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
| import numpy as np
| import pytest
|
| import pandas as pd
| from pandas import (
| DataFrame,
| MultiIndex,
| Series,
| )
| import pandas._testing as tm
|
|
| def test_unstack_preserves_object():
| mi = MultiIndex.from_product([["bar", "foo"], ["one", "two"]])
|
| ser = Series(np.arange(4.0), index=mi, dtype=object)
|
| res1 = ser.unstack()
| assert (res1.dtypes == object).all()
|
| res2 = ser.unstack(level=0)
| assert (res2.dtypes == object).all()
|
|
| def test_unstack():
| index = MultiIndex(
| levels=[["bar", "foo"], ["one", "three", "two"]],
| codes=[[1, 1, 0, 0], [0, 1, 0, 2]],
| )
|
| s = Series(np.arange(4.0), index=index)
| unstacked = s.unstack()
|
| expected = DataFrame(
| [[2.0, np.nan, 3.0], [0.0, 1.0, np.nan]],
| index=["bar", "foo"],
| columns=["one", "three", "two"],
| )
|
| tm.assert_frame_equal(unstacked, expected)
|
| unstacked = s.unstack(level=0)
| tm.assert_frame_equal(unstacked, expected.T)
|
| index = MultiIndex(
| levels=[["bar"], ["one", "two", "three"], [0, 1]],
| codes=[[0, 0, 0, 0, 0, 0], [0, 1, 2, 0, 1, 2], [0, 1, 0, 1, 0, 1]],
| )
| s = Series(np.random.randn(6), index=index)
| exp_index = MultiIndex(
| levels=[["one", "two", "three"], [0, 1]],
| codes=[[0, 1, 2, 0, 1, 2], [0, 1, 0, 1, 0, 1]],
| )
| expected = DataFrame({"bar": s.values}, index=exp_index).sort_index(level=0)
| unstacked = s.unstack(0).sort_index()
| tm.assert_frame_equal(unstacked, expected)
|
| # GH5873
| idx = MultiIndex.from_arrays([[101, 102], [3.5, np.nan]])
| ts = Series([1, 2], index=idx)
| left = ts.unstack()
| right = DataFrame(
| [[np.nan, 1], [2, np.nan]], index=[101, 102], columns=[np.nan, 3.5]
| )
| tm.assert_frame_equal(left, right)
|
| idx = MultiIndex.from_arrays(
| [
| ["cat", "cat", "cat", "dog", "dog"],
| ["a", "a", "b", "a", "b"],
| [1, 2, 1, 1, np.nan],
| ]
| )
| ts = Series([1.0, 1.1, 1.2, 1.3, 1.4], index=idx)
| right = DataFrame(
| [[1.0, 1.3], [1.1, np.nan], [np.nan, 1.4], [1.2, np.nan]],
| columns=["cat", "dog"],
| )
| tpls = [("a", 1), ("a", 2), ("b", np.nan), ("b", 1)]
| right.index = MultiIndex.from_tuples(tpls)
| tm.assert_frame_equal(ts.unstack(level=0), right)
|
|
| def test_unstack_tuplename_in_multiindex():
| # GH 19966
| idx = MultiIndex.from_product(
| [["a", "b", "c"], [1, 2, 3]], names=[("A", "a"), ("B", "b")]
| )
| ser = Series(1, index=idx)
| result = ser.unstack(("A", "a"))
|
| expected = DataFrame(
| [[1, 1, 1], [1, 1, 1], [1, 1, 1]],
| columns=MultiIndex.from_tuples([("a",), ("b",), ("c",)], names=[("A", "a")]),
| index=pd.Index([1, 2, 3], name=("B", "b")),
| )
| tm.assert_frame_equal(result, expected)
|
|
| @pytest.mark.parametrize(
| "unstack_idx, expected_values, expected_index, expected_columns",
| [
| (
| ("A", "a"),
| [[1, 1], [1, 1], [1, 1], [1, 1]],
| MultiIndex.from_tuples([(1, 3), (1, 4), (2, 3), (2, 4)], names=["B", "C"]),
| MultiIndex.from_tuples([("a",), ("b",)], names=[("A", "a")]),
| ),
| (
| (("A", "a"), "B"),
| [[1, 1, 1, 1], [1, 1, 1, 1]],
| pd.Index([3, 4], name="C"),
| MultiIndex.from_tuples(
| [("a", 1), ("a", 2), ("b", 1), ("b", 2)], names=[("A", "a"), "B"]
| ),
| ),
| ],
| )
| def test_unstack_mixed_type_name_in_multiindex(
| unstack_idx, expected_values, expected_index, expected_columns
| ):
| # GH 19966
| idx = MultiIndex.from_product(
| [["a", "b"], [1, 2], [3, 4]], names=[("A", "a"), "B", "C"]
| )
| ser = Series(1, index=idx)
| result = ser.unstack(unstack_idx)
|
| expected = DataFrame(
| expected_values, columns=expected_columns, index=expected_index
| )
| tm.assert_frame_equal(result, expected)
|
|
| def test_unstack_multi_index_categorical_values():
| mi = tm.makeTimeDataFrame().stack().index.rename(["major", "minor"])
| ser = Series(["foo"] * len(mi), index=mi, name="category", dtype="category")
|
| result = ser.unstack()
|
| dti = ser.index.levels[0]
| c = pd.Categorical(["foo"] * len(dti))
| expected = DataFrame(
| {"A": c.copy(), "B": c.copy(), "C": c.copy(), "D": c.copy()},
| columns=pd.Index(list("ABCD"), name="minor"),
| index=dti.rename("major"),
| )
| tm.assert_frame_equal(result, expected)
|
|
| def test_unstack_mixed_level_names():
| # GH#48763
| arrays = [["a", "a"], [1, 2], ["red", "blue"]]
| idx = MultiIndex.from_arrays(arrays, names=("x", 0, "y"))
| ser = Series([1, 2], index=idx)
| result = ser.unstack("x")
| expected = DataFrame(
| [[1], [2]],
| columns=pd.Index(["a"], name="x"),
| index=MultiIndex.from_tuples([(1, "red"), (2, "blue")], names=[0, "y"]),
| )
| tm.assert_frame_equal(result, expected)
|
|
