k 均值聚类
1.引入依赖
import numpy as np
import matplotlib.pyplot as plt
# 调用sklearn中的方法直接生成数据
from sklearn.datasets.samples_generator import make_blobs
2.数据加载和预处理
x, y = make_blobs(n_samples=100, centers=6, random_state=1234, cluster_std=0.6)
#print(x,y)
plt.figure(figsize=(6,6))
plt.scatter(x[:,0],x[:,1],c=y)
plt.show()
print(x.shape)
3. 算法实现
from scipy.spatial.distance import cdist
class K_Means():
# 初始化,参数k、迭代次数、初始中心点