Send output to:
Browser Blue - Charts White
Browser Black/White
CSV
Data X:
2 1 22 15 16 17 10 1 2 22 23 24 42 9 1 2 22 26 22 39 30 1 2 23 19 21 22 18 1 2 21 19 23 20 16 1 2 21 16 23 31 20 1 1 24 23 21 42 20 2 1 22 22 20 30 18 1 2 21 19 22 33 21 1 2 23 24 20 29 20 1 1 20 19 12 31 20 2 1 23 25 23 39 20 1 1 20 23 23 44 29 1 2 21 31 30 40 14 2 1 22 29 22 42 25 2 2 22 18 21 28 19 2 2 21 17 21 29 19 1 1 20 22 15 35 25 1 1 21 21 22 26 25 1 2 21 24 24 42 19 1 1 20 22 23 26 19 1 1 21 16 15 30 18 1 2 23 22 24 28 24 1 1 23 21 24 24 18 2 1 21 25 21 26 26 1 1 22 22 21 39 26 2 1 20 24 18 33 24 2 1 23 21 20 50 29 2 1 21 25 19 40 26 1 1 21 29 29 49 28 2 1 23 19 20 31 18 2 1 23 29 23 37 19 2 2 22 25 24 29 21 1 1 21 19 27 37 13 1 1 NA 27 28 16 19 1 2 21 25 24 28 26 1 2 21 23 29 29 17 1 1 22 24 24 31 19 2 2 22 23 22 34 28 1 2 22 25 25 30 15 1 1 22 26 24 31 16 1 1 23 23 14 44 18 2 1 NA 22 22 35 25 1 2 22 32 24 47 15 1 2 21 22 24 39 24 1 1 23 18 24 34 24 2 1 21 19 24 15 14 2 2 32 23 22 26 19 2 2 32 24 22 25 20 2 1 21 19 21 30 27 1 1 20 16 21 25 20 1 1 21 23 21 33 25 1 1 22 17 15 39 16 1 1 21 17 26 24 19 1 2 21 28 22 44 15 1 2 21 24 24 31 17 1 1 22 21 13 30 22 1 1 21 14 19 21 19 2 1 25 21 10 38 44 1 2 22 20 28 30 19 1 1 21 25 25 31 19 2 2 21 20 24 32 23 1 1 20 17 22 34 19 1 2 21 26 30 43 28 1 2 22 17 22 29 17 4 2 21 17 24 40 22 1 2 23 24 23 31 25 1 2 24 30 20 36 44 2 1 20 25 22 39 19 2 1 21 15 22 31 21 1 1 23 25 19 36 25 1 1 24 18 24 36 28 1 1 22 20 22 36 19 1 1 22 32 26 41 33 2 2 21 14 12 23 19 2 1 20 20 25 23 12 1 2 21 25 29 34 15 1 NA 21 25 23 31 23 1 1 22 25 23 26 21 1 1 21 35 17 32 29 1 2 21 29 26 48 15 1 1 22 25 27 37 23 1 2 23 21 23 31 25 1 1 23 21 20 29 18 1 1 21 24 24 44 24 1 1 22 26 22 27 20 1 1 24 24 26 31 19 1 2 21 20 29 37 21 1 1 25 24 20 31 33 2 1 24 18 17 29 17 1 1 21 17 16 25 19 1 2 21 22 24 39 19 1 1 22 22 24 33 23 1 1 22 22 19 26 21 2 1 21 24 29 39 20 1 1 24 32 25 33 19 1 2 21 19 25 22 16 1 2 21 21 24 27 20 1 2 22 23 29 31 18 2 1 22 26 22 40 11 1 2 21 18 23 45 18 2 1 21 19 15 33 23 1 1 22 22 29 26 19 1 2 21 27 21 28 21 2 1 21 21 23 28 16 2 1 22 20 20 30 24 2 2 21 21 25 47 23 1 1 21 20 28 30 20 1 1 21 29 18 37 23 1 1 23 30 25 23 25 1 1 22 23 24 24 24 2 1 21 29 23 15 19 1 2 22 19 25 39 15 1 1 22 26 27 32 20 1 1 22 22 24 23 14 2 1 23 26 24 41 34 2 1 24 27 26 39 24 2 1 22 19 18 42 26 2 2 21 24 26 38 23 1 2 21 26 23 30 18 2 2 22 22 28 19 11 1 1 20 23 20 45 28 1 1 23 25 23 36 15 1 2 21 19 24 36 26 1 1 22 20 21 33 20 2 1 23 25 25 35 21 2 1 21 14 16 29 21 1 2 21 20 19 28 15 1 1 23 27 22 40 30 1 2 21 21 27 28 21 1 2 21 21 24 36 12 1 2 21 14 17 28 23 2 1 23 21 21 42 30 1 1 21 23 21 27 22 2 1 22 18 19 32 21 1 2 22 20 25 27 19 1 2 21 19 24 30 22 1 2 21 15 21 31 18 1 2 24 23 26 26 16 1 1 21 26 25 47 19 1 1 21 21 25 28 20 1 2 20 13 13 31 12 2 2 21 24 25 26 21 1 2 NA 17 23 27 14 1 1 24 21 26 28 23 1 1 22 28 22 44 30 1 1 22 22 20 32 21 1 1 22 25 14 25 25 1 1 22 18 23 24 13 1 1 23 27 24 45 17 1 1 22 25 21 37 24 2 1 22 21 24 25 21
Names of X columns:
Roken Geslacht Leeftijd PS O CMD PEC
Endogenous Variable (Column Number)
Categorization
none
none
quantiles
hclust
equal
Number of categories (only if categorization<>none)
Cross-Validation? (only if categorization<>none)
yes
no
yes
Chart options
R Code
library(party) library(Hmisc) par1 <- as.numeric(par1) par3 <- as.numeric(par3) x <- data.frame(t(y)) is.data.frame(x) x <- x[!is.na(x[,par1]),] k <- length(x[1,]) n <- length(x[,1]) colnames(x)[par1] x[,par1] 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]) colnames(x) colnames(x)[par1] x[,par1] if (par2 == 'none') { m <- ctree(as.formula(paste(colnames(x)[par1],' ~ .',sep='')),data = x) } load(file='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='mytable3.tab') } } m bitmap(file='test1.png') plot(m) dev.off() bitmap(file='test1a.png') plot(x[,par1] ~ as.factor(where(m)),main='Response by Terminal Node',xlab='Terminal Node',ylab='Response') dev.off() 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) } bitmap(file='test2.png') 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() 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$Residuals)^2)),4)) a<-table.row.end(a) a<-table.end(a) table.save(a,file='mytable1.tab') a<-table.start() a<-table.row.start(a) a<-table.element(a,'Actuals, Predictions, and Residuals',4,TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a,'#',header=TRUE) a<-table.element(a,'Actuals',header=TRUE) a<-table.element(a,'Forecasts',header=TRUE) a<-table.element(a,'Residuals',header=TRUE) a<-table.row.end(a) for (i in 1:length(result$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='mytable.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='mytable2.tab') }
Compute
Summary of computational transaction
Raw Input
view raw input (R code)
Raw Output
view raw output of R engine
Computing time
2 seconds
R Server
Big Analytics Cloud Computing Center
Click here to blog (archive) this computation