removed file not needed

exercise_3/kmeans.py

-import numpy as np
-
-def initialize_centroids(data, k):
-    """
-    Randomly initialize k centroids from the dataset.
-    """
-    indices = np.random.choice(data.shape[0], k, replace=False)
-    return data[indices]
-
-def compute_distances(data, centroids):
-    """
-    Compute the distance from each point to each centroid.
-    """
-    distances = np.zeros((data.shape[0], len(centroids)))
-    for i, centroid in enumerate(centroids):
-        distances[:, i] = np.linalg.norm(data - centroid, axis=1)
-    return distances
-
-def assign_clusters(distances):
-    """
-    Assign each data point to the nearest centroid.
-    """
-    return np.argmin(distances, axis=1)
-
-def update_centroids(data, clusters, k):
-    """
-    Update the centroids as the mean of assigned points.
-    """
-    new_centroids = np.zeros((k, data.shape[1]))
-    for i in range(k):
-        new_centroids[i] = data[clusters == i].mean(axis=0)
-    return new_centroids
-
-def k_means(data, k, max_iterations=100, tolerance=1e-4):
-    """
-    Perform k-means clustering on the dataset.
-    """
-    centroids = initialize_centroids(data, k)
-    for _ in range(max_iterations):
-        distances = compute_distances(data, centroids)
-        clusters = assign_clusters(distances)
-        new_centroids = update_centroids(data, clusters, k)
-        
-        # Check for convergence
-        if np.linalg.norm(new_centroids - centroids) < tolerance:
-            break
-        
-        centroids = new_centroids
-    return clusters, centroids
-
-# Example usage
-data = np.random.rand(100, 2)  # Generate some random 2D data points
-k = 3  # Number of clusters
-clusters, centroids = k_means(data, k)
-print("Cluster assignments:", clusters)
-print("Centroids:", centroids)