Send output to:
Browser Blue - Charts White
Browser Black/White
CSV
Data X:
2 210907 79 94 112285 146283 30 -1 4 179321 108 103 101193 96933 30 3 0 149061 43 93 116174 95757 26 0 0 237213 78 123 66198 143983 38 3 -4 173326 86 148 71701 75851 44 4 4 133131 44 90 57793 59238 30 0 4 258873 104 124 80444 93163 40 0 0 324799 158 168 97668 151511 47 7 -1 230964 102 115 133824 136368 30 1 0 236785 77 71 101481 112642 31 0 1 344297 80 108 67654 127766 30 1 0 174724 123 120 69112 85646 34 4 3 174415 73 114 82753 98579 31 1 -1 223632 105 120 72654 131741 33 5 4 294424 107 124 101494 171975 33 13 3 325107 84 126 79215 159676 36 4 1 106408 33 37 31081 58391 14 0 0 96560 42 38 22996 31580 17 0 -2 265769 96 120 83122 136815 32 6 -3 269651 106 93 70106 120642 30 0 -4 149112 56 95 60578 69107 35 1 2 152871 59 90 79892 108016 28 3 2 362301 76 110 100708 79336 34 1 -4 183167 91 138 82875 93176 39 0 3 277965 115 133 139077 161632 39 2 2 218946 76 96 80670 102996 29 3 2 244052 101 164 143558 160604 44 4 0 341570 94 78 117105 158051 21 12 5 233328 92 102 120733 162647 28 0 -2 206161 75 99 73107 60622 28 3 0 311473 128 129 132068 179566 38 0 -2 207176 56 114 87011 96144 32 4 -3 196553 41 99 95260 129847 29 -1 2 143246 67 104 106671 71180 27 2 2 182192 77 138 70054 86767 40 1 2 194979 66 151 74011 93487 40 1 0 167488 69 72 83737 82981 28 0 4 143756 105 120 69094 73815 34 2 4 275541 116 115 93133 94552 33 0 2 152299 62 98 61370 67808 33 2 2 193339 100 71 84651 106175 35 4 -4 130585 67 107 95364 76669 29 0 3 112611 46 73 26706 57283 20 0 3 148446 135 129 126846 72413 37 6 2 182079 124 118 102860 96971 33 13 -1 243060 58 104 111813 120336 29 4 -3 162765 68 107 120293 93913 28 -1 0 85574 37 36 24266 32036 21 3 1 225060 93 139 109825 102255 41 0 -3 133328 56 56 40909 63506 20 2 3 100750 83 93 140867 68370 30 0 0 101523 59 87 61056 50517 22 1 0 243511 133 110 101338 103950 42 1 0 152474 106 83 65567 84396 32 0 3 132487 71 98 40735 55515 36 31 -3 317394 116 82 91413 209056 31 2 0 244749 98 115 76643 142775 33 5 -4 184510 64 140 110681 68847 40 1 2 128423 32 120 92696 20112 38 1 -1 97839 25 66 94785 61023 24 2 3 172494 46 139 86687 112494 43 13 2 229242 63 119 91721 78876 31 5 5 351619 95 141 115168 170745 40 3 2 324598 113 133 135777 122037 37 1 -2 195838 111 98 102372 112283 31 1 0 254488 120 117 103772 120691 39 4 3 199476 87 105 135400 122422 32 2 -2 92499 25 55 21399 25899 18 0 0 224330 131 132 130115 139296 39 4 6 181633 47 73 64466 89455 30 0 -3 271856 109 86 54990 147866 37 0 3 95227 37 48 34777 14336 32 0 0 98146 15 48 27114 30059 17 7 -2 118612 54 43 30080 41907 12 3 1 65475 16 46 69008 35885 13 4 0 108446 22 65 46300 55764 17 1 2 121848 37 52 30594 35619 17 0 2 76302 29 68 30976 40557 20 2 -3 98104 55 47 25568 44197 17 0 -2 30989 5 41 4154 4103 17 0 1 31774 0 47 4143 4694 17 0 -4 150580 27 71 45588 62991 22 2 0 54157 37 30 18625 24261 15 1 1 59382 29 24 26263 21425 12 0 0 84105 17 63 20055 27184 17 0
Names of X columns:
estscore time_in_rfc blogged_computations feedback_messages_p120 totsize totseconds compendiums_reviewed difference_hyperlinks-blogs
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