From: Benjamin Auder Date: Thu, 15 Nov 2018 16:51:58 +0000 (+0100) Subject: 'update' X-Git-Url: https://git.auder.net/variants/current/vendor/index.css?a=commitdiff_plain;h=3d5b50604d7e63fa0a0d6c37d34f6a4595bcfd34;p=morpheus.git 'update' --- diff --git a/vignettes/report.Rmd b/vignettes/report.Rmd new file mode 100644 index 0000000..4149717 --- /dev/null +++ b/vignettes/report.Rmd @@ -0,0 +1,162 @@ +--- +title: morpheus........... + +output: + pdf_document: + number_sections: true + toc_depth: 1 +--- + +```{r setup, results="hide", include=FALSE} +knitr::opts_chunk$set(echo = TRUE, include = TRUE, + cache = TRUE, comment="", cache.lazy = FALSE, + out.width = "100%", fig.align = "center") +``` + +0) Tell that we try to learn classification parameters in a non-EM way, using algebric manipulations. +1) Model. +2) Algorithm (as in article) +3) Experiments: show package usage + +# Expériences + +```{r, results="show", include=TRUE, echo=TRUE} +library(Rmixmod) #to get clustering probability matrix +library(ClusVis) +library(FactoMineR) #for PCA + +plotPCA <- function(prob) +{ + par(mfrow=c(2,2), mar=c(4,4,2,2), mgp=c(2,1,0)) + partition <- apply(prob, 1, which.max) + n <- nrow(prob) + K <- ncol(prob) + palette <- rainbow(K, s=.5) + cols <- palette[partition] + tmp <- PCA(rbind(prob, diag(K)), ind.sup=(n+1):(n+K), scale.unit=F, graph=F) + scores <- tmp$ind$coord[,1:3] #samples coords, by rows + ctrs <- tmp$ind.sup$coord #projections of indicator vectors (by cols) + for (i in 1:2) + { + for (j in (i+1):3) + { + absc <- scores[,i] + ords <- scores[,j] + xrange <- range(absc) + yrange <- range(ords) + plot(absc, ords, col=c(cols,rep(colors()[215],K),rep(1,K)), + pch=c(rep("o",n),rep(as.character(1:K),2)), + xlim=xrange, ylim=yrange, + xlab=paste0("Dim ", i, " (", round(tmp$eig[i,2],2), "%)"), + ylab=paste0("Dim ", j, " (", round(tmp$eig[j,2],2), "%)")) + ctrsavg <- t(apply(as.matrix(palette), 1, + function(cl) c(mean(absc[cols==cl]), mean(ords[cols==cl])))) + text(ctrsavg[,1], ctrsavg[,2], as.character(1:K), col=colors()[215]) + text(ctrs[,i], ctrs[,j], as.character(1:K), col=1) + title(paste0("PCA ", i, "-", j, " / K=",K)) + } + } + # TODO: + plot(0, xaxt="n", yaxt="n", xlab="", ylab="", col="white", bty="n") +} + +plotClvz <- function(xem, alt=FALSE) +{ + par(mfrow=c(2,2), mar=c(4,4,2,2), mgp=c(2,1,0)) + if (alt) { + resvisu <- clusvis(log(xem@bestResult@proba), xem@bestResult@parameters@proportions) + } else { + resvisu <- clusvisMixmod(xem) + } + plotDensityClusVisu(resvisu, positionlegend=NULL) + plotDensityClusVisu(resvisu, add.obs=TRUE, positionlegend=NULL) + # TODO: + plot(0, xaxt="n", yaxt="n", xlab="", ylab="", col="white", bty="n") + plot(0, xaxt="n", yaxt="n", xlab="", ylab="", col="white", bty="n") +} + +grlplot <- function(x, K, alt=FALSE) #x: data, K: nb classes +{ + xem <- mixmodCluster(x, K, strategy=mixmodStrategy(nbTryInInit=500,nbTry=25)) + plotPCA(xem@results[[1]]@proba) + plotClvz(xem, alt) +} +``` + +## Iris data + +```{r, results="show", include=TRUE, echo=TRUE} +data(iris) +x <- iris[,-5] #remove class info +for (i in 3:5) +{ + print(paste("Resultats en", i, "classes")) + grlplot(x, i) +} +``` + +### finance dataset (from Rmixmod package) +# +#This dataset has two categorical attributes (the year and financial status), and four continuous ones. +# +#Warnings, some probabilities of classification are exactly equal to zero then we cannot use ClusVis +# +#```{r, results="show", include=TRUE, echo=TRUE} +#data(finance) +#x <- finance[,-2] +#for (i in 3:5) +#{ +# print(paste("Resultats en", i, "classes")) +# grlplot(x, i, TRUE) +#} +#``` +# +### "Cathy dataset" (12 clusters) +# +#Warnings, some probabilities of classification are exactly equal to zero then we cannot use ClusVis +# +#```{r, results="hide", include=TRUE, echo=TRUE} +#cathy12 <- as.matrix(read.table("data/probapostCatdbBlocAtrazine-K12.txt")) +#resvisu <- clusvis(log(cathy12), prop = colMeans(cathy12)) +#par(mfrow=c(2,2), mar=c(4,4,2,2), mgp=c(2,1,0)) +#plotDensityClusVisu(resvisu, positionlegend = NULL) +#plotDensityClusVisu(resvisu, add.obs = TRUE, positionlegend = NULL) +#plotPCA(cathy12) +#``` +# +### Pima indian diabete +# +#[Source.](https://gist.github.com/ktisha/c21e73a1bd1700294ef790c56c8aec1f) +# +#```{r, results="show", include=TRUE, echo=TRUE} +#load("data/pimaData.rda") +#for (i in 3:5) +#{ +# print(paste("Resultats en", i, "classes")) +# grlplot(x, i) +#} +#``` +# +### Breast cancer +# +#[Source.](http://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+\%28diagnostic\%29) +# +#```{r, results="show", include=TRUE, echo=TRUE} +#load("data/wdbc.rda") +#for (i in 3:5) +#{ +# print(paste("Resultats en", i, "classes")) +# grlplot(x, i) +#} +#``` +# +### House-votes +# +#```{r, results="show", include=TRUE, echo=TRUE} +#load("data/house-votes.rda") +#for (i in 3:5) +#{ +# print(paste("Resultats en", i, "classes")) +# grlplot(x, i) +#} +#```