| 1 | context("clustering") |
| 2 | |
| 3 | test_that("clusteringTask1 behave as expected", |
| 4 | { |
| 5 | # Generate 60 reference sinusoïdal series (medoids to be found), |
| 6 | # and sample 900 series around them (add a small noise) |
| 7 | n = 900 |
| 8 | x = seq(0,9.5,0.1) |
| 9 | L = length(x) #96 1/4h |
| 10 | K1 = 60 |
| 11 | s = lapply( seq_len(K1), function(i) x^(1+i/30)*cos(x+i) ) |
| 12 | series = matrix(nrow=L, ncol=n) |
| 13 | for (i in seq_len(n)) |
| 14 | series[,i] = s[[I(i,K1)]] + rnorm(L,sd=0.01) |
| 15 | |
| 16 | getSeries = function(indices) { |
| 17 | indices = indices[indices <= n] |
| 18 | if (length(indices)>0) as.matrix(series[,indices]) else NULL |
| 19 | } |
| 20 | |
| 21 | wf = "haar" |
| 22 | ctype = "absolute" |
| 23 | getContribs = function(indices) curvesToContribs(as.matrix(series[,indices]),wf,ctype) |
| 24 | |
| 25 | require("cluster", quietly=TRUE) |
| 26 | algoClust1 = function(contribs,K) cluster::pam(t(contribs),K,diss=FALSE)$id.med |
| 27 | indices1 = clusteringTask1(1:n, getContribs, K1, algoClust1, 75, verbose=TRUE, parll=FALSE) |
| 28 | medoids_K1 = getSeries(indices1) |
| 29 | |
| 30 | expect_equal(dim(medoids_K1), c(L,K1)) |
| 31 | # Not easy to evaluate result: at least we expect it to be better than random selection of |
| 32 | # medoids within initial series |
| 33 | distor_good = computeDistortion(series, medoids_K1) |
| 34 | for (i in 1:3) |
| 35 | expect_lte( distor_good, computeDistortion(series,series[,sample(1:n, K1)]) ) |
| 36 | }) |
| 37 | |
| 38 | test_that("clusteringTask2 behave as expected", |
| 39 | { |
| 40 | skip("Unexplained failure") |
| 41 | |
| 42 | # Same 60 reference sinusoïdal series than in clusteringTask1 test, |
| 43 | # but this time we consider them as medoids - skipping stage 1 |
| 44 | # Here also we sample 900 series around the 60 "medoids" |
| 45 | n = 900 |
| 46 | x = seq(0,9.5,0.1) |
| 47 | L = length(x) #96 1/4h |
| 48 | K1 = 60 |
| 49 | K2 = 3 |
| 50 | #for (i in 1:60) {plot(x^(1+i/30)*cos(x+i),type="l",col=i,ylim=c(-50,50)); par(new=TRUE)} |
| 51 | s = lapply( seq_len(K1), function(i) x^(1+i/30)*cos(x+i) ) |
| 52 | series = matrix(nrow=L, ncol=n) |
| 53 | for (i in seq_len(n)) |
| 54 | series[,i] = s[[I(i,K1)]] + rnorm(L,sd=0.01) |
| 55 | |
| 56 | getRefSeries = function(indices) { |
| 57 | indices = indices[indices <= n] |
| 58 | if (length(indices)>0) as.matrix(series[,indices]) else NULL |
| 59 | } |
| 60 | |
| 61 | # Perfect situation: all medoids "after stage 1" are good. |
| 62 | medoids_K1 = bigmemory::as.big.matrix( sapply( 1:K1, function(i) s[[I(i,K1)]] ) ) |
| 63 | algoClust2 = function(dists,K) cluster::pam(dists,K,diss=TRUE)$id.med |
| 64 | medoids_K2 = clusteringTask2(medoids_K1, K2, algoClust2, getRefSeries, |
| 65 | n, 75, 4, 8, "little", verbose=TRUE, parll=FALSE) |
| 66 | |
| 67 | expect_equal(dim(medoids_K2), c(L,K2)) |
| 68 | # Not easy to evaluate result: at least we expect it to be better than random selection of |
| 69 | # synchrones within 1...K1 (from where distances computations + clustering was run) |
| 70 | synchrones = computeSynchrones(medoids_K1,getRefSeries,n,75,verbose=FALSE,parll=FALSE) |
| 71 | distor_good = computeDistortion(synchrones, medoids_K2) |
| 72 | for (i in 1:3) |
| 73 | expect_lte( distor_good, computeDistortion(synchrones, synchrones[,sample(1:K1,3)]) ) |
| 74 | }) |
| 75 | |
| 76 | # Compute the sum of (normalized) sum of squares of closest distances to a medoid. |
| 77 | # Note: medoids can be a big.matrix |
| 78 | computeDistortion = function(series, medoids) |
| 79 | { |
| 80 | if (bigmemory::is.big.matrix(medoids)) |
| 81 | medoids = medoids[,] #extract standard matrix |
| 82 | |
| 83 | n = ncol(series) ; L = nrow(series) |
| 84 | distortion = 0. |
| 85 | for (i in seq_len(n)) |
| 86 | distortion = distortion + min( colSums( sweep(medoids,1,series[,i],'-')^2 ) / L ) |
| 87 | |
| 88 | sqrt( distortion / n ) |
| 89 | } |