【Python-ML】SKlearn库原型聚类KMeans

# -*- coding: utf-8 -*-
'''
Created on 2018年1月25日
@author: Jason.F
@summary: 无监督聚类学习-KMeans算法
'''
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans
from matplotlib import cm
from sklearn.metrics import silhouette_samples

X,y = make_blobs(n_samples=150,n_features=2,centers=3,cluster_std=0.5,shuffle=True,random_state=0)
plt.scatter(X[:,0],X[:,1],c='red',marker='o',s=50)
plt.grid()
plt.show() 
#簇内物产平方和容忍度tol=1e-04
km = KMeans(n_clusters=3,init='random',n_init=10,max_iter=300,tol=1e-04,random_state=0)
y_km = km.fit_predict(X)
#可视化
plt.scatter(X[y_km==0,0],X[y_km==0,1],s=50,c='lightgreen',marker='s',label='cluster 1')
plt.scatter(X[y_km==1,0],X[y_km==1,1],s=50,c='orange',marker='o',label='cluster 2')
plt.scatter(X[y_km==2,0],X[y_km==2,1],s=50,c='lightblue',marker='v',label='cluster 3')
plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],s=250,c='red',marker='*',label='centroids 3')
plt.legend()
plt.grid()
plt.show()
'''
KMeans存在簇类k值的先验获取，可以通过肘部法则确定最佳簇类数量
KMeans++所选择初始中心点尽可能远
'''
print ('Distortion:%.2f'%km.inertia_)#簇内误差平方和
distortions=[]
for i in range(1,11):
    km=KMeans(n_clusters=i,init='k-means++',n_init=10,max_iter=300,random_state=0)
    km.fit(X)
    distortions.append(km.inertia_)
plt.plot(range(1,11),distortions,marker='o')
plt.xlabel('Number of clusters')
plt.ylabel('Distortion')
plt.show()
'''
轮廓分析使用图形工具来度量簇中样本聚集的秘籍成都，通过计算单个样本的轮廓系数(silhouette coefficient)
'''
km = KMeans(n_clusters=3,init='k-means++',n_init=10,max_iter=300,tol=1e-04,random_state=0)
y_km = km.fit_predict(X)
cluster_labels = np.unique(y_km)
n_clusters = cluster_labels.shape[0]
silhouette_vals = silhouette_samples(X, y_km, metric='euclidean')
y_ax_lower,y_ax_upper =0,0
yticks =[]
for i,c in enumerate(cluster_labels):
    c_silhouette_vals =silhouette_vals[y_km==c]
    c_silhouette_vals.sort()
    y_ax_upper+=len(c_silhouette_vals)
    color =cm.jet(i/n_clusters)
    plt.barh(range(y_ax_lower,y_ax_upper),c_silhouette_vals,height=1.0,edgecolor='none',color=color)
    yticks.append((y_ax_lower+y_ax_upper)/2)
    y_ax_lower += len(c_silhouette_vals)
silhouette_avg = np.mean(silhouette_vals)
plt.axvline(silhouette_avg,color='red',linestyle='--')
plt.yticks(yticks,cluster_labels+1)
plt.ylabel('Cluster')
plt.xlabel('Silhouette coefficient')
plt.show()

结果：

Distortion:72.48