"
| start = Timestamp(2018, 1, 1)
| end = Timestamp(2018, 1, 5)
| s = Series(date_range(start, end, tz=tz), name=name)
|
| result = s.describe()
|
| expected = Series(
| [
| 5,
| Timestamp("2018-01-03 00:00:00", tz=tz),
| Timestamp("2018-01-01 00:00:00", tz=tz),
| Timestamp("2018-01-02 00:00:00", tz=tz),
| Timestamp("2018-01-03 00:00:00", tz=tz),
| Timestamp("2018-01-04 00:00:00", tz=tz),
| Timestamp("2018-01-05 00:00:00", tz=tz),
| ],
| name=name,
| index=["count", "mean", "min", "25%", "50%", "75%", "max"],
| )
| tm.assert_series_equal(result, expected)
|
| def test_datetime_is_numeric_includes_datetime(self):
| s = Series(date_range("2012", periods=3))
| result = s.describe()
| expected = Series(
| [
| 3,
| Timestamp("2012-01-02"),
| Timestamp("2012-01-01"),
| Timestamp("2012-01-01T12:00:00"),
| Timestamp("2012-01-02"),
| Timestamp("2012-01-02T12:00:00"),
| Timestamp("2012-01-03"),
| ],
| index=["count", "mean", "min", "25%", "50%", "75%", "max"],
| )
| tm.assert_series_equal(result, expected)
|
| def test_numeric_result_dtype(self, any_numeric_dtype):
| # GH#48340 - describe should always return float on non-complex numeric input
| if is_extension_array_dtype(any_numeric_dtype):
| dtype = "Float64"
| else:
| dtype = "complex128" if is_complex_dtype(any_numeric_dtype) else None
|
| ser = Series([0, 1], dtype=any_numeric_dtype)
| if dtype == "complex128" and is_numpy_dev:
| with pytest.raises(
| TypeError, match=r"^a must be an array of real numbers$"
| ):
| ser.describe()
| return
| result = ser.describe()
| expected = Series(
| [
| 2.0,
| 0.5,
| ser.std(),
| 0,
| 0.25,
| 0.5,
| 0.75,
| 1.0,
| ],
| index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
| dtype=dtype,
| )
| tm.assert_series_equal(result, expected)
|
| def test_describe_one_element_ea(self):
| # GH#52515
| ser = Series([0.0], dtype="Float64")
| with tm.assert_produces_warning(None):
| result = ser.describe()
| expected = Series(
| [1, 0, NA, 0, 0, 0, 0, 0],
| dtype="Float64",
| index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
| )
| tm.assert_series_equal(result, expected)
|
|
