forked from gonum/stat
/
pca_test.go
183 lines (178 loc) · 6.26 KB
/
pca_test.go
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
// Copyright ©2016 The gonum Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package stat
import (
"testing"
"github.com/gonum/floats"
"github.com/gonum/matrix/mat64"
)
func TestPrincipalComponents(t *testing.T) {
tests:
for i, test := range []struct {
data mat64.Matrix
weights []float64
wantVecs *mat64.Dense
wantVars []float64
epsilon float64
}{
// Test results verified using R.
{
data: mat64.NewDense(3, 3, []float64{
1, 2, 3,
4, 5, 6,
7, 8, 9,
}),
wantVecs: mat64.NewDense(3, 3, []float64{
0.5773502691896258, 0.8164965809277261, 0,
0.577350269189626, -0.4082482904638632, -0.7071067811865476,
0.5773502691896258, -0.4082482904638631, 0.7071067811865475,
}),
wantVars: []float64{27, 0, 0},
epsilon: 1e-12,
},
{ // Truncated iris data.
data: mat64.NewDense(10, 4, []float64{
5.1, 3.5, 1.4, 0.2,
4.9, 3.0, 1.4, 0.2,
4.7, 3.2, 1.3, 0.2,
4.6, 3.1, 1.5, 0.2,
5.0, 3.6, 1.4, 0.2,
5.4, 3.9, 1.7, 0.4,
4.6, 3.4, 1.4, 0.3,
5.0, 3.4, 1.5, 0.2,
4.4, 2.9, 1.4, 0.2,
4.9, 3.1, 1.5, 0.1,
}),
wantVecs: mat64.NewDense(4, 4, []float64{
-0.6681110197952722, 0.7064764857539533, -0.14026590216895132, -0.18666578956412125,
-0.7166344774801547, -0.6427036135482664, -0.135650285905254, 0.23444848208629923,
-0.164411275166307, 0.11898477441068218, 0.9136367900709548, 0.35224901970831746,
-0.11415613655453069, -0.2714141920887426, 0.35664028439226514, -0.8866286823515034,
}),
wantVars: []float64{0.1665786313282786, 0.02065509475412993, 0.007944620317765855, 0.0019327647109368329},
epsilon: 1e-12,
},
{ // Truncated iris data to form wide matrix.
data: mat64.NewDense(3, 4, []float64{
5.1, 3.5, 1.4, 0.2,
4.9, 3.0, 1.4, 0.2,
4.7, 3.2, 1.3, 0.2,
}),
wantVecs: mat64.NewDense(4, 3, []float64{
-0.5705187254552365, -0.7505979435049239, 0.08084520834544455,
-0.8166537769529318, 0.5615147645527523, -0.032338083338177705,
-0.08709186238359454, -0.3482870890450082, -0.22636658336724505,
0, 0, -0.9701425001453315,
}),
wantVars: []float64{0.0844692361537822, 0.022197430512884326, 0},
epsilon: 1e-12,
},
{ // Truncated iris data transposed to check for operation on fat input.
data: mat64.NewDense(10, 4, []float64{
5.1, 3.5, 1.4, 0.2,
4.9, 3.0, 1.4, 0.2,
4.7, 3.2, 1.3, 0.2,
4.6, 3.1, 1.5, 0.2,
5.0, 3.6, 1.4, 0.2,
5.4, 3.9, 1.7, 0.4,
4.6, 3.4, 1.4, 0.3,
5.0, 3.4, 1.5, 0.2,
4.4, 2.9, 1.4, 0.2,
4.9, 3.1, 1.5, 0.1,
}).T(),
wantVecs: mat64.NewDense(10, 4, []float64{
-0.3366602459946619, -0.1373634006401213, 0.3465102523547623, -0.10290179303893479,
-0.31381852053861975, 0.5197145790632827, 0.5567296129086686, -0.15923062170153618,
-0.30857197637565165, -0.07670930360819002, 0.36159923003337235, 0.3342301027853355,
-0.29527124351656137, 0.16885455995353074, -0.5056204762881208, 0.32580913261444344,
-0.3327611073694004, -0.39365834489416474, 0.04900050959307464, 0.46812879383236555,
-0.34445484362044815, -0.2985206914561878, -0.1009714701361799, -0.16803618186050803,
-0.2986246350957691, -0.4222037823717799, -0.11838613462182519, -0.580283530375069,
-0.325911246223126, 0.024366468758217238, -0.12082035131864265, 0.16756027181337868,
-0.2814284432361538, 0.240812316260054, -0.24061437569068145, -0.365034616264623,
-0.31906138507685167, 0.4423912824105986, -0.2906412122303604, 0.027551046870337714,
}),
wantVars: []float64{41.8851906634233, 0.07762619213464989, 0.010516477775373585, 0},
epsilon: 1e-12,
},
{ // Truncated iris data unitary weights.
data: mat64.NewDense(10, 4, []float64{
5.1, 3.5, 1.4, 0.2,
4.9, 3.0, 1.4, 0.2,
4.7, 3.2, 1.3, 0.2,
4.6, 3.1, 1.5, 0.2,
5.0, 3.6, 1.4, 0.2,
5.4, 3.9, 1.7, 0.4,
4.6, 3.4, 1.4, 0.3,
5.0, 3.4, 1.5, 0.2,
4.4, 2.9, 1.4, 0.2,
4.9, 3.1, 1.5, 0.1,
}),
weights: []float64{1, 1, 1, 1, 1, 1, 1, 1, 1, 1},
wantVecs: mat64.NewDense(4, 4, []float64{
-0.6681110197952722, 0.7064764857539533, -0.14026590216895132, -0.18666578956412125,
-0.7166344774801547, -0.6427036135482664, -0.135650285905254, 0.23444848208629923,
-0.164411275166307, 0.11898477441068218, 0.9136367900709548, 0.35224901970831746,
-0.11415613655453069, -0.2714141920887426, 0.35664028439226514, -0.8866286823515034,
}),
wantVars: []float64{0.1665786313282786, 0.02065509475412993, 0.007944620317765855, 0.0019327647109368329},
epsilon: 1e-12,
},
{ // Truncated iris data non-unitary weights.
data: mat64.NewDense(10, 4, []float64{
5.1, 3.5, 1.4, 0.2,
4.9, 3.0, 1.4, 0.2,
4.7, 3.2, 1.3, 0.2,
4.6, 3.1, 1.5, 0.2,
5.0, 3.6, 1.4, 0.2,
5.4, 3.9, 1.7, 0.4,
4.6, 3.4, 1.4, 0.3,
5.0, 3.4, 1.5, 0.2,
4.4, 2.9, 1.4, 0.2,
4.9, 3.1, 1.5, 0.1,
}),
weights: []float64{2, 3, 1, 1, 1, 1, 1, 1, 1, 2},
wantVecs: mat64.NewDense(4, 4, []float64{
-0.618936145422414, 0.763069301531647, 0.124857741232537, 0.138035623677211,
-0.763958271606519, -0.603881770702898, 0.118267155321333, -0.194184052457746,
-0.143552119754944, 0.090014599564871, -0.942209377020044, -0.289018426115945,
-0.112599271966947, -0.212012782487076, -0.287515067921680, 0.927203898682805,
}),
wantVars: []float64{0.129621985550623, 0.022417487771598, 0.006454461065715, 0.002495076601075},
epsilon: 1e-12,
},
} {
var pc PC
var vecs *mat64.Dense
var vars []float64
for j := 0; j < 2; j++ {
ok := pc.PrincipalComponents(test.data, test.weights)
vecs = pc.Vectors(vecs)
vars = pc.Vars(vars)
if !ok {
t.Errorf("unexpected SVD failure for test %d use %d", i, j)
continue tests
}
if !mat64.EqualApprox(vecs, test.wantVecs, test.epsilon) {
t.Errorf("%d use %d: unexpected PCA result got:\n%v\nwant:\n%v",
i, j, mat64.Formatted(vecs), mat64.Formatted(test.wantVecs))
}
if !approxEqual(vars, test.wantVars, test.epsilon) {
t.Errorf("%d use %d: unexpected variance result got:%v, want:%v",
i, j, vars, test.wantVars)
}
}
}
}
func approxEqual(a, b []float64, epsilon float64) bool {
if len(a) != len(b) {
return false
}
for i, v := range a {
if !floats.EqualWithinAbsOrRel(v, b[i], epsilon, epsilon) {
return false
}
}
return true
}