统计学习方法第十四章作业：聚类—层次聚类聚合/分裂算法、K_means聚类算法 代码实现

层次聚类聚合/分裂算法

import numpy as np
import copy
import matplotlib.pyplot as plt

class Hierarchical_cluster:

    def __init__(self,k=None,p=2,dis_way='min',c_way='agg'):
        self.k = k
        self.p = p
        self.dis_way = dis_way
        self.c_way = c_way

    def cauclate_dis(self, x1, x2):
        return np.sum(abs(x1 - x2) ** self.p) ** (1 / self.p)

    def create_D_matrix(self):
        self.D = np.zeros((self.n,self.n))
        for i in range(self.n):
            for j in range(self.n):
                if i==j:
                    self.D[i][j] = 0
                if i>j:
                    self.D[i][j] = self.cauclate_dis(self.x[i],self.x[j])
                    self.D[j][i] = self.cauclate_dis(self.x[i],self.x[j])

    def cauclate_cluster_dis(self,c1,c2):
        if self.dis_way == 'min':
            min_ = 999999999
            for i in c1:
                for j in c2:
                    min_ = min(min_,self.D[i][j])
            return min_

        if self.dis_way == 'mean':
            mean1 = np.mean([self.x[i] for i in c1],axis=0)
            mean2 = np.mean([self.x[i] for i in c2],axis=0)
            return self.cauclate_dis(mean1,mean2)

    def split_C(self,C):
        C1 = []
        C2 = []
        max_ = 0
        for i in C:
            for j in C:
                if j >= i:
                    if self.D[i][j] >= max_:
                        max_ = self.D[i][j]
                        max_i = i
                        max_j = j
        C1.append(max_i)
        C2.append(max_j)
        for c in C:
            if c == max_i or c == max_j:
                continue
            elif self.D[max_i][c] >= self.D[max_j][c]:
                C2.append(c)
            else:
                C1.append(c)
        return C1, C2

    def fit(self,x):
        self