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
| import numpy as np
| import pytest
|
| import pandas as pd
| import pandas._testing as tm
|
|
| def test_basic():
| s = pd.Series([[0, 1, 2], np.nan, [], (3, 4)], index=list("abcd"), name="foo")
| result = s.explode()
| expected = pd.Series(
| [0, 1, 2, np.nan, np.nan, 3, 4], index=list("aaabcdd"), dtype=object, name="foo"
| )
| tm.assert_series_equal(result, expected)
|
|
| def test_mixed_type():
| s = pd.Series(
| [[0, 1, 2], np.nan, None, np.array([]), pd.Series(["a", "b"])], name="foo"
| )
| result = s.explode()
| expected = pd.Series(
| [0, 1, 2, np.nan, None, np.nan, "a", "b"],
| index=[0, 0, 0, 1, 2, 3, 4, 4],
| dtype=object,
| name="foo",
| )
| tm.assert_series_equal(result, expected)
|
|
| def test_empty():
| s = pd.Series(dtype=object)
| result = s.explode()
| expected = s.copy()
| tm.assert_series_equal(result, expected)
|
|
| def test_nested_lists():
| s = pd.Series([[[1, 2, 3]], [1, 2], 1])
| result = s.explode()
| expected = pd.Series([[1, 2, 3], 1, 2, 1], index=[0, 1, 1, 2])
| tm.assert_series_equal(result, expected)
|
|
| def test_multi_index():
| s = pd.Series(
| [[0, 1, 2], np.nan, [], (3, 4)],
| name="foo",
| index=pd.MultiIndex.from_product([list("ab"), range(2)], names=["foo", "bar"]),
| )
| result = s.explode()
| index = pd.MultiIndex.from_tuples(
| [("a", 0), ("a", 0), ("a", 0), ("a", 1), ("b", 0), ("b", 1), ("b", 1)],
| names=["foo", "bar"],
| )
| expected = pd.Series(
| [0, 1, 2, np.nan, np.nan, 3, 4], index=index, dtype=object, name="foo"
| )
| tm.assert_series_equal(result, expected)
|
|
| def test_large():
| s = pd.Series([range(256)]).explode()
| result = s.explode()
| tm.assert_series_equal(result, s)
|
|
| def test_invert_array():
| df = pd.DataFrame({"a": pd.date_range("20190101", periods=3, tz="UTC")})
|
| listify = df.apply(lambda x: x.array, axis=1)
| result = listify.explode()
| tm.assert_series_equal(result, df["a"].rename())
|
|
| @pytest.mark.parametrize(
| "s", [pd.Series([1, 2, 3]), pd.Series(pd.date_range("2019", periods=3, tz="UTC"))]
| )
| def test_non_object_dtype(s):
| result = s.explode()
| tm.assert_series_equal(result, s)
|
|
| def test_typical_usecase():
| df = pd.DataFrame(
| [{"var1": "a,b,c", "var2": 1}, {"var1": "d,e,f", "var2": 2}],
| columns=["var1", "var2"],
| )
| exploded = df.var1.str.split(",").explode()
| result = df[["var2"]].join(exploded)
| expected = pd.DataFrame(
| {"var2": [1, 1, 1, 2, 2, 2], "var1": list("abcdef")},
| columns=["var2", "var1"],
| index=[0, 0, 0, 1, 1, 1],
| )
| tm.assert_frame_equal(result, expected)
|
|
| def test_nested_EA():
| # a nested EA array
| s = pd.Series(
| [
| pd.date_range("20170101", periods=3, tz="UTC"),
| pd.date_range("20170104", periods=3, tz="UTC"),
| ]
| )
| result = s.explode()
| expected = pd.Series(
| pd.date_range("20170101", periods=6, tz="UTC"), index=[0, 0, 0, 1, 1, 1]
| )
| tm.assert_series_equal(result, expected)
|
|
| def test_duplicate_index():
| # GH 28005
| s = pd.Series([[1, 2], [3, 4]], index=[0, 0])
| result = s.explode()
| expected = pd.Series([1, 2, 3, 4], index=[0, 0, 0, 0], dtype=object)
| tm.assert_series_equal(result, expected)
|
|
| def test_ignore_index():
| # GH 34932
| s = pd.Series([[1, 2], [3, 4]])
| result = s.explode(ignore_index=True)
| expected = pd.Series([1, 2, 3, 4], index=[0, 1, 2, 3], dtype=object)
| tm.assert_series_equal(result, expected)
|
|
| def test_explode_sets():
| # https://github.com/pandas-dev/pandas/issues/35614
| s = pd.Series([{"a", "b", "c"}], index=[1])
| result = s.explode().sort_values()
| expected = pd.Series(["a", "b", "c"], index=[1, 1, 1])
| tm.assert_series_equal(result, expected)
|
|
| def test_explode_scalars_can_ignore_index():
| # https://github.com/pandas-dev/pandas/issues/40487
| s = pd.Series([1, 2, 3], index=["a", "b", "c"])
| result = s.explode(ignore_index=True)
| expected = pd.Series([1, 2, 3])
| tm.assert_series_equal(result, expected)
|
|
