-
Notifications
You must be signed in to change notification settings - Fork 41
/
Copy pathtest_dataset_slice.py
140 lines (113 loc) · 3.68 KB
/
test_dataset_slice.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
import os
import numpy as np
import pytest
import h5py
from continuum.datasets import InMemoryDataset, H5Dataset
@pytest.fixture
def dataset():
x = np.zeros((20, 4, 4, 3))
y = np.zeros((20,))
t = np.zeros((20,))
for i in range(20):
x[i] = i
c = 0
for i in range(0, 20, 2):
y[i] = c
y[i+1] = c
c += 1
for i in range(0, 20, 2):
t[i] = 1
return x, y, t
@pytest.fixture
def dataset2():
""""Dataset without task index"""
x = np.zeros((20, 4, 4, 3))
y = np.zeros((20,))
for i in range(20):
x[i] = i
c = 0
for i in range(0, 20, 2):
y[i] = c
y[i+1] = c
c += 1
return x, y, None
@pytest.mark.parametrize("keep_classes,discard_classes,keep_tasks,discard_tasks,error,ids", [
([1], [1], None, None, True, None),
(None, None, [1], [1], True, None),
(list(range(10)), None, None, None, False, list(range(20))),
([0, 1], None, None, None, False, [0, 1, 2, 3]),
(None, [0, 1], None, None, False, list(range(4, 20))),
(None, None, [0, 1], None, False, list(range(20))),
(None, None, [1], None, False, list(range(0, 20, 2))),
(None, None, None, [1], False, list(range(1, 20, 2))),
([0, 1], None, [1], None, False, [0, 2]),
])
def test_slice(
dataset,
keep_classes, discard_classes,
keep_tasks, discard_tasks,
error,
ids
):
dataset = InMemoryDataset(*dataset)
if error:
with pytest.raises(Exception):
sliced_dataset = dataset.slice(
keep_classes, discard_classes,
keep_tasks, discard_tasks
)
return
else:
sliced_dataset = dataset.slice(
keep_classes, discard_classes,
keep_tasks, discard_tasks
)
x, _, _ = sliced_dataset.get_data()
assert (np.unique(x) == np.array(ids)).all(), (np.unique(x), ids)
@pytest.mark.parametrize("keep_classes,discard_classes", [
([0, 1], None),
(None, [0, 1])
])
def test_slice_without_t(dataset2, keep_classes, discard_classes):
dataset = InMemoryDataset(*dataset2)
sliced_dataset = dataset.slice(keep_classes, discard_classes)
x, _, _ = sliced_dataset.get_data()
@pytest.mark.parametrize("keep_classes,discard_classes,keep_tasks,discard_tasks,error,ids", [
([1], [1], None, None, True, None),
(None, None, [1], [1], True, None),
(list(range(10)), None, None, None, False, list(range(20))),
([0, 1], None, None, None, False, [0, 1, 2, 3]),
(None, [0, 1], None, None, False, list(range(4, 20))),
(None, None, [0, 1], None, False, list(range(20))),
(None, None, [1], None, False, list(range(0, 20, 2))),
(None, None, None, [1], False, list(range(1, 20, 2))),
([0, 1], None, [1], None, False, [0, 2]),
])
def test_slice_h5(
tmpdir,
dataset,
keep_classes, discard_classes,
keep_tasks, discard_tasks,
error,
ids
):
dataset = H5Dataset(*dataset, data_path=os.path.join(tmpdir, "test.h5"))
if error:
with pytest.raises(Exception):
sliced_dataset = dataset.slice(
os.path.join(tmpdir, "test_bis.h5"),
keep_classes, discard_classes,
keep_tasks, discard_tasks
)
return
else:
sliced_dataset = dataset.slice(
os.path.join(tmpdir, "test_bis.h5"),
keep_classes, discard_classes,
keep_tasks, discard_tasks
)
h5_path, _, _ = sliced_dataset.get_data()
assert h5_path == os.path.join(tmpdir, "test_bis.h5")
with h5py.File(h5_path, 'r') as hf:
x = hf['x'][:]
assert (np.unique(x) == np.array(ids)).all(), (np.unique(x), ids)