forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_string.py
122 lines (74 loc) · 2.49 KB
/
test_string.py
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
import string
import numpy as np
import pytest
import pandas as pd
from pandas.core.arrays.string_ import StringArray, StringDtype
from pandas.tests.extension import base
@pytest.fixture
def dtype():
return StringDtype()
@pytest.fixture
def data():
strings = np.random.choice(list(string.ascii_letters), size=100)
while strings[0] == strings[1]:
strings = np.random.choice(list(string.ascii_letters), size=100)
return StringArray._from_sequence(strings)
@pytest.fixture
def data_missing():
"""Length 2 array with [NA, Valid]"""
return StringArray._from_sequence([pd.NA, "A"])
@pytest.fixture
def data_for_sorting():
return StringArray._from_sequence(["B", "C", "A"])
@pytest.fixture
def data_missing_for_sorting():
return StringArray._from_sequence(["B", pd.NA, "A"])
@pytest.fixture
def na_value():
return pd.NA
@pytest.fixture
def data_for_grouping():
return StringArray._from_sequence(["B", "B", pd.NA, pd.NA, "A", "A", "B", "C"])
class TestDtype(base.BaseDtypeTests):
pass
class TestInterface(base.BaseInterfaceTests):
pass
class TestConstructors(base.BaseConstructorsTests):
pass
class TestReshaping(base.BaseReshapingTests):
pass
class TestGetitem(base.BaseGetitemTests):
pass
class TestSetitem(base.BaseSetitemTests):
pass
class TestMissing(base.BaseMissingTests):
pass
class TestNoReduce(base.BaseNoReduceTests):
pass
class TestMethods(base.BaseMethodsTests):
@pytest.mark.skip(reason="returns nullable")
def test_value_counts(self, all_data, dropna):
return super().test_value_counts(all_data, dropna)
def test_memory_usage(self, data):
# GH 33963
series = pd.Series(data, dtype="string")
assert (
0 < series.nbytes <= series.memory_usage() < series.memory_usage(deep=True)
)
class TestCasting(base.BaseCastingTests):
pass
class TestComparisonOps(base.BaseComparisonOpsTests):
def _compare_other(self, s, data, op_name, other):
result = getattr(s, op_name)(other)
expected = getattr(s.astype(object), op_name)(other).astype("boolean")
self.assert_series_equal(result, expected)
def test_compare_scalar(self, data, all_compare_operators):
op_name = all_compare_operators
s = pd.Series(data)
self._compare_other(s, data, op_name, "abc")
class TestParsing(base.BaseParsingTests):
pass
class TestPrinting(base.BasePrintingTests):
pass
class TestGroupBy(base.BaseGroupbyTests):
pass