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
| import numpy as np
| import pytest
|
| from pandas import (
| DataFrame,
| Index,
| PeriodIndex,
| Series,
| )
| import pandas._testing as tm
|
|
| @pytest.mark.parametrize("by", ["A", "B", ["A", "B"]])
| def test_size(df, by):
| grouped = df.groupby(by=by)
| result = grouped.size()
| for key, group in grouped:
| assert result[key] == len(group)
|
|
| @pytest.mark.parametrize(
| "by",
| [
| [0, 0, 0, 0],
| [0, 1, 1, 1],
| [1, 0, 1, 1],
| [0, None, None, None],
| pytest.param([None, None, None, None], marks=pytest.mark.xfail),
| ],
| )
| def test_size_axis_1(df, axis_1, by, sort, dropna):
| # GH#45715
| counts = {key: sum(value == key for value in by) for key in dict.fromkeys(by)}
| if dropna:
| counts = {key: value for key, value in counts.items() if key is not None}
| expected = Series(counts, dtype="int64")
| if sort:
| expected = expected.sort_index()
| if tm.is_integer_dtype(expected.index) and not any(x is None for x in by):
| expected.index = expected.index.astype(np.int_)
|
| grouped = df.groupby(by=by, axis=axis_1, sort=sort, dropna=dropna)
| result = grouped.size()
| tm.assert_series_equal(result, expected)
|
|
| @pytest.mark.parametrize("by", ["A", "B", ["A", "B"]])
| @pytest.mark.parametrize("sort", [True, False])
| def test_size_sort(sort, by):
| df = DataFrame(np.random.choice(20, (1000, 3)), columns=list("ABC"))
| left = df.groupby(by=by, sort=sort).size()
| right = df.groupby(by=by, sort=sort)["C"].apply(lambda a: a.shape[0])
| tm.assert_series_equal(left, right, check_names=False)
|
|
| def test_size_series_dataframe():
| # https://github.com/pandas-dev/pandas/issues/11699
| df = DataFrame(columns=["A", "B"])
| out = Series(dtype="int64", index=Index([], name="A"))
| tm.assert_series_equal(df.groupby("A").size(), out)
|
|
| def test_size_groupby_all_null():
| # https://github.com/pandas-dev/pandas/issues/23050
| # Assert no 'Value Error : Length of passed values is 2, index implies 0'
| df = DataFrame({"A": [None, None]}) # all-null groups
| result = df.groupby("A").size()
| expected = Series(dtype="int64", index=Index([], name="A"))
| tm.assert_series_equal(result, expected)
|
|
| def test_size_period_index():
| # https://github.com/pandas-dev/pandas/issues/34010
| ser = Series([1], index=PeriodIndex(["2000"], name="A", freq="D"))
| grp = ser.groupby(level="A")
| result = grp.size()
| tm.assert_series_equal(result, ser)
|
|
| @pytest.mark.parametrize("as_index", [True, False])
| def test_size_on_categorical(as_index):
| df = DataFrame([[1, 1], [2, 2]], columns=["A", "B"])
| df["A"] = df["A"].astype("category")
| result = df.groupby(["A", "B"], as_index=as_index).size()
|
| expected = DataFrame(
| [[1, 1, 1], [1, 2, 0], [2, 1, 0], [2, 2, 1]], columns=["A", "B", "size"]
| )
| expected["A"] = expected["A"].astype("category")
| if as_index:
| expected = expected.set_index(["A", "B"])["size"].rename(None)
|
| tm.assert_equal(result, expected)
|
|
