Commit | Line | Data |
---|---|---|
56857861 BA |
1 | context("clustering") |
2 | ||
8702eb86 BA |
3 | #shorthand: map 1->1, 2->2, 3->3, 4->1, ..., 149->2, 150->3, ... (is base==3) |
4 | I = function(i, base) | |
5 | (i-1) %% base + 1 | |
56857861 BA |
6 | |
7 | test_that("computeClusters1 behave as expected", | |
8 | { | |
8702eb86 | 9 | require("MASS", quietly=TRUE) |
4bcfdbee BA |
10 | if (!require("clue", quietly=TRUE)) |
11 | skip("'clue' package not available") | |
56857861 | 12 | |
8702eb86 BA |
13 | # 3 gaussian clusters, 300 items; and then 7 gaussian clusters, 490 items |
14 | n = 300 | |
15 | d = 5 | |
16 | K = 3 | |
17 | for (ndK in list( c(300,5,3), c(490,10,7) )) | |
18 | { | |
19 | n = ndK[1] ; d = ndK[2] ; K = ndK[3] | |
20 | cs = n/K #cluster size | |
21 | Id = diag(d) | |
22 | coefs = do.call(rbind, | |
23 | lapply(1:K, function(i) MASS::mvrnorm(cs, c(rep(0,(i-1)),5,rep(0,d-i)), Id))) | |
24 | indices_medoids = computeClusters1(coefs, K) | |
25 | # Get coefs assignments (to medoids) | |
26 | assignment = sapply(seq_len(n), function(i) | |
27 | which.min( rowSums( sweep(coefs[indices_medoids,],2,coefs[i,],'-')^2 ) ) ) | |
28 | for (i in 1:K) | |
29 | expect_equal(sum(assignment==i), cs, tolerance=5) | |
30 | ||
31 | costs_matrix = matrix(nrow=K,ncol=K) | |
32 | for (i in 1:K) | |
33 | { | |
34 | for (j in 1:K) | |
35 | { | |
36 | # assign i (in result) to j (order 1,2,3) | |
37 | costs_matrix[i,j] = abs( mean(assignment[((i-1)*cs+1):(i*cs)]) - j ) | |
38 | } | |
39 | } | |
40 | permutation = as.integer( clue::solve_LSAP(costs_matrix) ) | |
41 | for (i in 1:K) | |
42 | { | |
43 | expect_equal( | |
44 | mean(assignment[((i-1)*cs+1):(i*cs)]), permutation[i], tolerance=0.05) | |
45 | } | |
46 | } | |
56857861 BA |
47 | }) |
48 | ||
49 | test_that("computeSynchrones behave as expected", | |
50 | { | |
8702eb86 BA |
51 | n = 300 |
52 | x = seq(0,9.5,0.1) | |
53 | L = length(x) #96 1/4h | |
54 | K = 3 | |
55 | s1 = cos(x) | |
56 | s2 = sin(x) | |
57 | s3 = c( s1[1:(L%/%2)] , s2[(L%/%2+1):L] ) | |
58 | #sum((s1-s2)^2) == 96 | |
59 | #sum((s1-s3)^2) == 58 | |
60 | #sum((s2-s3)^2) == 38 | |
61 | s = list(s1, s2, s3) | |
62 | series = matrix(nrow=n, ncol=L) | |
63 | for (i in seq_len(n)) | |
64 | series[i,] = s[[I(i,K)]] + rnorm(L,sd=0.01) | |
65 | getRefSeries = function(indices) { | |
66 | indices = indices[indices < n] | |
67 | if (length(indices)>0) series[indices,] else NULL | |
68 | } | |
69 | synchrones = computeSynchrones(rbind(s1,s2,s3), getRefSeries, 100) | |
56857861 | 70 | |
8702eb86 BA |
71 | expect_equal(dim(synchrones), c(K,L)) |
72 | for (i in 1:K) | |
73 | expect_equal(synchrones[i,], s[[i]], tolerance=0.01) | |
56857861 BA |
74 | }) |
75 | ||
8702eb86 BA |
76 | computeDistortion = function(series, medoids) |
77 | { | |
78 | n = nrow(series) ; L = ncol(series) | |
79 | distortion = 0. | |
80 | for (i in seq_len(n)) | |
81 | distortion = distortion + min( rowSums( sweep(medoids,2,series[i,],'-')^2 ) / L ) | |
82 | distortion / n | |
83 | } | |
84 | ||
56857861 BA |
85 | test_that("computeClusters2 behave as expected", |
86 | { | |
8702eb86 BA |
87 | n = 900 |
88 | x = seq(0,9.5,0.1) | |
89 | L = length(x) #96 1/4h | |
90 | K1 = 60 | |
91 | K2 = 3 | |
92 | #for (i in 1:60) {plot(x^(1+i/30)*cos(x+i),type="l",col=i,ylim=c(-50,50)); par(new=TRUE)} | |
93 | s = lapply( seq_len(K1), function(i) x^(1+i/30)*cos(x+i) ) | |
94 | series = matrix(nrow=n, ncol=L) | |
95 | for (i in seq_len(n)) | |
96 | series[i,] = s[[I(i,K1)]] + rnorm(L,sd=0.01) | |
97 | getRefSeries = function(indices) { | |
98 | indices = indices[indices < n] | |
99 | if (length(indices)>0) series[indices,] else NULL | |
100 | } | |
101 | # Artificially simulate 60 medoids - perfect situation, all equal to one of the refs | |
102 | medoids_K1 = do.call(rbind, lapply( 1:K1, function(i) s[[I(i,K1)]] ) ) | |
103 | medoids_K2 = computeClusters2(medoids_K1, K2, getRefSeries, 75) | |
56857861 | 104 | |
8702eb86 BA |
105 | expect_equal(dim(medoids_K2), c(K2,L)) |
106 | # Not easy to evaluate result: at least we expect it to be better than random selection of | |
107 | # medoids within 1...K1 (among references) | |
108 | ||
109 | distorGood = computeDistortion(series, medoids_K2) | |
110 | for (i in 1:3) | |
111 | expect_lte( distorGood, computeDistortion(series,medoids_K1[sample(1:K1, K2),]) ) | |
56857861 BA |
112 | }) |
113 | ||
114 | test_that("clusteringTask + computeClusters2 behave as expected", | |
115 | { | |
8702eb86 BA |
116 | n = 900 |
117 | x = seq(0,9.5,0.1) | |
118 | L = length(x) #96 1/4h | |
119 | K1 = 60 | |
120 | K2 = 3 | |
121 | s = lapply( seq_len(K1), function(i) x^(1+i/30)*cos(x+i) ) | |
122 | series = matrix(nrow=n, ncol=L) | |
123 | for (i in seq_len(n)) | |
124 | series[i,] = s[[I(i,K1)]] + rnorm(L,sd=0.01) | |
125 | getSeries = function(indices) { | |
126 | indices = indices[indices <= n] | |
127 | if (length(indices)>0) series[indices,] else NULL | |
128 | } | |
129 | wf = "haar" | |
4bcfdbee BA |
130 | ctype = "absolute" |
131 | getContribs = function(indices) curvesToContribs(series[indices,],wf,ctype) | |
132 | medoids_K1 = getSeries( clusteringTask(1:n, getContribs, K1, 75, 4) ) | |
8702eb86 | 133 | medoids_K2 = computeClusters2(medoids_K1, K2, getSeries, 120) |
56857861 | 134 | |
8702eb86 BA |
135 | expect_equal(dim(medoids_K1), c(K1,L)) |
136 | expect_equal(dim(medoids_K2), c(K2,L)) | |
137 | # Not easy to evaluate result: at least we expect it to be better than random selection of | |
138 | # medoids within 1...K1 (among references) | |
139 | distorGood = computeDistortion(series, medoids_K2) | |
140 | for (i in 1:3) | |
141 | expect_lte( distorGood, computeDistortion(series,medoids_K1[sample(1:K1, K2),]) ) | |
56857861 | 142 | }) |