机器学习笔记-聚类算法

聚类算法K-means

• 代码

import matplotlib.pyplot as plt
from sklearn.datasets.samples_generator import make_blobs
from sklearn.cluster import KMeans
from sklearn.metrics import calinski_harabaz_score

# 创建数据
X, y = make_blobs(n_samples=1000, n_features=2, centers=[
                  [-1, -1], [0, 0], [1, 1], [2, 2]], cluster_std=[0.4, 0.2, 0.2, 0.2], random_state=9)

plt.scatter(X[:, 0], X[:, 1], marker="o")
plt.show()
## 图

# kmeans训练,且可视化 聚类=2
y_pre = KMeans(n_clusters=2, random_state=9).fit_predict(X)

# 可视化展示
plt.scatter(X[