R version 3.0.2 (2013-09-25) -- "Frisbee Sailing" Copyright (C) 2013 The R Foundation for Statistical Computing 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(3,0,1,18,1,1,0,11,3,0,1,7,1,1,0,3,3,0,1,5,3,1,0,19,3,0,1,20,1,0,0,9,3,1,0,17,3,0,1,8,1,1,1,10,3,0,1,16,0,1,0,13,3,0,1,15,3,0,1,6,3,1,0,1,1,1,0,14,3,0,1,12,3,1,1,4,1,1,0,18,3,0,1,11,0,1,0,7,3,0,1,3,3,1,1,5,3,0,0,19,3,1,1,20,3,1,1,9,3,0,1,17,3,1,1,8,3,0,1,10,3,1,1,16,3,0,1,13,3,1,1,6,0,0,0,1,3,1,1,15,3,0,1,4,3,0,1,14,1,1,0,12,3,0,1,4,3,1,1,16,3,0,0,5,3,1,1,10,3,0,0,15,3,1,0,9,1,0,1,2,3,1,1,19,3,1,1,8,3,0,0,17,3,1,1,18,3,0,1,20,3,1,1,11,3,0,1,12,3,1,1,7,3,0,1,3,3,1,1,14,3,0,1,13,3,1,1,6,0,1,1,4,3,0,1,16,1,1,1,5,3,0,1,10,3,1,1,15,3,0,1,9,0,1,1,2,3,0,1,19,3,0,1,8,1,1,1,17,3,0,0,18,3,1,0,20,3,0,0,11,1,1,1,12,3,0,1,7,3,1,0,3,3,0,0,14,3,1,0,13,3,0,0,6,3,0,1,13,3,1,0,15,3,1,1,9,3,0,1,8,3,1,0,17,3,0,1,6,3,1,1,19,3,0,0,18,1,1,0,16,3,0,0,3,3,1,0,14,3,0,0,10,3,1,0,20,3,0,0,12,0,1,0,4),dim=c(4,91),dimnames=list(c('result','in_out','Messi_goals','rank_oppon'),1:91)) > y <- array(NA,dim=c(4,91),dimnames=list(c('result','in_out','Messi_goals','rank_oppon'),1:91)) > 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' > par4 <- 'no' > par3 <- '3' > par2 <- 'none' > par1 <- '1' > #'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$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_regression_trees.wasp/ > #Source of accompanying publication: > # > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Attaching package: 'zoo' The following objects are masked from 'package:base': as.Date, as.Date.numeric Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Hmisc library by Frank E Harrell Jr Type library(help='Hmisc'), ?Overview, or ?Hmisc.Overview') to see overall documentation. NOTE:Hmisc no longer redefines [.factor to drop unused levels when subsetting. To get the old behavior of Hmisc type dropUnusedLevels(). Attaching package: 'Hmisc' The following object is masked from 'package:survival': untangle.specials The following objects are masked from 'package:base': format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "result" > x[,par1] [1] 3 1 3 1 3 3 3 1 3 3 1 3 0 3 3 3 1 3 3 1 3 0 3 3 3 3 3 3 3 3 3 3 3 0 3 3 3 1 [39] 3 3 3 3 3 3 1 3 3 3 3 3 3 3 3 3 3 3 3 0 3 1 3 3 3 0 3 3 1 3 3 3 1 3 3 3 3 3 [77] 3 3 3 3 3 3 3 3 1 3 3 3 3 3 0 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$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 1 3 6 12 73 > colnames(x) [1] "result" "in_out" "Messi_goals" "rank_oppon" > colnames(x)[par1] [1] "result" > x[,par1] [1] 3 1 3 1 3 3 3 1 3 3 1 3 0 3 3 3 1 3 3 1 3 0 3 3 3 3 3 3 3 3 3 3 3 0 3 3 3 1 [39] 3 3 3 3 3 3 1 3 3 3 3 3 3 3 3 3 3 3 3 0 3 1 3 3 3 0 3 3 1 3 3 3 1 3 3 3 3 3 [77] 3 3 3 3 3 3 3 3 1 3 3 3 3 3 0 > 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/1g17n1386834812.tab") + } + } > m Conditional inference tree with 2 terminal nodes Response: result Inputs: in_out, Messi_goals, rank_oppon Number of observations: 91 1) in_out <= 0; criterion = 0.992, statistic = 9.08 2)* weights = 45 1) in_out > 0 3)* weights = 46 > postscript(file="/var/fisher/rcomp/tmp/28fh51386834812.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/3unup1386834812.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 3 2.844444 0.1555556 2 1 2.239130 -1.2391304 3 3 2.844444 0.1555556 4 1 2.239130 -1.2391304 5 3 2.844444 0.1555556 6 3 2.239130 0.7608696 7 3 2.844444 0.1555556 8 1 2.844444 -1.8444444 9 3 2.239130 0.7608696 10 3 2.844444 0.1555556 11 1 2.239130 -1.2391304 12 3 2.844444 0.1555556 13 0 2.239130 -2.2391304 14 3 2.844444 0.1555556 15 3 2.844444 0.1555556 16 3 2.239130 0.7608696 17 1 2.239130 -1.2391304 18 3 2.844444 0.1555556 19 3 2.239130 0.7608696 20 1 2.239130 -1.2391304 21 3 2.844444 0.1555556 22 0 2.239130 -2.2391304 23 3 2.844444 0.1555556 24 3 2.239130 0.7608696 25 3 2.844444 0.1555556 26 3 2.239130 0.7608696 27 3 2.239130 0.7608696 28 3 2.844444 0.1555556 29 3 2.239130 0.7608696 30 3 2.844444 0.1555556 31 3 2.239130 0.7608696 32 3 2.844444 0.1555556 33 3 2.239130 0.7608696 34 0 2.844444 -2.8444444 35 3 2.239130 0.7608696 36 3 2.844444 0.1555556 37 3 2.844444 0.1555556 38 1 2.239130 -1.2391304 39 3 2.844444 0.1555556 40 3 2.239130 0.7608696 41 3 2.844444 0.1555556 42 3 2.239130 0.7608696 43 3 2.844444 0.1555556 44 3 2.239130 0.7608696 45 1 2.844444 -1.8444444 46 3 2.239130 0.7608696 47 3 2.239130 0.7608696 48 3 2.844444 0.1555556 49 3 2.239130 0.7608696 50 3 2.844444 0.1555556 51 3 2.239130 0.7608696 52 3 2.844444 0.1555556 53 3 2.239130 0.7608696 54 3 2.844444 0.1555556 55 3 2.239130 0.7608696 56 3 2.844444 0.1555556 57 3 2.239130 0.7608696 58 0 2.239130 -2.2391304 59 3 2.844444 0.1555556 60 1 2.239130 -1.2391304 61 3 2.844444 0.1555556 62 3 2.239130 0.7608696 63 3 2.844444 0.1555556 64 0 2.239130 -2.2391304 65 3 2.844444 0.1555556 66 3 2.844444 0.1555556 67 1 2.239130 -1.2391304 68 3 2.844444 0.1555556 69 3 2.239130 0.7608696 70 3 2.844444 0.1555556 71 1 2.239130 -1.2391304 72 3 2.844444 0.1555556 73 3 2.239130 0.7608696 74 3 2.844444 0.1555556 75 3 2.239130 0.7608696 76 3 2.844444 0.1555556 77 3 2.844444 0.1555556 78 3 2.239130 0.7608696 79 3 2.239130 0.7608696 80 3 2.844444 0.1555556 81 3 2.239130 0.7608696 82 3 2.844444 0.1555556 83 3 2.239130 0.7608696 84 3 2.844444 0.1555556 85 1 2.239130 -1.2391304 86 3 2.844444 0.1555556 87 3 2.239130 0.7608696 88 3 2.844444 0.1555556 89 3 2.239130 0.7608696 90 3 2.844444 0.1555556 91 0 2.239130 -2.2391304 > 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/4jvcs1386834812.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/5yhz21386834812.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/6l5081386834812.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/7bb6r1386834812.tab") + } > > try(system("convert tmp/28fh51386834812.ps tmp/28fh51386834812.png",intern=TRUE)) character(0) > try(system("convert tmp/3unup1386834812.ps tmp/3unup1386834812.png",intern=TRUE)) character(0) > try(system("convert tmp/4jvcs1386834812.ps tmp/4jvcs1386834812.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 6.803 0.899 7.695