Clustering Algorithms

 

Expt No: 9                                           Clustering Algorithms

Date:

 

Aim: To write a program to demonstrate clustering algorithms

 

Program

import pandas as pd

from sklearn.cluster import KMeans

from sklearn.metrics import silhouette_score

from sklearn.mixture import GaussianMixture

import matplotlib.pyplot as plt

 

# Load the dataset and drop unnecessary fields

data = pd.read_csv('Mall_Customers.csv')

data.drop(['CustomerID', 'Genre', 'Spending Score'], axis=1, inplace=True)

 

# Use Silhouette Score method to find the optimal number of clusters

silhouette_scores = []

for n_clusters in range(2, 11):  # Trying cluster numbers from 2 to 10

    kmeans = KMeans(n_clusters=n_clusters, random_state=42)

    cluster_labels = kmeans.fit_predict(data)

    silhouette_avg = silhouette_score(data, cluster_labels)

    silhouette_scores.append(silhouette_avg)

 

# Display the optimal number of clusters

optimal_clusters = silhouette_scores.index(max(silhouette_scores)) + 2  # +2 because range starts from 2

print("Optimal number of clusters:", optimal_clusters)

 

# Plot Silhouette Scores

plt.plot(range(2, 11), silhouette_scores, marker='o')

plt.xlabel('Number of Clusters')

plt.ylabel('Silhouette Score')

plt.title('Silhouette Score vs Number of Clusters')

plt.show()

 

 

# Display KMeans clusters

optimal_kmeans = KMeans(n_clusters=optimal_clusters, random_state=42)

optimal_cluster_labels = optimal_kmeans.fit_predict(data)

 

# Plotting the clusters along with centroids

plt.scatter(data.iloc[:, 0], data.iloc[:, 1], c=optimal_cluster_labels, cmap='viridis')

plt.scatter(optimal_kmeans.cluster_centers_[:, 0], optimal_kmeans.cluster_centers_[:, 1], s=150, c='red', marker='o')

plt.xlabel('Annual Income')

plt.ylabel('Age')

plt.title('KMeans Clustering with {} clusters'.format(optimal_clusters))

plt.show()

 

 

# Fit Gaussian Mixture Model

gmm = GaussianMixture(n_components=optimal_clusters, random_state=42)

gmm.fit(data)

gmm_cluster_labels = gmm.predict(data)

 

# Display GMM clusters

plt.scatter(data.iloc[:, 0], data.iloc[:, 1], c=gmm_cluster_labels, cmap='viridis')

plt.scatter(gmm.means_[:, 0], gmm.means_[:, 1], s=150, c='red', marker='o')

plt.xlabel('Annual Income')

plt.ylabel('Age')

plt.title('Gaussian Mixture Model Clustering with {} clusters'.format(optimal_clusters))

plt.show()

 

 

 

Result: Thus the program to demonstrate clustering algorithms was written and executed.

Sample Output

Optimal number of clusters: 4