forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathtest_function.py
192 lines (153 loc) · 6.07 KB
/
test_function.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
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
183
184
185
186
187
188
189
190
191
192
import numpy as np
import pytest
from pandas.compat import IS64
import pandas as pd
import pandas._testing as tm
@pytest.mark.parametrize("ufunc", [np.abs, np.sign])
# np.sign emits a warning with nans, <https://github.com/numpy/numpy/issues/15127>
@pytest.mark.filterwarnings("ignore:invalid value encountered in sign")
def test_ufuncs_single(ufunc):
a = pd.array([1, 2, -3, np.nan], dtype="Float64")
result = ufunc(a)
expected = pd.array(ufunc(a.astype(float)), dtype="Float64")
tm.assert_extension_array_equal(result, expected)
s = pd.Series(a)
result = ufunc(s)
expected = pd.Series(expected)
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("ufunc", [np.log, np.exp, np.sin, np.cos, np.sqrt])
def test_ufuncs_single_float(ufunc):
a = pd.array([1.0, 0.2, 3.0, np.nan], dtype="Float64")
with np.errstate(invalid="ignore"):
result = ufunc(a)
expected = pd.array(ufunc(a.astype(float)), dtype="Float64")
tm.assert_extension_array_equal(result, expected)
s = pd.Series(a)
with np.errstate(invalid="ignore"):
result = ufunc(s)
expected = pd.Series(ufunc(s.astype(float)), dtype="Float64")
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("ufunc", [np.add, np.subtract])
def test_ufuncs_binary_float(ufunc):
# two FloatingArrays
a = pd.array([1, 0.2, -3, np.nan], dtype="Float64")
result = ufunc(a, a)
expected = pd.array(ufunc(a.astype(float), a.astype(float)), dtype="Float64")
tm.assert_extension_array_equal(result, expected)
# FloatingArray with numpy array
arr = np.array([1, 2, 3, 4])
result = ufunc(a, arr)
expected = pd.array(ufunc(a.astype(float), arr), dtype="Float64")
tm.assert_extension_array_equal(result, expected)
result = ufunc(arr, a)
expected = pd.array(ufunc(arr, a.astype(float)), dtype="Float64")
tm.assert_extension_array_equal(result, expected)
# FloatingArray with scalar
result = ufunc(a, 1)
expected = pd.array(ufunc(a.astype(float), 1), dtype="Float64")
tm.assert_extension_array_equal(result, expected)
result = ufunc(1, a)
expected = pd.array(ufunc(1, a.astype(float)), dtype="Float64")
tm.assert_extension_array_equal(result, expected)
@pytest.mark.parametrize("values", [[0, 1], [0, None]])
def test_ufunc_reduce_raises(values):
arr = pd.array(values, dtype="Float64")
res = np.add.reduce(arr)
expected = arr.sum(skipna=False)
tm.assert_almost_equal(res, expected)
@pytest.mark.skipif(not IS64, reason="GH 36579: fail on 32-bit system")
@pytest.mark.parametrize(
"pandasmethname, kwargs",
[
("var", {"ddof": 0}),
("var", {"ddof": 1}),
("kurtosis", {}),
("skew", {}),
("sem", {}),
],
)
def test_stat_method(pandasmethname, kwargs):
s = pd.Series(data=[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, np.nan, np.nan], dtype="Float64")
pandasmeth = getattr(s, pandasmethname)
result = pandasmeth(**kwargs)
s2 = pd.Series(data=[0.1, 0.2, 0.3, 0.4, 0.5, 0.6], dtype="float64")
pandasmeth = getattr(s2, pandasmethname)
expected = pandasmeth(**kwargs)
assert expected == result
def test_value_counts_na():
arr = pd.array([0.1, 0.2, 0.1, pd.NA], dtype="Float64")
result = arr.value_counts(dropna=False)
idx = pd.Index([0.1, 0.2, pd.NA], dtype=arr.dtype)
assert idx.dtype == arr.dtype
expected = pd.Series([2, 1, 1], index=idx)
tm.assert_series_equal(result, expected)
result = arr.value_counts(dropna=True)
expected = pd.Series([2, 1], index=idx[:-1])
tm.assert_series_equal(result, expected)
def test_value_counts_empty():
ser = pd.Series([], dtype="Float64")
result = ser.value_counts()
idx = pd.Index([], dtype="Float64")
assert idx.dtype == "Float64"
expected = pd.Series([], index=idx, dtype="int64")
tm.assert_series_equal(result, expected)
def test_value_counts_with_normalize():
ser = pd.Series([0.1, 0.2, 0.1, pd.NA], dtype="Float64")
result = ser.value_counts(normalize=True)
expected = pd.Series([2, 1], index=ser[:2]) / 3
assert expected.index.dtype == ser.dtype
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("skipna", [True, False])
@pytest.mark.parametrize("min_count", [0, 4])
def test_floating_array_sum(skipna, min_count, dtype):
arr = pd.array([1, 2, 3, None], dtype=dtype)
result = arr.sum(skipna=skipna, min_count=min_count)
if skipna and min_count == 0:
assert result == 6.0
else:
assert result is pd.NA
@pytest.mark.parametrize(
"values, expected", [([1, 2, 3], 6.0), ([1, 2, 3, None], 6.0), ([None], 0.0)]
)
def test_floating_array_numpy_sum(values, expected):
arr = pd.array(values, dtype="Float64")
result = np.sum(arr)
assert result == expected
@pytest.mark.parametrize("op", ["sum", "min", "max", "prod"])
def test_preserve_dtypes(op):
df = pd.DataFrame(
{
"A": ["a", "b", "b"],
"B": [1, None, 3],
"C": pd.array([0.1, None, 3.0], dtype="Float64"),
}
)
# op
result = getattr(df.C, op)()
assert isinstance(result, np.float64)
# groupby
result = getattr(df.groupby("A"), op)()
expected = pd.DataFrame(
{"B": np.array([1.0, 3.0]), "C": pd.array([0.1, 3], dtype="Float64")},
index=pd.Index(["a", "b"], name="A"),
)
tm.assert_frame_equal(result, expected)
@pytest.mark.parametrize("skipna", [True, False])
@pytest.mark.parametrize("method", ["min", "max"])
def test_floating_array_min_max(skipna, method, dtype):
arr = pd.array([0.0, 1.0, None], dtype=dtype)
func = getattr(arr, method)
result = func(skipna=skipna)
if skipna:
assert result == (0 if method == "min" else 1)
else:
assert result is pd.NA
@pytest.mark.parametrize("skipna", [True, False])
@pytest.mark.parametrize("min_count", [0, 9])
def test_floating_array_prod(skipna, min_count, dtype):
arr = pd.array([1.0, 2.0, None], dtype=dtype)
result = arr.prod(skipna=skipna, min_count=min_count)
if skipna and min_count == 0:
assert result == 2
else:
assert result is pd.NA