第八次作业：聚类--K均值算法：自主实现与sklearn.cluster.KMeans调用

import numpy as np
x = np.random.randint(1,100,[20,1])
y = np.zeros(20)
k = 3
def initcenter(x,k):
    return x[:k]
 
kc = initcenter(x,k)
kc
def nearest(kc,i):
    d=(abs(kc-i))
    w=np.where(d==np.min(d))
    return w[0][0]
 
kc = initcenter(x,k)
nearest(kc,56)
def xclassify(x,y,kc):
    for i in range(x.shape[0]):
        y[i] = nearest(kc,x[i])
    return y
 
kc = initcenter(x,k)
y = xclassify(x,y,kc)
print(kc,y)
def kcmean(x,y,kc,k):
    l = list(kc)
    flag = False
    for c in range(k):
        m = np.where(y == c)
        n = np.mean(x[m])
        if l[c] != n:
            l[c] = n
            flag = True
            print(l,flag)
    return (np.array(l),flag)
 
kc = initcenter(x,k)
flag = True
k = 3
 
 
while flag:
    y = xclassify(x,y,kc)
    kc,flag = kcmean(x,y,kc,k)

运行结果

 

二.鸢尾花花瓣长度数据做聚类并用散点图显示

import numpy as np
from sklearn.datasets import load_iris    
iris = load_iris()
x = iris.data[:,1]
y = np.zeros(150)

def initcenter(x,k):    #初始聚类中心数组
    return x[0:k].reshape(k)

def nearest(kc,i):       #数组中的值，与聚类中心最小距离所在类别的索引号
    d = (abs(kc-i))
    w = np.where(d == np.min(d))
    return w[0][0]

def xclassify(x,y,kc):
    for i in range(x.shape[0]):       #对数组的每个值进行分类，shape[0]读取矩阵第一维度的长度
        y[i] = nearest(kc,x[i])
    return y

def kcmean(x,y,kc,k):     #计算各聚类新均值
    l = list(kc)
    flag = False
    for c in range(k):
        print(c)
        m = np.where(y == c)
        n=np.mean(x[m])
        if l[c] != n:
            l[c] = n
            flag = True     #聚类中心发生变化
            print(l,flag)
    return (np.array(l),flag)


k = 3
kc = initcenter(x,k)

flag = True
print(x,y,kc,flag)

#判断聚类中心和目标函数的值是否发生改变，若不变，则输出结果，若改变，则返回2
while flag:
    y = xclassify(x,y,kc)
    kc, flag = kcmean(x,y,kc,k)
    print(y,kc,type(kc))
    
print(x,y)
import matplotlib.pyplot as plt
plt.scatter(x,x,c=y,s=50,cmap="rainbow");
plt.show()

运行结果