R version 2.13.0 (2011-04-13) Copyright (C) 2011 The R Foundation for Statistical Computing ISBN 3-900051-07-0 Platform: i486-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(97.06 + ,21454 + ,631923 + ,130678 + ,97.73 + ,23899 + ,654294 + ,120877 + ,98 + ,24939 + ,671833 + ,137114 + ,97.76 + ,23580 + ,586840 + ,134406 + ,97.48 + ,24562 + ,600969 + ,120262 + ,97.77 + ,24696 + ,625568 + ,130846 + ,97.96 + ,23785 + ,558110 + ,120343 + ,98.22 + ,23812 + ,630577 + ,98881 + ,98.51 + ,21917 + ,628654 + ,115678 + ,98.19 + ,19713 + ,603184 + ,120796 + ,98.37 + ,19282 + ,656255 + ,94261 + ,98.31 + ,18788 + ,600730 + ,89151 + ,98.6 + ,21453 + ,670326 + ,119880 + ,98.96 + ,24482 + ,678423 + ,131468 + ,99.11 + ,27474 + ,641502 + ,155089 + ,99.64 + ,27264 + ,625311 + ,149581 + ,100.02 + ,27349 + ,628177 + ,122788 + ,99.98 + ,30632 + ,589767 + ,143900 + ,100.32 + ,29429 + ,582471 + ,112115 + ,100.44 + ,30084 + ,636248 + ,109600 + ,100.51 + ,26290 + ,599885 + ,117446 + ,101 + ,24379 + ,621694 + ,118456 + ,100.88 + ,23335 + ,637406 + ,101901 + ,100.55 + ,21346 + ,595994 + ,89940 + ,100.82 + ,21106 + ,696308 + ,129143 + ,101.5 + ,24514 + ,674201 + ,126102 + ,102.15 + ,28353 + ,648861 + ,143048 + ,102.39 + ,30805 + ,649605 + ,142258 + ,102.54 + ,31348 + ,672392 + ,131011 + ,102.85 + ,34556 + ,598396 + ,146471 + ,103.47 + ,33855 + ,613177 + ,114073 + ,103.56 + ,34787 + ,638104 + ,114642 + ,103.69 + ,32529 + ,615632 + ,118226 + ,103.49 + ,29998 + ,634465 + ,111338 + ,103.47 + ,29257 + ,638686 + ,108701 + ,103.45 + ,28155 + ,604243 + ,80512 + ,103.48 + ,30466 + ,706669 + ,146865 + ,103.93 + ,35704 + ,677185 + ,137179 + ,103.89 + ,39327 + ,644328 + ,166536 + ,104.4 + ,39351 + ,664825 + ,137070 + ,104.79 + ,42234 + ,605707 + ,127090 + ,104.77 + ,43630 + ,600136 + ,139966 + ,105.13 + ,43722 + ,612166 + ,122243 + ,105.26 + ,43121 + ,599659 + ,109097 + ,104.96 + ,37985 + ,634210 + ,116591 + ,104.75 + ,37135 + ,618234 + ,111964 + ,105.01 + ,34646 + ,613576 + ,109754 + ,105.15 + ,33026 + ,627200 + ,77609 + ,105.2 + ,35087 + ,668973 + ,138445 + ,105.77 + ,38846 + ,651479 + ,127901 + ,105.78 + ,42013 + ,619661 + ,156615 + ,106.26 + ,43908 + ,644260 + ,133264 + ,106.13 + ,42868 + ,579936 + ,143521 + ,106.12 + ,44423 + ,601752 + ,152139 + ,106.57 + ,44167 + ,595376 + ,131523 + ,106.44 + ,43636 + ,588902 + ,113925 + ,106.54 + ,44382 + ,634341 + ,86495 + ,107.1 + ,42142 + ,594305 + ,127877 + ,108.1 + ,43452 + ,606200 + ,107017 + ,108.4 + ,36912 + ,610926 + ,78716 + ,108.84 + ,42413 + ,633685 + ,138278 + ,109.62 + ,45344 + ,639696 + ,144238 + ,110.42 + ,44873 + ,659451 + ,143679 + ,110.67 + ,47510 + ,593248 + ,159932 + ,111.66 + ,49554 + ,606677 + ,136781 + ,112.28 + ,47369 + ,599434 + ,148173 + ,112.87 + ,45998 + ,569578 + ,125673 + ,112.18 + ,48140 + ,629873 + ,105573 + ,112.36 + ,48441 + ,613438 + ,122405 + ,112.16 + ,44928 + ,604172 + ,128045 + ,111.49 + ,40454 + ,658328 + ,94467 + ,111.25 + ,38661 + ,612633 + ,85573 + ,111.36 + ,37246 + ,707372 + ,121501 + ,111.74 + ,36843 + ,739770 + ,125074 + ,111.1 + ,36424 + ,777535 + ,144979 + ,111.33 + ,37594 + ,685030 + ,142120 + ,111.25 + ,38144 + ,730234 + ,124213 + ,111.04 + ,38737 + ,714154 + ,144407 + ,110.97 + ,34560 + ,630872 + ,125170 + ,111.31 + ,36080 + ,719492 + ,109267 + ,111.02 + ,33508 + ,677023 + ,122354 + ,111.07 + ,35462 + ,679272 + ,122589 + ,111.36 + ,33374 + ,718317 + ,104982 + ,111.54 + ,32110 + ,645672 + ,90542) + ,dim=c(4 + ,84) + ,dimnames=list(c('conusmentenprijsindex' + ,'vacatures' + ,'werkloosheid' + ,'inschrijvingen') + ,1:84)) > y <- array(NA,dim=c(4,84),dimnames=list(c('conusmentenprijsindex','vacatures','werkloosheid','inschrijvingen'),1:84)) > for (i in 1:dim(x)[1]) + { + for (j in 1:dim(x)[2]) + { + y[i,j] <- as.numeric(x[i,j]) + } + } > par4 = 'yes' > par3 = '3' > par2 = 'quantiles' > 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$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_YOURPAGE.wasp/ > #Source of accompanying publication: > #Technical description: > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Attaching package: 'Hmisc' The following object(s) are masked from 'package:survival': untangle.specials The following object(s) are masked from 'package:base': format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "conusmentenprijsindex" > x[,par1] [1] 97.06 97.73 98.00 97.76 97.48 97.77 97.96 98.22 98.51 98.19 [11] 98.37 98.31 98.60 98.96 99.11 99.64 100.02 99.98 100.32 100.44 [21] 100.51 101.00 100.88 100.55 100.82 101.50 102.15 102.39 102.54 102.85 [31] 103.47 103.56 103.69 103.49 103.47 103.45 103.48 103.93 103.89 104.40 [41] 104.79 104.77 105.13 105.26 104.96 104.75 105.01 105.15 105.20 105.77 [51] 105.78 106.26 106.13 106.12 106.57 106.44 106.54 107.10 108.10 108.40 [61] 108.84 109.62 110.42 110.67 111.66 112.28 112.87 112.18 112.36 112.16 [71] 111.49 111.25 111.36 111.74 111.10 111.33 111.25 111.04 110.97 111.31 [81] 111.02 111.07 111.36 111.54 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$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]) [ 97.1,103) [102.5,107) [106.6,113] 28 28 28 > colnames(x) [1] "conusmentenprijsindex" "vacatures" "werkloosheid" [4] "inschrijvingen" > colnames(x)[par1] [1] "conusmentenprijsindex" > x[,par1] [1] [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [7] [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [13] [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [19] [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [25] [ 97.1,103) [ 97.1,103) [ 97.1,103) [ 97.1,103) [102.5,107) [102.5,107) [31] [102.5,107) [102.5,107) [102.5,107) [102.5,107) [102.5,107) [102.5,107) [37] [102.5,107) [102.5,107) [102.5,107) [102.5,107) [102.5,107) [102.5,107) [43] [102.5,107) [102.5,107) [102.5,107) [102.5,107) [102.5,107) [102.5,107) [49] [102.5,107) [102.5,107) [102.5,107) [102.5,107) [102.5,107) [102.5,107) [55] [106.6,113] [102.5,107) [102.5,107) [106.6,113] [106.6,113] [106.6,113] [61] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [67] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [73] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [79] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [106.6,113] [106.6,113] Levels: [ 97.1,103) [102.5,107) [106.6,113] > if (par2 == 'none') { + m <- ctree(as.formula(paste(colnames(x)[par1],' ~ .',sep='')),data = x) + } > > #Note: the /var/wessaorg/rcomp/createtable file can be downloaded at http://www.wessa.net/cretab > load(file="/var/wessaorg/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/wessaorg/rcomp/tmp/1tp111323526001.tab") + } + } m.ct.i.pred m.ct.i.actu 1 2 3 1 250 0 0 2 36 45 167 3 0 29 221 [1] 1 [1] 0.1814516 [1] 0.884 [1] 0.6898396 m.ct.x.pred m.ct.x.actu 1 2 3 1 29 1 0 2 4 3 25 3 0 9 21 [1] 0.9666667 [1] 0.09375 [1] 0.7 [1] 0.576087 > m Conditional inference tree with 3 terminal nodes Response: as.factor(conusmentenprijsindex) Inputs: vacatures, werkloosheid, inschrijvingen Number of observations: 84 1) vacatures <= 30805; criterion = 1, statistic = 57.55 2) vacatures <= 27474; criterion = 0.968, statistic = 6.526 3)* weights = 23 2) vacatures > 27474 4)* weights = 9 1) vacatures > 30805 5)* weights = 52 > postscript(file="/var/wessaorg/rcomp/tmp/2all91323526001.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/wessaorg/rcomp/tmp/37jdj1323526001.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,] 1 1 [2,] 1 1 [3,] 1 1 [4,] 1 1 [5,] 1 1 [6,] 1 1 [7,] 1 1 [8,] 1 1 [9,] 1 1 [10,] 1 1 [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,] 1 1 [25,] 1 1 [26,] 1 1 [27,] 1 1 [28,] 1 1 [29,] 2 3 [30,] 2 3 [31,] 2 3 [32,] 2 3 [33,] 2 3 [34,] 2 1 [35,] 2 1 [36,] 2 1 [37,] 2 1 [38,] 2 3 [39,] 2 3 [40,] 2 3 [41,] 2 3 [42,] 2 3 [43,] 2 3 [44,] 2 3 [45,] 2 3 [46,] 2 3 [47,] 2 3 [48,] 2 3 [49,] 2 3 [50,] 2 3 [51,] 2 3 [52,] 2 3 [53,] 2 3 [54,] 2 3 [55,] 3 3 [56,] 2 3 [57,] 2 3 [58,] 3 3 [59,] 3 3 [60,] 3 3 [61,] 3 3 [62,] 3 3 [63,] 3 3 [64,] 3 3 [65,] 3 3 [66,] 3 3 [67,] 3 3 [68,] 3 3 [69,] 3 3 [70,] 3 3 [71,] 3 3 [72,] 3 3 [73,] 3 3 [74,] 3 3 [75,] 3 3 [76,] 3 3 [77,] 3 3 [78,] 3 3 [79,] 3 3 [80,] 3 3 [81,] 3 3 [82,] 3 3 [83,] 3 3 [84,] 3 3 [ 97.1,103) [102.5,107) [106.6,113] [ 97.1,103) 28 0 0 [102.5,107) 4 0 24 [106.6,113] 0 0 28 > postscript(file="/var/wessaorg/rcomp/tmp/44qm41323526001.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/wessaorg/rcomp/tmp/5dvcf1323526001.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/wessaorg/rcomp/tmp/6c0kg1323526001.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/wessaorg/rcomp/tmp/748871323526001.tab") + } > > try(system("convert tmp/2all91323526001.ps tmp/2all91323526001.png",intern=TRUE)) character(0) > try(system("convert tmp/37jdj1323526001.ps tmp/37jdj1323526001.png",intern=TRUE)) character(0) > try(system("convert tmp/44qm41323526001.ps tmp/44qm41323526001.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 3.100 0.192 3.333