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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
|
import pytest
import numpy as np
from scipy import sparse
from sklearn.preprocessing import FunctionTransformer
from sklearn.utils.testing import (assert_equal, assert_array_equal,
assert_allclose_dense_sparse)
from sklearn.utils.testing import assert_warns_message, assert_no_warnings
from sklearn.utils.testing import ignore_warnings
def _make_func(args_store, kwargs_store, func=lambda X, *a, **k: X):
def _func(X, *args, **kwargs):
args_store.append(X)
args_store.extend(args)
kwargs_store.update(kwargs)
return func(X)
return _func
def test_delegate_to_func():
# (args|kwargs)_store will hold the positional and keyword arguments
# passed to the function inside the FunctionTransformer.
args_store = []
kwargs_store = {}
X = np.arange(10).reshape((5, 2))
assert_array_equal(
FunctionTransformer(_make_func(args_store, kwargs_store),
validate=False).transform(X),
X, 'transform should have returned X unchanged',
)
# The function should only have received X.
assert_equal(
args_store,
[X],
'Incorrect positional arguments passed to func: {args}'.format(
args=args_store,
),
)
assert_equal(
kwargs_store,
{},
'Unexpected keyword arguments passed to func: {args}'.format(
args=kwargs_store,
),
)
# reset the argument stores.
args_store[:] = [] # python2 compatible inplace list clear.
kwargs_store.clear()
y = object()
transformed = assert_warns_message(
DeprecationWarning, "pass_y is deprecated",
FunctionTransformer(
_make_func(args_store, kwargs_store),
pass_y=True, validate=False).transform, X, y)
assert_array_equal(transformed, X,
err_msg='transform should have returned X unchanged')
# The function should have received X and y.
assert_equal(
args_store,
[X, y],
'Incorrect positional arguments passed to func: {args}'.format(
args=args_store,
),
)
assert_equal(
kwargs_store,
{},
'Unexpected keyword arguments passed to func: {args}'.format(
args=kwargs_store,
),
)
@ignore_warnings(category=FutureWarning)
# ignore warning for validate=False 0.22
def test_np_log():
X = np.arange(10).reshape((5, 2))
# Test that the numpy.log example still works.
assert_array_equal(
FunctionTransformer(np.log1p).transform(X),
np.log1p(X),
)
@ignore_warnings(category=FutureWarning)
# ignore warning for validate=False 0.22
def test_kw_arg():
X = np.linspace(0, 1, num=10).reshape((5, 2))
F = FunctionTransformer(np.around, kw_args=dict(decimals=3))
# Test that rounding is correct
assert_array_equal(F.transform(X),
np.around(X, decimals=3))
@ignore_warnings(category=FutureWarning)
# ignore warning for validate=False 0.22
def test_kw_arg_update():
X = np.linspace(0, 1, num=10).reshape((5, 2))
F = FunctionTransformer(np.around, kw_args=dict(decimals=3))
F.kw_args['decimals'] = 1
# Test that rounding is correct
assert_array_equal(F.transform(X), np.around(X, decimals=1))
@ignore_warnings(category=FutureWarning)
# ignore warning for validate=False 0.22
def test_kw_arg_reset():
X = np.linspace(0, 1, num=10).reshape((5, 2))
F = FunctionTransformer(np.around, kw_args=dict(decimals=3))
F.kw_args = dict(decimals=1)
# Test that rounding is correct
assert_array_equal(F.transform(X), np.around(X, decimals=1))
@ignore_warnings(category=FutureWarning)
# ignore warning for validate=False 0.22
def test_inverse_transform():
X = np.array([1, 4, 9, 16]).reshape((2, 2))
# Test that inverse_transform works correctly
F = FunctionTransformer(
func=np.sqrt,
inverse_func=np.around, inv_kw_args=dict(decimals=3),
)
assert_array_equal(
F.inverse_transform(F.transform(X)),
np.around(np.sqrt(X), decimals=3),
)
@ignore_warnings(category=FutureWarning)
# ignore warning for validate=False 0.22
def test_check_inverse():
X_dense = np.array([1, 4, 9, 16], dtype=np.float64).reshape((2, 2))
X_list = [X_dense,
sparse.csr_matrix(X_dense),
sparse.csc_matrix(X_dense)]
for X in X_list:
if sparse.issparse(X):
accept_sparse = True
else:
accept_sparse = False
trans = FunctionTransformer(func=np.sqrt,
inverse_func=np.around,
accept_sparse=accept_sparse,
check_inverse=True,
validate=True)
assert_warns_message(UserWarning,
"The provided functions are not strictly"
" inverse of each other. If you are sure you"
" want to proceed regardless, set"
" 'check_inverse=False'.",
trans.fit, X)
trans = FunctionTransformer(func=np.expm1,
inverse_func=np.log1p,
accept_sparse=accept_sparse,
check_inverse=True,
validate=True)
Xt = assert_no_warnings(trans.fit_transform, X)
assert_allclose_dense_sparse(X, trans.inverse_transform(Xt))
# check that we don't check inverse when one of the func or inverse is not
# provided.
trans = FunctionTransformer(func=np.expm1, inverse_func=None,
check_inverse=True, validate=True)
assert_no_warnings(trans.fit, X_dense)
trans = FunctionTransformer(func=None, inverse_func=np.expm1,
check_inverse=True, validate=True)
assert_no_warnings(trans.fit, X_dense)
@pytest.mark.parametrize("validate, expected_warning",
[(None, FutureWarning),
(True, None),
(False, None)])
def test_function_transformer_future_warning(validate, expected_warning):
# FIXME: to be removed in 0.22
X = np.random.randn(100, 10)
transformer = FunctionTransformer(validate=validate)
with pytest.warns(expected_warning) as results:
transformer.fit_transform(X)
if expected_warning is None:
assert len(results) == 0
def test_function_transformer_frame():
pd = pytest.importorskip('pandas')
X_df = pd.DataFrame(np.random.randn(100, 10))
transformer = FunctionTransformer(validate=False)
X_df_trans = transformer.fit_transform(X_df)
assert hasattr(X_df_trans, 'loc')
|
