import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn import datasets
from sklearn.metrics import silhouette_score
import numpy as np
data = datasets.load_iris()
X = data.data
k_values = range(2, 11)
wcss = []
for k in k_values:
kmeans = KMeans(n_clusters=k, random_state=42)
kmeans.fit(X)
wcss.append(kmeans.inertia_)
plt.figure(figsize=(10, 6))
plt.plot(k_values, wcss, marker="o", linestyle="-", color="b")
plt.xlabel("Number of Clusters (K)")
plt.ylabel("Within-Cluster Sum of Squares (WCSS)")
plt.title("Elbow Method for Optimal K")
plt.xticks(np.arange(min(k_values), max(k_values) + 1, 1.0))
plt.grid(True)
plt.show()
optimal_k = 3
kmeans = KMeans(n_clusters=optimal_k, random_state=42)
kmeans.fit(X)
labels = kmeans.labels_
plt.figure(figsize=(10, 6))
for i in range(optimal_k):
cluster_data = X[labels == i]
plt.scatter(
cluster_data[:, 0], cluster_data[:, 1], label="Cluster {}".format(i + 1)
)
plt.scatter(
kmeans.cluster_centers_[:, 0],
kmeans.cluster_centers_[:, 1],
marker="*",
s=300,
c="black",
label="Centroids",
)
plt.xlabel("Feature 1")
plt.ylabel("Feature 2")
plt.title("K-Means Clustering (Optimal K = {})".format(optimal_k))
plt.legend()
plt.show()
for i in range(optimal_k):
cluster_data = X[labels == i]
centroid = kmeans.cluster_centers_[i]
num_data_points = len(cluster_data)
print(
"Cluster {} - Centroid: {}, Number of Data Points: {}".format(
i + 1, centroid, num_data_points
)
)
