Lab 4A: Clustering (Easy)

1. Explore the Data

1. Load Iris data

data(iris)

2. Load color brewer library

library(RColorBrewer)

3. Create a color palette

palette <- brewer.pal(3, "Set2")

4. Create a scatterplot matrix colored by species

plot(
  x = iris[1:4], 
  col = palette[as.numeric(iris$Species)],
  pch = 19)

5. View scatterplot of petal length vs width

plot(
  x = iris$Petal.Length, 
  y = iris$Petal.Width, 
  col = palette[as.numeric(iris$Species)],
  pch = 19)

2. Create Clusters with K-Means

1. Set seed to make randomness reproducable

set.seed(42)

2. Create K-means clusters

clusters <- kmeans(
  x = iris[, 1:4], 
  centers = 3, 
  nstart = 10)

3. Plot each cluster as a shape

plot(
  x = iris$Petal.Length, 
  y = iris$Petal.Width, 
  col = palette[as.numeric(iris$Species)], 
  pch = clusters$cluster)

4. Plot centroid of clusters

plot(
  x = iris$Petal.Length, 
  y = iris$Petal.Width, 
  col = palette[as.numeric(iris$Species)], 
  pch = clusters$cluster)
  
points(
  x = clusters$centers[, "Petal.Length"], 
  y = clusters$centers[, "Petal.Width"],
  pch = 4, 
  lwd = 4, 
  col = "blue")

3. Create Hierachical Clusters

1. Create hierachical clusters

hclusters <- hclust(dist(iris[ ,1:4]))

2. Plot dendrogram of clusters

plot(
  x = hclusters, 
  labels = as.numeric(iris$Species))

3. Cut tree into three clusters

cuts <- cut(
  x = as.dendrogram(hclusters), 
  h = 4)

4. Get clusters as vector

cuts2 <- cutree(
  tree = hclusters, 
  k = 3)

5. Plot clusters and color by species

plot(
  x = iris$Petal.Length, 
  y = iris$Petal.Width, 
  col = palette[as.numeric(iris$Species)], 
  pch = cuts2)