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
|
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import numpy as np
import numpy.testing as npt
import pandas as pd
from unittest import TestCase, main
from skbio import OrdinationResults
from skbio.stats.ordination import rda
from skbio.util import get_data_path, assert_ordination_results_equal
class TestRDAErrors(TestCase):
def setUp(self):
pass
def test_shape(self):
for n, p, n_, m in [(3, 4, 2, 1), (3, 4, 3, 10)]:
Y = pd.DataFrame(np.random.randn(n, p))
X = pd.DataFrame(np.random.randn(n_, m))
yield npt.assert_raises, ValueError, rda, Y, X, None, None
class TestRDAResults(TestCase):
# STATUS: L&L only shows results with scaling 1, and they agree
# with vegan's (module multiplying by a constant). I can also
# compute scaling 2, agreeing with vegan, but there are no written
# results in L&L.
def setUp(self):
"""Data from table 11.3 in Legendre & Legendre 1998."""
self.sample_ids = ['Site0', 'Site1', 'Site2', 'Site3', 'Site4',
'Site5', 'Site6', 'Site7', 'Site8', 'Site9']
self.feature_ids = ['Species0', 'Species1', 'Species2', 'Species3',
'Species4', 'Species5']
self.env_ids = list(map(str, range(4)))
self.pc_ids = ['RDA1', 'RDA2', 'RDA3', 'RDA4', 'RDA5', 'RDA6', 'RDA7']
self.Y = pd.DataFrame(
np.loadtxt(get_data_path('example2_Y')),
index=self.sample_ids, columns=self.feature_ids)
self.X = pd.DataFrame(
np.loadtxt(get_data_path('example2_X')),
index=self.sample_ids, columns=self.env_ids)
def test_scaling1(self):
scores = rda(self.Y, self.X, scaling=1)
sample_constraints = pd.DataFrame(np.loadtxt(
get_data_path('example2_sample_constraints_scaling1')))
# Load data as computed with vegan 2.0-8
vegan_features = pd.DataFrame(
np.loadtxt(get_data_path(
'example2_species_scaling1_from_vegan')),
index=self.feature_ids,
columns=self.pc_ids)
vegan_samples = pd.DataFrame(
np.loadtxt(get_data_path(
'example2_site_scaling1_from_vegan')),
index=self.sample_ids,
columns=self.pc_ids)
sample_constraints = pd.DataFrame(
np.loadtxt(get_data_path(
'example2_sample_constraints_scaling1')),
index=self.sample_ids,
columns=self.pc_ids)
mat = np.loadtxt(get_data_path(
'example2_biplot_scaling1'))
cropped_pc_ids = self.pc_ids[:mat.shape[1]]
biplot_scores = pd.DataFrame(mat,
index=self.env_ids,
columns=cropped_pc_ids)
proportion_explained = pd.Series([0.44275783, 0.25614586,
0.15280354, 0.10497021,
0.02873375, 0.00987052,
0.00471828],
index=self.pc_ids)
eigvals = pd.Series([25.897954, 14.982578, 8.937841, 6.139956,
1.680705, 0.577350, 0.275984],
index=self.pc_ids)
exp = OrdinationResults(
'RDA', 'Redundancy Analysis',
samples=vegan_samples,
features=vegan_features,
sample_constraints=sample_constraints,
biplot_scores=biplot_scores,
proportion_explained=proportion_explained,
eigvals=eigvals)
assert_ordination_results_equal(scores, exp,
ignore_directionality=True,
decimal=6)
def test_scaling2(self):
scores = rda(self.Y, self.X, scaling=2)
mat = np.loadtxt(get_data_path('example2_biplot_scaling2'))
cropped_pc_ids = self.pc_ids[:mat.shape[1]]
biplot_scores = pd.DataFrame(mat,
index=self.env_ids,
columns=cropped_pc_ids)
sample_constraints = pd.DataFrame(np.loadtxt(
get_data_path('example2_sample_constraints_scaling2')))
# Load data as computed with vegan 2.0-8
vegan_features = pd.DataFrame(
np.loadtxt(get_data_path(
'example2_species_scaling2_from_vegan')),
index=self.feature_ids,
columns=self.pc_ids)
vegan_samples = pd.DataFrame(
np.loadtxt(get_data_path(
'example2_site_scaling2_from_vegan')),
index=self.sample_ids,
columns=self.pc_ids)
sample_constraints = pd.DataFrame(
np.loadtxt(get_data_path(
'example2_sample_constraints_scaling2')),
index=self.sample_ids,
columns=self.pc_ids)
mat = np.loadtxt(get_data_path(
'example2_biplot_scaling2'))
cropped_pc_ids = self.pc_ids[:mat.shape[1]]
biplot_scores = pd.DataFrame(mat,
index=self.env_ids,
columns=cropped_pc_ids)
proportion_explained = pd.Series([0.44275783, 0.25614586,
0.15280354, 0.10497021,
0.02873375, 0.00987052,
0.00471828],
index=self.pc_ids)
eigvals = pd.Series([25.897954, 14.982578, 8.937841, 6.139956,
1.680705, 0.577350, 0.275984],
index=self.pc_ids)
exp = OrdinationResults(
'RDA', 'Redundancy Analysis',
samples=vegan_samples,
features=vegan_features,
sample_constraints=sample_constraints,
biplot_scores=biplot_scores,
proportion_explained=proportion_explained,
eigvals=eigvals)
assert_ordination_results_equal(scores, exp,
ignore_directionality=True,
decimal=6)
if __name__ == '__main__':
main()
|
