updated newsletter case

Tutorial_Scripts/Case_NewsletterResponses/BIA_T06_CS_newsletter_responses.Rmd

 ---
-title:  'Tutorial 6: Newsletter Case'
+title:  'Tutorial 5-6: Newsletter Case'
 output: html_notebook
 editor_options: 
   chunk_output_type: inline
@@ -16,20 +16,16 @@ library(lubridate)
 
 
 ```{r read the files with basic R functions}
-nl_mailsSend <- read.csv2("../../data/newsletter/newsletterData_mailsSend.csv",
-           encoding = "UTF-8", # this is usually not needed
-           stringsAsFactors = F # R formats columns with text as factor, 
-                                # this is not meaningful in our case
-           ) 
-nl_clicks <- read.csv2("../../data/newsletter/newsletterData_clicks.csv",
-           encoding = "UTF-8", stringsAsFactors = F)
-nl_links <- read.csv2("../../data/newsletter/newsletterData_links.csv",
-           encoding = "UTF-8", stringsAsFactors = F)
-nl_opens <- read.csv2("../../data/newsletter/newsletterData_opens.csv",
-           encoding = "UTF-8", stringsAsFactors = F)
+# Exercise 1
+nl_mailsSend <- read.csv2("../../data/newsletter/newsletterData_mailsSend.csv", encoding = "UTF-8")
+       
+nl_clicks <- read.csv2("../../data/newsletter/newsletterData_clicks.csv", encoding = "UTF-8")
+nl_links <- read.csv2("../../data/newsletter/newsletterData_links.csv", encoding = "UTF-8")
+nl_opens <- read.csv2("../../data/newsletter/newsletterData_opens.csv", encoding = "UTF-8")
 ```
 
 ```{r inspect the data}
+# Exercise 2
 summary(nl_mailsSend)
 str(nl_mailsSend)
 
@@ -45,14 +41,15 @@ str(nl_opens)
 
 ```{r format the data correctly (exercise 3-5)}
 # format the nl_mailsSend dataset
-
 nl_mailsSend$VID <- as.factor(nl_mailsSend$VID)
 nl_mailsSend$EmailID <- as.factor(nl_mailsSend$EmailID)
-nl_mailsSend$NumTipIDs <- as.factor(nl_mailsSend$NumTipIDs)
 nl_mailsSend$NewsletterTitle <- as.factor(nl_mailsSend$NewsletterTitle)
-nl_mailsSend$EnergyReport.EfficiencyLevel <- as.factor(nl_mailsSend$EnergyReport.EfficiencyLevel)
+nl_mailsSend$EnergyReport.Quarter <- as.factor(nl_mailsSend$EnergyReport.Quarter)
+
+table(nl_mailsSend$EnergyReport.EfficiencyLevel) # Efficiency levels have a natural ordering
+nl_mailsSend$EnergyReport.EfficiencyLevel <- factor(nl_mailsSend$EnergyReport.EfficiencyLevel, levels = c("A", "B", "C", "D", "E", "F", "G"), ordered = TRUE)
 nl_mailsSend$EnergyReport.HouseholdType <- as.factor(nl_mailsSend$EnergyReport.HouseholdType)
-nl_mailsSend$EnergyReport.HouseholdMembers <- as.factor(nl_mailsSend$EnergyReport.HouseholdMembers)
+nl_mailsSend$EnergyReport.HouseholdMembers <- factor(nl_mailsSend$EnergyReport.HouseholdMembers, levels = c("3-5", "6+"), ordered = T) # Classes of household members have a natural ordering
 
 # format the nl_clicks dataset
 
@@ -187,6 +184,8 @@ boxplot(nl_mailsSend$EnergyReport.Cons[nl_mailsSend$EnergyReport.Cons<3000], hor
 # exercise 27
 hist(nl_mailsSend$EnergyReport.Cons, breaks = 30)
 ```
+
+
 ```{r histogram with additional lines - exercise 28 + 29}
 # exercise 27-29
 hist(nl_mailsSend$EnergyReport.Cons, 
@@ -197,25 +196,37 @@ lines(density(nl_mailsSend$EnergyReport.Cons), col=2)
 abline(v=quantile(nl_mailsSend$EnergyReport.Cons, probs = c(0.25,0.5,0.75)), col=3)
 ```
 
+```{r bar and pie charts}
+# exercise 31
+x <- table(as_date(nl_mailsSend$SendDate))
+barplot(x) # barplot needs a frequency table
+
 
-```{r bar and pie charts with colors (exercise 30 extended)}
+# exercise 32
 library(RColorBrewer)
-mycolors <- brewer.pal(4, "Dark2")
+mycolors <- brewer.pal(length(x), "Dark2")
 
-barplot(table(as_date(nl_mailsSend$SendDate)), # barplot needs a frequency table
+barplot(x, # barplot needs a frequency table
         main="Number of emails sent per newsletter", # the plot title
         horiz = T, # horizontal barplot
         las=1, # aligns the axis labels to the reading direction
         cex.names = 0.6, # adjust size of the labels
-        col=mycolors[c(1,1,1,1,2,3,4)]) # set the colors
+        col=mycolors) # set the colors
+
+# exercise 33
+x <- round(prop.table(table(nl_mailsSend$EnergyReport.EfficiencyLevel))*100,2)
+pie(x = x)
+
+# exercise 34
+pie(x = x, labels = paste0(names(x), "(", x, "%)"), col = brewer.pal(n=length(x), name="Set1"))
+legend("topright", names(x), cex = 0.8, fill = brewer.pal(n=length(x), name="Set1"))
+
 
-pie(table(as_date(nl_mailsSend$SendDate)),
-    col=mycolors[c(1,1,1,1,2,3,4)], 
-    main="Number of emails sent per newsletter")
 ```
 
 
-```{r plot showing email opens and clicks over time}
+
+```{r Homework task: Plot showing email opens and clicks over time}
 
 # identify all opens per day
 actions_open <- nl_opens %>%