3.K均值算法

from sklearn.datasets import load_iris
import numpy as np
iris = load_iris()
data = iris[‘data‘]
data.shape
data[:,0]
n = len(data)   #样本个数
m = data.shape[1]   #样本属性个数
k = 3   #类中心的个数
dist = np.zeros([n, k+1]) #初始化距离矩阵,最后一列存放每个样本的类别
#1.选中心
center = data[:k, :] #初始类中心，选取前3个样本作为初始类中心
centernew = np.zeros([k, m])

while True:
    for i in range(n):
        for j in range(k):
            dist[i, j] = np.sqrt(sum((data[i, :] - center[j, :])**2))#2.求距离
        dist[i, k] = np.argmin(dist[i, :k])#3.归类

    #4.求新类中心
    for i in range(k):
       index = dist[:, k] == i   #判断距离矩阵中最后一列归属为哪一类
       centernew[i, :] = data[index, :].mean(axis=0)

    #5.判定结果
    if np.all((center == centernew)):
        break
    else:
        center = centernew
print(‘150个样本的归类：‘, dist[:, k])

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

iris=load_iris()
data=iris.data[:,1]
x=data.reshape(-1,1)

y=KMeans(n_clusters=3)
y.fit(x)

y_pre=y.predict(x)

plt.scatter(x[:,0],x[:,0],c=y_pre,s=50,cmap=‘rainbow‘)
plt.show()

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

data=load_iris()
x=data.data
y=KMeans(n_clusters=3)
y.fit(x)
y_pre=y.predict(x)

plt.scatter(x[:,2],x[:,3],c=y_pre,s=100,cmap=‘rainbow‘,alpha=0.5)
plt.show()