分析总结Python数据化运营KMeans聚类

import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn import metrics
import random
# 随机生成100组包含3组特征的数据
feature = [[random.random(),random.random(),random.random()] for i in range(100)]
label = [int(random.randint(0,2)) for i in range(100)]
# 转换数据格式
x_feature = np.array(feature)
# 训练聚类模型
n_clusters = 3  # 设置聚类数量
model_kmeans = KMeans(n_clusters=n_clusters, random_state=0)  # 建立聚类模型对象
model_kmeans.fit(x_feature)  # 训练聚类模型
y_pre = model_kmeans.predict(x_feature)  # 预测聚类模型
y_pre

# 样本距离最近的聚类中心的总和
inertias = model_kmeans.inertia_ 

# 调整后的兰德指数
adjusted_rand_s = metrics.adjusted_rand_score(label, y_pre)

# 互信息
mutual_info_s = metrics.mutual_info_score(label, y_pre)

# 调整后的互信息
adjusted_mutual_info_s = metrics.adjusted_mutual_info_score(label, y_pre) 

# 同质化得分
homogeneity_s = metrics.homogeneity_score(label, y_pre)  

# 完整性得分
completeness_s = metrics.completeness_score(label, y_pre) 

v_measure_s = metrics.v_measure_score(label, y_pre) 

# 平均轮廓系数
silhouette_s = metrics.silhouette_score(x_feature, y_pre, metric='euclidean') 

# Calinski和Harabaz得分
calinski_harabaz_s = metrics.calinski_harabasz_score(x_feature, y_pre) 

# 模型效果可视化
centers = model_kmeans.cluster_centers_  # 各类别中心
colors = ['#4EACC5', '#FF9C34', '#4E9A06']  # 设置不同类别的颜色
plt.figure()  # 建立画布
for i in range(n_clusters):  # 循环读类别
    index_sets = np.where(y_pre == i)  # 找到相同类的索引集合
    cluster = x_feature[index_sets]  # 将相同类的数据划分为一个聚类子集
    plt.scatter(cluster[:, 0], cluster[:, 1], c=colors[i], marker='.')  # 展示聚类子集内的样本点
    plt.plot(centers[i][0], centers[i][1], 'o', markerfacecolor=colors[i], markeredgecolor='k',
             markersize=6)  # 展示各聚类子集的中心
plt.show()  # 展示图像

# 模型应用
new_X = [1, 3.6,9.9]
cluster_label = model_kmeans.predict(np.array(new_X).reshape(1,-1))
print ('聚类预测结果为: %d' % cluster_label)