k均值聚类代码的实现

k means教程

0. 引入依赖

import numpy as np
import matplotlib.pyplot as plt
​
# 从sklearn中直接生成聚类数据
from sklearn.datasets.samples_generator import make_blobs

1. 数据加载

x, y = make_blobs( n_samples=100, centers=6, random_state=1234, cluster_std=0.6 )
​
plt.figure(figsize=(6,6))
plt.scatter(x[:,0], x[:,1], c=y)
plt.show()

2. 算法实现

# 引入scipy中的距离函数，默认欧式距离
from scipy.spatial.distance import cdist
​
class K_Means(object):
    # 初始化，参数 n_clusters（K）、迭代次数max_iter、初始质心 centroids
    def __init__(self, n_clusters=5, max_iter=300, centroids=[]):
        self.n_clusters = n_clusters
        self.max_iter = max_iter
        self.centroids = np.array( centroids, dtype=np.f