R version 2.15.2 (2012-10-26) -- "Trick or Treat" Copyright (C) 2012 The R Foundation for Statistical Computing ISBN 3-900051-07-0 Platform: i686-pc-linux-gnu (32-bit) 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(-4 + ,-16 + ,3 + ,0 + ,3 + ,-6 + ,-18 + ,5 + ,-2 + ,0 + ,-3 + ,-14 + ,0 + ,1 + ,-1 + ,-3 + ,-12 + ,-2 + ,-2 + ,-1 + ,-7 + ,-17 + ,6 + ,-2 + ,-4 + ,-9 + ,-23 + ,11 + ,-2 + ,1 + ,-11 + ,-28 + ,9 + ,-6 + ,-1 + ,-13 + ,-31 + ,17 + ,-4 + ,0 + ,-11 + ,-21 + ,21 + ,-2 + ,-1 + ,-9 + ,-19 + ,21 + ,0 + ,6 + ,-17 + ,-22 + ,41 + ,-5 + ,0 + ,-22 + ,-22 + ,57 + ,-4 + ,-3 + ,-25 + ,-25 + ,65 + ,-5 + ,-3 + ,-20 + ,-16 + ,68 + ,-1 + ,4 + ,-24 + ,-22 + ,73 + ,-2 + ,1 + ,-24 + ,-21 + ,71 + ,-4 + ,0 + ,-22 + ,-10 + ,71 + ,-1 + ,-4 + ,-19 + ,-7 + ,70 + ,1 + ,-2 + ,-18 + ,-5 + ,69 + ,1 + ,3 + ,-17 + ,-4 + ,65 + ,-2 + ,2 + ,-11 + ,7 + ,57 + ,1 + ,5 + ,-11 + ,6 + ,57 + ,1 + ,6 + ,-12 + ,3 + ,57 + ,3 + ,6 + ,-10 + ,10 + ,55 + ,3 + ,3 + ,-15 + ,0 + ,65 + ,1 + ,4 + ,-15 + ,-2 + ,65 + ,1 + ,7 + ,-15 + ,-1 + ,64 + ,0 + ,5 + ,-13 + ,2 + ,60 + ,2 + ,6 + ,-8 + ,8 + ,43 + ,2 + ,1 + ,-13 + ,-6 + ,47 + ,-1 + ,3 + ,-9 + ,-4 + ,40 + ,1 + ,6 + ,-7 + ,4 + ,31 + ,0 + ,0 + ,-4 + ,7 + ,27 + ,1 + ,3 + ,-4 + ,3 + ,24 + ,1 + ,4 + ,-2 + ,3 + ,23 + ,3 + ,7 + ,0 + ,8 + ,17 + ,2 + ,6 + ,-2 + ,3 + ,16 + ,0 + ,6 + ,-3 + ,-3 + ,15 + ,0 + ,6 + ,1 + ,4 + ,8 + ,3 + ,6 + ,-2 + ,-5 + ,5 + ,-2 + ,2 + ,-1 + ,-1 + ,6 + ,0 + ,2 + ,1 + ,5 + ,5 + ,1 + ,2 + ,-3 + ,0 + ,12 + ,-1 + ,3 + ,-4 + ,-6 + ,8 + ,-2 + ,-1 + ,-9 + ,-13 + ,17 + ,-1 + ,-4 + ,-9 + ,-15 + ,22 + ,-1 + ,4 + ,-7 + ,-8 + ,24 + ,1 + ,5 + ,-14 + ,-20 + ,36 + ,-2 + ,3 + ,-12 + ,-10 + ,31 + ,-5 + ,-1 + ,-16 + ,-22 + ,34 + ,-5 + ,-4 + ,-20 + ,-25 + ,47 + ,-6 + ,0 + ,-12 + ,-10 + ,33 + ,-4 + ,-1 + ,-12 + ,-8 + ,35 + ,-3 + ,-1 + ,-10 + ,-9 + ,31 + ,-3 + ,3 + ,-10 + ,-5 + ,35 + ,-1 + ,2 + ,-13 + ,-7 + ,39 + ,-2 + ,-4 + ,-16 + ,-11 + ,46 + ,-3 + ,-3 + ,-14 + ,-11 + ,40 + ,-3 + ,-1 + ,-17 + ,-16 + ,50 + ,-3 + ,3 + ,-24 + ,-28 + ,62 + ,-5 + ,-2) + ,dim=c(5 + ,60) + ,dimnames=list(c('Consumer_confidence_indicator' + ,'General_economic_situation' + ,'Unemployment_in_Belgium' + ,'Financial_situation_of_households' + ,'Saving_capacity_of_households ') + ,1:60)) > y <- array(NA,dim=c(5,60),dimnames=list(c('Consumer_confidence_indicator','General_economic_situation','Unemployment_in_Belgium','Financial_situation_of_households','Saving_capacity_of_households '),1:60)) > 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 = '2' > par2 = 'quantiles' > par1 = '1' > 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, 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) Hmisc library by Frank E Harrell Jr Type library(help='Hmisc'), ?Overview, or ?Hmisc.Overview') to see overall documentation. NOTE:Hmisc no longer redefines [.factor to drop unused levels when subsetting. To get the old behavior of Hmisc type dropUnusedLevels(). 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] "Consumer_confidence_indicator" > x[,par1] [1] -4 -6 -3 -3 -7 -9 -11 -13 -11 -9 -17 -22 -25 -20 -24 -24 -22 -19 -18 [20] -17 -11 -11 -12 -10 -15 -15 -15 -13 -8 -13 -9 -7 -4 -4 -2 0 -2 -3 [39] 1 -2 -1 1 -3 -4 -9 -9 -7 -14 -12 -16 -20 -12 -12 -10 -10 -13 -16 [58] -14 -17 -24 > 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]) [-25,-10) [-10, 1] 32 28 > colnames(x) [1] "Consumer_confidence_indicator" "General_economic_situation" [3] "Unemployment_in_Belgium" "Financial_situation_of_households" [5] "Saving_capacity_of_households." > colnames(x)[par1] [1] "Consumer_confidence_indicator" > x[,par1] [1] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-25,-10) [8] [-25,-10) [-25,-10) [-10, 1] [-25,-10) [-25,-10) [-25,-10) [-25,-10) [15] [-25,-10) [-25,-10) [-25,-10) [-25,-10) [-25,-10) [-25,-10) [-25,-10) [22] [-25,-10) [-25,-10) [-10, 1] [-25,-10) [-25,-10) [-25,-10) [-25,-10) [29] [-10, 1] [-25,-10) [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [36] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [43] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-10, 1] [-25,-10) [-25,-10) [50] [-25,-10) [-25,-10) [-25,-10) [-25,-10) [-10, 1] [-10, 1] [-25,-10) [57] [-25,-10) [-25,-10) [-25,-10) [-25,-10) Levels: [-25,-10) [-10, 1] > if (par2 == 'none') { + m <- ctree(as.formula(paste(colnames(x)[par1],' ~ .',sep='')),data = x) + } > > #Note: the /var/fisher/rcomp/createtable file can be downloaded at http://www.wessa.net/cretab > load(file="/var/fisher/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/fisher/rcomp/tmp/1x3b31355269660.tab") + } + } > m Conditional inference tree with 3 terminal nodes Response: as.factor(Consumer_confidence_indicator) Inputs: General_economic_situation, Unemployment_in_Belgium, Financial_situation_of_households, Saving_capacity_of_households. Number of observations: 60 1) Unemployment_in_Belgium <= 31; criterion = 1, statistic = 30.637 2) Financial_situation_of_households <= -2; criterion = 0.998, statistic = 11.934 3)* weights = 11 2) Financial_situation_of_households > -2 4)* weights = 17 1) Unemployment_in_Belgium > 31 5)* weights = 32 > postscript(file="/var/fisher/rcomp/tmp/226li1355269660.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/fisher/rcomp/tmp/399161355269660.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) + } > if (par2 != 'none') { + print(cbind(as.factor(x[,par1]),predict(m))) + myt <- table(as.factor(x[,par1]),predict(m)) + print(myt) + } [,1] [,2] [1,] 2 2 [2,] 2 2 [3,] 2 2 [4,] 2 2 [5,] 2 2 [6,] 2 2 [7,] 1 2 [8,] 1 2 [9,] 1 2 [10,] 2 2 [11,] 1 1 [12,] 1 1 [13,] 1 1 [14,] 1 1 [15,] 1 1 [16,] 1 1 [17,] 1 1 [18,] 1 1 [19,] 1 1 [20,] 1 1 [21,] 1 1 [22,] 1 1 [23,] 1 1 [24,] 2 1 [25,] 1 1 [26,] 1 1 [27,] 1 1 [28,] 1 1 [29,] 2 1 [30,] 1 1 [31,] 2 1 [32,] 2 2 [33,] 2 2 [34,] 2 2 [35,] 2 2 [36,] 2 2 [37,] 2 2 [38,] 2 2 [39,] 2 2 [40,] 2 2 [41,] 2 2 [42,] 2 2 [43,] 2 2 [44,] 2 2 [45,] 2 2 [46,] 2 2 [47,] 2 2 [48,] 1 1 [49,] 1 2 [50,] 1 1 [51,] 1 1 [52,] 1 1 [53,] 1 1 [54,] 2 2 [55,] 2 1 [56,] 1 1 [57,] 1 1 [58,] 1 1 [59,] 1 1 [60,] 1 1 [-25,-10) [-10, 1] [-25,-10) 28 4 [-10, 1] 4 24 > postscript(file="/var/fisher/rcomp/tmp/4vtoz1355269660.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$Residuals)^2)),4)) + a<-table.row.end(a) + a<-table.end(a) + table.save(a,file="/var/fisher/rcomp/tmp/5pqg21355269660.tab") + a<-table.start() + a<-table.row.start(a) + a<-table.element(a,'Actuals, Predictions, and Residuals',4,TRUE) + a<-table.row.end(a) + a<-table.row.start(a) + a<-table.element(a,'#',header=TRUE) + a<-table.element(a,'Actuals',header=TRUE) + a<-table.element(a,'Forecasts',header=TRUE) + a<-table.element(a,'Residuals',header=TRUE) + a<-table.row.end(a) + for (i in 1:length(result$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/fisher/rcomp/tmp/6mxbn1355269660.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/fisher/rcomp/tmp/7l1xc1355269660.tab") + } > > try(system("convert tmp/226li1355269660.ps tmp/226li1355269660.png",intern=TRUE)) character(0) > try(system("convert tmp/399161355269660.ps tmp/399161355269660.png",intern=TRUE)) character(0) > try(system("convert tmp/4vtoz1355269660.ps tmp/4vtoz1355269660.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 3.666 0.549 4.203