We want to compare the performance of the MiniBatchKMeans and KMeans: the MiniBatchKMeans is faster, but gives slightly different results (see Mini Batch K-Means).
We will cluster a set of data, first with KMeans and then with MiniBatchKMeans, and plot the results. We will also plot the points that are labelled differently between the two algorithms.
1 2 3 4 5 6 7 8 9 10 | print(__doc__)import timeimport numpy as npimport matplotlib.pyplot as pltfrom sklearn.cluster import MiniBatchKMeans, KMeansfrom sklearn.metrics.pairwise import pairwise_distances_argminfrom sklearn.datasets.samples_generator import make_blobs |
Generate sample data
1 2 3 4 5 6 | np.random.seed(0)batch_size = 45centers = [[1, 1], [-1, -1], [1, -1]]n_clusters = len(centers)X, labels_true = make_blobs(n_samples=3000, centers=centers, cluster_std=0.7) |
Compute clustering with Means
1 2 3 4 | k_means = KMeans(init='k-means++', n_clusters=3, n_init=10)t0 = time.time()k_means.fit(X)t_batch = time.time() - t0 |
Compute clustering with MiniBatchKMeans
1 2 3 4 5 | mbk = MiniBatchKMeans(init='k-means++', n_clusters=3, batch_size=batch_size, n_init=10, max_no_improvement=10, verbose=0)t0 = time.time()mbk.fit(X)t_mini_batch = time.time() - t0 |
Plot result
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 | fig = plt.figure(figsize=(8, 3))fig.subplots_adjust(left=0.02, right=0.98, bottom=0.05, top=0.9)colors = ['#4EACC5', '#FF9C34', '#4E9A06']# We want to have the same colors for the same cluster from the# MiniBatchKMeans and the KMeans algorithm. Let's pair the cluster centers per# closest one.k_means_cluster_centers = np.sort(k_means.cluster_centers_, axis=0)mbk_means_cluster_centers = np.sort(mbk.cluster_centers_, axis=0)k_means_labels = pairwise_distances_argmin(X, k_means_cluster_centers)mbk_means_labels = pairwise_distances_argmin(X, mbk_means_cluster_centers)order = pairwise_distances_argmin(k_means_cluster_centers, mbk_means_cluster_centers)# KMeansax = fig.add_subplot(1, 3, 1)for k, col in zip(range(n_clusters), colors): my_members = k_means_labels == k cluster_center = k_means_cluster_centers[k] ax.plot(X[my_members, 0], X[my_members, 1], 'w', markerfacecolor=col, marker='.') ax.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col, markeredgecolor='k', markersize=6)ax.set_title('KMeans')ax.set_xticks(())ax.set_yticks(())plt.text(-3.5, 1.8, 'train time: %.2fs\ninertia: %f' % ( t_batch, k_means.inertia_))# MiniBatchKMeansax = fig.add_subplot(1, 3, 2)for k, col in zip(range(n_clusters), colors): my_members = mbk_means_labels == order[k] cluster_center = mbk_means_cluster_centers[order[k]] ax.plot(X[my_members, 0], X[my_members, 1], 'w', markerfacecolor=col, marker='.') ax.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col, markeredgecolor='k', markersize=6)ax.set_title('MiniBatchKMeans')ax.set_xticks(())ax.set_yticks(())plt.text(-3.5, 1.8, 'train time: %.2fs\ninertia: %f' % (t_mini_batch, mbk.inertia_))# Initialise the different array to all Falsedifferent = (mbk_means_labels == 4)ax = fig.add_subplot(1, 3, 3)for k in range(n_clusters): different += ((k_means_labels == k) != (mbk_means_labels == order[k]))identic = np.logical_not(different)ax.plot(X[identic, 0], X[identic, 1], 'w', markerfacecolor='#bbbbbb', marker='.')ax.plot(X[different, 0], X[different, 1], 'w', markerfacecolor='m', marker='.')ax.set_title('Difference')ax.set_xticks(())ax.set_yticks(())plt.show() |
Total running time of the script: (0 minutes 0.374 seconds)
Download Python source code:
plot_mini_batch_kmeans.py
Download IPython notebook:
plot_mini_batch_kmeans.ipynb
Please login to continue.