Send output to:
Browser Blue - Charts White
Browser Black/White
CSV
Data X:
176508 12 60 38 146 165446 0 69 25 93 237213 0 78 38 140 133131 7 44 30 99 324799 0 158 47 181 236785 3 77 31 116 344297 1 80 30 108 174724 0 123 34 129 174415 0 73 31 118 223632 0 105 33 125 124817 0 47 25 95 325107 0 84 36 136 7176 0 0 0 0 265769 2 96 32 124 175824 0 57 20 80 111665 4 39 28 104 362301 2 76 34 125 168809 0 76 28 118 24188 0 8 4 12 329267 8 79 39 144 218946 1 76 29 108 244052 5 101 44 166 341570 1 94 21 80 256462 0 123 35 127 196553 2 41 29 111 174184 0 72 25 98 187559 8 75 36 135 73566 6 22 23 88 182999 6 73 34 129 152299 0 62 33 122 346485 0 118 38 147 193339 2 100 35 87 122774 0 24 24 90 112611 0 46 20 78 286468 1 57 29 111 148446 1 135 37 141 140344 6 33 25 93 220516 1 98 32 124 243060 4 58 29 112 162765 2 68 28 108 232138 0 131 31 117 85574 0 37 21 78 232317 0 118 33 126 164709 0 81 31 115 220801 1 51 18 72 92661 1 40 17 45 133328 0 56 20 78 61361 0 27 12 39 100750 0 83 30 119 101523 0 59 22 88 243511 0 133 42 155 22938 0 12 1 0 152474 0 106 32 123 132487 0 71 36 136 21054 0 4 0 0 209641 5 62 24 88 46698 0 14 13 52 131698 0 60 19 75 244749 2 98 33 124 272458 0 100 43 162 108043 1 45 14 54 351067 3 136 45 170 229242 4 63 31 120 84207 11 14 30 112 250047 0 41 18 71 299775 9 91 31 120 173260 3 41 21 79 92499 0 25 18 71 74408 4 29 7 28 181633 2 47 30 110 271856 1 109 37 147 95227 0 37 32 111 139942 0 54 22 88 72880 0 14 19 76 65475 2 16 13 51 71965 1 32 15 59 181528 0 32 16 61 134019 0 32 18 67 56375 7 10 13 49 65490 3 27 16 62 76302 0 29 20 76 104011 6 25 22 88 30989 0 5 17 68 63123 1 34 17 68 74914 0 35 23 90 81437 0 37 14 54 65745 0 26 21 77 56653 0 38 18 68 158399 0 23 18 72 73624 0 30 17 64 91899 0 18 15 59 139526 0 28 21 84 86678 0 12 15 59 150580 0 27 22 83 99611 0 41 21 81 31706 0 26 10 32 89806 0 27 16 62 19764 1 10 2 8 64187 0 10 16 61 72535 0 17 16 64 210907 3 79 30 115 120982 4 58 28 109 385534 0 121 25 96 149061 5 43 26 100 230964 4 102 30 116 135473 0 82 23 88 215147 0 101 36 135 153935 5 50 25 89 225548 5 81 31 118 210767 3 94 35 135 170266 4 44 42 154 294424 2 107 33 127 106408 1 33 14 46 96560 0 42 17 54 149112 6 56 35 128 152871 5 59 28 97 183167 0 91 39 149 103597 1 27 16 60 235800 8 105 23 84 143246 5 67 27 105 187681 2 114 28 107 167488 2 69 28 104 143756 0 105 34 132 243199 3 88 28 108 130585 5 67 29 109 182079 2 124 33 124 265318 10 110 52 199 310839 9 130 24 91 225060 7 93 41 158 144966 0 39 32 122 99466 0 28 23 91 102010 3 28 13 50 99923 0 44 25 99 317394 1 116 31 117 22648 0 12 13 39 31414 0 18 8 25 128423 8 32 38 145 97839 2 25 24 87 328107 3 129 41 159 158015 0 59 31 119 120445 0 36 16 59 324598 0 113 37 136 131069 4 47 30 107 204271 0 92 35 130 116048 0 50 20 75 195838 1 111 31 116 254488 10 120 39 150 224330 1 131 39 144 135781 2 45 14 47 81240 0 58 17 68 98146 0 15 17 68 59194 6 7 24 80 118612 2 54 12 48 135131 0 38 15 60 108446 1 22 17 68 121848 0 37 17 64 81872 0 32 16 64 58981 7 0 23 91 53515 2 5 22 88 98104 2 55 17 66 135458 3 43 12 48 31774 1 0 17 66 51567 2 21 14 56 102538 1 50 15 58 99373 1 12 18 72 86230 0 21 17 61 30837 0 8 4 15 64175 0 37 18 72 59382 0 29 12 41 119308 0 32 16 61 76702 0 35 21 67 84105 0 17 17 66
Names of X columns:
Tijd Gedeelde_compendia Aantal_blogs Reviews Reviews+120
Endogenous Variable (Column Number)
Categorization
quantiles
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