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
|
"""Test functionality of mldata fetching utilities."""
import os
import scipy as sp
import shutil
from sklearn import datasets
from sklearn.datasets import mldata_filename, fetch_mldata
from sklearn.utils.testing import assert_in
from sklearn.utils.testing import assert_not_in
from sklearn.utils.testing import mock_mldata_urlopen
from sklearn.utils.testing import assert_equal
from sklearn.utils.testing import assert_raises
from sklearn.utils.testing import assert_array_equal
from sklearn.utils.testing import assert_warns
import pytest
@pytest.fixture(scope='module')
def tmpdata(tmpdir_factory):
tmpdir = tmpdir_factory.mktemp('tmp')
tmpdir_path = str(tmpdir.join('mldata'))
os.makedirs(tmpdir_path)
yield str(tmpdir)
shutil.rmtree(str(tmpdir))
@pytest.mark.filterwarnings('ignore::DeprecationWarning')
def test_mldata_filename():
cases = [('datasets-UCI iris', 'datasets-uci-iris'),
('news20.binary', 'news20binary'),
('book-crossing-ratings-1.0', 'book-crossing-ratings-10'),
('Nile Water Level', 'nile-water-level'),
('MNIST (original)', 'mnist-original')]
for name, desired in cases:
assert_equal(mldata_filename(name), desired)
@pytest.mark.filterwarnings('ignore::DeprecationWarning')
def test_download(tmpdata):
"""Test that fetch_mldata is able to download and cache a data set."""
_urlopen_ref = datasets.mldata.urlopen
datasets.mldata.urlopen = mock_mldata_urlopen({
'mock': {
'label': sp.ones((150,)),
'data': sp.ones((150, 4)),
},
})
try:
mock = assert_warns(DeprecationWarning, fetch_mldata,
'mock', data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data"]:
assert_in(n, mock)
assert_equal(mock.target.shape, (150,))
assert_equal(mock.data.shape, (150, 4))
assert_raises(datasets.mldata.HTTPError,
assert_warns, DeprecationWarning,
fetch_mldata, 'not_existing_name')
finally:
datasets.mldata.urlopen = _urlopen_ref
@pytest.mark.filterwarnings('ignore::DeprecationWarning')
def test_fetch_one_column(tmpdata):
_urlopen_ref = datasets.mldata.urlopen
try:
dataname = 'onecol'
# create fake data set in cache
x = sp.arange(6).reshape(2, 3)
datasets.mldata.urlopen = mock_mldata_urlopen({dataname: {'x': x}})
dset = fetch_mldata(dataname, data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "data"]:
assert_in(n, dset)
assert_not_in("target", dset)
assert_equal(dset.data.shape, (2, 3))
assert_array_equal(dset.data, x)
# transposing the data array
dset = fetch_mldata(dataname, transpose_data=False, data_home=tmpdata)
assert_equal(dset.data.shape, (3, 2))
finally:
datasets.mldata.urlopen = _urlopen_ref
@pytest.mark.filterwarnings('ignore::DeprecationWarning')
def test_fetch_multiple_column(tmpdata):
_urlopen_ref = datasets.mldata.urlopen
try:
# create fake data set in cache
x = sp.arange(6).reshape(2, 3)
y = sp.array([1, -1])
z = sp.arange(12).reshape(4, 3)
# by default
dataname = 'threecol-default'
datasets.mldata.urlopen = mock_mldata_urlopen({
dataname: (
{
'label': y,
'data': x,
'z': z,
},
['z', 'data', 'label'],
),
})
dset = fetch_mldata(dataname, data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data", "z"]:
assert_in(n, dset)
assert_not_in("x", dset)
assert_not_in("y", dset)
assert_array_equal(dset.data, x)
assert_array_equal(dset.target, y)
assert_array_equal(dset.z, z.T)
# by order
dataname = 'threecol-order'
datasets.mldata.urlopen = mock_mldata_urlopen({
dataname: ({'y': y, 'x': x, 'z': z},
['y', 'x', 'z']), })
dset = fetch_mldata(dataname, data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data", "z"]:
assert_in(n, dset)
assert_not_in("x", dset)
assert_not_in("y", dset)
assert_array_equal(dset.data, x)
assert_array_equal(dset.target, y)
assert_array_equal(dset.z, z.T)
# by number
dataname = 'threecol-number'
datasets.mldata.urlopen = mock_mldata_urlopen({
dataname: ({'y': y, 'x': x, 'z': z},
['z', 'x', 'y']),
})
dset = fetch_mldata(dataname, target_name=2, data_name=0,
data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data", "x"]:
assert_in(n, dset)
assert_not_in("y", dset)
assert_not_in("z", dset)
assert_array_equal(dset.data, z)
assert_array_equal(dset.target, y)
# by name
dset = fetch_mldata(dataname, target_name='y', data_name='z',
data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data", "x"]:
assert_in(n, dset)
assert_not_in("y", dset)
assert_not_in("z", dset)
finally:
datasets.mldata.urlopen = _urlopen_ref
|
