-
Notifications
You must be signed in to change notification settings - Fork 82
/
test_simple_imputer.py
151 lines (124 loc) · 6.16 KB
/
test_simple_imputer.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
import numpy as np
import pandas as pd
import pytest
from pandas.testing import assert_frame_equal
from evalml.pipelines.components import SimpleImputer
def test_median():
X = pd.DataFrame([[np.nan, 0, 1, np.nan],
[1, 2, 3, 2],
[10, 2, np.nan, 2],
[10, 2, 5, np.nan],
[6, 2, 7, 0]])
transformer = SimpleImputer(impute_strategy='median')
X_expected_arr = pd.DataFrame([[8, 0, 1, 2],
[1, 2, 3, 2],
[10, 2, 4, 2],
[10, 2, 5, 2],
[6, 2, 7, 0]])
X_t = transformer.fit_transform(X)
assert_frame_equal(X_expected_arr, X_t, check_dtype=False)
def test_mean():
X = pd.DataFrame([[np.nan, 0, 1, np.nan],
[1, 2, 3, 2],
[1, 2, 3, 0]])
# test impute_strategy
transformer = SimpleImputer(impute_strategy='mean')
X_expected_arr = pd.DataFrame([[1, 0, 1, 1],
[1, 2, 3, 2],
[1, 2, 3, 0]])
X_t = transformer.fit_transform(X)
assert_frame_equal(X_expected_arr, X_t, check_dtype=False)
def test_constant():
# test impute strategy is constant and fill value is not specified
X = pd.DataFrame([[np.nan, 0, 1, np.nan],
["a", 2, np.nan, 3],
["b", 2, 3, 0]])
transformer = SimpleImputer(impute_strategy='constant', fill_value=3)
X_expected_arr = pd.DataFrame([[3, 0, 1, 3],
["a", 2, 3, 3],
["b", 2, 3, 0]])
X_t = transformer.fit_transform(X)
assert_frame_equal(X_expected_arr, X_t, check_dtype=False)
def test_most_frequent():
X = pd.DataFrame([[np.nan, 0, 1, np.nan],
["a", 2, np.nan, 3],
["b", 2, 1, 0]])
transformer = SimpleImputer(impute_strategy='most_frequent')
X_expected_arr = pd.DataFrame([["a", 0, 1, 0],
["a", 2, 1, 3],
["b", 2, 1, 0]])
X_t = transformer.fit_transform(X)
assert_frame_equal(X_expected_arr, X_t, check_dtype=False)
def test_col_with_non_numeric():
# test col with all strings
X = pd.DataFrame([["a", 0, 1, np.nan],
["b", 2, 3, 3],
["a", 2, 3, 1],
[np.nan, 2, 3, 0]])
transformer = SimpleImputer(impute_strategy='mean')
with pytest.raises(ValueError, match="Cannot use mean strategy with non-numeric data"):
transformer.fit_transform(X)
with pytest.raises(ValueError, match="Cannot use mean strategy with non-numeric data"):
transformer.fit(X)
transformer = SimpleImputer(impute_strategy='median')
with pytest.raises(ValueError, match="Cannot use median strategy with non-numeric data"):
transformer.fit_transform(X)
with pytest.raises(ValueError, match="Cannot use median strategy with non-numeric data"):
transformer.fit(X)
transformer = SimpleImputer(impute_strategy='most_frequent')
X_expected_arr = pd.DataFrame([["a", 0, 1, 0],
["b", 2, 3, 3],
["a", 2, 3, 1],
["a", 2, 3, 0]])
X_t = transformer.fit_transform(X)
assert_frame_equal(X_expected_arr, X_t, check_dtype=False)
transformer = SimpleImputer(impute_strategy='constant', fill_value=2)
X_expected_arr = pd.DataFrame([["a", 0, 1, 2],
["b", 2, 3, 3],
["a", 2, 3, 1],
[2, 2, 3, 0]])
X_t = transformer.fit_transform(X)
assert_frame_equal(X_expected_arr, X_t, check_dtype=False)
def test_fit_transform_drop_all_nan_columns():
X = pd.DataFrame({"all_nan": [np.nan, np.nan, np.nan],
"some_nan": [np.nan, 1, 0],
"another_col": [0, 1, 2]})
transformer = SimpleImputer(impute_strategy='most_frequent')
X_expected_arr = pd.DataFrame({"some_nan": [0, 1, 0], "another_col": [0, 1, 2]})
X_t = transformer.fit_transform(X)
assert_frame_equal(X_expected_arr, X_t, check_dtype=False)
assert_frame_equal(X, pd.DataFrame({"all_nan": [np.nan, np.nan, np.nan],
"some_nan": [np.nan, 1, 0],
"another_col": [0, 1, 2]}))
def test_transform_drop_all_nan_columns():
X = pd.DataFrame({"all_nan": [np.nan, np.nan, np.nan],
"some_nan": [np.nan, 1, 0],
"another_col": [0, 1, 2]})
transformer = SimpleImputer(impute_strategy='most_frequent')
transformer.fit(X)
X_expected_arr = pd.DataFrame({"some_nan": [0, 1, 0], "another_col": [0, 1, 2]})
assert_frame_equal(X_expected_arr, transformer.transform(X), check_dtype=False)
assert_frame_equal(X, pd.DataFrame({"all_nan": [np.nan, np.nan, np.nan],
"some_nan": [np.nan, 1, 0],
"another_col": [0, 1, 2]}))
def test_transform_drop_all_nan_columns_empty():
X = pd.DataFrame([[np.nan, np.nan, np.nan]])
transformer = SimpleImputer(impute_strategy='most_frequent')
assert transformer.fit_transform(X).empty
assert_frame_equal(X, pd.DataFrame([[np.nan, np.nan, np.nan]]))
transformer = SimpleImputer(impute_strategy='most_frequent')
transformer.fit(X)
assert transformer.transform(X).empty
assert_frame_equal(X, pd.DataFrame([[np.nan, np.nan, np.nan]]))
def test_numpy_input():
X = np.array([[np.nan, 0, 1, np.nan],
[np.nan, 2, 3, 2],
[np.nan, 2, 3, 0]])
transformer = SimpleImputer(impute_strategy='mean')
X_expected_arr = np.array([[0, 1, 1],
[2, 3, 2],
[2, 3, 0]])
assert np.allclose(X_expected_arr, transformer.fit_transform(X))
np.testing.assert_almost_equal(X, np.array([[np.nan, 0, 1, np.nan],
[np.nan, 2, 3, 2],
[np.nan, 2, 3, 0]]))