R version 2.13.0 (2011-04-13) Copyright (C) 2011 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(186448 + ,17822 + ,1942 + ,16739 + ,4872 + ,1020 + ,190530 + ,22422 + ,2547 + ,17851 + ,4905 + ,1200 + ,194207 + ,18817 + ,2033 + ,17034 + ,4971 + ,1279 + ,190855 + ,22043 + ,2049 + ,18055 + ,4971 + ,1308 + ,200779 + ,19191 + ,2007 + ,18216 + ,4930 + ,1173 + ,204428 + ,23171 + ,2660 + ,18960 + ,5001 + ,1291 + ,207617 + ,19463 + ,2063 + ,17903 + ,5059 + ,1466 + ,212071 + ,22522 + ,2113 + ,18842 + ,5085 + ,1507 + ,214239 + ,20265 + ,2145 + ,18907 + ,5111 + ,1478 + ,215883 + ,24249 + ,2866 + ,19862 + ,5190 + ,1629 + ,223484 + ,20299 + ,2163 + ,18836 + ,5076 + ,1712 + ,221529 + ,25455 + ,2157 + ,19846 + ,5134 + ,1727 + ,225247 + ,21089 + ,2201 + ,19511 + ,4804 + ,1519 + ,226699 + ,26237 + ,2838 + ,20318 + ,4579 + ,1617 + ,231406 + ,21362 + ,2142 + ,19843 + ,4526 + ,1637 + ,232324 + ,26489 + ,2253 + ,20975 + ,4550 + ,1633 + ,237192 + ,21828 + ,2258 + ,20485 + ,4566 + ,1469 + ,236727 + ,27496 + ,2979 + ,21407 + ,4588 + ,1657 + ,240698 + ,21991 + ,2288 + ,20404 + ,4564 + ,1599 + ,240688 + ,27611 + ,2431 + ,21454 + ,4723 + ,1420 + ,245283 + ,22512 + ,2393 + ,21558 + ,4553 + ,1495 + ,243556 + ,28581 + ,3244 + ,22442 + ,4556 + ,1623 + ,247826 + ,23000 + ,2476 + ,21201 + ,4542 + ,1346 + ,245798 + ,28385 + ,2490 + ,21804 + ,4234 + ,1613 + ,250479 + ,23387 + ,2547 + ,22537 + ,4341 + ,1563 + ,249216 + ,30192 + ,3461 + ,22736 + ,4269 + ,2071 + ,251896 + ,24346 + ,2549 + ,21525 + ,4217 + ,1584 + ,247616 + ,30393 + ,2496 + ,22427 + ,4207 + ,1843 + ,249994 + ,24753 + ,2532 + ,23437 + ,4267 + ,1598 + ,246552 + ,31723 + ,3553 + ,23366 + ,4249 + ,1687 + ,248771 + ,24838 + ,2555 + ,22281 + ,4217 + ,1473 + ,247551 + ,32272 + ,2565 + ,22994 + ,4172 + ,2080 + ,249745 + ,25219 + ,2548 + ,24007 + ,4161 + ,1703 + ,245742 + ,33191 + ,3932 + ,24145 + ,4103 + ,1832 + ,249019 + ,26218 + ,2525 + ,23065 + ,4027 + ,1781 + ,245841 + ,33537 + ,2633 + ,24374 + ,4042 + ,2481 + ,248771 + ,27975 + ,2657 + ,24805 + ,4120 + ,1977 + ,244723 + ,34356 + ,3829 + ,25159 + ,4188 + ,1974 + ,246878 + ,27082 + ,2769 + ,23751 + ,4185 + ,1777 + ,246014 + ,34333 + ,2816 + ,25487 + ,4216 + ,2303 + ,248496 + ,28141 + ,3052 + ,25608 + ,4250 + ,1480 + ,244351 + ,36125 + ,4146 + ,26396 + ,4259 + ,1907 + ,248016 + ,28451 + ,3185 + ,25207 + ,4206 + ,1610 + ,246509 + ,35801 + ,3147 + ,27000 + ,4132 + ,1546 + ,249426 + ,28979 + ,3161 + ,27369 + ,3944 + ,1718 + ,247840 + ,37285 + ,4311 + ,28401 + ,3872 + ,1841 + ,251035 + ,30310 + ,3155 + ,27126 + ,3797 + ,1650 + ,250161 + ,36721 + ,3284 + ,28474 + ,3840 + ,1671 + ,254278 + ,29534 + ,3350 + ,28926 + ,3895 + ,1974 + ,250801 + ,38626 + ,4268 + ,29894 + ,3633 + ,2153 + ,253985 + ,29654 + ,3220 + ,28822 + ,3622 + ,1898 + ,249174 + ,42638 + ,8289 + ,29849 + ,3562 + ,2725 + ,251287 + ,31372 + ,3419 + ,30624 + ,3555 + ,2047 + ,247947 + ,39603 + ,3902 + ,31038 + ,3489 + ,1698 + ,249992 + ,31647 + ,3223 + ,29468 + ,3500 + ,1768 + ,243805 + ,39946 + ,3447 + ,31294 + ,3373 + ,1921 + ,255812 + ,31518 + ,3389 + ,32110 + ,3285 + ,9782 + ,250417 + ,42743 + ,4637 + ,32827 + ,3292 + ,2231 + ,253033 + ,33462 + ,3509 + ,31327 + ,3241 + ,2062 + ,248705 + ,41744 + ,4107 + ,32749 + ,3266 + ,2132 + ,253950 + ,33142 + ,3632 + ,33598 + ,3168 + ,2465 + ,251484 + ,41753 + ,4490 + ,33878 + ,3181 + ,2198 + ,251093 + ,35487 + ,3649 + ,32292 + ,3246 + ,2330 + ,245996 + ,44720 + ,3983 + ,34021 + ,3159 + ,1214 + ,252721 + ,33472 + ,3678 + ,34955 + ,3209 + ,2517 + ,248019 + ,45134 + ,4570 + ,35322 + ,3220 + ,2255 + ,250464 + ,36255 + ,3778 + ,33816 + ,3305 + ,2379 + ,245571 + ,46228 + ,4153 + ,35766 + ,3251 + ,2349 + ,252690 + ,35483 + ,4027 + ,36770 + ,3281 + ,2219 + ,250183 + ,47663 + ,5050 + ,37762 + ,3304 + ,2470 + ,253639 + ,38064 + ,4155 + ,36298 + ,3270 + ,2540 + ,254436 + ,47177 + ,4475 + ,39219 + ,3377 + ,2667 + ,265280 + ,35062 + ,4117 + ,39664 + ,3235 + ,3507 + ,268705 + ,45062 + ,5193 + ,40178 + ,3125 + ,2972 + ,270643 + ,36943 + ,4199 + ,38402 + ,3091 + ,2678 + ,271480 + ,46194 + ,4391 + ,40957 + ,3102 + ,2979) + ,dim=c(6 + ,76) + ,dimnames=list(c('Netto' + ,'Parafiscaal' + ,'Niet-parafiscaal' + ,'Lopende' + ,'Rente' + ,'Kapitaal') + ,1:76)) > y <- array(NA,dim=c(6,76),dimnames=list(c('Netto','Parafiscaal','Niet-parafiscaal','Lopende','Rente','Kapitaal'),1:76)) > 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$_version), Office for Research Development and Education, URL http://www.wessa.net/rwasp_YOURPAGE.wasp/ > #Source of accompanying publication: > #Technical description: > library(party) Loading required package: survival Loading required package: splines Loading required package: grid Loading required package: modeltools Loading required package: stats4 Loading required package: coin Loading required package: mvtnorm Loading required package: zoo Loading required package: sandwich Loading required package: strucchange Loading required package: vcd Loading required package: MASS Loading required package: colorspace > library(Hmisc) Attaching package: 'Hmisc' The following object(s) are masked from 'package:survival': untangle.specials The following object(s) are masked from 'package:base': format.pval, round.POSIXt, trunc.POSIXt, units > par1 <- as.numeric(par1) > par3 <- as.numeric(par3) > x <- data.frame(t(y)) > is.data.frame(x) [1] TRUE > x <- x[!is.na(x[,par1]),] > k <- length(x[1,]) > n <- length(x[,1]) > colnames(x)[par1] [1] "Netto" > x[,par1] [1] 186448 190530 194207 190855 200779 204428 207617 212071 214239 215883 [11] 223484 221529 225247 226699 231406 232324 237192 236727 240698 240688 [21] 245283 243556 247826 245798 250479 249216 251896 247616 249994 246552 [31] 248771 247551 249745 245742 249019 245841 248771 244723 246878 246014 [41] 248496 244351 248016 246509 249426 247840 251035 250161 254278 250801 [51] 253985 249174 251287 247947 249992 243805 255812 250417 253033 248705 [61] 253950 251484 251093 245996 252721 248019 250464 245571 252690 250183 [71] 253639 254436 265280 268705 270643 271480 > if (par2 == 'kmeans') { + cl <- kmeans(x[,par1], par3) + print(cl) + clm <- matrix(cbind(cl$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]) [186448,247947) [247947,271480] 38 38 > colnames(x) [1] "Netto" "Parafiscaal" "Niet.parafiscaal" "Lopende" [5] "Rente" "Kapitaal" > colnames(x)[par1] [1] "Netto" > x[,par1] [1] [186448,247947) [186448,247947) [186448,247947) [186448,247947) [5] [186448,247947) [186448,247947) [186448,247947) [186448,247947) [9] [186448,247947) [186448,247947) [186448,247947) [186448,247947) [13] [186448,247947) [186448,247947) [186448,247947) [186448,247947) [17] [186448,247947) [186448,247947) [186448,247947) [186448,247947) [21] [186448,247947) [186448,247947) [186448,247947) [186448,247947) [25] [247947,271480] [247947,271480] [247947,271480] [186448,247947) [29] [247947,271480] [186448,247947) [247947,271480] [186448,247947) [33] [247947,271480] [186448,247947) [247947,271480] [186448,247947) [37] [247947,271480] [186448,247947) [186448,247947) [186448,247947) [41] [247947,271480] [186448,247947) [247947,271480] [186448,247947) [45] [247947,271480] [186448,247947) [247947,271480] [247947,271480] [49] [247947,271480] [247947,271480] [247947,271480] [247947,271480] [53] [247947,271480] [247947,271480] [247947,271480] [186448,247947) [57] [247947,271480] [247947,271480] [247947,271480] [247947,271480] [61] [247947,271480] [247947,271480] [247947,271480] [186448,247947) [65] [247947,271480] [247947,271480] [247947,271480] [186448,247947) [69] [247947,271480] [247947,271480] [247947,271480] [247947,271480] [73] [247947,271480] [247947,271480] [247947,271480] [247947,271480] Levels: [186448,247947) [247947,271480] > if (par2 == 'none') { + m <- ctree(as.formula(paste(colnames(x)[par1],' ~ .',sep='')),data = x) + } > > #Note: the /var/wessaorg/rcomp/createtable file can be downloaded at http://www.wessa.net/cretab > load(file="/var/wessaorg/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/wessaorg/rcomp/tmp/1kur71323868925.tab") + } + } m.ct.i.pred m.ct.i.actu 1 2 1 270 62 2 35 299 [1] 0.813253 [1] 0.8952096 [1] 0.8543544 m.ct.x.pred m.ct.x.actu 1 2 1 35 13 2 10 36 [1] 0.7291667 [1] 0.7826087 [1] 0.7553191 > m Conditional inference tree with 4 terminal nodes Response: as.factor(Netto) Inputs: Parafiscaal, Niet.parafiscaal, Lopende, Rente, Kapitaal Number of observations: 76 1) Rente <= 4027; criterion = 1, statistic = 35.428 2)* weights = 33 1) Rente > 4027 3) Rente <= 4341; criterion = 0.979, statistic = 8.199 4) Parafiscaal <= 30192; criterion = 0.996, statistic = 11.229 5)* weights = 11 4) Parafiscaal > 30192 6)* weights = 9 3) Rente > 4341 7)* weights = 23 > postscript(file="/var/wessaorg/rcomp/tmp/22a391323868925.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/wessaorg/rcomp/tmp/3v5y51323868925.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 1 [3,] 1 1 [4,] 1 1 [5,] 1 1 [6,] 1 1 [7,] 1 1 [8,] 1 1 [9,] 1 1 [10,] 1 1 [11,] 1 1 [12,] 1 1 [13,] 1 1 [14,] 1 1 [15,] 1 1 [16,] 1 1 [17,] 1 1 [18,] 1 1 [19,] 1 1 [20,] 1 1 [21,] 1 1 [22,] 1 1 [23,] 1 1 [24,] 1 2 [25,] 2 2 [26,] 2 2 [27,] 2 2 [28,] 1 1 [29,] 2 2 [30,] 1 1 [31,] 2 2 [32,] 1 1 [33,] 2 2 [34,] 1 1 [35,] 2 2 [36,] 1 1 [37,] 2 2 [38,] 1 1 [39,] 1 2 [40,] 1 1 [41,] 2 2 [42,] 1 1 [43,] 2 2 [44,] 1 1 [45,] 2 2 [46,] 1 2 [47,] 2 2 [48,] 2 2 [49,] 2 2 [50,] 2 2 [51,] 2 2 [52,] 2 2 [53,] 2 2 [54,] 2 2 [55,] 2 2 [56,] 1 2 [57,] 2 2 [58,] 2 2 [59,] 2 2 [60,] 2 2 [61,] 2 2 [62,] 2 2 [63,] 2 2 [64,] 1 2 [65,] 2 2 [66,] 2 2 [67,] 2 2 [68,] 1 2 [69,] 2 2 [70,] 2 2 [71,] 2 2 [72,] 2 2 [73,] 2 2 [74,] 2 2 [75,] 2 2 [76,] 2 2 [186448,247947) [247947,271480] [186448,247947) 32 6 [247947,271480] 0 38 > postscript(file="/var/wessaorg/rcomp/tmp/4mukm1323868925.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/wessaorg/rcomp/tmp/5lru51323868925.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/wessaorg/rcomp/tmp/6mrti1323868925.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/wessaorg/rcomp/tmp/7a4lq1323868925.tab") + } > > try(system("convert tmp/22a391323868925.ps tmp/22a391323868925.png",intern=TRUE)) character(0) > try(system("convert tmp/3v5y51323868925.ps tmp/3v5y51323868925.png",intern=TRUE)) character(0) > try(system("convert tmp/4mukm1323868925.ps tmp/4mukm1323868925.png",intern=TRUE)) character(0) > > > proc.time() user system elapsed 3.225 0.252 3.523