Python实现DBSCAN聚类算法（简单样例测试）

发现高密度的核心样品并从中膨胀团簇。

Python代码如下：

 # -*- coding: utf-8 -*-
 """
 Demo of DBSCAN clustering algorithm
 Finds core samples of high density and expands clusters from them.
 """
 print(__doc__)
 # 引入相关包
 import numpy as np
 from sklearn.cluster import DBSCAN
 from sklearn import metrics
 from sklearn.datasets.samples_generator import make_blobs
 from sklearn.preprocessing import StandardScaler
 import matplotlib.pyplot as plt
 # 初始化样本数据
 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)
 # 计算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_
 # 聚类的结果
 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,
                                            average_method='arithmetic'))
 print("Silhouette Coefficient: %0.3f"
       % metrics.silhouette_score(X, labels))
 # 绘出结果
 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:
         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()

测试结果如下：

最终结果绘图：

具体数据：