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

Posted 2021-01-15 844115-l

1.用python实现K均值算法

import numpy as np
x = np.random.randint(1,100,[20,1])
y = np.zeros(20)
k = 3

x
y

1(1) 选取数据空间中的K个对象作为初始中心，每个对象代表一个聚类中心；

def initcenter(x,k):
    return x[:k]

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,14)

 

1.(2） 对于样本中的数据对象，根据它们与这些聚类中心的欧氏距离，按距离最近的准则将它们分到距离它们最近的聚类中心（最相似）所对应的类；

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

 

 

def initcenter(x,k):
    return x[: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

kc = initcenter(x,k)
y = xclassify(x,y,kc)
print(kc,y)

 

 

m = np.where(y == 0)
m

np.mean(x[m])

kc[0]=24
kc

2. 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 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)

        if m[0].shape != (0,):
            n = np.mean(x[m])
            if l[c] != n:
                l[c] = n
                flag = True    #聚类中心发生改变
                return (np.array(1),flag)

def xclassify(x,y,kc):
    for i in range(x.shape[0]):    #对数组的每个值分类
        y[i] = nearest(kc,x[i])
    return y

k = 3
kc = initcenter(x,k)

falg = True
print(x, y, kc, flag)
while flag:
    y = xclassify(x, y, kc)
    xc, flag = kcmean(x, y, kc, k)
    
print(y,kc)

 运行结果：

 

import matplotlib.pyplot as plt
plt.scatter(x, x, c=y, s=50, cmap=‘rainbow‘,marker=‘p‘,alpha=0.5);
plt.show()

 

3.用sklearn.cluster.KMeans，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.cluster import KMeans
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt

iris_data = load_iris()
X=iris_data.data
# 花瓣长度
petal_length = X[:, 2:3]
x= petal_length
print(x)
k_means = KMeans(n_clusters=3)
est = k_means.fit(x)
kc = est.cluster_centers_
y_kmeans = k_means.predict(x)

plt.scatter(x,np.linspace(1,150,150),c=y_kmeans,marker=‘o‘,cmap=‘rainbow‘,linewidths=4)
plt.show()

 运行结果：

 

 

 

 

4.鸢尾花完整数据做聚类并用散点图显示

from sklearn.cluster import KMeans
import numpy as np
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
data = load_iris()
iris = data.data
petal_len = iris
print(petal_len)
k_means = KMeans(n_clusters=3) #三个聚类中心
result = k_means.fit(petal_len) #Kmeans自动分类
kc = result.cluster_centers_ #自动分类后的聚类中心
y_means = k_means.predict(petal_len) #预测Y值
plt.scatter(petal_len[:,0],petal_len[:,2],c=y_means, marker=‘p‘,cmap=‘rainbow‘)
plt.show()

 运行结果：