ds: 2r, 4r, 5r, 8r

ds/25-1/r/4.R

@@ -95,7 +95,44 @@ plot_kmeans(data, k, log=FALSE)
 plot_kmeans(data, klog, log=TRUE)
 
 library(ggdendro)
-distance = dist(df, method = "euclidean")
-clust = hclust(distance, method = "complete")
+
+
+plot_hclust = function(df, linkage, k) {
+  data = df[,c("income", "elec")]
+  distance = dist(data, method = "euclidean")
+  clust = hclust(distance, method = linkage)
+  data$cluster = as.factor(cutree(clust, k = k))
+  data$state = rownames(df)
+  print(cutree(clust, k = k))
+  print(data)
+  plt = ggplot() +
+    geom_point(
+      data = data,
+      aes(
+        x = income,
+        y = elec, 
+        color = cluster
+      )
+    ) +
+    geom_text(
+      data = data,
+      vjust = 1.5,
+      size = 2,
+      aes(
+        x = income,
+        y = elec,
+        label = state
+      )
+    )
+    theme_minimal()
+    print(plt)
+}
+
+plot_hclust(data, "average", 5)
+
+distance = dist(data, method = "euclidean")
+
+clust = hclust(distance, method = "single")
 plot(ggdendrogram(clust))
-cutree(clust, k = k)
+
+cutree(clust, k = 3)