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
|
import numpy as np
from numpy.testing import assert_array_equal
import pytest
from sklearn.feature_extraction import FeatureHasher
from sklearn.utils._testing import (ignore_warnings,
fails_if_pypy)
pytestmark = fails_if_pypy
def test_feature_hasher_dicts():
h = FeatureHasher(n_features=16)
assert "dict" == h.input_type
raw_X = [{"foo": "bar", "dada": 42, "tzara": 37},
{"foo": "baz", "gaga": "string1"}]
X1 = FeatureHasher(n_features=16).transform(raw_X)
gen = (iter(d.items()) for d in raw_X)
X2 = FeatureHasher(n_features=16, input_type="pair").transform(gen)
assert_array_equal(X1.toarray(), X2.toarray())
def test_feature_hasher_strings():
# mix byte and Unicode strings; note that "foo" is a duplicate in row 0
raw_X = [["foo", "bar", "baz", "foo".encode("ascii")],
["bar".encode("ascii"), "baz", "quux"]]
for lg_n_features in (7, 9, 11, 16, 22):
n_features = 2 ** lg_n_features
it = (x for x in raw_X) # iterable
h = FeatureHasher(n_features=n_features, input_type="string",
alternate_sign=False)
X = h.transform(it)
assert X.shape[0] == len(raw_X)
assert X.shape[1] == n_features
assert X[0].sum() == 4
assert X[1].sum() == 3
assert X.nnz == 6
def test_hashing_transform_seed():
# check the influence of the seed when computing the hashes
# import is here to avoid importing on pypy
from sklearn.feature_extraction._hashing_fast import (
transform as _hashing_transform)
raw_X = [["foo", "bar", "baz", "foo".encode("ascii")],
["bar".encode("ascii"), "baz", "quux"]]
raw_X_ = (((f, 1) for f in x) for x in raw_X)
indices, indptr, _ = _hashing_transform(raw_X_, 2 ** 7, str,
False)
raw_X_ = (((f, 1) for f in x) for x in raw_X)
indices_0, indptr_0, _ = _hashing_transform(raw_X_, 2 ** 7, str,
False, seed=0)
assert_array_equal(indices, indices_0)
assert_array_equal(indptr, indptr_0)
raw_X_ = (((f, 1) for f in x) for x in raw_X)
indices_1, _, _ = _hashing_transform(raw_X_, 2 ** 7, str,
False, seed=1)
with pytest.raises(AssertionError):
assert_array_equal(indices, indices_1)
def test_feature_hasher_pairs():
raw_X = (iter(d.items()) for d in [{"foo": 1, "bar": 2},
{"baz": 3, "quux": 4, "foo": -1}])
h = FeatureHasher(n_features=16, input_type="pair")
x1, x2 = h.transform(raw_X).toarray()
x1_nz = sorted(np.abs(x1[x1 != 0]))
x2_nz = sorted(np.abs(x2[x2 != 0]))
assert [1, 2] == x1_nz
assert [1, 3, 4] == x2_nz
def test_feature_hasher_pairs_with_string_values():
raw_X = (iter(d.items()) for d in [{"foo": 1, "bar": "a"},
{"baz": "abc", "quux": 4, "foo": -1}])
h = FeatureHasher(n_features=16, input_type="pair")
x1, x2 = h.transform(raw_X).toarray()
x1_nz = sorted(np.abs(x1[x1 != 0]))
x2_nz = sorted(np.abs(x2[x2 != 0]))
assert [1, 1] == x1_nz
assert [1, 1, 4] == x2_nz
raw_X = (iter(d.items()) for d in [{"bax": "abc"},
{"bax": "abc"}])
x1, x2 = h.transform(raw_X).toarray()
x1_nz = np.abs(x1[x1 != 0])
x2_nz = np.abs(x2[x2 != 0])
assert [1] == x1_nz
assert [1] == x2_nz
assert_array_equal(x1, x2)
def test_hash_empty_input():
n_features = 16
raw_X = [[], (), iter(range(0))]
h = FeatureHasher(n_features=n_features, input_type="string")
X = h.transform(raw_X)
assert_array_equal(X.A, np.zeros((len(raw_X), n_features)))
def test_hasher_invalid_input():
with pytest.raises(ValueError):
FeatureHasher(input_type="gobbledygook")
with pytest.raises(ValueError):
FeatureHasher(n_features=-1)
with pytest.raises(ValueError):
FeatureHasher(n_features=0)
with pytest.raises(TypeError):
FeatureHasher(n_features='ham')
h = FeatureHasher(n_features=np.uint16(2 ** 6))
with pytest.raises(ValueError):
h.transform([])
with pytest.raises(Exception):
h.transform([[5.5]])
with pytest.raises(Exception):
h.transform([[None]])
def test_hasher_set_params():
# Test delayed input validation in fit (useful for grid search).
hasher = FeatureHasher()
hasher.set_params(n_features=np.inf)
with pytest.raises(TypeError):
hasher.fit()
def test_hasher_zeros():
# Assert that no zeros are materialized in the output.
X = FeatureHasher().transform([{'foo': 0}])
assert X.data.shape == (0,)
@ignore_warnings(category=FutureWarning)
def test_hasher_alternate_sign():
X = [list("Thequickbrownfoxjumped")]
Xt = FeatureHasher(alternate_sign=True,
input_type='string').fit_transform(X)
assert Xt.data.min() < 0 and Xt.data.max() > 0
Xt = FeatureHasher(alternate_sign=False,
input_type='string').fit_transform(X)
assert Xt.data.min() > 0
def test_hash_collisions():
X = [list("Thequickbrownfoxjumped")]
Xt = FeatureHasher(alternate_sign=True, n_features=1,
input_type='string').fit_transform(X)
# check that some of the hashed tokens are added
# with an opposite sign and cancel out
assert abs(Xt.data[0]) < len(X[0])
Xt = FeatureHasher(alternate_sign=False, n_features=1,
input_type='string').fit_transform(X)
assert Xt.data[0] == len(X[0])
|
