Changes made during L07

R/BIA_L07_Clustering_SMD.Rmd

@@ -67,23 +67,29 @@ plotcl(Formatted_Readings, Cluster2$cluster, ylab="Consumption (kWh)", main="Max
 #Transform the values to a more normally distributed form and run the k-means agaein
 Datas <- sqrt(Formatted_Readings)
 Datasn <- Datas/rowMeans(Datas)
-set.seed(4)
-Cluster3 <- kmeans(Datasn, centers=3)
+Datasn <- Datasn[-297] #remove outlier
+set.seed(7)
+Cluster3 <- kmeans(Datasn,
+                   centers=3)
 plotcl(Formatted_Readings, Cluster3$cluster, ylab="Consumption (kWh)", main="Sqrt and Max-normaized consumption", lim=c(0,1.2))
 
+#some details about the model 
+
+table(Cluster3$cluster) # size of the clusters 1
+Cluster3$size           # size of the clusters 2
+
+Cluster3$withinss       # variance in the clusters
+Cluster3$betweenss      # variance between the clusters
 ```
 
 ```{r obtain the optimal number of clusters}
-set.seed(2)
 Clusters <- list()
-Clusters[[1]] <- kmeans(Datasn, centers=2)
-Clusters[[2]] <- kmeans(Datasn, centers=3)
-Clusters[[3]] <- kmeans(Datasn, centers=4)
-Clusters[[4]] <- kmeans(Datasn, centers=5)
-Clusters[[5]] <- kmeans(Datasn, centers=6)
-Clusters[[6]] <- kmeans(Datasn, centers=7)
-Clusters[[7]] <- kmeans(Datasn, centers=8)
-Clusters[[8]] <- kmeans(Datasn, centers=9)
+for(i in 1:8){
+  set.seed(7)
+  Clusters[[i]] <- kmeans(Datasn, centers=i+1)
+}
+
+Clusters[[2]]$size
 
 #the total sum of squares
 tot.withinss <- sapply(Clusters, function(v){return(v$tot.withinss)})
@@ -112,7 +118,7 @@ C <- 1-cor(t(Formatted_Readings))
 Dendrogram <- agnes(C,diss=T,method="complete")
 plot(Dendrogram, which.plot=2) #plot the dendrogram
 
-Cluster4 <- cutree(Dendrogram, k=3)
+Cluster4 <- cutree(Dendrogram, k=4)
 plotcl(Formatted_Readings, Cluster4, main="Hierarchical clustering results", ylab="Consumption (kWh)", lim=c(0,1.3))
 
 ```