K-Means算法原理

import pandas as pd
from matplotlib import pyplot as plt
from sklearn.cluster import k_means

# 1、读取数据文件
df = pd.read_csv("data.csv", header=0)
df.head()

# 2、原始文件画图
X = df['x']
y = df['y']
plt.scatter(X, y)
plt.show()

# 3、k-means分为三类
model = k_means(df, n_clusters=3)
print(model)

# 4、分类后画图
cluster_centers = model[0]
cluster_labels = model[1]
plt.scatter(X, y, c=cluster_labels)
for center in cluster_centers:
    plt.scatter(center[0], center[1], marker="p", edgecolors="red")
plt.show()

# 肘部法则
index = [] # 横坐标数组
inertia = [] # 纵坐标数组

# K 从 1~ 10 聚类
for i in range(9):
    model = k_means(df, n_clusters=i + 1)
    index.append(i + 1)
    inertia.append(model[2])

# 绘制折线图
plt.plot(index, inertia, "-o")
plt.show()

#轮廓系数
from sklearn.metrics import silhouette_score # 导入轮廓系数计算模块

index2 = [] # 横坐标
silhouette = [] # 轮廓系数列表

# K 从 2 ~ 10 聚类
for i in range(8):
    model = k_means(df, n_clusters=i + 2)
    index2.append(i + 2)
    silhouette.append(silhouette_score(df, model[1]))

print(silhouette) # 输出不同聚类下的轮廓系数

# 绘制折线图
plt.plot(index2, silhouette, "-o")
plt.show()