# -*- coding: utf-8 -*- ''' Created on 2018年1月25日 @author: Jason.F @summary: 無監督聚類學習-層次聚類(hierarchical clustering)，自下向上的凝聚和自頂向下的分裂兩種方法。 ''' import pandas as pd import numpy as np import matplotlib.pyplot as plt from scipy.spatial.distance import pdist,squareform from scipy.cluster.hierarchy import linkage from scipy.cluster.hierarchy import dendrogram from sklearn.cluster import AgglomerativeClustering np.random.seed(123) variables = ['X','Y','Z'] labels=['ID_0','ID_1','ID_2','ID_3','ID_4'] X=np.random.random_sample([5,3])*10 #層次聚類樹 df = pd.DataFrame(X,columns=variables,index=labels) print (df) #計算距離關聯矩陣，兩兩樣本間的歐式距離 #row_dist = pd.DataFrame(squareform(pdist(df,metric='euclidean')),columns=labels,index=labels) #print (row_dist) #print (help(linkage)) row_clusters = linkage(pdist(df,metric='euclidean'),method='complete')#使用抽秘籍距離矩陣 #row_clusters = linkage(df.values,method='complete',metric='euclidean') print (pd.DataFrame(row_clusters,columns=['row label1','row label2','distance','no. of items in clust.'],index=['cluster %d'%(i+1) for i in range(row_clusters.shape[0])])) #層次聚類樹 row_dendr = dendrogram(row_clusters,labels=labels) plt.tight_layout() plt.ylabel('Euclidean distance') plt.show() #層次聚類熱度圖 fig =plt.figure(figsize=(8,8)) axd =fig.add_axes([0.09,0.1,0.2,0.6]) row_dendr = dendrogram(row_clusters,orientation='right') df_rowclust = df.ix[row_dendr['leaves'][::-1]] axm = fig.add_axes([0.23,0.1,0.6,0.6]) cax = axm.matshow(df_rowclust,interpolation='nearest',cmap='hot_r') axd.set_xticks([]) axd.set_yticks([]) for i in axd.spines.values():i.set_visible(False) fig.colorbar(cax) axm.set_xticklabels(['']+list(df_rowclust.columns)) axm.set_yticklabels(['']+list(df_rowclust.index)) plt.show()#凝聚層次聚類，應用對層次聚類樹剪枝 ac=AgglomerativeClustering(n_clusters=2,affinity='euclidean',linkage='complete') labels = ac.fit_predict(X) print ('cluster labels:%s'%labels)

結果：

X Y Z ID_0 6.964692 2.861393 2.268515 ID_1 5.513148 7.194690 4.231065 ID_2 9.807642 6.848297 4.809319 ID_3 3.921175 3.431780 7.290497 ID_4 4.385722 0.596779 3.980443row label1 row label2 distance no. of items in clust. cluster 1 0.0 4.0 3.835396 2.0 cluster 2 1.0 2.0 4.347073 2.0 cluster 3 3.0 5.0 5.899885 3.0 cluster 4 6.0 7.0 8.316594 5.0 cluster labels:[0 1 1 0 0]

總結

以上是生活随笔為你收集整理的【Python-ML】SKlearn库层次聚类凝聚AgglomerativeClustering模型的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。