密度聚类

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
plt.rcParams['axes.unicode_minus']=False
plt.rcParams['font.sans-serif']=['SimHei']
class DBScan (object):
    def __init__(self,p,l_stauts):
        self.point=p
        self.labels_stats=l_stauts
        self.db=DBSCAN(eps=0.2,min_samples=10).fit(self.point)
    def draw(self):
        coreSamplesMask=np.zeros_like(self.db.labels_,dtype=bool)
        coreSamplesMask[self.db.core_sample_indices_]=True
        labels=self.db.labels_
        nclusters=denoise(labels)
        #输出模型评估参数，包括估计的集群数量、均匀度、完整性、V度量、
        #调整后的RI、调整后的互信息量、轮廓系数
        print('Estimated number of clusters: %d'%nclusters)
        print("Homogeneity: %0.3f"%metrics.homogeneity_score(self.labels_stats, labels))
        print("Completeness: %0.3f"%metrics.completeness_score(self.labels_stats, labels))
        print("V-measure: %0.3f"%metrics.v_measure_score(self.labels_stats, labels))
        print("Adjusted Rand Index: %0.3f"%metrics.adjusted_rand_score(self.labels_stats, labels))
        print("Adjusted Mutual Information: %0.3f"%metrics.adjusted_mutual_info_score(self.labels_stats, labels))
        print("Silhouette Coefficient: %0.3f"%metrics.silhouette_score(self.point, labels))
        #黑色被移除并被标记为噪音
        unique_labels=set(labels)
        colors=plt.cm.Spectral(np.linspace(0,1,len(unique_labels)))
        for k, col in zip(unique_labels,colors):
            if k==-1:
                #黑色是噪声
                col='k'
            classMemberMask=(labels==k)
            #绘制分类点集
            xy=self.point[classMemberMask&coreSamplesMask]
            plt.plot(xy[:,0],xy[:,1],'o',markerfacecolor=col,
                     markeredgecolor='k',markersize=6)
            #绘制噪声点集
            xy=self.point[classMemberMask&~coreSamplesMask]
            plt.plot(xy[:,0],xy[:,1],'o',markerfacecolor=col,
                     markeredgecolor='k',markersize=3)
        plt.title('集群的估计数量: %d'%nclusters)
        plt.show()
def denoise (labels):
    #标签中的簇数（忽略噪声）
    clusters=len(set(labels))-(1 if -1 in labels else 0)
    return clusters
def standar_scaler(points):
    p=StandardScaler().fit_transform(points)
    return p
if __name__=="__main__":
    centers=[[1, 1],[-1, -1],[-1, 1],[1,-1]]
    point,labelsTrue=make_blobs(n_samples=1000,centers=centers,cluster_std=0.4,random_state=0)
    point=standar_scaler(point)
    db=DBScan(point,labelsTrue)
    db.draw()