import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.preprocessing import StandardScaler

# Generate synthetic 2D data
np.random.seed(42)
X, _ = make_blobs(n_samples=150, centers=3, n_features=2, cluster_std=2.5)

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

# Plot the initial data distribution
plt.figure(figsize=(8, 6))
plt.scatter(X[:, 0], X[:, 1], c='gray', edgecolor='k', s=50)
plt.title('Initial Data Distribution')
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.grid(True)
plt.show()

def kmeans_clustering(X, n_clusters, max_iters=10):
    # Randomly initialize centroids
    np.random.seed(42)
    centroids = X[np.random.choice(X.shape[0], n_clusters, replace=False)]
    
    for i in range(max_iters):
        # Assign clusters based on closest centroid
        distances = np.linalg.norm(X[:, np.newaxis] - centroids, axis=2)
        labels = np.argmin(distances, axis=1)
        # Plot current state
        plt.figure(figsize=(8, 6))
        for j in range(n_clusters):
            plt.scatter(X[labels == j][:, 0], X[labels == j][:, 1], label=f'Cluster {j+1}')
            plt.scatter(centroids[j, 0], centroids[j, 1], s=200, c='black', marker='X')
            # Add centroid coordinates as text
            plt.text(centroids[j, 0], centroids[j, 1], f'({centroids[j, 0]:.2f}, {centroids[j, 1]:.2f})',
                     fontsize=10, color='red', ha='center', va='center')
        plt.title(f'Iteration {i+1}')
        plt.xlabel('Feature 1')
        plt.ylabel('Feature 2')
        plt.legend()
        plt.grid(True)
        plt.show()
        # Update centroids
        new_centroids = np.array([X[labels == j].mean(axis=0) for j in range(n_clusters)])
        # Check for convergence
        if np.all(centroids == new_centroids):
            break
        centroids = new_centroids
# Perform K-means clustering and visualize iterations
kmeans_clustering(X, n_clusters=3, max_iters=10)