projects / epclust.git / blame
| Commit | Line | Data |
|---|---|---|
| b7cd987d BA |
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)$id.med | |
| 27 | indices1 <- clusteringTask1(1:n, getContribs, K1, algoClust1, 140, verbose=TRUE) | |
| 28 | medoids_K1 <- getSeries(indices1) | |
| 29 | ||
| 30 | expect_equal(dim(medoids_K1), c(L,K1)) | |
| 31 | # Not easy to evaluate result: at least we expect it to be better than random selection of | |
| 32 | # medoids within initial series | |
| 33 | distor_good <- computeDistortion(series, medoids_K1) | |
| 34 | for (i in 1:3) | |
| 35 | expect_lte( distor_good, computeDistortion(series,series[,sample(1:n, K1)]) ) | |
| 36 | }) | |
| 37 | ||
| 38 | test_that("clusteringTask2 behave as expected", | |
| 39 | { | |
| 40 | # Same 60 reference sinusoïdal series than in clusteringTask1 test, | |
| 41 | # but this time we consider them as medoids - skipping stage 1 | |
| 42 | # Here also we sample 900 series around the 60 "medoids" | |
| 43 | n <- 900 | |
| 44 | x <- seq(0,9.5,0.1) | |
| 45 | L <- length(x) #96 1/4h | |
| 46 | K1 <- 60 | |
| 47 | K2 <- 3 | |
| 48 | #for (i in 1:60) {plot(x^(1+i/30)*cos(x+i),type="l",col=i,ylim=c(-50,50)); par(new=TRUE)} | |
| 49 | s <- lapply( seq_len(K1), function(i) x^(1+i/30)*cos(x+i) ) | |
| 50 | series <- matrix(nrow=L, ncol=n) | |
| 51 | for (i in seq_len(n)) | |
| 52 | series[,i] <- s[[I(i,K1)]] + rnorm(L,sd=0.01) | |
| 53 | ||
| 54 | getSeries <- function(indices) { | |
| 55 | indices <- indices[indices <= n] | |
| 56 | if (length(indices)>0) as.matrix(series[,indices]) else NULL | |
| 57 | } | |
| 58 | ||
| 59 | # Perfect situation: all medoids "after stage 1" are ~good | |
| 60 | algoClust2 <- function(dists,K) cluster::pam(dists,K,diss=TRUE)$id.med | |
| 61 | indices2 <- clusteringTask2(1:K1, getSeries, K2, algoClust2, 210, 3, 4, 8, "little", | |
| 62 | verbose=TRUE) | |
| 63 | medoids_K2 <- getSeries(indices2) | |
| 64 | ||
| 65 | expect_equal(dim(medoids_K2), c(L,K2)) | |
| 66 | # Not easy to evaluate result: at least we expect it to be better than random selection of | |
| 67 | # synchrones within 1...K1 (from where distances computations + clustering was run) | |
| 68 | distor_good <- computeDistortion(series, medoids_K2) | |
| 69 | #TODO: This fails; why? | |
| 70 | # for (i in 1:3) | |
| 71 | # expect_lte( distor_good, computeDistortion(series, series[,sample(1:K1,3)]) ) | |
| 72 | }) |