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]

def xclassify(x,y,kc):     
    for i in range(x.shape[0]):
        y[i]=nearest(kc,x[i])
        return y


def kcmean(x,y,kc,k):
    l=list(kc)
    flag=False
    for c in range(k):
        print(c)
        m=np.where(y==c)
        print(m,x[m])
        n=np.mean(x[m])
        print(kc[c],n)
        if l[c]!=n:
            kc[c]=n        
            print(type(kc),kc[c])
            l[c]=n
            flag=True       
            print(l,flag)
            return(np.array(l),flag)
flag=True
print("x值为",x,"y值为",y,"kc值为",kc,"flag值为",flag)



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=x,s=50,cmap="rainbow");
plt.show()



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):   
    return x[0:k].reshape(k)

def nearest(kc,i):       
    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]):      
        y[i] = nearest(kc,x[i])
    return y

def kcmean(x,y,kc,k):    
    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    
            print(l,flag)
    return (np.array(l),flag)


k = 3
kc = initcenter(x,k)

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



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="Paired");
plt.show()


#用sklearn.cluster.KMeans，鸢尾花花瓣长度数据做聚类并用散点图显示
import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import load_iris

iris = load_iris()
X = iris.data
X

from sklearn.cluster import KMeans

est = KMeans(n_clusters = 3)
est.fit(X)
kc = est.cluster_centers_
y_kmeans = est.predict(X)  

print(y_kmeans,kc)
print(kc.shape,y_kmeans.shape,np.shape)

plt.scatter(X[:,0],X[:,1],c=y_kmeans,s=50,cmap='rainbow');
plt.show()

截图