X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2Ftests%2Ftestthat%2Ftest.clustering.R;h=7116e73d8e982615441962e19e888a8577f17464;hb=37c82bbafbffc19e8b47a521952bac58f189e9ea;hp=eeed5761f82a3087ada4c3c16817762b0dcd11b6;hpb=d300b49cd63d0539d29bbee120fa8237f7acee9b;p=epclust.git diff --git a/epclust/tests/testthat/test.clustering.R b/epclust/tests/testthat/test.clustering.R index eeed576..7116e73 100644 --- a/epclust/tests/testthat/test.clustering.R +++ b/epclust/tests/testthat/test.clustering.R @@ -1,2 +1,186 @@ -computeClusters -computeSynchrones +context("clustering") + +#shorthand: map 1->1, 2->2, 3->3, 4->1, ..., 149->2, 150->3, ... (is base==3) +I = function(i, base) + (i-1) %% base + 1 + +test_that("computeClusters1&2 behave as expected", +{ + require("MASS", quietly=TRUE) + if (!require("clue", quietly=TRUE)) + skip("'clue' package not available") + + # 3 gaussian clusters, 300 items; and then 7 gaussian clusters, 490 items + n = 300 + d = 5 + K = 3 + for (ndK in list( c(300,5,3), c(490,10,7) )) + { + n = ndK[1] ; d = ndK[2] ; K = ndK[3] + cs = n/K #cluster size + Id = diag(d) + coefs = sapply(1:K, function(i) MASS::mvrnorm(cs, c(rep(0,(i-1)),5,rep(0,d-i)), Id)) + indices_medoids1 = computeClusters1(coefs, K, verbose=TRUE) + indices_medoids2 = computeClusters2(dist(coefs), K, verbose=TRUE) + # Get coefs assignments (to medoids) + assignment1 = sapply(seq_len(n), function(i) + which.min( colSums( sweep(coefs[,indices_medoids1],1,coefs[,i],'-')^2 ) ) ) + assignment2 = sapply(seq_len(n), function(i) + which.min( colSums( sweep(coefs[,indices_medoids2],1,coefs[,i],'-')^2 ) ) ) + for (i in 1:K) + { + expect_equal(sum(assignment1==i), cs, tolerance=5) + expect_equal(sum(assignment2==i), cs, tolerance=5) + } + + costs_matrix1 = matrix(nrow=K,ncol=K) + costs_matrix2 = matrix(nrow=K,ncol=K) + for (i in 1:K) + { + for (j in 1:K) + { + # assign i (in result) to j (order 1,2,3) + costs_matrix1[i,j] = abs( mean(assignment1[((i-1)*cs+1):(i*cs)]) - j ) + costs_matrix2[i,j] = abs( mean(assignment2[((i-1)*cs+1):(i*cs)]) - j ) + } + } + permutation1 = as.integer( clue::solve_LSAP(costs_matrix1) ) + permutation2 = as.integer( clue::solve_LSAP(costs_matrix2) ) + for (i in 1:K) + { + expect_equal( + mean(assignment1[((i-1)*cs+1):(i*cs)]), permutation1[i], tolerance=0.05) + expect_equal( + mean(assignment2[((i-1)*cs+1):(i*cs)]), permutation2[i], tolerance=0.05) + } + } +}) + +test_that("computeSynchrones behave as expected", +{ + n = 300 + x = seq(0,9.5,0.1) + L = length(x) #96 1/4h + K = 3 + s1 = cos(x) + s2 = sin(x) + s3 = c( s1[1:(L%/%2)] , s2[(L%/%2+1):L] ) + #sum((s1-s2)^2) == 96 + #sum((s1-s3)^2) == 58 + #sum((s2-s3)^2) == 38 + s = list(s1, s2, s3) + series = matrix(nrow=L, ncol=n) + for (i in seq_len(n)) + series[,i] = s[[I(i,K)]] + rnorm(L,sd=0.01) + getRefSeries = function(indices) { + indices = indices[indices <= n] + if (length(indices)>0) series[,indices] else NULL + } + synchrones = computeSynchrones(bigmemory::as.big.matrix(cbind(s1,s2,s3)), getRefSeries, + n, 100, verbose=TRUE, parll=FALSE) + + expect_equal(dim(synchrones), c(L,K)) + for (i in 1:K) + expect_equal(synchrones[,i], s[[i]], tolerance=0.01) +}) + +# NOTE: medoids can be a big.matrix +computeDistortion = function(series, medoids) +{ + n = nrow(series) ; L = ncol(series) + distortion = 0. + if (bigmemory::is.big.matrix(medoids)) + medoids = medoids[,] + for (i in seq_len(n)) + distortion = distortion + min( colSums( sweep(medoids,1,series[,i],'-')^2 ) / L ) + distortion / n +} + +test_that("clusteringTask1 behave as expected", +{ + n = 900 + x = seq(0,9.5,0.1) + L = length(x) #96 1/4h + K1 = 60 + s = lapply( seq_len(K1), function(i) x^(1+i/30)*cos(x+i) ) + series = matrix(nrow=n, ncol=L) + for (i in seq_len(n)) + series[,i] = s[[I(i,K1)]] + rnorm(L,sd=0.01) + getSeries = function(indices) { + indices = indices[indices <= n] + if (length(indices)>0) series[,indices] else NULL + } + wf = "haar" + ctype = "absolute" + getContribs = function(indices) curvesToContribs(series[,indices],wf,ctype) + indices1 = clusteringTask1(1:n, getContribs, K1, 75, verbose=TRUE, parll=FALSE) + medoids_K1 = getSeries(indices1) + + expect_equal(dim(medoids_K1), c(L,K1)) + # Not easy to evaluate result: at least we expect it to be better than random selection of + # medoids within initial series + distorGood = computeDistortion(series, medoids_K1) + for (i in 1:3) + expect_lte( distorGood, computeDistortion(series,series[,sample(1:n, K1)]) ) +}) + +test_that("clusteringTask2 behave as expected", +{ + n = 900 + x = seq(0,9.5,0.1) + L = length(x) #96 1/4h + K1 = 60 + K2 = 3 + #for (i in 1:60) {plot(x^(1+i/30)*cos(x+i),type="l",col=i,ylim=c(-50,50)); par(new=TRUE)} + s = lapply( seq_len(K1), function(i) x^(1+i/30)*cos(x+i) ) + series = matrix(nrow=n, ncol=L) + for (i in seq_len(n)) + series[i,] = s[[I(i,K1)]] + rnorm(L,sd=0.01) + getRefSeries = function(indices) { + indices = indices[indices <= n] + if (length(indices)>0) series[,indices] else NULL + } + # Artificially simulate 60 medoids - perfect situation, all equal to one of the refs + medoids_K1 = bigmemory::as.big.matrix( sapply( 1:K1, function(i) s[[I(i,K1)]] ) ) + medoids_K2 = clusteringTask2(medoids_K1, K2, getRefSeries, n, 75, verbose=TRUE, parll=FALSE) + + expect_equal(dim(medoids_K2), c(L,K2)) + # Not easy to evaluate result: at least we expect it to be better than random selection of + # medoids within 1...K1 (among references) + distorGood = computeDistortion(series, medoids_K2) + for (i in 1:3) + expect_lte( distorGood, computeDistortion(series,medoids_K1[,sample(1:K1, K2)]) ) +}) + +#NOTE: rather redundant test +#test_that("clusteringTask1 + clusteringTask2 behave as expected", +#{ +# n = 900 +# x = seq(0,9.5,0.1) +# L = length(x) #96 1/4h +# K1 = 60 +# K2 = 3 +# s = lapply( seq_len(K1), function(i) x^(1+i/30)*cos(x+i) ) +# series = matrix(nrow=n, ncol=L) +# for (i in seq_len(n)) +# series[i,] = s[[I(i,K1)]] + rnorm(L,sd=0.01) +# getSeries = function(indices) { +# indices = indices[indices <= n] +# if (length(indices)>0) series[indices,] else NULL +# } +# wf = "haar" +# ctype = "absolute" +# getContribs = function(indices) curvesToContribs(series[indices,],wf,ctype) +# require("bigmemory", quietly=TRUE) +# indices1 = clusteringTask1(1:n, getContribs, K1, 75, verbose=TRUE, parll=FALSE) +# medoids_K1 = bigmemory::as.big.matrix( getSeries(indices1) ) +# medoids_K2 = clusteringTask2(medoids_K1, K2, getSeries, n, 120, verbose=TRUE, parll=FALSE) +# +# expect_equal(dim(medoids_K1), c(K1,L)) +# expect_equal(dim(medoids_K2), c(K2,L)) +# # Not easy to evaluate result: at least we expect it to be better than random selection of +# # medoids within 1...K1 (among references) +# distorGood = computeDistortion(series, medoids_K2) +# for (i in 1:3) +# expect_lte( distorGood, computeDistortion(series,medoids_K1[sample(1:K1, K2),]) ) +#})