changed folds to 10

added t.test example

Tutorial_Scripts/Case_EnergyRetailAnalytics/BIA_T09_Classification.Rmd

@@ -62,6 +62,7 @@ household <- 8
 plot(ts(smd[household,], frequency = 4*24), 
      main="Weekly load curve")
 
+
 #plot the monday
 plot(ts(smd[household,1:(24*4)], frequency = 4), 
      main="Load curves for each day")
@@ -90,7 +91,7 @@ calcFeatures.smd <- function(SMD){
   # define some times
   weekday <-   1:(5*4*24)
   weekend <-   (5*4*24+1):672
-  night <-       ( 1*4+1):( 6*4)
+  night <-       ( 1*4+1):(6*4)
   morning <-     ( 6*4+1):(10*4)
   noon <-        (10*4+1):(14*4)
   afternoon <-   (14*4+1):(18*4)

Tutorial_Scripts/Case_EnergyRetailAnalytics/BIA_T10_Classification2.Rmd

@@ -137,12 +137,15 @@ plot(performance(pred, "tpr", "fpr"))
 
 ```{r Classification with an advanced evaluation technique: cross-validation}
 set.seed(1506)
-all_data$crossfolds <- sample(1:5, nrow(all_data), replace = TRUE)
+
+folds <- 10
+
+all_data$crossfolds <- sample(1:folds, nrow(all_data), replace = TRUE)
 
 # list for the interim results
 results <- list()
 
-for(foldIndex in 1:5){
+for(foldIndex in 1:folds){
   # creating data for the 
   testdata <- na.omit(all_data[all_data$crossfolds==foldIndex, c("pNumResidents2", selected.features)])
   traindata <- na.omit(all_data[all_data$crossfolds!=foldIndex, c("pNumResidents2", selected.features)])
@@ -183,5 +186,10 @@ auc_mean
 
 #the ROC curve shows true-positive-rate vs. false-positive rate
 plot(performance(pred, "tpr", "fpr"))
+
+
+# Test if the AUCs are expexted to be greater than random (AUC=0.5)
+t.test(auc_array, mu = 0.5, alternative = "greater")
+
 ```
 

Tutorial_Scripts/Case_EnergyRetailAnalytics/BIA_T10_Classification2_exercise.Rmd

@@ -130,12 +130,15 @@ propabilities <- attributes(clres)$probabilities
 
 ```{r Classification with an advanced evaluation technique: cross-validation}
 set.seed(1506)
-all_data$crossfolds <- sample(1:5, nrow(all_data), replace = TRUE)
+
+folds <- 10
+
+all_data$crossfolds <- sample(1:folds, nrow(all_data), replace = TRUE)
 
 # list for the interim results
 results <- list()
 
-for(foldIndex in 1:5){
+for(foldIndex in 1:folds){
   # creating data for the 
   testdata <- na.omit(all_data[all_data$crossfolds==foldIndex, c("pNumResidents2", selected.features)])
   traindata <- na.omit(all_data[all_data$crossfolds!=foldIndex, c("pNumResidents2", selected.features)])