Send output to:
Browser Blue - Charts White
Browser Black/White
CSV
Data X:
2 41 38 14 12 2 39 32 18 11 2 30 35 11 14 1 31 33 12 12 2 34 37 16 21 2 35 29 18 12 2 39 31 14 22 2 34 36 14 11 2 36 35 15 10 2 37 38 15 13 1 38 31 17 10 2 36 34 19 8 1 38 35 10 15 2 39 38 16 14 2 33 37 18 10 1 32 33 14 14 1 36 32 14 14 2 38 38 17 11 1 39 38 14 10 2 32 32 16 13 1 32 33 18 7 2 31 31 11 14 2 39 38 14 12 2 37 39 12 14 1 39 32 17 11 2 41 32 9 9 1 36 35 16 11 2 33 37 14 15 2 33 33 15 14 1 34 33 11 13 2 31 28 16 9 1 27 32 13 15 2 37 31 17 10 2 34 37 15 11 1 34 30 14 13 1 32 33 16 8 1 29 31 9 20 1 36 33 15 12 2 29 31 17 10 1 35 33 13 10 1 37 32 15 9 2 34 33 16 14 1 38 32 16 8 1 35 33 12 14 2 38 28 12 11 2 37 35 11 13 2 38 39 15 9 2 33 34 15 11 2 36 38 17 15 1 38 32 13 11 2 32 38 16 10 1 32 30 14 14 1 32 33 11 18 2 34 38 12 14 1 32 32 12 11 2 37 32 15 12 2 39 34 16 13 2 29 34 15 9 1 37 36 12 10 2 35 34 12 15 1 30 28 8 20 1 38 34 13 12 2 34 35 11 12 2 31 35 14 14 2 34 31 15 13 1 35 37 10 11 2 36 35 11 17 1 30 27 12 12 2 39 40 15 13 1 35 37 15 14 1 38 36 14 13 2 31 38 16 15 2 34 39 15 13 1 38 41 15 10 1 34 27 13 11 2 39 30 12 19 2 37 37 17 13 2 34 31 13 17 1 28 31 15 13 1 37 27 13 9 1 33 36 15 11 1 37 38 16 10 2 35 37 15 9 1 37 33 16 12 2 32 34 15 12 2 33 31 14 13 1 38 39 15 13 2 33 34 14 12 2 29 32 13 15 2 33 33 7 22 2 31 36 17 13 2 36 32 13 15 2 35 41 15 13 2 32 28 14 15 2 29 30 13 10 2 39 36 16 11 2 37 35 12 16 2 35 31 14 11 1 37 34 17 11 1 32 36 15 10 2 38 36 17 10 1 37 35 12 16 2 36 37 16 12 1 32 28 11 11 2 33 39 15 16 1 40 32 9 19 2 38 35 16 11 1 41 39 15 16 1 36 35 10 15 2 43 42 10 24 2 30 34 15 14 2 31 33 11 15 2 32 41 13 11 1 32 33 14 15 2 37 34 18 12 1 37 32 16 10 2 33 40 14 14 2 34 40 14 13 2 33 35 14 9 2 38 36 14 15 2 33 37 12 15 2 31 27 14 14 2 38 39 15 11 2 37 38 15 8 2 33 31 15 11 2 31 33 13 11 1 39 32 17 8 2 44 39 17 10 2 33 36 19 11 2 35 33 15 13 1 32 33 13 11 1 28 32 9 20 2 40 37 15 10 1 27 30 15 15 1 37 38 15 12 2 32 29 16 14 1 28 22 11 23 1 34 35 14 14 2 30 35 11 16 2 35 34 15 11 1 31 35 13 12 2 32 34 15 10 1 30 34 16 14 2 30 35 14 12 1 31 23 15 12 2 40 31 16 11 2 32 27 16 12 1 36 36 11 13 1 32 31 12 11 1 35 32 9 19 2 38 39 16 12 2 42 37 13 17 1 34 38 16 9 2 35 39 12 12 2 35 34 9 19 2 33 31 13 18 2 36 32 13 15 2 32 37 14 14 2 33 36 19 11 2 34 32 13 9 2 32 35 12 18 2 34 36 13 16
Names of X columns:
Gender Connected Separate Happiness Depression
Endogenous Variable (Column Number)
Categorization
Do not include Seasonal Dummies
none
quantiles
hclust
equal
Number of categories (only if categorization<>none)
Cross-Validation? (only if categorization<>none)
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