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
| """
| Tests that duplicate columns are handled appropriately when parsed by the
| CSV engine. In general, the expected result is that they are either thoroughly
| de-duplicated (if mangling requested) or ignored otherwise.
| """
| from io import StringIO
|
| import pytest
|
| from pandas import (
| DataFrame,
| Index,
| )
| import pandas._testing as tm
|
| xfail_pyarrow = pytest.mark.usefixtures("pyarrow_xfail")
|
|
| pytestmark = pytest.mark.filterwarnings(
| "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
| )
|
|
| @xfail_pyarrow # ValueError: Found non-unique column index
| def test_basic(all_parsers):
| parser = all_parsers
|
| data = "a,a,b,b,b\n1,2,3,4,5"
| result = parser.read_csv(StringIO(data), sep=",")
|
| expected = DataFrame([[1, 2, 3, 4, 5]], columns=["a", "a.1", "b", "b.1", "b.2"])
| tm.assert_frame_equal(result, expected)
|
|
| @xfail_pyarrow # ValueError: Found non-unique column index
| def test_basic_names(all_parsers):
| # See gh-7160
| parser = all_parsers
|
| data = "a,b,a\n0,1,2\n3,4,5"
| expected = DataFrame([[0, 1, 2], [3, 4, 5]], columns=["a", "b", "a.1"])
|
| result = parser.read_csv(StringIO(data))
| tm.assert_frame_equal(result, expected)
|
|
| def test_basic_names_raise(all_parsers):
| # See gh-7160
| parser = all_parsers
|
| data = "0,1,2\n3,4,5"
| with pytest.raises(ValueError, match="Duplicate names"):
| parser.read_csv(StringIO(data), names=["a", "b", "a"])
|
|
| @xfail_pyarrow # ValueError: Found non-unique column index
| @pytest.mark.parametrize(
| "data,expected",
| [
| ("a,a,a.1\n1,2,3", DataFrame([[1, 2, 3]], columns=["a", "a.2", "a.1"])),
| (
| "a,a,a.1,a.1.1,a.1.1.1,a.1.1.1.1\n1,2,3,4,5,6",
| DataFrame(
| [[1, 2, 3, 4, 5, 6]],
| columns=["a", "a.2", "a.1", "a.1.1", "a.1.1.1", "a.1.1.1.1"],
| ),
| ),
| (
| "a,a,a.3,a.1,a.2,a,a\n1,2,3,4,5,6,7",
| DataFrame(
| [[1, 2, 3, 4, 5, 6, 7]],
| columns=["a", "a.4", "a.3", "a.1", "a.2", "a.5", "a.6"],
| ),
| ),
| ],
| )
| def test_thorough_mangle_columns(all_parsers, data, expected):
| # see gh-17060
| parser = all_parsers
|
| result = parser.read_csv(StringIO(data))
| tm.assert_frame_equal(result, expected)
|
|
| @pytest.mark.parametrize(
| "data,names,expected",
| [
| (
| "a,b,b\n1,2,3",
| ["a.1", "a.1", "a.1.1"],
| DataFrame(
| [["a", "b", "b"], ["1", "2", "3"]], columns=["a.1", "a.1.1", "a.1.1.1"]
| ),
| ),
| (
| "a,b,c,d,e,f\n1,2,3,4,5,6",
| ["a", "a", "a.1", "a.1.1", "a.1.1.1", "a.1.1.1.1"],
| DataFrame(
| [["a", "b", "c", "d", "e", "f"], ["1", "2", "3", "4", "5", "6"]],
| columns=["a", "a.1", "a.1.1", "a.1.1.1", "a.1.1.1.1", "a.1.1.1.1.1"],
| ),
| ),
| (
| "a,b,c,d,e,f,g\n1,2,3,4,5,6,7",
| ["a", "a", "a.3", "a.1", "a.2", "a", "a"],
| DataFrame(
| [
| ["a", "b", "c", "d", "e", "f", "g"],
| ["1", "2", "3", "4", "5", "6", "7"],
| ],
| columns=["a", "a.1", "a.3", "a.1.1", "a.2", "a.2.1", "a.3.1"],
| ),
| ),
| ],
| )
| def test_thorough_mangle_names(all_parsers, data, names, expected):
| # see gh-17095
| parser = all_parsers
|
| with pytest.raises(ValueError, match="Duplicate names"):
| parser.read_csv(StringIO(data), names=names)
|
|
| @xfail_pyarrow # AssertionError: DataFrame.columns are different
| def test_mangled_unnamed_placeholders(all_parsers):
| # xref gh-13017
| orig_key = "0"
| parser = all_parsers
|
| orig_value = [1, 2, 3]
| df = DataFrame({orig_key: orig_value})
|
| # This test recursively updates `df`.
| for i in range(3):
| expected = DataFrame(columns=Index([], dtype="str"))
|
| for j in range(i + 1):
| col_name = "Unnamed: 0" + f".{1*j}" * min(j, 1)
| expected.insert(loc=0, column=col_name, value=[0, 1, 2])
|
| expected[orig_key] = orig_value
| df = parser.read_csv(StringIO(df.to_csv()))
|
| tm.assert_frame_equal(df, expected)
|
|
| @xfail_pyarrow # ValueError: Found non-unique column index
| def test_mangle_dupe_cols_already_exists(all_parsers):
| # GH#14704
| parser = all_parsers
|
| data = "a,a,a.1,a,a.3,a.1,a.1.1\n1,2,3,4,5,6,7"
| result = parser.read_csv(StringIO(data))
| expected = DataFrame(
| [[1, 2, 3, 4, 5, 6, 7]],
| columns=["a", "a.2", "a.1", "a.4", "a.3", "a.1.2", "a.1.1"],
| )
| tm.assert_frame_equal(result, expected)
|
|
| @xfail_pyarrow # ValueError: Found non-unique column index
| def test_mangle_dupe_cols_already_exists_unnamed_col(all_parsers):
| # GH#14704
| parser = all_parsers
|
| data = ",Unnamed: 0,,Unnamed: 2\n1,2,3,4"
| result = parser.read_csv(StringIO(data))
| expected = DataFrame(
| [[1, 2, 3, 4]],
| columns=["Unnamed: 0.1", "Unnamed: 0", "Unnamed: 2.1", "Unnamed: 2"],
| )
| tm.assert_frame_equal(result, expected)
|
|
| @pytest.mark.parametrize("usecol, engine", [([0, 1, 1], "python"), ([0, 1, 1], "c")])
| def test_mangle_cols_names(all_parsers, usecol, engine):
| # GH 11823
| parser = all_parsers
| data = "1,2,3"
| names = ["A", "A", "B"]
| with pytest.raises(ValueError, match="Duplicate names"):
| parser.read_csv(StringIO(data), names=names, usecols=usecol, engine=engine)
|
|
