python 聚类与EM算法模型

其他 2018-08-06 11:25:11 阅读次数: 0 
运行环境：win10 64位 py 3.6 pycharm 2018.1.1
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets.samples_generator import make_blobs
from sklearn import cluster
from sklearn.metrics import adjusted_rand_score
from sklearn import mixture

#产生测试数据
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
#观察样本点分布
def plot_data(*data):
    X, labels_true = data
    labels = np.unique(labels_true)
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    colors = 'rgbyckm'
    for i, label in enumerate(labels):
        position = labels_true == label
        ax.scatter(X[position,0],X[position,1],label='cluster %d'%label,color=colors[i%len(colors)])
    ax.legend(loc='best',framealpha=0.5)
    ax.set_xlabel('x[0]')
    ax.set_ylabel('x[1]')
    ax.set_title('data')
    plt.show()

X,labels_true = create_data([[1,1],[2,2],[1,2],[10,20]],1000,0.5)
plot_data(X,labels_true)

这里写图片描述

#K均值聚类（KMeans）
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_)

centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_Kmeans(X, labels_true)
#考察簇的数量的影响
def test_Kmeans_nclusters(*data):
    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_)
    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()
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_Kmeans_nclusters(X, labels_true)

这里写图片描述

#考察k均值算法运行的次数和选择初始中心向量策略的影响
def test_Kmeans_n_init(*data):
    X, labels_true = data
    nums = range(1,50)
    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.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()

这里写图片描述

#密度聚类
def test_DBSCAN(*data):
    X, labels_true = data
    clst = cluster.DBSCAN()
    predicted_labels = clst.fit_predict(X)
    print("ARI:%s"% adjusted_rand_score(labels_true, predicted_labels))
    print("Core sample num:%d"%len(clst.core_sample_indices_))
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_DBSCAN(X, labels_true)
#考察参数的影响
def test_DBSCAN_epsilon(*data):
    X,labels_true = data
    epsilons = np.logspace(-1, 1.5)
    ARIs = []
    Core_nums = []
    for epsilon in epsilons:
        clst = cluster.DBSCAN(eps=epsilon)
        predicted_labels = clst.fit_predict(X)
        ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
        Core_nums.append(len(clst.core_sample_indices_))
    #绘图
    fig = plt.figure()
    ax = fig.add_subplot(1,2,1)
    ax.plot(epsilons,ARIs,marker='+')
    ax.set_xscale('log')
    ax.set_xlabel(r'$\epsilon$')
    ax.set_ylim(0, 1)
    ax.set_ylabel('ARI')

    ax = fig.add_subplot(1, 2, 2)
    ax.plot(epsilons, Core_nums, marker='o')
    ax.set_xscale('log')
    ax.set_xlabel(r'$\epsilon$')
    ax.set_ylabel('Core_Nums')
    fig.suptitle('DBSCAN')
    plt.show()
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_DBSCAN_epsilon(X, labels_true)

这里写图片描述

#考察MinPts参数的影响
def test_DBSCAN_min_samples(*data):
    X, labels_true = data
    min_samples = range(1,100)
    ARIs = []
    Core_nums = []
    for num in min_samples:
        clst = cluster.DBSCAN(min_samples=num)
        predicted_labels = clst.fit_predict(X)
        ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
        Core_nums.append(len(clst.core_sample_indices_))
        #绘图
    fig = plt.figure()
    ax = fig.add_subplot(1,2,1)
    ax.plot(min_samples,ARIs,marker='+')
    ax.set_xlabel('min_samples')
    ax.set_ylim(0, 1)
    ax.set_ylabel('ARI')

    ax = fig.add_subplot(1,2,2)
    ax.plot(min_samples, Core_nums,marker='o')
    ax.set_xlabel('min_samples')
    ax.set_ylabel("Core_Nums")

    fig.suptitle("DBSCAN")
    plt.show()
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_DBSCAN_min_samples(X, labels_true)

这里写图片描述

#层次聚类
def test_AgglomerativeClustering(*data):
    X, labels_true = data
    clst = cluster.AgglomerativeClustering()
    predicted_labels = clst.fit_predict(X)
    print("ARI:%s"%adjusted_rand_score(labels_true,predicted_labels))
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_AgglomerativeClustering(X, labels_true)
# 考察簇的数量对于聚类效果的影响
def test_AgglomerativeClustering_nclusters(*data):
    X, labels_true = data
    nums = range(1, 50)
    ARIs = []
    for num in nums:
        clst = cluster.AgglomerativeClustering(n_clusters=num)
        predicted_labels = clst.fit_predict(X)
        ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
    #绘图
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    ax.plot(nums,ARIs,marker='+')
    ax.set_xlabel("n_clusters")
    ax.set_ylabel('ARI')
    fig.suptitle("AgglomerativeClustering")
    plt.show()
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_AgglomerativeClustering_nclusters(X, labels_true)

这里写图片描述

#然后在考察链接方式的影响，给出测试函数
def test_AgglomerativeClustering_linkage(*data):
    X, labels_true = data
    nums = range(1, 50)
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)

    linkages = ['ward','complete','average']
    markers = '+o*'
    for i, linkage in enumerate(linkages):
        ARIs = []
        for num in nums:
            clst = cluster.AgglomerativeClustering(n_clusters=num,linkage=linkage)
            predicted_labels = clst.fit_predict(X)
            ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
        ax.plot(nums,ARIs,marker = markers[i],label='linkage:%s'%linkage)
    ax.set_xlabel('n_clusters')
    ax.set_ylabel('ARI')
    ax.legend(loc='best')
    fig.suptitle('AgglomerativeClustering')
    plt.show()
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_AgglomerativeClustering_linkage(X, labels_true)

这里写图片描述

#混合高斯模型
def test_GMM(*data):
    X, labels_true = data
    clst = mixture.GaussianMixture()
    clst_m = clst.fit(X)
    predicted_labels = clst.predict(X)
    print("ARI:%s" % adjusted_rand_score(labels_true, predicted_labels))
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_GMM(X, labels_true)
#考察簇的数量对n_components对聚类效果的影响
def test_GMM_n_components(*data):
    X, labels_true = data
    nums = range(1, 50)
    ARIs = []
    for num in nums:
        clst = mixture.GaussianMixture(n_components=num)
        clst.fit(X)
        predicted_labels = clst.predict(X)
        ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
    #绘图
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    ax.plot(nums,ARIs,marker='+')
    ax.set_xlabel('n_components')
    ax.set_ylabel('ARI')
    fig.suptitle('GMM')
    plt.show()
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_GMM_n_components(X, labels_true)
#考察簇的数量对n_components对聚类效果的影响
def test_GMM_n_components(*data):
    X, labels_true = data
    nums = range(1, 50)
    ARIs = []
    for num in nums:
        clst = mixture.GaussianMixture(n_components=num)
        clst.fit(X)
        predicted_labels = clst.predict(X)
        ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
    #绘图
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    ax.plot(nums,ARIs,marker='+')
    ax.set_xlabel('n_components')
    ax.set_ylabel('ARI')
    fig.suptitle('GMM')
    plt.show()
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_GMM_n_components(X, labels_true)

这里写图片描述

#最后考察协方差类型的影响，给出测试函数
def test_GMM_cov_type(*data):
    X, labels_true = data
    nums = range(1, 50)
    cov_types = ['spherical','tied','diag','full']
    markers = '+o*s'
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    for i,cov_type in enumerate(cov_types):
        ARIs = []
        for num in nums:
            clst = mixture.GaussianMixture(n_components=num,covariance_type=cov_type)
            clst.fit(X)
            predicted_labels = clst.predict(X)
            ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
        ax.plot(nums,ARIs,marker = markers[i],label='covariance_type:%s'%cov_type)
    ax.set_xlabel("n_components")
    ax.legend(loc='best')
    ax.set_ylabel("ARI")
    fig.suptitle('GMM')
    plt.show()
centers = [[1,1],[2,2],[1,2],[10,20]]
X, labels_true = create_data(centers,1000,0.5)
test_GMM_cov_type(X, labels_true)

这里写图片描述

猜你喜欢

转载自blog.csdn.net/dingming001/article/details/80957097
今日推荐
NetBSD 禁止提交由 AI 生成的代码
Apache Doris 2.0.10 版本正式发布！
开源日报 | 大模型开战；大模型独角兽被曝卖身；周鸿祎建议谷歌开源所有产品；最大开源AI社区提供1000万美元共享GPU
开源日报 | Chrome内置Gemini的意义不在于Gemini；中国AI追随之路的五大误区；ECharts创始人“下海”养鱼；谷歌I/O开发者大会什么都有，只是没有惊喜
微软回应中国区AI团队“打包赴美”传闻
基于大语言模型的开源知识库问答系统 MaxKB GitHub Star 数量突破 5,000 个！
周排行
女程序员是这样被恶搞的
B/S 和 C/S 的优缺点
vector一直申请会怎样？
座头鲸识别比赛(Humpback Whale Identification)总结
Linux高性能服务器编程——I/O复用 select
Mysql连接数据库（当包使用）
通过URI获取的文件路径为null的解决方法
1022-Primes on Interval(素数筛选+二分查找) ZCMU
Python出现： TypeError: expected string or buffer
bzoj2434: [Noi2011]阿狸的打字机 ac自动机+树状数组
每日归档
更多
2024-05-18(4)
2024-05-17(34)
2024-05-16(6)
2024-05-15(24)
2024-05-14(0)
2024-05-13(18)
2024-05-12(0)
2024-05-11(38)
2024-05-10(38)
2024-05-09(35)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022