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
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
|
from math import ceil
import pytest
import numpy as np
from numpy.testing import assert_allclose
from numpy.testing import assert_equal
from numpy.testing import assert_raises
from keras_preprocessing import sequence
def test_pad_sequences():
a = [[1], [1, 2], [1, 2, 3]]
# test padding
b = sequence.pad_sequences(a, maxlen=3, padding='pre')
assert_allclose(b, [[0, 0, 1], [0, 1, 2], [1, 2, 3]])
b = sequence.pad_sequences(a, maxlen=3, padding='post')
assert_allclose(b, [[1, 0, 0], [1, 2, 0], [1, 2, 3]])
# test truncating
b = sequence.pad_sequences(a, maxlen=2, truncating='pre')
assert_allclose(b, [[0, 1], [1, 2], [2, 3]])
b = sequence.pad_sequences(a, maxlen=2, truncating='post')
assert_allclose(b, [[0, 1], [1, 2], [1, 2]])
# test value
b = sequence.pad_sequences(a, maxlen=3, value=1)
assert_allclose(b, [[1, 1, 1], [1, 1, 2], [1, 2, 3]])
def test_pad_sequences_str():
a = [['1'], ['1', '2'], ['1', '2', '3']]
# test padding
b = sequence.pad_sequences(a, maxlen=3, padding='pre', value='pad', dtype=object)
assert_equal(b, [['pad', 'pad', '1'], ['pad', '1', '2'], ['1', '2', '3']])
b = sequence.pad_sequences(a, maxlen=3, padding='post', value='pad', dtype='<U3')
assert_equal(b, [['1', 'pad', 'pad'], ['1', '2', 'pad'], ['1', '2', '3']])
# test truncating
b = sequence.pad_sequences(a, maxlen=2, truncating='pre', value='pad',
dtype=object)
assert_equal(b, [['pad', '1'], ['1', '2'], ['2', '3']])
b = sequence.pad_sequences(a, maxlen=2, truncating='post', value='pad',
dtype='<U3')
assert_equal(b, [['pad', '1'], ['1', '2'], ['1', '2']])
with pytest.raises(ValueError, match="`dtype` int32 is not compatible with "):
sequence.pad_sequences(a, maxlen=2, truncating='post', value='pad')
def test_pad_sequences_vector():
a = [[[1, 1]],
[[2, 1], [2, 2]],
[[3, 1], [3, 2], [3, 3]]]
# test padding
b = sequence.pad_sequences(a, maxlen=3, padding='pre')
assert_allclose(b, [[[0, 0], [0, 0], [1, 1]],
[[0, 0], [2, 1], [2, 2]],
[[3, 1], [3, 2], [3, 3]]])
b = sequence.pad_sequences(a, maxlen=3, padding='post')
assert_allclose(b, [[[1, 1], [0, 0], [0, 0]],
[[2, 1], [2, 2], [0, 0]],
[[3, 1], [3, 2], [3, 3]]])
# test truncating
b = sequence.pad_sequences(a, maxlen=2, truncating='pre')
assert_allclose(b, [[[0, 0], [1, 1]],
[[2, 1], [2, 2]],
[[3, 2], [3, 3]]])
b = sequence.pad_sequences(a, maxlen=2, truncating='post')
assert_allclose(b, [[[0, 0], [1, 1]],
[[2, 1], [2, 2]],
[[3, 1], [3, 2]]])
# test value
b = sequence.pad_sequences(a, maxlen=3, value=1)
assert_allclose(b, [[[1, 1], [1, 1], [1, 1]],
[[1, 1], [2, 1], [2, 2]],
[[3, 1], [3, 2], [3, 3]]])
def test_make_sampling_table():
a = sequence.make_sampling_table(3)
assert_allclose(a, np.asarray([0.00315225, 0.00315225, 0.00547597]),
rtol=.1)
def test_skipgrams():
# test with no window size and binary labels
couples, labels = sequence.skipgrams(np.arange(3), vocabulary_size=3)
for couple in couples:
assert couple[0] in [0, 1, 2] and couple[1] in [0, 1, 2]
# test window size and categorical labels
couples, labels = sequence.skipgrams(np.arange(5),
vocabulary_size=5,
window_size=1,
categorical=True)
for couple in couples:
assert couple[0] - couple[1] <= 3
for l in labels:
assert len(l) == 2
def test_remove_long_seq():
maxlen = 5
seq = [
[1, 2, 3],
[1, 2, 3, 4, 5, 6],
]
label = ['a', 'b']
new_seq, new_label = sequence._remove_long_seq(maxlen, seq, label)
assert new_seq == [[1, 2, 3]]
assert new_label == ['a']
def test_TimeseriesGenerator_serde():
data = np.array([[i] for i in range(50)])
targets = np.array([[i] for i in range(50)])
data_gen = sequence.TimeseriesGenerator(data, targets,
length=10,
sampling_rate=2,
batch_size=2)
json_gen = data_gen.to_json()
recovered_gen = sequence.timeseries_generator_from_json(json_gen)
assert data_gen.batch_size == recovered_gen.batch_size
assert data_gen.end_index == recovered_gen.end_index
assert data_gen.length == recovered_gen.length
assert data_gen.reverse == recovered_gen.reverse
assert data_gen.sampling_rate == recovered_gen.sampling_rate
assert data_gen.shuffle == recovered_gen.shuffle
assert data_gen.start_index == data_gen.start_index
assert data_gen.stride == data_gen.stride
assert (data_gen.data == recovered_gen.data).all()
assert (data_gen.targets == recovered_gen.targets).all()
def test_TimeseriesGenerator():
data = np.array([[i] for i in range(50)])
targets = np.array([[i] for i in range(50)])
data_gen = sequence.TimeseriesGenerator(data, targets,
length=10,
sampling_rate=2,
batch_size=2)
assert len(data_gen) == 20
assert (np.allclose(data_gen[0][0],
np.array([[[0], [2], [4], [6], [8]],
[[1], [3], [5], [7], [9]]])))
assert (np.allclose(data_gen[0][1],
np.array([[10], [11]])))
assert (np.allclose(data_gen[1][0],
np.array([[[2], [4], [6], [8], [10]],
[[3], [5], [7], [9], [11]]])))
assert (np.allclose(data_gen[1][1],
np.array([[12], [13]])))
data_gen = sequence.TimeseriesGenerator(data, targets,
length=10,
sampling_rate=2,
reverse=True,
batch_size=2)
assert len(data_gen) == 20
assert (np.allclose(data_gen[0][0],
np.array([[[8], [6], [4], [2], [0]],
[[9], [7], [5], [3], [1]]])))
assert (np.allclose(data_gen[0][1],
np.array([[10], [11]])))
data_gen = sequence.TimeseriesGenerator(data, targets,
length=10,
sampling_rate=2,
shuffle=True,
batch_size=1)
batch = data_gen[0]
r = batch[1][0][0]
assert (np.allclose(batch[0],
np.array([[[r - 10],
[r - 8],
[r - 6],
[r - 4],
[r - 2]]])))
assert (np.allclose(batch[1], np.array([[r], ])))
data_gen = sequence.TimeseriesGenerator(data, targets,
length=10,
sampling_rate=2,
stride=2,
batch_size=2)
assert len(data_gen) == 10
assert (np.allclose(data_gen[1][0],
np.array([[[4], [6], [8], [10], [12]],
[[6], [8], [10], [12], [14]]])))
assert (np.allclose(data_gen[1][1],
np.array([[14], [16]])))
data_gen = sequence.TimeseriesGenerator(data, targets,
length=10,
sampling_rate=2,
start_index=10,
end_index=30,
batch_size=2)
assert len(data_gen) == 6
assert (np.allclose(data_gen[0][0],
np.array([[[10], [12], [14], [16], [18]],
[[11], [13], [15], [17], [19]]])))
assert (np.allclose(data_gen[0][1],
np.array([[20], [21]])))
data = np.array([np.random.random_sample((1, 2, 3, 4)) for i in range(50)])
targets = np.array([np.random.random_sample((3, 2, 1)) for i in range(50)])
data_gen = sequence.TimeseriesGenerator(data, targets,
length=10,
sampling_rate=2,
start_index=10,
end_index=30,
batch_size=2)
assert len(data_gen) == 6
assert np.allclose(data_gen[0][0], np.array(
[np.array(data[10:19:2]), np.array(data[11:20:2])]))
assert (np.allclose(data_gen[0][1],
np.array([targets[20], targets[21]])))
with assert_raises(ValueError) as context:
sequence.TimeseriesGenerator(data, targets, length=50)
error = str(context.exception)
assert '`start_index+length=50 > end_index=49` is disallowed' in error
def test_TimeSeriesGenerator_doesnt_miss_any_sample():
x = np.array([[i] for i in range(10)])
for length in range(3, 10):
g = sequence.TimeseriesGenerator(x, x,
length=length,
batch_size=1)
expected = max(0, len(x) - length)
actual = len(g)
assert expected == actual
if len(g) > 0:
# All elements in range(length, 10) should be used as current step
expected = np.arange(length, 10).reshape(-1, 1)
y = np.concatenate([g[ix][1] for ix in range(len(g))], axis=0)
assert_allclose(y, expected)
x = np.array([[i] for i in range(23)])
strides = (1, 1, 5, 7, 3, 5, 3)
lengths = (3, 3, 4, 3, 1, 3, 7)
batch_sizes = (6, 6, 6, 5, 6, 6, 6)
shuffles = (False, True, True, False, False, False, False)
for stride, length, batch_size, shuffle in zip(strides,
lengths,
batch_sizes,
shuffles):
g = sequence.TimeseriesGenerator(x, x,
length=length,
sampling_rate=1,
stride=stride,
start_index=0,
end_index=None,
shuffle=shuffle,
reverse=False,
batch_size=batch_size)
if shuffle:
# all batches have the same size when shuffle is True.
expected_sequences = ceil(
(23 - length) / float(batch_size * stride)) * batch_size
else:
# last batch will be different if `(samples - length) / stride`
# is not a multiple of `batch_size`.
expected_sequences = ceil((23 - length) / float(stride))
expected_batches = ceil(expected_sequences / float(batch_size))
y = [g[ix][1] for ix in range(len(g))]
actual_sequences = sum(len(_y) for _y in y)
actual_batches = len(y)
assert expected_sequences == actual_sequences
assert expected_batches == actual_batches
if __name__ == '__main__':
pytest.main([__file__])
|
