test_dbscan.py 文件源码

def test_dbscan_similarity():
    # Tests the DBSCAN algorithm with a similarity array.
    # Parameters chosen specifically for this task.
    eps = 0.15
    min_samples = 10
    # Compute similarities
    D = distance.squareform(distance.pdist(X))
    D /= np.max(D)
    # Compute DBSCAN
    core_samples, labels = dbscan(D, metric="precomputed", eps=eps,
                                  min_samples=min_samples)
    # number of clusters, ignoring noise if present
    n_clusters_1 = len(set(labels)) - (1 if -1 in labels else 0)

    assert_equal(n_clusters_1, n_clusters)

    db = DBSCAN(metric="precomputed", eps=eps, min_samples=min_samples)
    labels = db.fit(D).labels_

    n_clusters_2 = len(set(labels)) - int(-1 in labels)
    assert_equal(n_clusters_2, n_clusters)