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
| """
| Tests the usecols functionality during parsing
| for all of the parsers defined in parsers.py
| """
| from io import StringIO
|
| import pytest
|
| from pandas import (
| DataFrame,
| Index,
| Timestamp,
| )
| import pandas._testing as tm
|
| _msg_validate_usecols_arg = (
| "'usecols' must either be list-like "
| "of all strings, all unicode, all "
| "integers or a callable."
| )
| _msg_validate_usecols_names = (
| "Usecols do not match columns, columns expected but not found: {0}"
| )
|
| # TODO(1.4): Change these to xfails whenever parse_dates support(which was
| # intentionally disable to keep small PR sizes) is added back
| pytestmark = pytest.mark.usefixtures("pyarrow_skip")
|
|
| @pytest.mark.parametrize("usecols", [[0, 2, 3], [3, 0, 2]])
| def test_usecols_with_parse_dates(all_parsers, usecols):
| # see gh-9755
| data = """a,b,c,d,e
| 0,1,2014-01-01,09:00,4
| 0,1,2014-01-02,10:00,4"""
| parser = all_parsers
| parse_dates = [[1, 2]]
|
| cols = {
| "a": [0, 0],
| "c_d": [Timestamp("2014-01-01 09:00:00"), Timestamp("2014-01-02 10:00:00")],
| }
| expected = DataFrame(cols, columns=["c_d", "a"])
| result = parser.read_csv(StringIO(data), usecols=usecols, parse_dates=parse_dates)
| tm.assert_frame_equal(result, expected)
|
|
| def test_usecols_with_parse_dates2(all_parsers):
| # see gh-13604
| parser = all_parsers
| data = """2008-02-07 09:40,1032.43
| 2008-02-07 09:50,1042.54
| 2008-02-07 10:00,1051.65"""
|
| names = ["date", "values"]
| usecols = names[:]
| parse_dates = [0]
|
| index = Index(
| [
| Timestamp("2008-02-07 09:40"),
| Timestamp("2008-02-07 09:50"),
| Timestamp("2008-02-07 10:00"),
| ],
| name="date",
| )
| cols = {"values": [1032.43, 1042.54, 1051.65]}
| expected = DataFrame(cols, index=index)
|
| result = parser.read_csv(
| StringIO(data),
| parse_dates=parse_dates,
| index_col=0,
| usecols=usecols,
| header=None,
| names=names,
| )
| tm.assert_frame_equal(result, expected)
|
|
| def test_usecols_with_parse_dates3(all_parsers):
| # see gh-14792
| parser = all_parsers
| data = """a,b,c,d,e,f,g,h,i,j
| 2016/09/21,1,1,2,3,4,5,6,7,8"""
|
| usecols = list("abcdefghij")
| parse_dates = [0]
|
| cols = {
| "a": Timestamp("2016-09-21"),
| "b": [1],
| "c": [1],
| "d": [2],
| "e": [3],
| "f": [4],
| "g": [5],
| "h": [6],
| "i": [7],
| "j": [8],
| }
| expected = DataFrame(cols, columns=usecols)
|
| result = parser.read_csv(StringIO(data), usecols=usecols, parse_dates=parse_dates)
| tm.assert_frame_equal(result, expected)
|
|
| def test_usecols_with_parse_dates4(all_parsers):
| data = "a,b,c,d,e,f,g,h,i,j\n2016/09/21,1,1,2,3,4,5,6,7,8"
| usecols = list("abcdefghij")
| parse_dates = [[0, 1]]
| parser = all_parsers
|
| cols = {
| "a_b": "2016/09/21 1",
| "c": [1],
| "d": [2],
| "e": [3],
| "f": [4],
| "g": [5],
| "h": [6],
| "i": [7],
| "j": [8],
| }
| expected = DataFrame(cols, columns=["a_b"] + list("cdefghij"))
|
| result = parser.read_csv(
| StringIO(data),
| usecols=usecols,
| parse_dates=parse_dates,
| )
| tm.assert_frame_equal(result, expected)
|
|
| @pytest.mark.parametrize("usecols", [[0, 2, 3], [3, 0, 2]])
| @pytest.mark.parametrize(
| "names",
| [
| list("abcde"), # Names span all columns in original data.
| list("acd"), # Names span only the selected columns.
| ],
| )
| def test_usecols_with_parse_dates_and_names(all_parsers, usecols, names):
| # see gh-9755
| s = """0,1,2014-01-01,09:00,4
| 0,1,2014-01-02,10:00,4"""
| parse_dates = [[1, 2]]
| parser = all_parsers
|
| cols = {
| "a": [0, 0],
| "c_d": [Timestamp("2014-01-01 09:00:00"), Timestamp("2014-01-02 10:00:00")],
| }
| expected = DataFrame(cols, columns=["c_d", "a"])
|
| result = parser.read_csv(
| StringIO(s), names=names, parse_dates=parse_dates, usecols=usecols
| )
| tm.assert_frame_equal(result, expected)
|
|
