def kmeans(data, k, c=None):
    if c is not None:
        centroids = c
    else:
        centroids = []
        centroids = randomize_centroids(data, centroids, k)

    old_centroids = [[] for i in range(k)]

    iterations = 0
    while not (has_converged(centroids, old_centroids, iterations)):
        iterations += 1

        clusters = [[] for i in range(k)]

        # assign data points to clusters
        clusters = euclidean_dist(data, centroids, clusters)

        # recalculate centroids
        index = 0
        for cluster in clusters:
            old_centroids[index] = centroids[index]
            centroids[index] = np.mean(cluster, axis=0).tolist()
            index += 1


    print("The total number of data instances is: " + str(len(data)))