epclust/tests/testthat/test.clustering.R

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