Implementation of K-Means Clustering - Python

 import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

from sklearn.datasets import make_blobs

import numpy as np

# 1. Generate sample data

# X contains the data points, y_true contains the actual labels (for verification/comparison)

X, y_true = make_blobs(n_samples=300, centers=3, cluster_std=0.60, random_state=0)

# Plot the initial data points

plt.scatter(X[:, 0], X[:, 1], s=50)

plt.title('Original Data Points')

plt.show()

# 2. Initialize the KMeans model

# n_clusters defines 'k', the number of clusters to form

kmeans = KMeans(n_clusters=3, init='k-means++', random_state=0, n_init=10)

# 3. Fit the model to the data and predict the cluster labels

y_kmeans = kmeans.fit_predict(X)

# 4. Get the final cluster centers (centroids)

centers = kmeans.cluster_centers_

# 5. Visualize the results

plt.figure(figsize=(8, 6))

# Plot data points colored by their assigned cluster

plt.scatter(X[:, 0], X[:, 1], c=y_kmeans, s=50, cmap='viridis')

# Plot the centroids as black markers

plt.scatter(centers[:, 0], centers[:, 1], c='black', s=200, alpha=0.7, marker='*')

plt.title('K-Means Clustering Results')

plt.xlabel('Feature 1')

plt.ylabel('Feature 2')

plt.show()