added some improvements

Tutorial_Scripts/Case_EnergyRetailAnalytics/BIA_T09_Classification _exercise.Rmd

@@ -9,7 +9,7 @@ This file is part of the lecture Business Intelligence & Analytics (EESYS-BIA-M)
 
 
 ```{r Load libraries}
-library(FSelector) #for feature selection
+library(FSelector) #for feature selection / you need Java installed to load this package
 library(party) #for classification algorithm decision trees
 library(class) #for classification algorithm kNN
 library(e1071) #for classification algorithm SVM
@@ -46,34 +46,34 @@ calcFeatures.smd <- function(SMD){
 
   # define some times
   weekday <-   1:(5*4*24)
-  weekend <-   (5*4*24+1):672
-  night <-       ( 1*4+1):( 6*4)
-  morning <-     ( 6*4+1):(10*4)
-  noon <-        (10*4+1):(14*4)
-  afternoon <-   (14*4+1):(18*4)
-  evening <-     (18*4+1):(22*4)
+  weekend <-   
+  night <-     
+  morning <-   
+  noon <-      
+  afternoon <- 
+  evening <-   
   
   #data.frame for the results
   D=data.frame(c_week=mean(dm15, na.rm = T))
   
   #calculate consumption features
   D$c_night <-     mean(dm15[night,     1:7], na.rm = T)
-  D$c_morning <-   mean(dm15[morning,   1:7], na.rm = T)
-  D$c_noon <-      mean(dm15[noon,      1:7], na.rm = T)
-  D$c_afternoon <- mean(dm15[afternoon, 1:7], na.rm = T)
-  D$c_evening <-   mean(dm15[evening,   1:7], na.rm = T)
+  D$c_morning <-   mean()
+  D$c_noon <-      mean()
+  D$c_afternoon <- mean()
+  D$c_evening <-   mean()
   
   #calculate statistical features
-  D$s_we_max <- max(dm15[weekend], na.rm = T)
-  D$s_we_min <- min(dm15[weekend], na.rm = T)
-  D$s_wd_max <- max(dm15[weekday], na.rm = T)
-  D$s_wd_min <- min(dm15[weekday], na.rm = T)
+  D$s_we_max <- max()
+  D$s_we_min <- min()
+  D$s_wd_max <- max()
+  D$s_wd_min <- min()
   
   #calculate relations
   D$r_min_wd_we <- D$s_wd_min / D$s_we_min #division by 0 leads to NaN!
   D$r_min_wd_we <- ifelse(is.na(D$r_min_wd_we), 0, D$r_min_wd_we)
-  D$r_max_wd_we <- D$s_wd_max / D$s_we_max
-  D$r_max_wd_we <- ifelse(is.na(D$r_max_wd_we), 0, D$r_max_wd_we)
+  D$r_max_wd_we <- 
+  D$r_max_wd_we <- 
   
   return(D)
 }
@@ -109,7 +109,7 @@ for(i in 2:nrow(smd)){
 
 ```{r Classification Basic evaluation approach}
 
-## decisoon tree
+## decison tree
 
 #train the model
 
@@ -127,7 +127,7 @@ for(i in 2:nrow(smd)){
 
 ## kNN
 
-# predict test cases from training data (lazy learning algoritm has no explicit training step!)
+# predict test cases from training data (lazy learning algorithm has no explicit training step!)
 
 #create confusion matrix and calculate accuracy
 

Tutorial_Scripts/Case_EnergyRetailAnalytics/BIA_T09_Classification.Rmd

@@ -9,7 +9,7 @@ This file is part of the lecture Business Intelligence & Analytics (EESYS-BIA-M)
 
 
 ```{r Load libraries}
-library(FSelector) #for feature selection
+library(FSelector) #for feature selection / you need Java installed to load this package
 library(party) #for classification algorithm decision trees
 library(class) #for classification algorithm kNN
 library(e1071) #for classification algorithm SVM
@@ -144,7 +144,7 @@ alldata <- cbind(customers, features)
 #simple call of the feature selection function
 cfs(pNumResidents ~ ., alldata)
 
-#Problem: other dependant variables are selected -> only use relevant variables in feature setection!
+#Problem: other dependent variables are selected -> only use relevant variables in feature selection!
 
 #create a vector containing all feature names
 all.features <- setdiff(colnames(alldata), c("VID", "residents.numAdult",