assign each point to the cluster with the closest centroid python

1def kmeans(X, k, maxiter, seed = None):
2    """
3    specify the number of clusters k and
4    the maximum iteration to run the algorithm
5    """
6    n_row, n_col = X.shape
7
8    # randomly choose k data points as initial centroids
9    if seed is not None:
10        np.random.seed(seed)
11    
12    rand_indices = np.random.choice(n_row, size = k)
13    centroids = X[rand_indices]
14
15    for itr in range(maxiter):
16        # compute distances between each data point and the set of centroids
17        # and assign each data point to the closest centroid
18        distances_to_centroids = pairwise_distances(X, centroids, metric = 'euclidean')
19        cluster_assignment = np.argmin(distances_to_centroids, axis = 1)
20
21        # select all data points that belong to cluster i and compute
22        # the mean of these data points (each feature individually)
23        # this will be our new cluster centroids
24        new_centroids = np.array([X[cluster_assignment == i].mean(axis = 0) for i in range(k)])
25        
26        # if the updated centroid is still the same,
27        # then the algorithm converged
28        if np.all(centroids == new_centroids):
29            break
30        
31        centroids = new_centroids
32    
33    return centroids, cluster_assignment
34