Send output to:
Browser Blue - Charts White
Browser Black/White
CSV
Data X:
157382 48 18 20465 23975 0 168465 45 20 33629 85634 1 7215 0 0 1423 1929 0 122259 49 26 25629 36294 0 221399 76 30 54002 72255 0 454489 118 36 151036 189748 1 134379 42 23 33287 61834 1 150416 62 30 31172 68167 0 121391 48 30 28113 38462 0 275326 67 26 57803 101219 1 121593 50 24 49830 43270 2 172071 71 30 52143 76183 0 86249 41 21 21055 31476 0 201902 77 25 47007 62157 4 144113 45 17 28735 46261 4 144677 54 19 59147 50063 3 134153 75 33 78950 64483 0 64149 0 15 13497 2341 5 122294 54 34 46154 48149 0 27918 13 18 53249 12743 0 52197 16 15 10726 18743 0 191463 78 27 83700 97057 0 176034 35 25 40400 17675 0 98629 38 34 33797 33106 1 143546 50 21 36205 53311 1 139780 39 21 30165 42754 0 174181 58 25 58534 59056 0 163773 70 28 44663 101621 0 312831 55 28 92556 118120 0 184024 52 20 40078 79572 0 151621 50 28 34711 42744 0 164516 54 20 31076 65931 2 120414 53 17 74608 38575 4 214975 76 25 58092 28795 0 200609 54 24 42009 94440 1 0 0 0 0 0 0 191923 46 27 36022 38229 0 93107 44 14 23333 31972 3 129419 35 32 53349 40071 9 233497 82 31 92596 132480 0 178228 73 21 49598 62797 2 126602 31 34 44093 40429 0 94332 25 23 84205 45545 2 164183 57 24 63369 57568 1 95704 44 22 60132 39019 2 139901 40 22 37403 53866 2 81293 23 35 24460 38345 1 189007 63 21 46456 50210 0 173779 43 31 66616 80947 1 146552 62 26 41554 43461 7 48188 12 22 22346 14812 0 113870 67 21 30874 37819 0 266451 60 27 68701 102738 0 229437 55 26 35728 54509 0 174876 53 33 29010 62956 1 119070 35 11 23110 55411 6 186704 50 26 38844 50611 0 72559 25 26 27084 26692 0 111940 47 23 35139 60056 0 166226 30 38 57476 25155 10 135901 50 29 33277 42840 6 102141 36 19 31141 39358 0 115753 43 19 61281 47241 11 102194 44 24 25820 49611 3 148531 25 26 23284 41833 0 94982 38 29 35378 48930 0 178613 68 36 74990 110600 8 128907 83 25 29653 52235 2 102378 48 24 64622 53986 0 31970 5 21 4157 4105 0 204812 53 19 29245 59331 3 104972 36 12 50008 47796 1 95276 62 28 52338 38302 2 101560 46 21 13310 14063 1 144193 67 34 92901 54414 0 71921 2 32 10956 9903 2 126905 64 27 34241 53987 1 140303 59 28 75043 88937 0 60138 16 21 21152 21928 0 84971 34 31 42249 29487 0 80420 54 26 42005 35334 0 244190 39 29 41152 57596 0 56252 26 23 14399 29750 0 97181 37 25 28263 41029 0 50913 17 22 17215 12416 0 143910 32 26 48140 51158 0 218900 55 33 62897 79935 0 90772 50 22 22883 26552 0 90385 39 24 41622 25807 6 136220 30 21 40715 50620 0 115572 45 28 65897 61467 5 139075 66 23 76542 65292 1 148950 39 25 37477 55516 0 124626 27 15 53216 42006 0 49176 22 13 40911 26273 0 215480 45 36 57021 90248 0 182328 95 24 73116 61476 0 19349 13 1 3895 9604 0 183873 26 24 46609 45108 3 146020 40 31 29351 47232 0 51201 13 4 2325 3439 0 58280 41 20 31747 30553 0 115944 51 23 32665 24751 0 101515 27 23 19249 34458 1 72904 30 12 15292 24649 0 27676 2 16 5842 2342 0 131173 79 29 33994 52739 0 89920 12 10 13018 6245 0 0 0 0 0 0 0 85610 46 25 98177 35381 0 106742 25 21 37941 19595 0 126825 49 23 31032 50848 0 109807 52 21 32683 39443 0 71894 36 21 34545 27023 0 3616 0 0 0 0 0 0 0 0 0 0 0 154806 35 23 27525 61022 0 136333 68 29 66856 63528 0 147766 26 28 28549 34835 1 113245 36 23 38610 37172 0 43410 7 1 2781 13 0 152455 67 25 41211 62548 1 88874 30 17 22698 31334 0 111924 55 29 41194 20839 8 60373 3 12 32689 5084 3 19764 10 2 5752 9927 1 125760 46 20 26757 53229 2 108685 23 25 22527 29877 0 141868 48 29 44810 37310 0 11796 1 2 0 0 0 10674 0 0 0 0 0 131263 33 18 100674 50067 0 6836 0 1 0 0 0 153278 48 21 57786 47708 5 5118 5 0 0 0 0 40248 8 4 5444 6012 1 0 0 0 0 0 0 100798 25 25 28470 27749 0 84315 21 26 61849 47555 0 7131 0 0 0 0 1 8812 0 4 2179 1336 0 63952 15 17 8019 11017 1 120111 47 21 39644 55184 0 94127 17 22 23494 43485 1
Names of X columns:
time blogs reviews CWcharacters CWseconds shared
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