Newer
Older
'''
Created on 12/09/2013
@author: mmpe
'''
import h5py
import numpy as np
from wetb import gtsdf
import unittest
import os
import shutil
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
f = "tmp/"
def setUp(self):
unittest.TestCase.setUp(self)
if not os.path.isdir(self.f):
os.makedirs(self.f)
def test_minimum_requirements (self):
fn = self.f + "minimum.hdf5"
f = h5py.File(fn, "w")
#no type
self.assertRaises(ValueError, gtsdf.load, fn)
f.attrs["type"] = "General time series data format"
#no no_blocks
self.assertRaises(ValueError, gtsdf.load, fn)
f.attrs["no_blocks"] = 0
#no block0000
self.assertRaises(ValueError, gtsdf.load, fn)
b = f.create_group("block0000")
#no data
self.assertRaises(ValueError, gtsdf.load, fn)
b.create_dataset("data", data=np.empty((0, 0)))
gtsdf.load(fn)
def test_save_no_hdf5_ext(self):
fn = self.f + "no_hdf5_ext"
gtsdf.save(fn, np.arange(12).reshape(4, 3))
_, _, info = gtsdf.load(fn + ".hdf5")
self.assertEqual(info['name'], 'no_hdf5_ext')
def test_load_filename(self):
fn = self.f + "filename.hdf5"
gtsdf.save(fn, np.arange(12).reshape(4, 3))
_, _, info = gtsdf.load(fn)
self.assertEqual(info['name'], 'filename')
def test_load_fileobject(self):
fn = self.f + "fileobject.hdf5"
gtsdf.save(fn, np.arange(12).reshape(4, 3))
_, _, info = gtsdf.load(fn)
self.assertEqual(info['name'], 'fileobject')
def test_save_wrong_no_attr_info(self):
fn = self.f + "wrong_no_attr_info.hdf5"
self.assertRaises(AssertionError, gtsdf.save, fn, np.arange(12).reshape(4, 3), attribute_names=['Att1'])
self.assertRaises(AssertionError, gtsdf.save, fn, np.arange(12).reshape(4, 3), attribute_units=['s'])
self.assertRaises(AssertionError, gtsdf.save, fn, np.arange(12).reshape(4, 3), attribute_descriptions=['desc'])
def test_info(self):
fn = self.f + "info.hdf5"
gtsdf.save(fn, np.arange(12).reshape(6, 2),
name='datasetname',
description='datasetdescription',
attribute_names=['att1', 'att2'],
attribute_units=['s', 'm/s'],
attribute_descriptions=['d1', 'd2'])
_, _, info = gtsdf.load(fn)
self.assertEqual(info['name'], "datasetname")
self.assertEqual(info['type'], "General time series data format")
self.assertEqual(info['description'], "datasetdescription")
self.assertEqual(list(info['attribute_names']), ['att1', 'att2'])
self.assertEqual(list(info['attribute_units']), ['s', 'm/s'])
self.assertEqual(list(info['attribute_descriptions']), ['d1', 'd2'])
def test_no_time(self):
fn = self.f + 'time.hdf5'
gtsdf.save(fn, np.arange(12).reshape(6, 2))
time, _, _ = gtsdf.load(fn)
np.testing.assert_array_equal(time, np.arange(6))
def test_int_time(self):
fn = self.f + 'time.hdf5'
gtsdf.save(fn, np.arange(12).reshape(6, 2), time=range(4, 10))
time, _, _ = gtsdf.load(fn)
np.testing.assert_array_equal(time, range(4, 10))
def test_time_offset(self):
fn = self.f + 'time.hdf5'
gtsdf.save(fn, np.arange(12).reshape(6, 2), time=range(6), time_start=4)
time, _, _ = gtsdf.load(fn)
np.testing.assert_array_equal(time, range(4, 10))
def test_time_gain_offset(self):
fn = self.f + 'time.hdf5'
gtsdf.save(fn, np.arange(12).reshape(6, 2), time=range(6), time_step=1 / 4, time_start=4)
time, _, _ = gtsdf.load(fn)
np.testing.assert_array_equal(time, np.arange(4, 5.5, .25))
def test_float_time(self):
fn = self.f + 'time.hdf5'
gtsdf.save(fn, np.arange(12).reshape(6, 2), time=np.arange(4, 5.5, .25))
time, _, _ = gtsdf.load(fn)
np.testing.assert_array_equal(time, np.arange(4, 5.5, .25))
def test_data(self):
fn = self.f + 'data.hdf5'
d = np.arange(12).reshape(6, 2)
gtsdf.save(fn, d)
f = h5py.File(fn)
self.assertEqual(f['block0000']['data'].dtype, np.uint16)
f.close()
_, data, _ = gtsdf.load(fn)
np.testing.assert_array_almost_equal(data, np.arange(12).reshape(6, 2), 4)
def test_data_float(self):
fn = self.f + 'time.hdf5'
d = np.arange(12).reshape(6, 2)
gtsdf.save(fn, d, dtype=np.float32)
f = h5py.File(fn)
self.assertEqual(f['block0000']['data'].dtype, np.float32)
f.close()
_, data, _ = gtsdf.load(fn)
np.testing.assert_array_equal(data, np.arange(12).reshape(6, 2))
def test_all(self):
fn = self.f + "all.hdf5"
gtsdf.save(fn, np.arange(12).reshape(6, 2),
name='datasetname',
time=range(6), time_step=1 / 4, time_start=4,
description='datasetdescription',
attribute_names=['att1', 'att2'],
attribute_units=['s', 'm/s'],
attribute_descriptions=['d1', 'd2'])
time, data, info = gtsdf.load(fn)
self.assertEqual(info['name'], "datasetname")
self.assertEqual(info['type'], "General time series data format")
self.assertEqual(info['description'], "datasetdescription")
self.assertEqual(list(info['attribute_names']), ['att1', 'att2'])
self.assertEqual(list(info['attribute_units']), ['s', 'm/s'])
self.assertEqual(list(info['attribute_descriptions']), ['d1', 'd2'])
np.testing.assert_array_equal(time, np.arange(4, 5.5, .25))
np.testing.assert_array_almost_equal(data, np.arange(12).reshape(6, 2), 4)
def test_append(self):
fn = self.f + 'append.hdf5'
d = np.arange(12, dtype=np.float32).reshape(6, 2)
d[2, 0] = np.nan
gtsdf.save(fn, d)
_, data, _ = gtsdf.load(fn)
np.testing.assert_array_almost_equal(data, d, 4)
gtsdf.append_block(fn, d)
_, data, _ = gtsdf.load(fn)
self.assertEqual(data.shape, (12, 2))
np.testing.assert_array_almost_equal(data, np.append(d, d, 0), 4)
def test_nan_float(self):
fn = self.f + 'nan.hdf5'
d = np.arange(12, dtype=np.float32).reshape(6, 2)
d[2, 0] = np.nan
gtsdf.save(fn, d)
_, data, _ = gtsdf.load(fn)
np.testing.assert_array_almost_equal(data, d, 4)
def test_outlier(self):
fn = self.f + 'outlier.hdf5'
d = np.arange(12, dtype=np.float32).reshape(6, 2)
d[2, 0] = 10 ** 4
d[3, 1] = 10 ** 4
self.assertRaises(Warning, gtsdf.save, fn, d)
_, data, _ = gtsdf.load(fn)
def test_inf(self):
fn = self.f + 'outlier.hdf5'
d = np.arange(12, dtype=np.float32).reshape(6, 2)
d[2, 0] = np.inf
d[3, 1] = 10 ** 3
self.assertRaises(ValueError, gtsdf.save, fn, d)
def test_loadpandas(self):
fn = self.f + "all.hdf5"
gtsdf.save(fn, np.arange(12).reshape(6, 2),
name='datasetname',
time=range(6), time_step=1 / 4, time_start=4,
description='datasetdescription',
attribute_names=['att1', 'att2'],
attribute_units=['s', 'm/s'],
attribute_descriptions=['d1', 'd2'])
df = gtsdf.load_pandas(fn)
if __name__ == "__main__":
#import sys;sys.argv = ['', 'Test.testName']
unittest.main()