ml8

//pip install scikit-learn-extra


import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.preprocessing import StandardScaler
from sklearn_extra.cluster import KMedoids
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
from sklearn.metrics import silhouette_score

# Load the Iris dataset
iris = load_iris()
X = iris.data
y = iris.target

# Standardize the data
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Apply K-Medoids clustering
kmedoids = KMedoids(n_clusters=3, random_state=42, method='pam')
kmedoids.fit(X_scaled)

# Get the predicted clusters
y_kmedoids = kmedoids.predict(X_scaled)

# Evaluate clustering using Silhouette Score
silhouette_avg = silhouette_score(X_scaled, y_kmedoids)
print(f"Silhouette Score: {silhouette_avg:.2f}")

# Visualize the clusters using PCA
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)

plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y_kmedoids, cmap='viridis', s=50)
plt.title('K-Medoids Clustering on Iris Dataset (PCA-reduced data)')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.show()