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(695 + ,0 + ,641 + ,696 + ,729 + ,839 + ,627 + ,608 + ,638 + ,0 + ,695 + ,641 + ,696 + ,729 + ,696 + ,651 + ,762 + ,0 + ,638 + ,695 + ,641 + ,696 + ,825 + ,691 + ,635 + ,0 + ,762 + ,638 + ,695 + ,641 + ,677 + ,627 + ,721 + ,0 + ,635 + ,762 + ,638 + ,695 + ,656 + ,634 + ,854 + ,0 + ,721 + ,635 + ,762 + ,638 + ,785 + ,731 + ,418 + ,0 + ,854 + ,721 + ,635 + ,762 + ,412 + ,475 + ,367 + ,0 + ,418 + ,854 + ,721 + ,635 + ,352 + ,337 + ,824 + ,0 + ,367 + ,418 + ,854 + ,721 + ,839 + ,803 + ,687 + ,0 + ,824 + ,367 + ,418 + ,854 + ,729 + ,722 + ,601 + ,0 + ,687 + ,824 + ,367 + ,418 + ,696 + ,590 + ,676 + ,0 + ,601 + ,687 + ,824 + ,367 + ,641 + ,724 + ,740 + ,0 + ,676 + ,601 + ,687 + ,824 + ,695 + ,627 + ,691 + ,0 + ,740 + ,676 + ,601 + ,687 + ,638 + ,696 + ,683 + ,0 + ,691 + ,740 + ,676 + ,601 + ,762 + ,825 + ,594 + ,0 + ,683 + ,691 + ,740 + ,676 + ,635 + ,677 + ,729 + ,0 + ,594 + ,683 + ,691 + ,740 + ,721 + ,656 + ,731 + ,0 + ,729 + ,594 + ,683 + ,691 + ,854 + ,785 + ,386 + ,0 + ,731 + ,729 + ,594 + ,683 + ,418 + ,412 + ,331 + ,0 + ,386 + ,731 + ,729 + ,594 + ,367 + ,352 + ,706 + ,0 + ,331 + ,386 + ,731 + ,729 + ,824 + ,839 + ,715 + ,0 + ,706 + ,331 + ,386 + ,731 + ,687 + ,729 + ,657 + ,0 + ,715 + ,706 + ,331 + ,386 + ,601 + ,696 + ,653 + ,0 + ,657 + ,715 + ,706 + ,331 + ,676 + ,641 + ,642 + ,0 + ,653 + ,657 + ,715 + ,706 + ,740 + ,695 + ,643 + ,0 + ,642 + ,653 + ,657 + ,715 + ,691 + ,638 + ,718 + ,0 + ,643 + ,642 + ,653 + ,657 + ,683 + ,762 + ,654 + ,0 + ,718 + ,643 + ,642 + ,653 + ,594 + ,635 + ,632 + ,0 + ,654 + ,718 + ,643 + ,642 + ,729 + ,721 + ,731 + ,0 + ,632 + ,654 + ,718 + ,643 + ,731 + ,854 + ,392 + ,1 + ,731 + ,632 + ,654 + ,718 + ,386 + ,418 + ,344 + ,1 + ,392 + ,731 + ,632 + ,654 + ,331 + ,367 + ,792 + ,1 + ,344 + ,392 + ,731 + ,632 + ,706 + ,824 + ,852 + ,1 + ,792 + ,344 + ,392 + ,731 + ,715 + ,687 + ,649 + ,1 + ,852 + ,792 + ,344 + ,392 + ,657 + ,601 + ,629 + ,1 + ,649 + ,852 + ,792 + ,344 + ,653 + ,676 + ,685 + ,1 + ,629 + ,649 + ,852 + ,792 + ,642 + ,740 + ,617 + ,1 + ,685 + ,629 + ,649 + ,852 + ,643 + ,691 + ,715 + ,1 + ,617 + ,685 + ,629 + ,649 + ,718 + ,683 + ,715 + ,1 + ,715 + ,617 + ,685 + ,629 + ,654 + ,594 + ,629 + ,1 + ,715 + ,715 + ,617 + ,685 + ,632 + ,729 + ,916 + ,1 + ,629 + ,715 + ,715 + ,617 + ,731 + ,731 + ,531 + ,1 + ,916 + ,629 + ,715 + ,715 + ,392 + ,386 + ,357 + ,1 + ,531 + ,916 + ,629 + ,715 + ,344 + ,331 + ,917 + ,1 + ,357 + ,531 + ,916 + ,629 + ,792 + ,706 + ,828 + ,1 + ,917 + ,357 + ,531 + ,916 + ,852 + ,715 + ,708 + ,1 + ,828 + ,917 + ,357 + ,531 + ,649 + ,657 + ,858 + ,1 + ,708 + ,828 + ,917 + ,357 + ,629 + ,653 + ,775 + ,1 + ,858 + ,708 + ,828 + ,917 + ,685 + ,642 + ,785 + ,1 + ,775 + ,858 + ,708 + ,828 + ,617 + ,643 + ,1006 + ,1 + ,785 + ,775 + ,858 + ,708 + ,715 + ,718 + ,789 + ,1 + ,1006 + ,785 + ,775 + ,858 + ,715 + ,654 + ,734 + ,1 + ,789 + ,1006 + ,785 + ,775 + ,629 + ,632 + ,906 + ,1 + ,734 + ,789 + ,1006 + ,785 + ,916 + ,731 + ,532 + ,1 + ,906 + ,734 + ,789 + ,1006 + ,531 + ,392 + ,387 + ,1 + ,532 + ,906 + ,734 + ,789 + ,357 + ,344 + ,991 + ,1 + ,387 + ,532 + ,906 + ,734 + ,917 + ,792 + ,841 + ,1 + ,991 + ,387 + ,532 + ,906 + ,828 + ,852 + ,892 + ,1 + ,841 + ,991 + ,387 + ,532 + ,708 + ,649 + ,782 + ,1 + ,892 + ,841 + ,991 + ,387 + ,858 + ,629) + ,dim=c(8 + ,60) + ,dimnames=list(c('faillissement' + ,'crisis' + ,'t-1' + ,'t-2' + ,'t-3' + ,'t-4' + ,'t-12' + ,'t-24 ') + ,1:60)) > y <- array(NA,dim=c(8,60),dimnames=list(c('faillissement','crisis','t-1','t-2','t-3','t-4','t-12','t-24 '),1:60)) > 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 = '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$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_YOURPAGE.wasp/ > #Source of accompanying publication: > #Technical description: > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Attaching package: 'Hmisc' The following object(s) are masked from 'package:survival': untangle.specials The following object(s) are masked from 'package:base': format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "faillissement" > x[,par1] [1] 695 638 762 635 721 854 418 367 824 687 601 676 740 691 683 [16] 594 729 731 386 331 706 715 657 653 642 643 718 654 632 731 [31] 392 344 792 852 649 629 685 617 715 715 629 916 531 357 917 [46] 828 708 858 775 785 1006 789 734 906 532 387 991 841 892 782 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$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]) [331, 706) [706,1006] 30 30 > colnames(x) [1] "faillissement" "crisis" "t.1" "t.2" [5] "t.3" "t.4" "t.12" "t.24." > colnames(x)[par1] [1] "faillissement" > x[,par1] [1] [331, 706) [331, 706) [706,1006] [331, 706) [706,1006] [706,1006] [7] [331, 706) [331, 706) [706,1006] [331, 706) [331, 706) [331, 706) [13] [706,1006] [331, 706) [331, 706) [331, 706) [706,1006] [706,1006] [19] [331, 706) [331, 706) [706,1006] [706,1006] [331, 706) [331, 706) [25] [331, 706) [331, 706) [706,1006] [331, 706) [331, 706) [706,1006] [31] [331, 706) [331, 706) [706,1006] [706,1006] [331, 706) [331, 706) [37] [331, 706) [331, 706) [706,1006] [706,1006] [331, 706) [706,1006] [43] [331, 706) [331, 706) [706,1006] [706,1006] [706,1006] [706,1006] [49] [706,1006] [706,1006] [706,1006] [706,1006] [706,1006] [706,1006] [55] [331, 706) [331, 706) [706,1006] [706,1006] [706,1006] [706,1006] Levels: [331, 706) [706,1006] > 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/1lfq21292956123.tab") + } + } m.ct.i.pred m.ct.i.actu 1 2 1 206 67 2 43 217 [1] 0.7545788 [1] 0.8346154 [1] 0.793621 m.ct.x.pred m.ct.x.actu 1 2 1 17 10 2 15 25 [1] 0.6296296 [1] 0.625 [1] 0.6268657 > m Conditional inference tree with 3 terminal nodes Response: as.factor(faillissement) Inputs: crisis, t.1, t.2, t.3, t.4, t.12, t.24. Number of observations: 60 1) t.12 <= 677; criterion = 1, statistic = 20.556 2)* weights = 29 1) t.12 > 677 3) crisis <= 0; criterion = 0.95, statistic = 7.206 4)* weights = 17 3) crisis > 0 5)* weights = 14 > postscript(file="/var/www/rcomp/tmp/2lfq21292956123.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/3lfq21292956123.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,] 1 1 [2,] 1 2 [3,] 2 2 [4,] 1 1 [5,] 2 1 [6,] 2 2 [7,] 1 1 [8,] 1 1 [9,] 2 2 [10,] 1 2 [11,] 1 2 [12,] 1 1 [13,] 2 2 [14,] 1 1 [15,] 1 2 [16,] 1 1 [17,] 2 2 [18,] 2 2 [19,] 1 1 [20,] 1 1 [21,] 2 2 [22,] 2 2 [23,] 1 1 [24,] 1 1 [25,] 1 2 [26,] 1 2 [27,] 2 2 [28,] 1 1 [29,] 1 2 [30,] 2 2 [31,] 1 1 [32,] 1 1 [33,] 2 2 [34,] 2 2 [35,] 1 1 [36,] 1 1 [37,] 1 1 [38,] 1 1 [39,] 2 2 [40,] 2 1 [41,] 1 1 [42,] 2 2 [43,] 1 1 [44,] 1 1 [45,] 2 2 [46,] 2 2 [47,] 2 1 [48,] 2 1 [49,] 2 2 [50,] 2 1 [51,] 2 2 [52,] 2 2 [53,] 2 1 [54,] 2 2 [55,] 1 1 [56,] 1 1 [57,] 2 2 [58,] 2 2 [59,] 2 2 [60,] 2 2 [331, 706) [706,1006] [331, 706) 23 7 [706,1006] 6 24 > postscript(file="/var/www/rcomp/tmp/4e6p41292956123.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/5agnd1292956123.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/62pmy1292956123.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/7o82m1292956123.tab") + } > > try(system("convert tmp/2lfq21292956123.ps tmp/2lfq21292956123.png",intern=TRUE)) character(0) > try(system("convert tmp/3lfq21292956123.ps tmp/3lfq21292956123.png",intern=TRUE)) character(0) > try(system("convert tmp/4e6p41292956123.ps tmp/4e6p41292956123.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 2.540 0.380 2.908