吴裕雄 python 机器学习——K均值聚类KMeans模型

import numpy as np
import matplotlib.pyplot as plt

from sklearn import  cluster
from sklearn.metrics import adjusted_rand_score
from sklearn.datasets.samples_generator import make_blobs

def create_data(centers,num=100,std=0.7):
    X, labels_true = make_blobs(n_samples=num, centers=centers, cluster_std=std)
    return  X,labels_true

# 用于产生聚类的中心点
centers=[[1,1],[2,2],[1,2],[10,20]] 
# 产生用于聚类的数据集
X,labels_true=create_data(centers,1000,0.5)

#K-MEANS聚类模型
def test_Kmeans(*data):
    X,labels_true=data
    clst=cluster.KMeans()
    clst.fit(X)
    predicted_labels=clst.predict(X)
    print("ARI:%s"% adjusted_rand_score(labels_true,predicted_labels))
    print("Sum center distance %s"%clst.inertia_)

# 用于产生聚类的中心点
centers=[[1,1],[2,2],[1,2],[10,20]] 
# 产生用于聚类的数据集
X,labels_true=create_data(centers,1000,0.5)
#  调用 test_Kmeans 函数
test_Kmeans(X,labels_true)

def test_Kmeans_nclusters(*data):
    '''
    测试 KMeans 的聚类结果随 n_clusters 参数的影响
    '''
    X,labels_true=data
    nums=range(1,50)
    ARIs=[]
    Distances=[]
    for num in nums:
        clst=cluster.KMeans(n_clusters=num)
        clst.fit(X)
        predicted_labels=clst.predict(X)
        ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
        Distances.append(clst.inertia_)
    ## 绘图
    fig=plt.figure()
    ax=fig.add_subplot(1,2,1)
    ax.plot(nums,ARIs,marker="+")
    ax.set_xlabel("n_clusters")
    ax.set_ylabel("ARI")
    ax=fig.add_subplot(1,2,2)
    ax.plot(nums,Distances,marker='o')
    ax.set_xlabel("n_clusters")
    ax.set_ylabel("inertia_")
    fig.suptitle("KMeans")
    plt.show()
    
test_Kmeans_nclusters(X,labels_true) #  调用 test_Kmeans_nclusters 函数

def test_Kmeans_n_init(*data):
    '''
    测试 KMeans 的聚类结果随 n_init 和 init  参数的影响
    '''
    X,labels_true=data
    nums=range(1,50)
    ## 绘图
    fig=plt.figure()

    ARIs_k=[]
    Distances_k=[]
    ARIs_r=[]
    Distances_r=[]
    for num in nums:
            clst=cluster.KMeans(n_init=num,init='k-means++')
            clst.fit(X)
            predicted_labels=clst.predict(X)
            ARIs_k.append(adjusted_rand_score(labels_true,predicted_labels))
            Distances_k.append(clst.inertia_)

            clst=cluster.KMeans(n_init=num,init='random')
            clst.fit(X)
            predicted_labels=clst.predict(X)
            ARIs_r.append(adjusted_rand_score(labels_true,predicted_labels))
            Distances_r.append(clst.inertia_)

    ax=fig.add_subplot(1,2,1)
    ax.plot(nums,ARIs_k,marker="+",label="k-means++")
    ax.plot(nums,ARIs_r,marker="+",label="random")
    ax.set_xlabel("n_init")
    ax.set_ylabel("ARI")
    ax.set_ylim(0,1)
    ax.legend(loc='best')
    ax=fig.add_subplot(1,2,2)
    ax.plot(nums,Distances_k,marker='o',label="k-means++")
    ax.plot(nums,Distances_r,marker='o',label="random")
    ax.set_xlabel("n_init")
    ax.set_ylabel("inertia_")
    ax.legend(loc='best')

    fig.suptitle("KMeans")
    plt.show()
    
test_Kmeans_n_init(X,labels_true) #  调用 test_Kmeans_n_init 函数