updated Tutorial 9

Tutorial_Scripts/Case_EnergyRetailAnalytics/BIA_T09_Classification _exercise.Rmd

@@ -38,10 +38,53 @@ household <- 8
 # Define and implement 10 features from SMD (e.g. mean consumption, mean 
 # consumption in the evening)
 
-
+calcFeatures.smd <- function(SMD){
+  #SMD: the load trace for one week (vector with 672 elements)
+  
+  #create a matrix with 7 columns for each day
+  dm15=matrix(as.numeric(SMD),ncol=7)
+
+  # 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)
+  
+  #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$c_evening <-   mean(dm15[evening,   1:7], na.rm = T)
+  
+  #calculate statistical features
+  D$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$s_wd_min <- min(dm15[weekday], na.rm = T)
+  
+  #calculate relations
+  D$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)
+  
+  return(D)
+}
 
 #calculate the features for one household
+calcFeatures.smd(smd[2,])
 
+features <- calcFeatures.smd(smd[1,])
+for(i in 2:nrow(smd)){
+  features <- rbind(features, calcFeatures.smd(smd[i,]))
+}
 ```
 
 

Tutorial_Scripts/Case_EnergyRetailAnalytics/BIA_T09_Classification.Rmd

@@ -63,16 +63,16 @@ plot(ts(smd[household,], frequency = 4*24),
      main="Weekly load curve")
 
 #plot the monday
-plot(ts(smd[household,1:(24*4)], frequency = 4*24), 
-     main="Load curve of monday")
+plot(ts(smd[household,1:(24*4)], frequency = 4), 
+     main="Load curves for each day")
 
 #add the other days to the same plot
 cols <- heat.colors(8)
 for(i in 1:6){
-  lines(ts(smd[household,(i*24*4):((i+1)*24*4)], frequency = 4*24), 
+  lines(ts(smd[household,(i*24*4):((i+1)*24*4)], frequency = 4), 
         col=cols[i])  
 }
-legend("topleft",legend = c("Mon", "Tue", "Wed", "Thu", "Fri","Sat","Sun"), 
+legend("topleft",legend = c("Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"), 
        col = c("black",cols), lty = 1)
 ```
 

Tutorial_Scripts/Case_NewsletterResponses/BIA_T06_CS_newsletter_responses.Rmd

@@ -182,7 +182,7 @@ plot(nl_mailsSend$EnergyReport.Cons, log="y")
 plot(nl_mailsSend$EnergyReport.Cons, nl_mailsSend$EnergyReport.PrevCons, log="xy")
 
 # exercise 26
-boxplot(nl_mailsSend$EnergyReport.Cons)
+boxplot(nl_mailsSend$EnergyReport.Cons[nl_mailsSend$EnergyReport.Cons<3000], horizontal = T)
 
 # exercise 27
 hist(nl_mailsSend$EnergyReport.Cons, breaks = 30)