R version 2.9.0 (2009-04-17) Copyright (C) 2009 The R Foundation for Statistical Computing ISBN 3-900051-07-0 R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type 'license()' or 'licence()' for distribution details. R is a collaborative project with many contributors. Type 'contributors()' for more information and 'citation()' on how to cite R or R packages in publications. Type 'demo()' for some demos, 'help()' for on-line help, or 'help.start()' for an HTML browser interface to help. Type 'q()' to quit R. > x <- array(list(172.69,104.31,172.98,103.88,172.98,103.88,172.89,103.86,173.38,103.89,173.20,103.98,173.24,103.98,172.86,104.29,172.86,104.29,172.74,104.24,172.28,103.98,171.05,103.54,171.07,103.44,171.07,103.32,171.07,103.30,171.11,103.26,170.72,103.14,170.49,103.11,170.48,102.91,170.48,103.23,170.48,103.23,170.57,103.14,170.39,102.91,170.04,102.42,169.67,102.10,169.57,102.07,169.57,102.06,169.53,101.98,169.24,101.83,169.29,101.75,169.21,101.56,168.58,101.66,168.58,101.65,168.55,101.61,168.46,101.52,167.39,101.31,167.16,101.19,167.16,101.11,167.16,101.10,167.17,101.07,166.52,100.98,166.35,100.93,166.19,100.92,166.19,101.02,166.19,101.01,166.07,100.97,166.64,100.89,166.26,100.62,166.44,100.53,166.27,100.48,166.27,100.48,166.30,100.47,165.97,100.52,164.58,100.49,164.28,100.47,163.93,100.44),dim=c(2,56),dimnames=list(c('Gemconsprijsblazers','consumptieindexkleding'),1:56)) > y <- array(NA,dim=c(2,56),dimnames=list(c('Gemconsprijsblazers','consumptieindexkleding'),1:56)) > for (i in 1:dim(x)[1]) + { + for (j in 1:dim(x)[2]) + { + y[i,j] <- as.numeric(x[i,j]) + } + } > par4 = 'no' > par3 = '3' > par2 = 'none' > par1 = '1' > #'GNU S' R Code compiled by R2WASP v. 1.0.44 () > #Author: Dr. Ian E. Holliday > #To cite this work: Ian E. Holliday, 2009, YOUR SOFTWARE TITLE (vNUMBER) in Free Statistics Software (v$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_YOURPAGE.wasp/ > #Source of accompanying publication: > #Technical description: > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Attaching package: 'zoo' The following object(s) are masked from package:base : as.Date.numeric Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Attaching package: 'Hmisc' The following object(s) are masked from package:survival : untangle.specials The following object(s) are masked from package:base : format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "Gemconsprijsblazers" > x[,par1] [1] 172.69 172.98 172.98 172.89 173.38 173.20 173.24 172.86 172.86 172.74 [11] 172.28 171.05 171.07 171.07 171.07 171.11 170.72 170.49 170.48 170.48 [21] 170.48 170.57 170.39 170.04 169.67 169.57 169.57 169.53 169.24 169.29 [31] 169.21 168.58 168.58 168.55 168.46 167.39 167.16 167.16 167.16 167.17 [41] 166.52 166.35 166.19 166.19 166.19 166.07 166.64 166.26 166.44 166.27 [51] 166.27 166.30 165.97 164.58 164.28 163.93 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$centers,1:par3),ncol=2) + clm <- clm[sort.list(clm[,1]),] + for (i in 1:par3) { + cl$cluster[cl$cluster==clm[i,2]] <- paste('C',i,sep='') + } + cl$cluster <- as.factor(cl$cluster) + print(cl$cluster) + x[,par1] <- cl$cluster + } > if (par2 == 'quantiles') { + x[,par1] <- cut2(x[,par1],g=par3) + } > if (par2 == 'hclust') { + hc <- hclust(dist(x[,par1])^2, 'cen') + print(hc) + memb <- cutree(hc, k = par3) + dum <- c(mean(x[memb==1,par1])) + for (i in 2:par3) { + dum <- c(dum, mean(x[memb==i,par1])) + } + hcm <- matrix(cbind(dum,1:par3),ncol=2) + hcm <- hcm[sort.list(hcm[,1]),] + for (i in 1:par3) { + memb[memb==hcm[i,2]] <- paste('C',i,sep='') + } + memb <- as.factor(memb) + print(memb) + x[,par1] <- memb + } > if (par2=='equal') { + ed <- cut(as.numeric(x[,par1]),par3,labels=paste('C',1:par3,sep='')) + x[,par1] <- as.factor(ed) + } > table(x[,par1]) 163.93 164.28 164.58 165.97 166.07 166.19 166.26 166.27 166.3 166.35 166.44 1 1 1 1 1 3 1 2 1 1 1 166.52 166.64 167.16 167.17 167.39 168.46 168.55 168.58 169.21 169.24 169.29 1 1 3 1 1 1 1 2 1 1 1 169.53 169.57 169.67 170.04 170.39 170.48 170.49 170.57 170.72 171.05 171.07 1 2 1 1 1 3 1 1 1 1 3 171.11 172.28 172.69 172.74 172.86 172.89 172.98 173.2 173.24 173.38 1 1 1 1 2 1 2 1 1 1 > colnames(x) [1] "Gemconsprijsblazers" "consumptieindexkleding" > colnames(x)[par1] [1] "Gemconsprijsblazers" > x[,par1] [1] 172.69 172.98 172.98 172.89 173.38 173.20 173.24 172.86 172.86 172.74 [11] 172.28 171.05 171.07 171.07 171.07 171.11 170.72 170.49 170.48 170.48 [21] 170.48 170.57 170.39 170.04 169.67 169.57 169.57 169.53 169.24 169.29 [31] 169.21 168.58 168.58 168.55 168.46 167.39 167.16 167.16 167.16 167.17 [41] 166.52 166.35 166.19 166.19 166.19 166.07 166.64 166.26 166.44 166.27 [51] 166.27 166.30 165.97 164.58 164.28 163.93 > if (par2 == 'none') { + m <- ctree(as.formula(paste(colnames(x)[par1],' ~ .',sep='')),data = x) + } > > #Note: the /var/www/html/rcomp/createtable file can be downloaded at http://www.wessa.net/cretab > load(file="/var/www/html/rcomp/createtable") > > if (par2 != 'none') { + m <- ctree(as.formula(paste('as.factor(',colnames(x)[par1],') ~ .',sep='')),data = x) + if (par4=='yes') { + a<-table.start() + a<-table.row.start(a) + a<-table.element(a,'10-Fold Cross Validation',3+2*par3,TRUE) + a<-table.row.end(a) + a<-table.row.start(a) + a<-table.element(a,'',1,TRUE) + a<-table.element(a,'Prediction (training)',par3+1,TRUE) + a<-table.element(a,'Prediction (testing)',par3+1,TRUE) + a<-table.row.end(a) + a<-table.row.start(a) + a<-table.element(a,'Actual',1,TRUE) + for (jjj in 1:par3) a<-table.element(a,paste('C',jjj,sep=''),1,TRUE) + a<-table.element(a,'CV',1,TRUE) + for (jjj in 1:par3) a<-table.element(a,paste('C',jjj,sep=''),1,TRUE) + a<-table.element(a,'CV',1,TRUE) + a<-table.row.end(a) + for (i in 1:10) { + ind <- sample(2, nrow(x), replace=T, prob=c(0.9,0.1)) + m.ct <- ctree(as.formula(paste('as.factor(',colnames(x)[par1],') ~ .',sep='')),data =x[ind==1,]) + if (i==1) { + m.ct.i.pred <- predict(m.ct, newdata=x[ind==1,]) + m.ct.i.actu <- x[ind==1,par1] + m.ct.x.pred <- predict(m.ct, newdata=x[ind==2,]) + m.ct.x.actu <- x[ind==2,par1] + } else { + m.ct.i.pred <- c(m.ct.i.pred,predict(m.ct, newdata=x[ind==1,])) + m.ct.i.actu <- c(m.ct.i.actu,x[ind==1,par1]) + m.ct.x.pred <- c(m.ct.x.pred,predict(m.ct, newdata=x[ind==2,])) + m.ct.x.actu <- c(m.ct.x.actu,x[ind==2,par1]) + } + } + print(m.ct.i.tab <- table(m.ct.i.actu,m.ct.i.pred)) + numer <- 0 + for (i in 1:par3) { + print(m.ct.i.tab[i,i] / sum(m.ct.i.tab[i,])) + numer <- numer + m.ct.i.tab[i,i] + } + print(m.ct.i.cp <- numer / sum(m.ct.i.tab)) + print(m.ct.x.tab <- table(m.ct.x.actu,m.ct.x.pred)) + numer <- 0 + for (i in 1:par3) { + print(m.ct.x.tab[i,i] / sum(m.ct.x.tab[i,])) + numer <- numer + m.ct.x.tab[i,i] + } + print(m.ct.x.cp <- numer / sum(m.ct.x.tab)) + for (i in 1:par3) { + a<-table.row.start(a) + a<-table.element(a,paste('C',i,sep=''),1,TRUE) + for (jjj in 1:par3) a<-table.element(a,m.ct.i.tab[i,jjj]) + a<-table.element(a,round(m.ct.i.tab[i,i]/sum(m.ct.i.tab[i,]),4)) + for (jjj in 1:par3) a<-table.element(a,m.ct.x.tab[i,jjj]) + a<-table.element(a,round(m.ct.x.tab[i,i]/sum(m.ct.x.tab[i,]),4)) + a<-table.row.end(a) + } + a<-table.row.start(a) + a<-table.element(a,'Overall',1,TRUE) + for (jjj in 1:par3) a<-table.element(a,'-') + a<-table.element(a,round(m.ct.i.cp,4)) + for (jjj in 1:par3) a<-table.element(a,'-') + a<-table.element(a,round(m.ct.x.cp,4)) + a<-table.row.end(a) + a<-table.end(a) + table.save(a,file="/var/www/html/rcomp/tmp/1xvcr1293184942.tab") + } + } > m Conditional inference tree with 4 terminal nodes Response: Gemconsprijsblazers Input: consumptieindexkleding Number of observations: 56 1) consumptieindexkleding <= 101.66; criterion = 1, statistic = 51.859 2) consumptieindexkleding <= 101.02; criterion = 1, statistic = 19.047 3)* weights = 16 2) consumptieindexkleding > 101.02 4)* weights = 10 1) consumptieindexkleding > 101.66 5) consumptieindexkleding <= 103.54; criterion = 1, statistic = 25.185 6)* weights = 19 5) consumptieindexkleding > 103.54 7)* weights = 11 > postscript(file="/var/www/html/rcomp/tmp/2xvcr1293184942.ps",horizontal=F,onefile=F,pagecentre=F,paper="special",width=8.3333333333333,height=5.5555555555556) > plot(m) > dev.off() null device 1 > postscript(file="/var/www/html/rcomp/tmp/374tu1293184942.ps",horizontal=F,onefile=F,pagecentre=F,paper="special",width=8.3333333333333,height=5.5555555555556) > plot(x[,par1] ~ as.factor(where(m)),main='Response by Terminal Node',xlab='Terminal Node',ylab='Response') > dev.off() null device 1 > if (par2 == 'none') { + forec <- predict(m) + result <- as.data.frame(cbind(x[,par1],forec,x[,par1]-forec)) + colnames(result) <- c('Actuals','Forecasts','Residuals') + print(result) + } Actuals Forecasts Residuals 1 172.69 172.9182 -0.22818182 2 172.98 172.9182 0.06181818 3 172.98 172.9182 0.06181818 4 172.89 172.9182 -0.02818182 5 173.38 172.9182 0.46181818 6 173.20 172.9182 0.28181818 7 173.24 172.9182 0.32181818 8 172.86 172.9182 -0.05818182 9 172.86 172.9182 -0.05818182 10 172.74 172.9182 -0.17818182 11 172.28 172.9182 -0.63818182 12 171.05 170.3100 0.74000000 13 171.07 170.3100 0.76000000 14 171.07 170.3100 0.76000000 15 171.07 170.3100 0.76000000 16 171.11 170.3100 0.80000000 17 170.72 170.3100 0.41000000 18 170.49 170.3100 0.18000000 19 170.48 170.3100 0.17000000 20 170.48 170.3100 0.17000000 21 170.48 170.3100 0.17000000 22 170.57 170.3100 0.26000000 23 170.39 170.3100 0.08000000 24 170.04 170.3100 -0.27000000 25 169.67 170.3100 -0.64000000 26 169.57 170.3100 -0.74000000 27 169.57 170.3100 -0.74000000 28 169.53 170.3100 -0.78000000 29 169.24 170.3100 -1.07000000 30 169.29 170.3100 -1.02000000 31 169.21 167.9420 1.26800000 32 168.58 167.9420 0.63800000 33 168.58 167.9420 0.63800000 34 168.55 167.9420 0.60800000 35 168.46 167.9420 0.51800000 36 167.39 167.9420 -0.55200000 37 167.16 167.9420 -0.78200000 38 167.16 167.9420 -0.78200000 39 167.16 167.9420 -0.78200000 40 167.17 167.9420 -0.77200000 41 166.52 165.9031 0.61687500 42 166.35 165.9031 0.44687500 43 166.19 165.9031 0.28687500 44 166.19 165.9031 0.28687500 45 166.19 165.9031 0.28687500 46 166.07 165.9031 0.16687500 47 166.64 165.9031 0.73687500 48 166.26 165.9031 0.35687500 49 166.44 165.9031 0.53687500 50 166.27 165.9031 0.36687500 51 166.27 165.9031 0.36687500 52 166.30 165.9031 0.39687500 53 165.97 165.9031 0.06687500 54 164.58 165.9031 -1.32312500 55 164.28 165.9031 -1.62312500 56 163.93 165.9031 -1.97312500 > if (par2 != 'none') { + print(cbind(as.factor(x[,par1]),predict(m))) + myt <- table(as.factor(x[,par1]),predict(m)) + print(myt) + } > postscript(file="/var/www/html/rcomp/tmp/4ivax1293184942.ps",horizontal=F,onefile=F,pagecentre=F,paper="special",width=8.3333333333333,height=5.5555555555556) > if(par2=='none') { + op <- par(mfrow=c(2,2)) + plot(density(result$Actuals),main='Kernel Density Plot of Actuals') + plot(density(result$Residuals),main='Kernel Density Plot of Residuals') + plot(result$Forecasts,result$Actuals,main='Actuals versus Predictions',xlab='Predictions',ylab='Actuals') + plot(density(result$Forecasts),main='Kernel Density Plot of Predictions') + par(op) + } > if(par2!='none') { + plot(myt,main='Confusion Matrix',xlab='Actual',ylab='Predicted') + } > dev.off() null device 1 > if (par2 == 'none') { + detcoef <- cor(result$Forecasts,result$Actuals) + a<-table.start() + a<-table.row.start(a) + a<-table.element(a,'Goodness of Fit',2,TRUE) + a<-table.row.end(a) + a<-table.row.start(a) + a<-table.element(a,'Correlation',1,TRUE) + a<-table.element(a,round(detcoef,4)) + a<-table.row.end(a) + a<-table.row.start(a) + a<-table.element(a,'R-squared',1,TRUE) + a<-table.element(a,round(detcoef*detcoef,4)) + a<-table.row.end(a) + a<-table.row.start(a) + a<-table.element(a,'RMSE',1,TRUE) + a<-table.element(a,round(sqrt(mean((result$Residuals)^2)),4)) + a<-table.row.end(a) + a<-table.end(a) + table.save(a,file="/var/www/html/rcomp/tmp/53w931293184942.tab") + a<-table.start() + a<-table.row.start(a) + a<-table.element(a,'Actuals, Predictions, and Residuals',4,TRUE) + a<-table.row.end(a) + a<-table.row.start(a) + a<-table.element(a,'#',header=TRUE) + a<-table.element(a,'Actuals',header=TRUE) + a<-table.element(a,'Forecasts',header=TRUE) + a<-table.element(a,'Residuals',header=TRUE) + a<-table.row.end(a) + for (i in 1:length(result$Actuals)) { + a<-table.row.start(a) + a<-table.element(a,i,header=TRUE) + a<-table.element(a,result$Actuals[i]) + a<-table.element(a,result$Forecasts[i]) + a<-table.element(a,result$Residuals[i]) + a<-table.row.end(a) + } + a<-table.end(a) + table.save(a,file="/var/www/html/rcomp/tmp/67e7r1293184942.tab") + } > if (par2 != 'none') { + a<-table.start() + a<-table.row.start(a) + a<-table.element(a,'Confusion Matrix (predicted in columns / actuals in rows)',par3+1,TRUE) + a<-table.row.end(a) + a<-table.row.start(a) + a<-table.element(a,'',1,TRUE) + for (i in 1:par3) { + a<-table.element(a,paste('C',i,sep=''),1,TRUE) + } + a<-table.row.end(a) + for (i in 1:par3) { + a<-table.row.start(a) + a<-table.element(a,paste('C',i,sep=''),1,TRUE) + for (j in 1:par3) { + a<-table.element(a,myt[i,j]) + } + a<-table.row.end(a) + } + a<-table.end(a) + table.save(a,file="/var/www/html/rcomp/tmp/7ax6f1293184942.tab") + } > > try(system("convert tmp/2xvcr1293184942.ps tmp/2xvcr1293184942.png",intern=TRUE)) character(0) > try(system("convert tmp/374tu1293184942.ps tmp/374tu1293184942.png",intern=TRUE)) character(0) > try(system("convert tmp/4ivax1293184942.ps tmp/4ivax1293184942.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 2.180 0.573 6.789