R version 2.9.0 (2009-04-17) Copyright (C) 2009 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. 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(12008.00 + ,4.00 + ,9169.00 + ,5.90 + ,8788.00 + ,7.10 + ,8417.00 + ,10.50 + ,8247.00 + ,15.10 + ,8197.00 + ,16.80 + ,8236.00 + ,15.30 + ,8253.00 + ,18.40 + ,7733.00 + ,16.10 + ,8366.00 + ,11.30 + ,8626.00 + ,7.90 + ,8863.00 + ,5.60 + ,10102.00 + ,3.40 + ,8463.00 + ,4.80 + ,9114.00 + ,6.50 + ,8563.00 + ,8.50 + ,8872.00 + ,15.10 + ,8301.00 + ,15.70 + ,8301.00 + ,18.70 + ,8278.00 + ,19.20 + ,7736.00 + ,12.90 + ,7973.00 + ,14.40 + ,8268.00 + ,6.20 + ,9476.00 + ,3.30 + ,11100.00 + ,4.60 + ,8962.00 + ,7.10 + ,9173.00 + ,7.80 + ,8738.00 + ,9.90 + ,8459.00 + ,13.60 + ,8078.00 + ,17.10 + ,8411.00 + ,17.80 + ,8291.00 + ,18.60 + ,7810.00 + ,14.70 + ,8616.00 + ,10.50 + ,8312.00 + ,8.60 + ,9692.00 + ,4.40 + ,9911.00 + ,2.30 + ,8915.00 + ,2.80 + ,9452.00 + ,8.80 + ,9112.00 + ,10.70 + ,8472.00 + ,13.90 + ,8230.00 + ,19.30 + ,8384.00 + ,19.50 + ,8625.00 + ,20.40 + ,8221.00 + ,15.30 + ,8649.00 + ,7.90 + ,8625.00 + ,8.30 + ,10443.00 + ,4.50 + ,10357.00 + ,3.20 + ,8586.00 + ,5.00 + ,8892.00 + ,6.60 + ,8329.00 + ,11.10 + ,8101.00 + ,12.80 + ,7922.00 + ,16.30 + ,8120.00 + ,17.40 + ,7838.00 + ,18.90 + ,7735.00 + ,15.80 + ,8406.00 + ,11.70 + ,8209.00 + ,6.40 + ,9451.00 + ,2.90 + ,10041.00 + ,4.70 + ,9411.00 + ,2.40 + ,10405.00 + ,7.20 + ,8467.00 + ,10.70 + ,8464.00 + ,13.40 + ,8102.00 + ,18.30 + ,7627.00 + ,18.40 + ,7513.00 + ,16.80 + ,7510.00 + ,16.60 + ,8291.00 + ,14.10 + ,8064.00 + ,6.10 + ,9383.00 + ,3.50 + ,9706.00 + ,1.70 + ,8579.00 + ,2.30 + ,9474.00 + ,4.50 + ,8318.00 + ,9.30 + ,8213.00 + ,14.20 + ,8059.00 + ,17.30 + ,9111.00 + ,23.00 + ,7708.00 + ,16.30 + ,7680.00 + ,18.40 + ,8014.00 + ,14.20 + ,8007.00 + ,9.10 + ,8718.00 + ,5.90 + ,9486.00 + ,7.20 + ,9113.00 + ,6.80 + ,9025.00 + ,8.00 + ,8476.00 + ,14.30 + ,7952.00 + ,14.60 + ,7759.00 + ,17.50 + ,7835.00 + ,17.20 + ,7600.00 + ,17.20 + ,7651.00 + ,14.10 + ,8319.00 + ,10.40 + ,8812.00 + ,6.80 + ,8630.00 + ,4.10) + ,dim=c(2 + ,96) + ,dimnames=list(c('Sterftecijfers' + ,'Temperatuur') + ,1:96)) > y <- array(NA,dim=c(2,96),dimnames=list(c('Sterftecijfers','Temperatuur'),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 = 'yes' > par3 = '4' > 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$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_YOURPAGE.wasp/ > #Source of accompanying publication: > #Technical description: > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Attaching package: 'zoo' The following object(s) are masked from package:base : as.Date.numeric Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Attaching package: 'Hmisc' The following object(s) are masked from package:survival : untangle.specials The following object(s) are masked from package:base : format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "Sterftecijfers" > x[,par1] [1] 12008 9169 8788 8417 8247 8197 8236 8253 7733 8366 8626 8863 [13] 10102 8463 9114 8563 8872 8301 8301 8278 7736 7973 8268 9476 [25] 11100 8962 9173 8738 8459 8078 8411 8291 7810 8616 8312 9692 [37] 9911 8915 9452 9112 8472 8230 8384 8625 8221 8649 8625 10443 [49] 10357 8586 8892 8329 8101 7922 8120 7838 7735 8406 8209 9451 [61] 10041 9411 10405 8467 8464 8102 7627 7513 7510 8291 8064 9383 [73] 9706 8579 9474 8318 8213 8059 9111 7708 7680 8014 8007 8718 [85] 9486 9113 9025 8476 7952 7759 7835 7600 7651 8319 8812 8630 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$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, 8120) [8120, 8459) [8459, 9025) [9025,12008] 24 24 24 24 > colnames(x) [1] "Sterftecijfers" "Temperatuur" > colnames(x)[par1] [1] "Sterftecijfers" > x[,par1] [1] [9025,12008] [9025,12008] [8459, 9025) [8120, 8459) [8120, 8459) [6] [8120, 8459) [8120, 8459) [8120, 8459) [7510, 8120) [8120, 8459) [11] [8459, 9025) [8459, 9025) [9025,12008] [8459, 9025) [9025,12008] [16] [8459, 9025) [8459, 9025) [8120, 8459) [8120, 8459) [8120, 8459) [21] [7510, 8120) [7510, 8120) [8120, 8459) [9025,12008] [9025,12008] [26] [8459, 9025) [9025,12008] [8459, 9025) [8459, 9025) [7510, 8120) [31] [8120, 8459) [8120, 8459) [7510, 8120) [8459, 9025) [8120, 8459) [36] [9025,12008] [9025,12008] [8459, 9025) [9025,12008] [9025,12008] [41] [8459, 9025) [8120, 8459) [8120, 8459) [8459, 9025) [8120, 8459) [46] [8459, 9025) [8459, 9025) [9025,12008] [9025,12008] [8459, 9025) [51] [8459, 9025) [8120, 8459) [7510, 8120) [7510, 8120) [8120, 8459) [56] [7510, 8120) [7510, 8120) [8120, 8459) [8120, 8459) [9025,12008] [61] [9025,12008] [9025,12008] [9025,12008] [8459, 9025) [8459, 9025) [66] [7510, 8120) [7510, 8120) [7510, 8120) [7510, 8120) [8120, 8459) [71] [7510, 8120) [9025,12008] [9025,12008] [8459, 9025) [9025,12008] [76] [8120, 8459) [8120, 8459) [7510, 8120) [9025,12008] [7510, 8120) [81] [7510, 8120) [7510, 8120) [7510, 8120) [8459, 9025) [9025,12008] [86] [9025,12008] [9025,12008] [8459, 9025) [7510, 8120) [7510, 8120) [91] [7510, 8120) [7510, 8120) [7510, 8120) [8120, 8459) [8459, 9025) [96] [8459, 9025) Levels: [7510, 8120) [8120, 8459) [8459, 9025) [9025,12008] > if (par2 == 'none') { + m <- ctree(as.formula(paste(colnames(x)[par1],' ~ .',sep='')),data = x) + } > > #Note: the /var/www/html/rcomp/createtable file can be downloaded at http://www.wessa.net/cretab > load(file="/var/www/html/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/rcomp/tmp/1j4wk1292187334.tab") + } + } m.ct.i.pred m.ct.i.actu 1 2 3 4 1 182 12 15 1 2 110 49 48 6 3 49 14 109 46 4 4 8 63 143 [1] 0.8666667 [1] 0.2300469 [1] 0.5 [1] 0.6559633 [1] 0.5622817 m.ct.x.pred m.ct.x.actu 1 2 3 4 1 25 2 2 1 2 15 1 11 0 3 4 2 8 8 4 1 1 8 12 [1] 0.8333333 [1] 0.03703704 [1] 0.3636364 [1] 0.5454545 [1] 0.4554455 > m Conditional inference tree with 5 terminal nodes Response: as.factor(Sterftecijfers) Input: Temperatuur Number of observations: 96 1) Temperatuur <= 4.7; criterion = 1, statistic = 47.098 2)* weights = 17 1) Temperatuur > 4.7 3) Temperatuur <= 11.7; criterion = 1, statistic = 24.993 4)* weights = 35 3) Temperatuur > 11.7 5) Temperatuur <= 14.3; criterion = 0.993, statistic = 12.082 6)* weights = 10 5) Temperatuur > 14.3 7) Temperatuur <= 18.4; criterion = 0.988, statistic = 10.97 8)* weights = 26 7) Temperatuur > 18.4 9)* weights = 8 > postscript(file="/var/www/html/rcomp/tmp/2cvvn1292187334.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/rcomp/tmp/3cvvn1292187334.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,] 4 4 [2,] 4 3 [3,] 3 3 [4,] 2 3 [5,] 2 1 [6,] 2 1 [7,] 2 1 [8,] 2 1 [9,] 1 1 [10,] 2 3 [11,] 3 3 [12,] 3 3 [13,] 4 4 [14,] 3 3 [15,] 4 3 [16,] 3 3 [17,] 3 1 [18,] 2 1 [19,] 2 2 [20,] 2 2 [21,] 1 1 [22,] 1 1 [23,] 2 3 [24,] 4 4 [25,] 4 4 [26,] 3 3 [27,] 4 3 [28,] 3 3 [29,] 3 1 [30,] 1 1 [31,] 2 1 [32,] 2 2 [33,] 1 1 [34,] 3 3 [35,] 2 3 [36,] 4 4 [37,] 4 4 [38,] 3 4 [39,] 4 3 [40,] 4 3 [41,] 3 1 [42,] 2 2 [43,] 2 2 [44,] 3 2 [45,] 2 1 [46,] 3 3 [47,] 3 3 [48,] 4 4 [49,] 4 4 [50,] 3 3 [51,] 3 3 [52,] 2 3 [53,] 1 1 [54,] 1 1 [55,] 2 1 [56,] 1 2 [57,] 1 1 [58,] 2 3 [59,] 2 3 [60,] 4 4 [61,] 4 4 [62,] 4 4 [63,] 4 3 [64,] 3 3 [65,] 3 1 [66,] 1 1 [67,] 1 1 [68,] 1 1 [69,] 1 1 [70,] 2 1 [71,] 1 3 [72,] 4 4 [73,] 4 4 [74,] 3 4 [75,] 4 4 [76,] 2 3 [77,] 2 1 [78,] 1 1 [79,] 4 2 [80,] 1 1 [81,] 1 1 [82,] 1 1 [83,] 1 3 [84,] 3 3 [85,] 4 3 [86,] 4 3 [87,] 4 3 [88,] 3 1 [89,] 1 1 [90,] 1 1 [91,] 1 1 [92,] 1 1 [93,] 1 1 [94,] 2 3 [95,] 3 3 [96,] 3 4 [7510, 8120) [8120, 8459) [8459, 9025) [9025,12008] [7510, 8120) 21 1 2 0 [8120, 8459) 10 5 9 0 [8459, 9025) 5 1 15 3 [9025,12008] 0 1 9 14 > postscript(file="/var/www/html/rcomp/tmp/45nd81292187334.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/rcomp/tmp/5qnte1292187334.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/rcomp/tmp/6u6sk1292187334.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/rcomp/tmp/7x6871292187334.tab") + } > > try(system("convert tmp/2cvvn1292187334.ps tmp/2cvvn1292187334.png",intern=TRUE)) character(0) > try(system("convert tmp/3cvvn1292187334.ps tmp/3cvvn1292187334.png",intern=TRUE)) character(0) > try(system("convert tmp/45nd81292187334.ps tmp/45nd81292187334.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 2.562 0.489 5.385