X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2Ftests%2Ftestthat%2Ftest.clustering.R;h=a4d59d9d72ba0e62168f69e97fd988232e518770;hp=527f6bda2544bbc80ce6330e25cecc03dda2fc23;hb=8702eb86906bd6d59e07bb887e690a20f29be63f;hpb=86223e279a954d946ae641888f5107ed9feb6217

diff --git a/epclust/tests/testthat/test.clustering.R b/epclust/tests/testthat/test.clustering.R
index 527f6bd..a4d59d9 100644
--- a/epclust/tests/testthat/test.clustering.R
+++ b/epclust/tests/testthat/test.clustering.R
@@ -1,25 +1,140 @@
 context("clustering")
 
-#TODO: load some dataset ASCII CSV
-#data_bin_file <<- "/tmp/epclust_test.bin"
-#unlink(data_bin_file)
+#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 behave as expected",
 {
+	require("MASS", quietly=TRUE)
+	require("clue", quietly=TRUE)
 
+	# 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 = do.call(rbind,
+			lapply(1:K, function(i) MASS::mvrnorm(cs, c(rep(0,(i-1)),5,rep(0,d-i)), Id)))
+		indices_medoids = computeClusters1(coefs, K)
+		# Get coefs assignments (to medoids)
+		assignment = sapply(seq_len(n), function(i)
+			which.min( rowSums( sweep(coefs[indices_medoids,],2,coefs[i,],'-')^2 ) ) )
+		for (i in 1:K)
+			expect_equal(sum(assignment==i), cs, tolerance=5)
+
+		costs_matrix = 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_matrix[i,j] = abs( mean(assignment[((i-1)*cs+1):(i*cs)]) - j )
+			}
+		}
+		permutation = as.integer( clue::solve_LSAP(costs_matrix) )
+		for (i in 1:K)
+		{
+			expect_equal(
+				mean(assignment[((i-1)*cs+1):(i*cs)]), permutation[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=n, ncol=L)
+	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(rbind(s1,s2,s3), getRefSeries, 100)
 
+	expect_equal(dim(synchrones), c(K,L))
+	for (i in 1:K)
+		expect_equal(synchrones[i,], s[[i]], tolerance=0.01)
 })
 
+computeDistortion = function(series, medoids)
+{
+	n = nrow(series) ; L = ncol(series)
+	distortion = 0.
+	for (i in seq_len(n))
+		distortion = distortion + min( rowSums( sweep(medoids,2,series[i,],'-')^2 ) / L )
+	distortion / n
+}
+
 test_that("computeClusters2 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 = do.call(rbind, lapply( 1:K1, function(i) s[[I(i,K1)]] ) )
+	medoids_K2 = computeClusters2(medoids_K1, K2, getRefSeries, 75)
 
+	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),]) )
 })
 
 test_that("clusteringTask + computeClusters2 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"
+	getCoefs = function(indices) curvesToCoefs(series[indices,],wf)
+	medoids_K1 = getSeries( clusteringTask(1:n, getCoefs, K1, 75, 4) )
+	medoids_K2 = computeClusters2(medoids_K1, K2, getSeries, 120)
 
+	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),]) )
 })