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(6.80 + ,225.00 + ,0.44 + ,0.67 + ,9.20 + ,6.30 + ,180.00 + ,0.44 + ,0.80 + ,11.70 + ,6.40 + ,190.00 + ,0.46 + ,0.76 + ,15.80 + ,6.20 + ,180.00 + ,0.42 + ,0.65 + ,8.60 + ,6.90 + ,205.00 + ,0.45 + ,0.90 + ,23.20 + ,6.40 + ,225.00 + ,0.43 + ,0.78 + ,27.40 + ,6.30 + ,185.00 + ,0.49 + ,0.77 + ,9.30 + ,6.80 + ,235.00 + ,0.47 + ,0.75 + ,16.00 + ,6.90 + ,235.00 + ,0.44 + ,0.82 + ,4.70 + ,6.70 + ,210.00 + ,0.48 + ,0.83 + ,12.50 + ,6.90 + ,245.00 + ,0.52 + ,0.63 + ,20.10 + ,6.90 + ,245.00 + ,0.49 + ,0.76 + ,9.10 + ,6.30 + ,185.00 + ,0.37 + ,0.71 + ,8.10 + ,6.10 + ,185.00 + ,0.42 + ,0.78 + ,8.60 + ,6.20 + ,180.00 + ,0.44 + ,0.78 + ,20.30 + ,6.80 + ,220.00 + ,0.50 + ,0.88 + ,25.00 + ,6.50 + ,194.00 + ,0.50 + ,0.83 + ,19.20 + ,7.60 + ,225.00 + ,0.43 + ,0.57 + ,3.30 + ,6.30 + ,210.00 + ,0.37 + ,0.82 + ,11.20 + ,7.10 + ,240.00 + ,0.50 + ,0.71 + ,10.50 + ,6.80 + ,225.00 + ,0.40 + ,0.77 + ,10.10 + ,7.30 + ,263.00 + ,0.48 + ,0.66 + ,7.20 + ,6.40 + ,210.00 + ,0.48 + ,0.24 + ,13.60 + ,6.80 + ,235.00 + ,0.43 + ,0.73 + ,9.00 + ,7.20 + ,230.00 + ,0.56 + ,0.72 + ,24.60 + ,6.40 + ,190.00 + ,0.44 + ,0.76 + ,12.60 + ,6.60 + ,220.00 + ,0.49 + ,0.75 + ,5.60 + ,6.80 + ,210.00 + ,0.40 + ,0.74 + ,8.70 + ,6.10 + ,180.00 + ,0.42 + ,0.71 + ,7.70 + ,6.50 + ,235.00 + ,0.49 + ,0.74 + ,24.10 + ,6.40 + ,185.00 + ,0.48 + ,0.86 + ,11.70 + ,6.00 + ,175.00 + ,0.39 + ,0.72 + ,7.70 + ,6.00 + ,192.00 + ,0.44 + ,0.79 + ,9.60 + ,7.30 + ,263.00 + ,0.48 + ,0.66 + ,7.20 + ,6.10 + ,180.00 + ,0.34 + ,0.82 + ,12.30 + ,6.70 + ,240.00 + ,0.52 + ,0.73 + ,8.90 + ,6.40 + ,210.00 + ,0.48 + ,0.85 + ,13.60 + ,5.80 + ,160.00 + ,0.41 + ,0.81 + ,11.20 + ,6.90 + ,230.00 + ,0.41 + ,0.60 + ,2.80 + ,7.00 + ,245.00 + ,0.41 + ,0.57 + ,3.20 + ,7.30 + ,228.00 + ,0.45 + ,0.73 + ,9.40 + ,5.90 + ,155.00 + ,0.29 + ,0.71 + ,11.90 + ,6.20 + ,200.00 + ,0.45 + ,0.80 + ,15.40 + ,6.80 + ,235.00 + ,0.55 + ,0.78 + ,7.40 + ,7.00 + ,235.00 + ,0.48 + ,0.74 + ,18.90 + ,5.90 + ,105.00 + ,0.36 + ,0.84 + ,7.90 + ,6.10 + ,180.00 + ,0.53 + ,0.79 + ,12.20 + ,5.70 + ,185.00 + ,0.35 + ,0.70 + ,11.00 + ,7.10 + ,245.00 + ,0.41 + ,0.78 + ,2.80 + ,5.80 + ,180.00 + ,0.43 + ,0.87 + ,11.80 + ,7.40 + ,240.00 + ,0.60 + ,0.71 + ,17.10 + ,6.80 + ,225.00 + ,0.48 + ,0.70 + ,11.60 + ,6.80 + ,215.00 + ,0.46 + ,0.73 + ,5.80 + ,7.00 + ,230.00 + ,0.44 + ,0.76 + ,8.30) + ,dim=c(5 + ,54) + ,dimnames=list(c('X1' + ,'X2' + ,'X3' + ,'X4' + ,'X5 ') + ,1:54)) > y <- array(NA,dim=c(5,54),dimnames=list(c('X1','X2','X3','X4','X5 '),1:54)) > 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 = '0' > par2 = 'none' > par1 = '3' > par4 <- 'no' > par3 <- '0' > par2 <- 'none' > par1 <- '3' > #'GNU S' R Code compiled by R2WASP v. 1.2.291 () > #Author: root > #To cite this work: Wessa P., 2012, Recursive Partitioning (Regression Trees) (v1.0.3) in Free Statistics Software (v$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_regression_trees.wasp/ > #Source of accompanying publication: > # > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Attaching package: 'zoo' The following object(s) are masked from 'package:base': as.Date, as.Date.numeric Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Hmisc library by Frank E Harrell Jr Type library(help='Hmisc'), ?Overview, or ?Hmisc.Overview') to see overall documentation. NOTE:Hmisc no longer redefines [.factor to drop unused levels when subsetting. To get the old behavior of Hmisc type dropUnusedLevels(). Attaching package: 'Hmisc' The following object(s) are masked from 'package:survival': untangle.specials The following object(s) are masked from 'package:base': format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "X3" > x[,par1] [1] 0.44 0.44 0.46 0.42 0.45 0.43 0.49 0.47 0.44 0.48 0.52 0.49 0.37 0.42 0.44 [16] 0.50 0.50 0.43 0.37 0.50 0.40 0.48 0.48 0.43 0.56 0.44 0.49 0.40 0.42 0.49 [31] 0.48 0.39 0.44 0.48 0.34 0.52 0.48 0.41 0.41 0.41 0.45 0.29 0.45 0.55 0.48 [46] 0.36 0.53 0.35 0.41 0.43 0.60 0.48 0.46 0.44 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$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]) 0.29 0.34 0.35 0.36 0.37 0.39 0.4 0.41 0.42 0.43 0.44 0.45 0.46 0.47 0.48 0.49 1 1 1 1 2 1 2 4 3 4 7 3 2 1 8 4 0.5 0.52 0.53 0.55 0.56 0.6 3 2 1 1 1 1 > colnames(x) [1] "X1" "X2" "X3" "X4" "X5." > colnames(x)[par1] [1] "X3" > x[,par1] [1] 0.44 0.44 0.46 0.42 0.45 0.43 0.49 0.47 0.44 0.48 0.52 0.49 0.37 0.42 0.44 [16] 0.50 0.50 0.43 0.37 0.50 0.40 0.48 0.48 0.43 0.56 0.44 0.49 0.40 0.42 0.49 [31] 0.48 0.39 0.44 0.48 0.34 0.52 0.48 0.41 0.41 0.41 0.45 0.29 0.45 0.55 0.48 [46] 0.36 0.53 0.35 0.41 0.43 0.60 0.48 0.46 0.44 > 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/1nttf1355172982.tab") + } + } > m Conditional inference tree with 2 terminal nodes Response: X3 Inputs: X1, X2, X4, X5. Number of observations: 54 1) X2 <= 185; criterion = 0.999, statistic = 13.832 2)* weights = 16 1) X2 > 185 3)* weights = 38 > postscript(file="/var/fisher/rcomp/tmp/25gz61355172982.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/3nld01355172982.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 0.44 0.4660526 -0.026052632 2 0.44 0.4112500 0.028750000 3 0.46 0.4660526 -0.006052632 4 0.42 0.4112500 0.008750000 5 0.45 0.4660526 -0.016052632 6 0.43 0.4660526 -0.036052632 7 0.49 0.4112500 0.078750000 8 0.47 0.4660526 0.003947368 9 0.44 0.4660526 -0.026052632 10 0.48 0.4660526 0.013947368 11 0.52 0.4660526 0.053947368 12 0.49 0.4660526 0.023947368 13 0.37 0.4112500 -0.041250000 14 0.42 0.4112500 0.008750000 15 0.44 0.4112500 0.028750000 16 0.50 0.4660526 0.033947368 17 0.50 0.4660526 0.033947368 18 0.43 0.4660526 -0.036052632 19 0.37 0.4660526 -0.096052632 20 0.50 0.4660526 0.033947368 21 0.40 0.4660526 -0.066052632 22 0.48 0.4660526 0.013947368 23 0.48 0.4660526 0.013947368 24 0.43 0.4660526 -0.036052632 25 0.56 0.4660526 0.093947368 26 0.44 0.4660526 -0.026052632 27 0.49 0.4660526 0.023947368 28 0.40 0.4660526 -0.066052632 29 0.42 0.4112500 0.008750000 30 0.49 0.4660526 0.023947368 31 0.48 0.4112500 0.068750000 32 0.39 0.4112500 -0.021250000 33 0.44 0.4660526 -0.026052632 34 0.48 0.4660526 0.013947368 35 0.34 0.4112500 -0.071250000 36 0.52 0.4660526 0.053947368 37 0.48 0.4660526 0.013947368 38 0.41 0.4112500 -0.001250000 39 0.41 0.4660526 -0.056052632 40 0.41 0.4660526 -0.056052632 41 0.45 0.4660526 -0.016052632 42 0.29 0.4112500 -0.121250000 43 0.45 0.4660526 -0.016052632 44 0.55 0.4660526 0.083947368 45 0.48 0.4660526 0.013947368 46 0.36 0.4112500 -0.051250000 47 0.53 0.4112500 0.118750000 48 0.35 0.4112500 -0.061250000 49 0.41 0.4660526 -0.056052632 50 0.43 0.4112500 0.018750000 51 0.60 0.4660526 0.133947368 52 0.48 0.4660526 0.013947368 53 0.46 0.4660526 -0.006052632 54 0.44 0.4660526 -0.026052632 > if (par2 != 'none') { + print(cbind(as.factor(x[,par1]),predict(m))) + myt <- table(as.factor(x[,par1]),predict(m)) + print(myt) + } > postscript(file="/var/fisher/rcomp/tmp/4lda91355172982.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/5f5s91355172982.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/6fd8t1355172982.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/7u9dd1355172982.tab") + } > > try(system("convert tmp/25gz61355172982.ps tmp/25gz61355172982.png",intern=TRUE)) character(0) > try(system("convert tmp/3nld01355172982.ps tmp/3nld01355172982.png",intern=TRUE)) character(0) > try(system("convert tmp/4lda91355172982.ps tmp/4lda91355172982.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 3.799 0.591 4.377