USML1

import numpy as np
import matplotlib.pyplot as plt

# Generate sample data
from sklearn.datasets import make_blobs
X, y_true = make_blobs(n_samples=300, centers=4, cluster_std=0.60, random_state=0)

# Number of clusters
k = 4

# Initialize centroids randomly from the data points
def initialize_centroids(X, k):
    indices = np.random.choice(X.shape[0], k, replace=False)
    return X[indices]

# Assign each point to the nearest centroid
def assign_clusters(X, centroids):
    distances = np.linalg.norm(X[:, np.newaxis] - centroids, axis=2)
    return np.argmin(distances, axis=1)

# Recalculate centroids
def update_centroids(X, labels, k):
    new_centroids = np.array([X[labels == i].mean(axis=0) for i in range(k)])
    return new_centroids

# K-means main function
def k_means(X, k, iterations=100):
    centroids = initialize_centroids(X, k)

    for _ in range(iterations):
        labels = assign_clusters(X, centroids)
        new_centroids = update_centroids(X, labels, k)

        # Stop if centroids do not change
        if np.all(centroids == new_centroids):
            break
        centroids = new_centroids

    return centroids, labels

# Run K-means
centroids, labels = k_means(X, k)

# Visualize results
plt.figure(figsize=(8, 6))
plt.scatter(X[:, 0], X[:, 1], c=labels, s=30, cmap='viridis')
plt.scatter(centroids[:, 0], centroids[:, 1], c='red', s=200, alpha=0.6, marker='X')
plt.title("K-Means Clustering")
plt.show()