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
| """
| Tests dtype specification during parsing
| for all of the parsers defined in parsers.py
| """
| from io import StringIO
|
| import numpy as np
| import pytest
|
| from pandas import (
| Categorical,
| DataFrame,
| Index,
| MultiIndex,
| Series,
| concat,
| )
| import pandas._testing as tm
|
| # TODO(1.4): Change me into individual xfails at release time
| pytestmark = pytest.mark.usefixtures("pyarrow_skip")
|
|
| def test_dtype_all_columns_empty(all_parsers):
| # see gh-12048
| parser = all_parsers
| result = parser.read_csv(StringIO("A,B"), dtype=str)
|
| expected = DataFrame({"A": [], "B": []}, dtype=str)
| tm.assert_frame_equal(result, expected)
|
|
| def test_empty_pass_dtype(all_parsers):
| parser = all_parsers
|
| data = "one,two"
| result = parser.read_csv(StringIO(data), dtype={"one": "u1"})
|
| expected = DataFrame(
| {"one": np.empty(0, dtype="u1"), "two": np.empty(0, dtype=object)},
| )
| tm.assert_frame_equal(result, expected)
|
|
| def test_empty_with_index_pass_dtype(all_parsers):
| parser = all_parsers
|
| data = "one,two"
| result = parser.read_csv(
| StringIO(data), index_col=["one"], dtype={"one": "u1", 1: "f"}
| )
|
| expected = DataFrame(
| {"two": np.empty(0, dtype="f")}, index=Index([], dtype="u1", name="one")
| )
| tm.assert_frame_equal(result, expected)
|
|
| def test_empty_with_multi_index_pass_dtype(all_parsers):
| parser = all_parsers
|
| data = "one,two,three"
| result = parser.read_csv(
| StringIO(data), index_col=["one", "two"], dtype={"one": "u1", 1: "f8"}
| )
|
| exp_idx = MultiIndex.from_arrays(
| [np.empty(0, dtype="u1"), np.empty(0, dtype=np.float64)],
| names=["one", "two"],
| )
| expected = DataFrame({"three": np.empty(0, dtype=object)}, index=exp_idx)
| tm.assert_frame_equal(result, expected)
|
|
| def test_empty_with_mangled_column_pass_dtype_by_names(all_parsers):
| parser = all_parsers
|
| data = "one,one"
| result = parser.read_csv(StringIO(data), dtype={"one": "u1", "one.1": "f"})
|
| expected = DataFrame(
| {"one": np.empty(0, dtype="u1"), "one.1": np.empty(0, dtype="f")},
| )
| tm.assert_frame_equal(result, expected)
|
|
| def test_empty_with_mangled_column_pass_dtype_by_indexes(all_parsers):
| parser = all_parsers
|
| data = "one,one"
| result = parser.read_csv(StringIO(data), dtype={0: "u1", 1: "f"})
|
| expected = DataFrame(
| {"one": np.empty(0, dtype="u1"), "one.1": np.empty(0, dtype="f")},
| )
| tm.assert_frame_equal(result, expected)
|
|
| def test_empty_with_dup_column_pass_dtype_by_indexes(all_parsers):
| # see gh-9424
| parser = all_parsers
| expected = concat(
| [Series([], name="one", dtype="u1"), Series([], name="one.1", dtype="f")],
| axis=1,
| )
|
| data = "one,one"
| result = parser.read_csv(StringIO(data), dtype={0: "u1", 1: "f"})
| tm.assert_frame_equal(result, expected)
|
|
| def test_empty_with_dup_column_pass_dtype_by_indexes_raises(all_parsers):
| # see gh-9424
| parser = all_parsers
| expected = concat(
| [Series([], name="one", dtype="u1"), Series([], name="one.1", dtype="f")],
| axis=1,
| )
| expected.index = expected.index.astype(object)
|
| with pytest.raises(ValueError, match="Duplicate names"):
| data = ""
| parser.read_csv(StringIO(data), names=["one", "one"], dtype={0: "u1", 1: "f"})
|
|
| @pytest.mark.parametrize(
| "dtype,expected",
| [
| (np.float64, DataFrame(columns=["a", "b"], dtype=np.float64)),
| (
| "category",
| DataFrame({"a": Categorical([]), "b": Categorical([])}),
| ),
| (
| {"a": "category", "b": "category"},
| DataFrame({"a": Categorical([]), "b": Categorical([])}),
| ),
| ("datetime64[ns]", DataFrame(columns=["a", "b"], dtype="datetime64[ns]")),
| (
| "timedelta64[ns]",
| DataFrame(
| {
| "a": Series([], dtype="timedelta64[ns]"),
| "b": Series([], dtype="timedelta64[ns]"),
| },
| ),
| ),
| (
| {"a": np.int64, "b": np.int32},
| DataFrame(
| {"a": Series([], dtype=np.int64), "b": Series([], dtype=np.int32)},
| ),
| ),
| (
| {0: np.int64, 1: np.int32},
| DataFrame(
| {"a": Series([], dtype=np.int64), "b": Series([], dtype=np.int32)},
| ),
| ),
| (
| {"a": np.int64, 1: np.int32},
| DataFrame(
| {"a": Series([], dtype=np.int64), "b": Series([], dtype=np.int32)},
| ),
| ),
| ],
| )
| def test_empty_dtype(all_parsers, dtype, expected):
| # see gh-14712
| parser = all_parsers
| data = "a,b"
|
| result = parser.read_csv(StringIO(data), header=0, dtype=dtype)
| tm.assert_frame_equal(result, expected)
|
|
