Python实现简单层次聚类算法以及可视化

import numpy as npimport data_helpernp.random.seed(1)def get_raw_data(n): _data=np.random.rand(n,2) #生成数据的格式是n个（x,y） _groups={idx:[[x,y]] for idx,(x,y) in enumerate(_data)} return _groupsdef cal_distance(cluster1,cluster2): #采用最小距离作为聚类标准 _min_distance=10000 for x1,y1 in cluster1:  for x2,y2 in cluster2:   _distance=(x1-x2)**2+(y1-y2)**2   if _distance<_min_distance:    _min_distance=_distance return _distancegroups=get_raw_data(10)count=0while len(groups)!=1:#判断是不是所有的数据是不是归为了同一类 min_distance=10000 len_groups=len(groups)  for i in groups.keys():  for j in groups.keys():   if i>=j:    continue   distance=cal_distance(groups[i],groups[j])   if distance<min_distance:    min_distance=distance    min_i=i    min_j=j#这里的j>i groups[min_i].extend(groups.pop(min_j)) data_helper.draw_data(groups) #一共n个簇，共迭代n-1次