R version 2.8.0 (2008-10-20) Copyright (C) 2008 The R Foundation for Statistical Computing ISBN 3-900051-07-0 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. Natural language support but running in an English locale 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(12008,4.0,9169,5.9,8788,7.1,8417,10.5,8247,15.1,8197,16.8,8236,15.3,8253,18.4,7733,16.1,8366,11.3,8626,7.9,8863,5.6,10102,3.4,8463,4.8,9114,6.5,8563,8.5,8872,15.1,8301,15.7,8301,18.7,8278,19.2,7736,12.9,7973,14.4,8268,6.2,9476,3.3,11100,4.6,8962,7.1,9173,7.8,8738,9.9,8459,13.6,8078,17.1,8411,17.8,8291,18.6,7810,14.7,8616,10.5,8312,8.6,9692,4.4,9911,2.3,8915,2.8,9452,8.8,9112,10.7,8472,13.9,8230,19.3,8384,19.5,8625,20.4,8221,15.3,8649,7.9,8625,8.3,10443,4.5,10357,3.2,8586,5.0,8892,6.6,8329,11.1,8101,12.8,7922,16.3,8120,17.4,7838,18.9,7735,15.8,8406,11.7,8209,6.4,9451,2.9,10041,4.7,9411,2.4,10405,7.2,8467,10.7,8464,13.4,8102,18.3,7627,18.4,7513,16.8,7510,16.6,8291,14.1,8064,6.1,9383,3.5,9706,1.7,8579,2.3,9474,4.5,8318,9.3,8213,14.2,8059,17.3,9111,23.0,7708,16.3,7680,18.4,8014,14.2,8007,9.1,8718,5.9,9486,7.2,9113,6.8,9025,8.0,8476,14.3,7952,14.6,7759,17.5,7835,17.2,7600,17.2,7651,14.1,8319,10.4,8812,6.8,8630,4.1),dim=c(2,96),dimnames=list(c('Sterfte','Temp'),1:96)) > y <- array(NA,dim=c(2,96),dimnames=list(c('Sterfte','Temp'),1:96)) > 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' > #'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$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_YOURPAGE.wasp/ > #Source of accompanying publication: > #Technical description: > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Attaching package: 'zoo' The following object(s) are masked from package:base : as.Date.numeric Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Attaching package: 'Hmisc' The following object(s) are masked from package:survival : untangle.specials The following object(s) are masked from package:base : format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "Sterfte" > x[,par1] [1] 12008 9169 8788 8417 8247 8197 8236 8253 7733 8366 8626 8863 [13] 10102 8463 9114 8563 8872 8301 8301 8278 7736 7973 8268 9476 [25] 11100 8962 9173 8738 8459 8078 8411 8291 7810 8616 8312 9692 [37] 9911 8915 9452 9112 8472 8230 8384 8625 8221 8649 8625 10443 [49] 10357 8586 8892 8329 8101 7922 8120 7838 7735 8406 8209 9451 [61] 10041 9411 10405 8467 8464 8102 7627 7513 7510 8291 8064 9383 [73] 9706 8579 9474 8318 8213 8059 9111 7708 7680 8014 8007 8718 [85] 9486 9113 9025 8476 7952 7759 7835 7600 7651 8319 8812 8630 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$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]) [7510, 8459) [8459,12008] 48 48 > colnames(x) [1] "Sterfte" "Temp" > colnames(x)[par1] [1] "Sterfte" > x[,par1] [1] [8459,12008] [8459,12008] [8459,12008] [7510, 8459) [7510, 8459) [6] [7510, 8459) [7510, 8459) [7510, 8459) [7510, 8459) [7510, 8459) [11] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [16] [8459,12008] [8459,12008] [7510, 8459) [7510, 8459) [7510, 8459) [21] [7510, 8459) [7510, 8459) [7510, 8459) [8459,12008] [8459,12008] [26] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [7510, 8459) [31] [7510, 8459) [7510, 8459) [7510, 8459) [8459,12008] [7510, 8459) [36] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [41] [8459,12008] [7510, 8459) [7510, 8459) [8459,12008] [7510, 8459) [46] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [51] [8459,12008] [7510, 8459) [7510, 8459) [7510, 8459) [7510, 8459) [56] [7510, 8459) [7510, 8459) [7510, 8459) [7510, 8459) [8459,12008] [61] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [8459,12008] [66] [7510, 8459) [7510, 8459) [7510, 8459) [7510, 8459) [7510, 8459) [71] [7510, 8459) [8459,12008] [8459,12008] [8459,12008] [8459,12008] [76] [7510, 8459) [7510, 8459) [7510, 8459) [8459,12008] [7510, 8459) [81] [7510, 8459) [7510, 8459) [7510, 8459) [8459,12008] [8459,12008] [86] [8459,12008] [8459,12008] [8459,12008] [7510, 8459) [7510, 8459) [91] [7510, 8459) [7510, 8459) [7510, 8459) [7510, 8459) [8459,12008] [96] [8459,12008] Levels: [7510, 8459) [8459,12008] > if (par2 == 'none') { + m <- ctree(as.formula(paste(colnames(x)[par1],' ~ .',sep='')),data = x) + } > > #Note: the /var/www/html/freestat/rcomp/createtable file can be downloaded at http://www.wessa.net/cretab > load(file="/var/www/html/freestat/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/html/freestat/rcomp/tmp/1w87p1292078251.tab") + } + } > m Conditional inference tree with 2 terminal nodes Response: as.factor(Sterfte) Input: Temp Number of observations: 96 1) Temp <= 8.5; criterion = 1, statistic = 43.081 2)* weights = 39 1) Temp > 8.5 3)* weights = 57 > postscript(file="/var/www/html/freestat/rcomp/tmp/2w87p1292078251.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/html/freestat/rcomp/tmp/3w87p1292078251.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,] 1 1 [5,] 1 1 [6,] 1 1 [7,] 1 1 [8,] 1 1 [9,] 1 1 [10,] 1 1 [11,] 2 2 [12,] 2 2 [13,] 2 2 [14,] 2 2 [15,] 2 2 [16,] 2 2 [17,] 2 1 [18,] 1 1 [19,] 1 1 [20,] 1 1 [21,] 1 1 [22,] 1 1 [23,] 1 2 [24,] 2 2 [25,] 2 2 [26,] 2 2 [27,] 2 2 [28,] 2 1 [29,] 2 1 [30,] 1 1 [31,] 1 1 [32,] 1 1 [33,] 1 1 [34,] 2 1 [35,] 1 1 [36,] 2 2 [37,] 2 2 [38,] 2 2 [39,] 2 1 [40,] 2 1 [41,] 2 1 [42,] 1 1 [43,] 1 1 [44,] 2 1 [45,] 1 1 [46,] 2 2 [47,] 2 2 [48,] 2 2 [49,] 2 2 [50,] 2 2 [51,] 2 2 [52,] 1 1 [53,] 1 1 [54,] 1 1 [55,] 1 1 [56,] 1 1 [57,] 1 1 [58,] 1 1 [59,] 1 2 [60,] 2 2 [61,] 2 2 [62,] 2 2 [63,] 2 2 [64,] 2 1 [65,] 2 1 [66,] 1 1 [67,] 1 1 [68,] 1 1 [69,] 1 1 [70,] 1 1 [71,] 1 2 [72,] 2 2 [73,] 2 2 [74,] 2 2 [75,] 2 2 [76,] 1 1 [77,] 1 1 [78,] 1 1 [79,] 2 1 [80,] 1 1 [81,] 1 1 [82,] 1 1 [83,] 1 1 [84,] 2 2 [85,] 2 2 [86,] 2 2 [87,] 2 2 [88,] 2 1 [89,] 1 1 [90,] 1 1 [91,] 1 1 [92,] 1 1 [93,] 1 1 [94,] 1 1 [95,] 2 2 [96,] 2 2 [7510, 8459) [8459,12008] [7510, 8459) 45 3 [8459,12008] 12 36 > postscript(file="/var/www/html/freestat/rcomp/tmp/4pi6a1292078251.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/html/freestat/rcomp/tmp/53r411292078251.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/html/freestat/rcomp/tmp/6w1341292078251.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/html/freestat/rcomp/tmp/7zj2a1292078251.tab") + } > > try(system("convert tmp/2w87p1292078251.ps tmp/2w87p1292078251.png",intern=TRUE)) character(0) > try(system("convert tmp/3w87p1292078251.ps tmp/3w87p1292078251.png",intern=TRUE)) character(0) > try(system("convert tmp/4pi6a1292078251.ps tmp/4pi6a1292078251.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 3.325 0.648 3.461