R version 2.12.0 (2010-10-15) Copyright (C) 2010 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(235.1,9700,280.7,9081,264.6,9084,240.7,9743,201.4,8587,240.8,9731,241.1,9563,223.8,9998,206.1,9437,174.7,10038,203.3,9918,220.5,9252,299.5,9737,347.4,9035,338.3,9133,327.7,9487,351.6,8700,396.6,9627,438.8,8947,395.6,9283,363.5,8829,378.8,9947,357,9628,369,9318,464.8,9605,479.1,8640,431.3,9214,366.5,9567,326.3,8547,355.1,9185,331.6,9470,261.3,9123,249,9278,205.5,10170,235.6,9434,240.9,9655,264.9,9429,253.8,8739,232.3,9552,193.8,9687,177,9019,213.2,9672,207.2,9206,180.6,9069,188.6,9788,175.4,10312,199,10105,179.6,9863,225.8,9656,234,9295,200.2,9946,183.6,9701,178.2,9049,203.2,10190,208.5,9706,191.8,9765,172.8,9893,148,9994,159.4,10433,154.5,10073,213.2,10112,196.4,9266,182.8,9820,176.4,10097,153.6,9115,173.2,10411,171,9678,151.2,10408,161.9,10153,157.2,10368,201.7,10581,236.4,10597,356.1,10680,398.3,9738,403.7,9556),dim=c(2,75),dimnames=list(c('Werkloosheid','Geboortes'),1:75)) > y <- array(NA,dim=c(2,75),dimnames=list(c('Werkloosheid','Geboortes'),1:75)) > 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 = '2' > #'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$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_YOURPAGE.wasp/ > #Source of accompanying publication: > #Technical description: > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Attaching package: 'Hmisc' The following object(s) are masked from 'package:survival': untangle.specials The following object(s) are masked from 'package:base': format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "Geboortes" > x[,par1] [1] 9700 9081 9084 9743 8587 9731 9563 9998 9437 10038 9918 9252 [13] 9737 9035 9133 9487 8700 9627 8947 9283 8829 9947 9628 9318 [25] 9605 8640 9214 9567 8547 9185 9470 9123 9278 10170 9434 9655 [37] 9429 8739 9552 9687 9019 9672 9206 9069 9788 10312 10105 9863 [49] 9656 9295 9946 9701 9049 10190 9706 9765 9893 9994 10433 10073 [61] 10112 9266 9820 10097 9115 10411 9678 10408 10153 10368 10581 10597 [73] 10680 9738 9556 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$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]) [8547, 9656) [9656,10680] 38 37 > colnames(x) [1] "Werkloosheid" "Geboortes" > colnames(x)[par1] [1] "Geboortes" > x[,par1] [1] [9656,10680] [8547, 9656) [8547, 9656) [9656,10680] [8547, 9656) [6] [9656,10680] [8547, 9656) [9656,10680] [8547, 9656) [9656,10680] [11] [9656,10680] [8547, 9656) [9656,10680] [8547, 9656) [8547, 9656) [16] [8547, 9656) [8547, 9656) [8547, 9656) [8547, 9656) [8547, 9656) [21] [8547, 9656) [9656,10680] [8547, 9656) [8547, 9656) [8547, 9656) [26] [8547, 9656) [8547, 9656) [8547, 9656) [8547, 9656) [8547, 9656) [31] [8547, 9656) [8547, 9656) [8547, 9656) [9656,10680] [8547, 9656) [36] [8547, 9656) [8547, 9656) [8547, 9656) [8547, 9656) [9656,10680] [41] [8547, 9656) [9656,10680] [8547, 9656) [8547, 9656) [9656,10680] [46] [9656,10680] [9656,10680] [9656,10680] [9656,10680] [8547, 9656) [51] [9656,10680] [9656,10680] [8547, 9656) [9656,10680] [9656,10680] [56] [9656,10680] [9656,10680] [9656,10680] [9656,10680] [9656,10680] [61] [9656,10680] [8547, 9656) [9656,10680] [9656,10680] [8547, 9656) [66] [9656,10680] [9656,10680] [9656,10680] [9656,10680] [9656,10680] [71] [9656,10680] [9656,10680] [9656,10680] [9656,10680] [8547, 9656) Levels: [8547, 9656) [9656,10680] > if (par2 == 'none') { + m <- ctree(as.formula(paste(colnames(x)[par1],' ~ .',sep='')),data = x) + } > > #Note: the /var/www/rcomp/createtable file can be downloaded at http://www.wessa.net/cretab > load(file="/var/www/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/rcomp/tmp/1c5kq1293029507.tab") + } + } > m Conditional inference tree with 2 terminal nodes Response: as.factor(Geboortes) Input: Werkloosheid Number of observations: 75 1) Werkloosheid <= 240.8; criterion = 1, statistic = 18.962 2)* weights = 45 1) Werkloosheid > 240.8 3)* weights = 30 > postscript(file="/var/www/rcomp/tmp/2c5kq1293029507.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/rcomp/tmp/3c5kq1293029507.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,] 1 1 [3,] 1 1 [4,] 2 2 [5,] 1 2 [6,] 2 2 [7,] 1 1 [8,] 2 2 [9,] 1 2 [10,] 2 2 [11,] 2 2 [12,] 1 2 [13,] 2 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,] 2 1 [23,] 1 1 [24,] 1 1 [25,] 1 1 [26,] 1 1 [27,] 1 1 [28,] 1 1 [29,] 1 1 [30,] 1 1 [31,] 1 1 [32,] 1 1 [33,] 1 1 [34,] 2 2 [35,] 1 2 [36,] 1 1 [37,] 1 1 [38,] 1 1 [39,] 1 2 [40,] 2 2 [41,] 1 2 [42,] 2 2 [43,] 1 2 [44,] 1 2 [45,] 2 2 [46,] 2 2 [47,] 2 2 [48,] 2 2 [49,] 2 2 [50,] 1 2 [51,] 2 2 [52,] 2 2 [53,] 1 2 [54,] 2 2 [55,] 2 2 [56,] 2 2 [57,] 2 2 [58,] 2 2 [59,] 2 2 [60,] 2 2 [61,] 2 2 [62,] 1 2 [63,] 2 2 [64,] 2 2 [65,] 1 2 [66,] 2 2 [67,] 2 2 [68,] 2 2 [69,] 2 2 [70,] 2 2 [71,] 2 2 [72,] 2 2 [73,] 2 1 [74,] 2 1 [75,] 1 1 [8547, 9656) [9656,10680] [8547, 9656) 26 12 [9656,10680] 4 33 > postscript(file="/var/www/rcomp/tmp/4nwjt1293029507.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/rcomp/tmp/5johk1293029507.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/rcomp/tmp/6bxyn1293029507.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/rcomp/tmp/7xyfb1293029507.tab") + } > > try(system("convert tmp/2c5kq1293029507.ps tmp/2c5kq1293029507.png",intern=TRUE)) character(0) > try(system("convert tmp/3c5kq1293029507.ps tmp/3c5kq1293029507.png",intern=TRUE)) character(0) > try(system("convert tmp/4nwjt1293029507.ps tmp/4nwjt1293029507.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 1.87 0.65 2.51