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

#随机生成一组整数sample
import numpy as np
sample=np.random.randint(1,100,[50,1])  
k=3#要分成的类别数
y=np.zeros(50)
#定义一个函数来存放开始的聚类中心kc
def start_center(sample,k):
    return sample[:3]
kc=start_center(sample,k)

?def nearest(kc,i):
    d=abs(kc-i)
    t=np.where(d ==np.min(d))
    return t[0][0]
nearest(kc,34)
#对其进行对应的分类
?def xclassify(sample,y,kc):
    for i in range(30):
        y[i]=nearest(kc,sample[i])
    return y
y=xclassify(sample,y,kc)
print(kc,y)

def kcmean(sample,y,kc,k):
    l=list(kc)
    flag=False
    for j in range(k):#对k的类别进行遍历
        m=np.where(y==j)
        print(j,sample[j])
        junzhi=np.mean(sample[m])#求出每个类别的均值
        print(kc[j],junzhi)
        if l[j]!=junzhi: #判断求出的均值是否与开始的看类别值相等
            l[j]=junzhi
            flag=True
    return(np.array(l),flag)

flag=True
while flag:
    y=xclassify(sample,y,kc)
    kc,flag=kcmean(sample,y,kc,k)
    print(y,kc)
print(sample,y)

import matplotlib.pyplot as plt
import numpy as np

data=load_iris()
data_length=data[‘data‘][:,2]#取出鸢尾花花瓣的长度
x=data_length
y=np.zeros(x.shape[0])
kc = start_center(x,3)
flag=True
while flag:
    y=xclassify(x,y,kc)
    kc,flag=kcmean(x,y,kc,k)
print(y,kc)
#用散点图来显示
plt.scatter(x,x,s=x,c=y,cmap=‘rainbow‘,alpha=0.5,linewidths=4)
plt.show()

from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import numpy as np
# 用sklearn.cluster.KMeans，鸢尾花花瓣长度数据做聚类并用散点图显示.
data=load_iris()
data_length=data[‘data‘][:,2:3]#取出鸢尾花花瓣的长度
x=data_length
#y=np.zeros(x.shape[0])
k1=KMeans(n_clusters=3)#将其类别分为3类
k1.fit(x)
kc1=k1.cluster_centers_
y_kmeans=k1.predict(x)##预测每个样本的聚类索引
print(y_kmeans,kc1)
plt.scatter(x,np.linspace(1,150,150),c=y_kmeans,marker=‘x‘,cmap=‘rainbow‘,linewidths=4)
plt.show()