test_dbscan.py 文件源码

def test_dbscan_feature():
    # Tests the DBSCAN algorithm with a feature vector array.
    # Parameters chosen specifically for this task.
    # Different eps to other test, because distance is not normalised.
    eps = 0.8
    min_samples = 10
    metric = 'euclidean'
    # Compute DBSCAN
    # parameters chosen for task
    core_samples, labels = dbscan(X, metric=metric, eps=eps,
                                  min_samples=min_samples)

    # number of clusters, ignoring noise if present
    n_clusters_1 = len(set(labels)) - int(-1 in labels)
    assert_equal(n_clusters_1, n_clusters)

    db = DBSCAN(metric=metric, eps=eps, min_samples=min_samples)
    labels = db.fit(X).labels_

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