Send output to:
Browser Blue - Charts White
Browser Black/White
CSV
Data X:
96560 76 129 17 22996 0 0 78 62 72 112611 41 36 20 26706 3 7 44 56 64 98146 40 37 17 27114 0 1 80 49 66 121848 39 45 17 30594 2 0 73 63 78 31774 23 48 17 4143 1 2 107 67 71 65475 18 24 13 69008 1 0 42 59 71 108446 60 90 17 46300 0 2 76 40 59 76302 31 26 20 30976 2 2 69 34 65 30989 14 35 17 4154 -2 0 62 37 48 150580 77 124 22 45588 -4 0 46 61 72 59382 49 49 12 26263 1 0 133 60 66 341570 168 190 21 117105 0 0 71 57 68 133328 55 79 20 40909 -3 0 46 56 75 101523 42 76 22 61056 0 1 131 67 73 92499 32 57 18 21399 -2 2 47 38 59 118612 46 72 12 30080 -2 0 15 49 72 98104 54 132 17 25568 -3 0 37 32 65 84105 20 45 17 20055 0 1 0 63 69 237213 84 74 38 66198 0 3 79 67 71 133131 55 52 30 57793 4 3 77 43 54 344297 75 86 30 67654 1 5 101 84 84 174415 100 63 31 82753 3 0 105 49 66 294424 77 59 33 101494 4 2 124 58 73 362301 119 715 34 100708 2 0 83 63 69 167488 45 77 28 83737 0 0 106 29 70 152299 53 63 33 61370 2 2 25 58 72 243511 71 65 42 101338 0 2 16 62 63 132487 41 97 36 40735 3 1 22 54 66 172494 52 52 43 86687 3 0 29 53 60 224330 83 52 39 130115 0 0 5 66 66 181633 70 48 30 64466 6 0 27 53 71 210907 56 81 30 112285 2 0 29 26 50 236785 119 75 31 101481 0 5 43 43 52 244052 68 66 44 143558 2 0 158 53 70 143756 46 57 34 69094 4 4 102 54 60 182079 63 63 33 102860 2 0 123 47 76 100750 72 67 30 140867 3 0 105 43 60 152474 65 45 32 65567 0 1 33 57 70 97839 38 42 24 94785 -1 2 96 41 75 149061 44 66 26 116174 0 6 56 37 54 324799 154 108 47 97668 0 5 59 52 65 230964 53 43 30 133824 -1 0 91 52 73 174724 92 135 34 69112 0 1 76 67 42 223632 73 52 33 72654 -1 1 94 70 65 106408 30 32 14 31081 1 2 41 68 75 265769 146 37 32 83122 -2 5 67 43 66 149112 56 65 35 60578 -4 2 100 56 70 152871 58 74 28 79892 2 5 67 74 81 183167 66 66 39 82875 -4 1 135 58 71 218946 41 112 29 80670 2 4 58 63 68 196553 57 50 29 95260 -3 0 56 64 67 143246 103 42 27 106671 2 0 59 53 76 193339 78 47 35 84651 2 1 116 51 71 130585 46 57 29 95364 -4 2 98 54 70 148446 91 63 37 126846 3 8 32 48 65 243060 63 110 29 111813 -1 4 63 50 68 317394 86 53 31 91413 -3 0 113 45 70 244749 95 144 33 76643 0 1 111 61 64 128423 64 89 38 92696 2 10 120 56 70 229242 247 128 31 91721 2 0 25 46 66 324598 110 128 37 135777 2 1 109 51 59 195838 67 50 31 102372 -2 0 37 37 78 254488 83 50 39 103772 0 2 54 42 67 271856 103 91 37 54990 -3 2 55 69 67 95227 34 70 32 34777 3 0 17 56 61
Names of X columns:
tijd login vieuws revieuws size test shared blogged intrisieke extrisieke
Endogenous Variable (Column Number)
Categorization
none
none
quantiles
hclust
equal
Number of categories (only if categorization<>none)
Cross-Validation? (only if categorization<>none)
no
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