我做了一个步骤，无需修改sklearn和递归函数。使用前请注意：
- 合并距离有时会相对于子级合并距离减小。我添加了三种处理这些情况的方法：以最大，什么都不做或以l2范数增加。l2规范逻辑尚未验证。请检查自己最适合您的。
导入软件包：
from sklearn.cluster import AgglomerativeClusteringimport numpy as npimport matplotlib.pyplot as pltfrom scipy.cluster.hierarchy import dendrogram
计算重量和距离的功能：
def get_distances(X,model,mode='l2'): distances = [] weights = [] children=model.children_ dims = (X.shape[1],1) distCache = {} weightCache = {} for childs in children: c1 = X[childs[0]].reshape(dims) c2 = X[childs[1]].reshape(dims) c1Dist = 0 c1W = 1 c2Dist = 0 c2W = 1 if childs[0] in distCache.keys(): c1Dist = distCache[childs[0]] c1W = weightCache[childs[0]] if childs[1] in distCache.keys(): c2Dist = distCache[childs[1]] c2W = weightCache[childs[1]] d = np.linalg.norm(c1-c2) cc = ((c1W*c1)+(c2W*c2))/(c1W+c2W) X = np.vstack((X,cc.T)) newChild_id = X.shape[0]-1 # How to deal with a higher level cluster merge with lower distance: if mode=='l2': # Increase the higher level cluster size suing an l2 norm added_dist = (c1Dist**2+c2Dist**2)**0.5 dNew = (d**2 + added_dist**2)**0.5 elif mode == 'max': # If the previrous clusters had higher distance, use that one dNew = max(d,c1Dist,c2Dist) elif mode == 'actual': # Plot the actual distance. dNew = d wNew = (c1W + c2W) distCache[newChild_id] = dNew weightCache[newChild_id] = wNew distances.append(dNew) weights.append( wNew) return distances, weights使用2个子群集制作2个群集的样本数据：
# Make 4 distributions, two of which form a bigger clusterX1_1 = np.random.randn(25,2)+[8,1.5]X1_2 = np.random.randn(25,2)+[8,-1.5]X2_1 = np.random.randn(25,2)-[8,3]X2_2 = np.random.randn(25,2)-[8,-3]# Merge the four distributionsX = np.vstack([X1_1,X1_2,X2_1,X2_2])# Plot the clusterscolors = ['r']*25 + ['b']*25 + ['g']*25 + ['y']*25plt.scatter(X[:,0],X[:,1],c=colors)
样本数据：
拟合聚类模型
model = AgglomerativeClustering(n_clusters=2,linkage="ward")model.fit(X)
调用该函数以查找距离，并将其传递给树状图
distance, weight = get_distances(X,model)linkage_matrix = np.column_stack([model.children_, distance, weight]).astype(float)plt.figure(figsize=(20,10))dendrogram(linkage_matrix)plt.show()
Ouput树状图：
