n_points_per_cluster = 250
C1 = [-5, -2] + .8 * np.random.randn(n_points_per_cluster, 2)
C2 = [4, -1] + .1 * np.random.randn(n_points_per_cluster, 2)
C3 = [1, -2] + .2 * np.random.randn(n_points_per_cluster, 2)
C4 = [-2, 3] + .3 * np.random.randn(n_points_per_cluster, 2)
C5 = [3, -2] + 1.6 * np.random.randn(n_points_per_cluster, 2)
C6 = [5, 6] + 2 * np.random.randn(n_points_per_cluster, 2)
X = np.vstack((C1, C2, C3, C4, C5, C6))
clust = OPTICS(min_samples=9, rejection_ratio=0.5)
# Run the fit
clust.fit(X)
_, labels_025 = clust.extract_dbscan(0.25)
_, labels_075 = clust.extract_dbscan(0.75)
space = np.r_[0:len(X):1]
R = clust.reachability_[clust.ordering_]
C = clust.labels_[clust.ordering_]
plt.figure(figsize=(10, 7))
G = gridspec.GridSpec(2, 3)
ax1 = plt.subplot(G[0, :])
ax1.set_ylabel('Reachability (epsilon distance)')
ax1.set_title('Reachability Plot')
ax2 = plt.subplot(G[1, 0])
ax2.set_title('Automatic Clustering')
ax3 = plt.subplot(G[1, 1])
ax3.set_title('Clustering at 0.25 epsilon cut')
n_points_per_cluster = 250 C1 = [-5, -2] + .8 * np.random.randn(n_points_per_cluster, 2) C2 = [4, -1] + .1 * np.random.randn(n_points_per_cluster, 2) C3 = [1, -2] + .2 * np.random.randn(n_points_per_cluster, 2) C4 = [-2, 3] + .3 * np.random.randn(n_points_per_cluster, 2) C5 = [3, -2] + 1.6 * np.random.randn(n_points_per_cluster, 2) C6 = [5, 6] + 2 * np.random.randn(n_points_per_cluster, 2) X = np.vstack((C1, C2, C3, C4, C5, C6)) clust = OPTICS(min_samples=9, rejection_ratio=0.5) # Run the fit clust.fit(X) _, labels_025 = clust.extract_dbscan(0.25) _, labels_075 = clust.extract_dbscan(0.75) space = np.arange(len(X)) reachability = clust.reachability_[clust.ordering_] labels = clust.labels_[clust.ordering_] plt.figure(figsize=(10, 7)) G = gridspec.GridSpec(2, 3) ax1 = plt.subplot(G[0, :]) ax2 = plt.subplot(G[1, 0]) ax3 = plt.subplot(G[1, 1]) ax4 = plt.subplot(G[1, 2]) # Reachability plot color = ['g.', 'r.', 'b.', 'y.', 'c.']
