hierarchical_clustering.py 文件源码

def example_naivehierarchicalclustering():
    """Naive hierarchical clustering algorithm using DTW and based on .

    For a more efficient approach, check:
    Mueen, A and Keogh, E, Extracting Optimal Performance from Dynamic Time Warping,
    Tutorial, KDD 2016
    http://www.cs.unm.edu/~mueen/DTW.pdf

    :return: None
    """
    series = [
        np.array([0.0, 0.0, 2.0, 1.0, 1.0, 0.0, 0.0]),
        np.array([0.0, 0.0, 2.0, 1.0, 1.0, 0.0, 0.0]),
        np.array([2.0, 1.0, 1.0, 0.0, 0.0, 0.0, 0.0]),
        np.array([2.0, 1.0, 1.0, 0.0, 0.0, 2.0, 3.0]),
        np.array([4.0, 2.0, 1.0, 0.0, 0.0, 1.0, 3.0])
    ]

    dists = dtw.distance_matrix_fast(series)
    print("Distance matrix:\n{}".format(dists))

    dists_cond = np.zeros(size_cond(len(series)))
    idx = 0
    for r in range(len(series)-1):
        dists_cond[idx:idx+len(series)-r-1] = dists[r, r+1:]
        idx += len(series)-r-1

    z = linkage(dists_cond, method='complete', metric='euclidean')
    print(z)

    fig, axes = plt.subplots(2, 1, figsize=(8, 3))
    for idx, serie in enumerate(series):
        serie += idx * 0.1
        axes[0].plot(serie, label=str(idx))
        axes[0].text(0 + 0.15 * (-1)**idx * idx, serie[0] + 0.15 * idx, idx)
        axes[0].add_line(Line2D([0, 0 + 0.15 * (-1)**idx * idx], [serie[0], serie[0] + 0.15 * idx],
                                linewidth=1, color='gray'))
    axes[0].legend(loc=1)
    dendrogram(z, ax=axes[1])
    plt.show(block=True)