-
-
Notifications
You must be signed in to change notification settings - Fork 395
/
testmultiinterface.py
185 lines (152 loc) · 8.57 KB
/
testmultiinterface.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
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
"""
Tests for the Dataset Element types.
"""
from unittest import SkipTest
import numpy as np
from holoviews.core.data import Dataset
from holoviews.core.data.interface import DataError
from holoviews.element import Path
from holoviews.element.comparison import ComparisonTestCase
try:
import pandas as pd
except:
pd = None
try:
import dask.dataframe as dd
except:
dd = None
class MultiInterfaceTest(ComparisonTestCase):
"""
Test of the MultiInterface.
"""
def test_multi_array_dataset(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
for i, ds in enumerate(mds.split()):
self.assertEqual(ds, Path(arrays[i], kdims=['x', 'y'], datatype=['array']))
def test_multi_dict_dataset(self):
arrays = [{'x': np.arange(i, i+2), 'y': np.arange(i, i+2)} for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
for i, ds in enumerate(mds.split()):
self.assertEqual(ds, Path(arrays[i], kdims=['x', 'y'], datatype=['dictionary']))
def test_multi_df_dataset(self):
if not pd:
raise SkipTest('Pandas not available')
arrays = [pd.DataFrame(np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]), columns=['x', 'y'])
for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
for i, ds in enumerate(mds.split()):
self.assertEqual(ds, Path(arrays[i], kdims=['x', 'y'], datatype=['dataframe']))
def test_multi_dask_df_dataset(self):
if not dd:
raise SkipTest('Dask not available')
arrays = [dd.from_pandas(pd.DataFrame(np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]),
columns=['x', 'y']), npartitions=2)
for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
for i, ds in enumerate(mds.split()):
self.assertEqual(ds, Path(arrays[i], kdims=['x', 'y'], datatype=['dask']))
def test_multi_array_dataset_add_dimension_scalar(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular']).add_dimension('A', 0, 'Scalar', True)
for i, ds in enumerate(mds.split()):
self.assertEqual(ds, Path({('x', 'y'): arrays[i], 'A': 'Scalar'}, ['x', 'y'],
'A', datatype=['dictionary']))
def test_multi_dict_dataset_add_dimension_scalar(self):
arrays = [{'x': np.arange(i, i+2), 'y': np.arange(i, i+2)} for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular']).add_dimension('A', 0, 'Scalar', True)
for i, ds in enumerate(mds.split()):
self.assertEqual(ds, Path(dict(arrays[i], A='Scalar'), ['x', 'y'],
'A', datatype=['dictionary']))
def test_multi_dict_dataset_add_dimension_values(self):
arrays = [{'x': np.arange(i, i+2), 'y': np.arange(i, i+2)} for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular']).add_dimension('A', 0, [0,1], True)
for i, ds in enumerate(mds.split()):
self.assertEqual(ds, Path(dict(arrays[i], A=i), ['x', 'y'],
'A', datatype=['dictionary']))
def test_multi_array_length(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(len(mds), 5)
def test_multi_empty_length(self):
mds = Path([], kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(len(mds), 0)
def test_multi_array_range(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(mds.range(0), (0, 2))
def test_multi_empty_range(self):
mds = Path([], kdims=['x', 'y'], datatype=['multitabular'])
low, high = mds.range(0)
self.assertFalse(np.isfinite(np.NaN))
self.assertFalse(np.isfinite(np.NaN))
def test_multi_array_shape(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(mds.shape, (5, 2))
def test_multi_empty_shape(self):
mds = Path([], kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(mds.shape, (0, 2))
def test_multi_array_values(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(mds.dimension_values(0), np.array([0., 1, np.NaN, 1, 2]))
def test_multi_empty_array_values(self):
mds = Path([], kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(mds.dimension_values(0), np.array([]))
def test_multi_array_values_coordinates_nonexpanded(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(mds.dimension_values(0, expanded=False), np.array([0., 1, 1, 2]))
def test_multi_array_values_coordinates_nonexpanded_constant_kdim(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2), np.ones(2)*i]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], vdims=['z'], datatype=['multitabular'])
self.assertEqual(mds.dimension_values(2, expanded=False), np.array([0, 1]))
def test_multi_array_redim(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular']).redim(x='x2')
for i, ds in enumerate(mds.split()):
self.assertEqual(ds, Path(arrays[i], kdims=['x2', 'y']))
def test_multi_mixed_interface_raises(self):
arrays = [np.random.rand(10, 2) if j else {'x': range(10), 'y': range(10)}
for i in range(2) for j in range(2)]
with self.assertRaises(DataError):
Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
def test_multi_mixed_dims_raises(self):
arrays = [{'x': range(10), 'y' if j else 'z': range(10)}
for i in range(2) for j in range(2)]
with self.assertRaises(DataError):
Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
def test_multi_split(self):
arrays = [np.column_stack([np.arange(i, i+2), np.arange(i, i+2)]) for i in range(2)]
mds = Path(arrays, kdims=['x', 'y'], datatype=['multitabular'])
for arr1, arr2 in zip(mds.split(datatype='array'), arrays):
self.assertEqual(arr1, arr2)
def test_multi_split_empty(self):
mds = Path([], kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(len(mds.split()), 0)
def test_multi_values_empty(self):
mds = Path([], kdims=['x', 'y'], datatype=['multitabular'])
self.assertEqual(mds.dimension_values(0), np.array([]))
def test_multi_dict_groupby(self):
arrays = [{'x': np.arange(i, i+2), 'y': i} for i in range(2)]
mds = Dataset(arrays, kdims=['x', 'y'], datatype=['multitabular'])
for i, (k, ds) in enumerate(mds.groupby('y').items()):
self.assertEqual(k, arrays[i]['y'])
self.assertEqual(ds, Dataset([arrays[i]], kdims=['x']))
def test_multi_dict_groupby_non_scalar(self):
arrays = [{'x': np.arange(i, i+2), 'y': i} for i in range(2)]
mds = Dataset(arrays, kdims=['x', 'y'], datatype=['multitabular'])
with self.assertRaises(ValueError):
mds.groupby('x')
def test_multi_array_groupby(self):
arrays = [np.array([(1+i, i), (2+i, i), (3+i, i)]) for i in range(2)]
mds = Dataset(arrays, kdims=['x', 'y'], datatype=['multitabular'])
for i, (k, ds) in enumerate(mds.groupby('y').items()):
self.assertEqual(k, arrays[i][0, 1])
self.assertEqual(ds, Dataset([arrays[i]], kdims=['x']))
def test_multi_array_groupby_non_scalar(self):
arrays = [np.array([(1+i, i), (2+i, i), (3+i, i)]) for i in range(2)]
mds = Dataset(arrays, kdims=['x', 'y'], datatype=['multitabular'])
with self.assertRaises(ValueError):
mds.groupby('x')