updated Tutorial 7 and 8

Tutorial_Scripts/Case_EnergyRetailAnalytics/BIA_T08_Clustering_exercise.Rmd

----
-title:  'Tutorial 8: Clustering'
-output: html_notebook
-editor_options: 
-  chunk_output_type: inline
----
-
-This file is part of the lecture Business Intelligence & Analytics (EESYS-BIA-M), Information Systems and Energy Efficient Systems, University of Bamberg.
-
-
-```{r Load libraries}
-library(dplyr)
-library(lubridate)
-library(psych)
-library(cluster)
-library(readr)
-```
-
-```{r Read and prepare data}
-# read data
-consumption <- read_csv(file="../../data/clustering/bam_energy_report_consumption.csv", na = "NULL")
-customer <- read_csv(file="../../data/clustering/bam_energy_report_customers.csv", na = "NULL")
-logins <- read_csv(file="../../data/clustering/bam_energy_report_logins.csv", na = "NULL")
-survey <- read_csv(file="../../data/clustering/bam_energy_report_survey.csv", na = "NULL")
-portal_points <- read_csv(file="../../data/clustering/bam_energy_report_portal_points.csv", na = "NULL")
-
-# convert data
-consumption$CustomerID <- as.character(consumption$CustomerID)
-customer$CustomerID <- as.character(customer$CustomerID)
-logins$CustomerID <- as.character(logins$CustomerID)
-survey$CustomerID <- as.character(survey$CustomerID)
-portal_points$CustomerID <- as.character(portal_points$CustomerID)
-
-# aggregate and calculate data
-survey$answers <- rowSums(!is.na(survey[,-1]))
-portal_points_agg <- portal_points %>% group_by(CustomerID) %>% summarize(points = sum(Points), different_actions = n_distinct(TaskCode))
-logins_agg <- logins %>% group_by(CustomerID) %>% summarize(n_logins = n())
-consumption$consumption_normalized <- consumption$consumption_2012 / consumption$billing_days_2012
-
-# Join data together
-data <- customer %>% left_join(consumption, by="CustomerID") %>%
-  left_join(logins_agg, by="CustomerID") %>% 
-  left_join(survey, by="CustomerID") %>% 
-  left_join(portal_points_agg, by="CustomerID")
-```
-
-```{r Clustering 1 - A first try with extreme values}
-data_clustering <- data %>% select(CustomerID, NumDevices, LivingAreaM2, HouseholdMembers, n_logins, points, different_actions) %>% na.omit()
-
-# simple clustering
-k <- 3
-set.seed(1)
-cluster1 <- kmeans(x = data_clustering[,-1], centers = k)
-
-data_clustering$kmeans_cluster1 <- cluster1$cluster
-
-table(data_clustering$kmeans_cluster1)
-# What we see:  One cluster with only one customer inside. why? Let's look at the values
-
-describeBy((data_clustering %>% select(-one_of(c("CustomerID")))), group="kmeans_cluster1", skew=FALSE)
-
-# extreme value at the number of logins
-
-plot(data_clustering$n_logins, data_clustering$kmeans_cluster1)
-```
-
-```{r Clustering 2 - A second try with untransformed data}
-
-```
-
-```{r Clustering 3 - A third try with transformed data}
-
-```
-
-```{r Determine the right number of clusters}
-
-```
-
-```{r Clustering 4 - Using an hierarchical clustering approach}
-
-```
-
-