diff --git a/.Rhistory b/.Rhistory
new file mode 100644
index 0000000..e69de29
diff --git a/wrapper.xgb.cv.logistic.r b/wrapper.xgb.cv.logistic.r
index 80abed4..a1f3f6d 100644
--- a/wrapper.xgb.cv.logistic.r
+++ b/wrapper.xgb.cv.logistic.r
@@ -42,16 +42,30 @@ PredClass = ifelse(cv$pred >0.5,1,0)
 ###Test accuracy of predictions
 Confusion = confusionMatrix(as.factor(PredClass),as.factor(CVtrain_y))
 
-###Calculate ROC
+###Calculate Out of Bag ROC
 Pred = cv$pred[order(CVtrain_y)]
 Truth = CVtrain_y[order(CVtrain_y)]
-ROC = roc_auc_vec(
+CVROC = roc_auc_vec(
   estimate = Pred,
   truth = as.factor(Truth),event_level="second")
 
-
+###Calculate ROC for mean training preds across fold models
+Preds = vector(length = 0)
+Truth = vector(length = 0)
+for(fold in 1:Nfolds)
+ {
+ Model = xgb.Booster.complete(cv$models[[fold]])
+ Preds = c(Preds,predict(Model, newdata = CVtrain_x[-(cv$folds[[fold]]),]))
+ Truth = c(Truth,CVtrain_y[-(cv$folds[[fold]])])
+ }
+Preds = Preds[order(Truth)]
+Truth = Truth[order(Truth)]
+
+TrainingROC = roc_auc_vec(
+  estimate = Preds,
+  truth = as.factor(Truth),event_level="second")
 ###Print box plots of predicted probabilities against observed occurrences for each class 
-xgbm.cv.fit.boxplot.logistic(cv$pred,Data[, colnames(Data) == Response],ROC,path)
+xgbm.cv.fit.boxplot.logistic(cv$pred,Data[, colnames(Data) == Response],ROC = c(TrainingROC,CVROC),path)
 
 ####Use custom function to generate predictor importance bar plots
 Filename = paste0(path,"PredictorImportance.png")
@@ -80,8 +94,10 @@ if(DoInteraction == TRUE)
 OutList = list()
 Key = "Model"
 OutList[[Key]] = cv
-Key = "ROC"
-OutList[[Key]] = ROC
+Key = "OOBROC"
+OutList[[Key]] = CVROC
+Key = "TrainingROC"
+OutList[[Key]] = TrainingROC
 Key = "ConfusionMatrix"
 OutList[[Key]] = Confusion
 Key = "Predictor importance"
diff --git a/xgb.cv.fit.boxplot.r b/xgb.cv.fit.boxplot.r
index fe514d5..080f9db 100644
--- a/xgb.cv.fit.boxplot.r
+++ b/xgb.cv.fit.boxplot.r
@@ -1,8 +1,10 @@
 ##################################################
-###Simple boxplot of predicted probabilities for 
+###Simple boxplot of predicted probabilities for out of bag observations for 
 ###binary and multiclass responses
 ###Separate plots fitted for each level of multiclass responses
 ###Designed for easy inspection of xgb.cv predictions
+###Use out of bag predictions as better indication of ability to 
+###discriminate success or failure in new data
 ##################################################
 
 xgbm.cv.fit.boxplot.multi = function(pred, ###$pred from xgb.cv output
@@ -32,7 +34,7 @@ xgbm.cv.fit.boxplot.logistic = function(pred,###$pred from xgb.cv output
   Y = CVtrain_y
   Pred = pred[order(Y)]
   Y=Y[order(Y)]
-  Title = paste0("ROC = ",round(ROC,digits = 3))
+  Title = paste0("Training ROC = ",round(ROC[1],digits = 3),"; OOB ROC = ",round(ROC[2],digits = 3))
   Filename = paste0(path,"FitBoxplot.png")
   png(Filename, height = 1600,width = 1600)
   par(mar = c(10,12,12,2), cex.main = 4,cex.lab = 3.6,cex.axis = 3.4,mgp = c(7,2,0))
diff --git a/xgb.cv.fit.scatterplot.r b/xgb.cv.fit.scatterplot.r
index e63491a..1c60cfd 100644
--- a/xgb.cv.fit.scatterplot.r
+++ b/xgb.cv.fit.scatterplot.r
@@ -11,7 +11,8 @@ xgbm.cv.fit.scatterplot = function(pred,CVtrain_y,path)
   png(Filename, height = 1600,width = 1600)
   par(mar = c(10,12,12,2), cex.main = 4,cex.lab = 3.6,cex.axis = 3.4,mgp = c(7,3.5,0))
   plot(pred~CVtrain_y, main = Title,
-          xlab = paste0("Observed response"),ylab = paste0("Fitted response"))
+          xlab = paste0("Observed response"),ylab = paste0("Fitted response"), pch = NA)
+  points(CVtrain_y,pred, cex = 2, col = 1)
   abline(0,1,col = 2,lwd = 3)
   dev.off()
   }
diff --git a/xgb.cv.predict.r b/xgb.cv.predict.r
index 2295f0c..7d9b9cc 100644
--- a/xgb.cv.predict.r
+++ b/xgb.cv.predict.r
@@ -12,15 +12,13 @@ xgb.cv.predict = function(cv, ###xgb.cv model object
                           )
 {
 ###Predict function requires data as a matrix
-PredData = as.matrix(PredData[,colnames(PredData) %in% Predictors])
-Preds = vector(length = 0)
-Fold = vector(length = 0)
+PredX = as.matrix(PredData[,colnames(PredData) %in% Predictors])
+Preds = as.data.frame(matrix(nrow = nrow(PredX), ncol = 0))
 for(fold in 1:Nfolds)
  {
  Model = xgb.Booster.complete(cv$models[[fold]])
- Preds = c(Preds,predict(Model, newdata = PredData))
- Fold = c(Fold, rep(fold, times = nrow(PredData)))
+ Preds = cbind(Preds,predict(Model, newdata = PredX))
  }
-return(cbind(Fold,Preds))  
+return(Preds)  
 }