基于python的 sklearn 的DBSCAN 算法样例

淡淡的烟草味﹌ 2022-12-13 09:59 172阅读 0赞

print(__doc__)
    
    import numpy as np
    
    from sklearn.cluster import DBSCAN
    from sklearn import metrics
    from sklearn.datasets import make_blobs
    from sklearn.preprocessing import StandardScaler
    
    
    # #############################################################################
    # Generate sample data
    centers = [[1, 1], [-1, -1], [1, -1]]
    X, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,
                                random_state=0)
    
    X = StandardScaler().fit_transform(X)
    
    # #############################################################################
    # Compute DBSCAN
    db = DBSCAN(eps=0.3, min_samples=10).fit(X)
    core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
    core_samples_mask[db.core_sample_indices_] = True
    labels = db.labels_
    
    # Number of clusters in labels, ignoring noise if present.
    n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
    n_noise_ = list(labels).count(-1)
    
    print('Estimated number of clusters: %d' % n_clusters_)
    print('Estimated number of noise points: %d' % n_noise_)
    print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
    print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
    print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
    print("Adjusted Rand Index: %0.3f"
          % metrics.adjusted_rand_score(labels_true, labels))
    print("Adjusted Mutual Information: %0.3f"
          % metrics.adjusted_mutual_info_score(labels_true, labels))
    print("Silhouette Coefficient: %0.3f"
          % metrics.silhouette_score(X, labels))
    
    # #############################################################################
    # Plot result
    import matplotlib.pyplot as plt
    
    # Black removed and is used for noise instead.
    unique_labels = set(labels)
    colors = [plt.cm.Spectral(each)
              for each in np.linspace(0, 1, len(unique_labels))]
    for k, col in zip(unique_labels, colors):
        if k == -1:
            # Black used for noise.
            col = [0, 0, 0, 1]
    
        class_member_mask = (labels == k)
    
        xy = X[class_member_mask & core_samples_mask]
        plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
                 markeredgecolor='k', markersize=14)
    
        xy = X[class_member_mask & ~core_samples_mask]
        plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
                 markeredgecolor='k', markersize=6)
    
    plt.title('Estimated number of clusters: %d' % n_clusters_)
    plt.show()

![Estimated number of clusters: 3][Estimated number of clusters_ 3]

欢迎关注公众号：算法工程师的学习日志，获取算法工程师的学习资料

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FpbmdmZW5neGQx_size_16_color_FFFFFF_t_70][]

[Estimated number of clusters_ 3]: /images/20221123/bc606f86113f4ec082eb59ed6c367846.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FpbmdmZW5neGQx_size_16_color_FFFFFF_t_70]: /images/20221123/ecc4a3b9ce354ec88cb5398a841ed8dd.png