sklearn聚类模型：基于密度的DBSCAN；基于混合高斯模型的GMM

# kmeans聚类
from sklearn.cluster import KMeans
estimator = KMeans(n_clusters=2)#构造聚类器
y_pred =estimator.fit_predict(X_train_2)#聚类

clr = [‘b‘ if i==0 else ‘y‘ if i==1 else ‘r‘ for i in y_pred]
plt.scatter(X_train[:,0],X_train[:,1],c=clr)


# DBSCAN（Density-Based Spatial Clustering of Application with Noise）基于密度的空间聚类算法
from sklearn.cluster import DBSCAN
dbs1 = DBSCAN(eps=0.5, # 邻域半径 
min_samples=5 ) # 最小样本点数，MinPts
y_pred = dbs1.fit_predict(X_train_2) #训练集的标签

clr = [‘b‘ if i==0 else ‘y‘ if i==1 else ‘r‘ for i in y_pred]
plt.scatter(X_train_2[:,0],X_train_2[:,1],c=clr)


#混合高斯模型Gaussian Mixture Model(GMM)聚类
from sklearn import mixture
clf = mixture.GaussianMixture(n_components=2,covariance_type=‘full‘)
clf.fit(X_train_2) #.fit_predict
y_pred = clf.predict(X_train_2)

#预测
clr = [‘b‘ if i==0 else ‘y‘ if i==1 else ‘r‘ for i in y_pred]
plt.scatter(X_train_2[:,0],X_train_2[:,1],c=clr)