#用python实现K均值算法
import numpy as np
x = np.random.randint(1,50,[20,1])
y = np.zeros(20)
k = 3
#(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 initcen(x,k):
return x[:k]
#(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;
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
#(3)更新聚类中心:将每个类别中所有对象所对应的均值作为该类别的聚类中心,计算目标函数的值;
def kcmean(x,y,kc,k):
l = list(kc)
flag = False
for c in range(k):
m = np.where(y ==0)
n = np.mean(x[m])
if l[c] != n:
l[c] = n
flag = True
print(l,flag)
return (np.array(l),flag)
#(4) 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)
kc = initcen(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)
![](https://img2018.cnblogs.com/blog/1482909/201810/1482909-20181031171511998-64911443.png)
from sklearn.datasets import load_iris
iris = load_iris()
datas = iris.data
iris_length=datas[:,2]
#(1) 用鸢尾花花瓣作分析
x = np.array(iris_length)
y = np.zeros(x.shape[0])
kc = initcen(x,3)
flag = True
while flag:
y = xclassify(x,y,kc)
kc,flag = kcmean(x,y,kc,3)
print(kc,flag)
# (2)分析鸢尾花花瓣长度的数据,并用散点图表示出来
import matplotlib.pyplot as plt
plt.scatter(iris_length, iris_length, marker='p', c=y, alpha=0.5, linewidths=4, cmap='Paired')
plt.show()
![](https://img2018.cnblogs.com/blog/1482909/201810/1482909-20181031171721379-396712106.png)
![](https://img2018.cnblogs.com/blog/1482909/201810/1482909-20181031171735504-1216708959.png)
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[:,2:3]
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,np.linspace(1,150,150),c=y_means,marker='x')
plt.show()
![](https://img2018.cnblogs.com/blog/1482909/201810/1482909-20181031172026840-1941171136.png)
#4. 鸢尾花完整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) #预测每个样本的聚类索引
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()
![](https://img2018.cnblogs.com/blog/1482909/201810/1482909-20181031172802988-185812881.png)