Skip to content

Commit bf118ac

Browse files
authored
Add files via upload
1 parent 6088bcd commit bf118ac

File tree

2 files changed

+30
-0
lines changed

2 files changed

+30
-0
lines changed

K_Means_Project4/Figure_1.png

25.4 KB
Loading

K_Means_Project4/K_Means.py

Lines changed: 30 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,30 @@
1+
# -*- coding: utf-8 -*-
2+
"""
3+
Created on Sat Aug 4 15:55:01 2018
4+
5+
@author: wzy
6+
"""
7+
# 聚类数据生成器
8+
from sklearn.datasets import make_blobs
9+
# KMeans算法使用
10+
from sklearn.cluster import KMeans
11+
import matplotlib.pyplot as plt
12+
13+
if __name__ == '__main__':
14+
# 生成聚类数据 150个样本,每个样本两个特征,一共聚为3簇,簇内标准差为0.5,所有样本数据随机排序,采用随机数种子
15+
x, y = make_blobs(n_samples=150, n_features=2, centers=3, cluster_std=0.5, shuffle=True, random_state=0)
16+
# 绘制样本点的散点图
17+
plt.scatter(x[:, 0], x[:, 1], marker='o', color='blue')
18+
# 聚为3个簇,从训练数据用k-means++寻找质心,初始样本中心的个数为10个,最大迭代次数为300,SSE为10^(-4)
19+
km = KMeans(n_clusters=3, init="k-means++", n_init=10, max_iter=300, tol=1e-4, random_state=0)
20+
# 用K-means计算并且将X作为测试集分簇
21+
y_km = km.fit_predict(x)
22+
# 绘制不同簇的点
23+
plt.scatter(x[y_km==0, 0], x[y_km==0, 1], s=50, c='orange', marker='o', label='cluster 1')
24+
plt.scatter(x[y_km==1, 0], x[y_km==1, 1], s=50, c='green', marker='s', label='cluster 2')
25+
plt.scatter(x[y_km==2, 0], x[y_km==2, 1], s=50, c='blue', marker='^', label='cluster 3')
26+
# 绘制簇的中心点
27+
plt.scatter(km.cluster_centers_[:, 0], km.cluster_centers_[:, 1], s=250, marker="*", c="red", label="cluster center")
28+
plt.legend()
29+
plt.grid()
30+
plt.show()

0 commit comments

Comments
 (0)