python进行聚类(scikit-lean、scipy)

用于聚类的数据集

%matplotlib inlineimport scipy.io as sioimport matplotlib.pyplot as plt'''各种聚类数据'''#two_clusterdef two_cluster():    two_cluster=u'cluster_data/two_cluster.mat'    two_cluster=sio.loadmat(two_cluster)['X'].T    data = two_cluster    return data#three_clusterdef three_cluster():    path=u'cluster_data/three_cluster.mat'    three_cluster=sio.loadmat(path)['X'].T    data = three_cluster        return data#five_clusterdef five_cluster():    path=u'cluster_data/five_cluster.mat'    five_cluster=sio.loadmat(path)    x=five_cluster['x'] #得到的数据为二行n列    y=five_cluster['y'] #到的数据为一行n列    data = np.vstack((x,y)).T #先垂直合并，而后转置    #data = np.array([x[0,:],x[1,:],y[0,:]]).T #list与array互换    return data#spiraldef spiral():    path=u'cluster_data/spiral.mat'    spiral=sio.loadmat(path)['spiral']    spiral = spiral[0::3,:] #每隔3行取一个数据    data = spiral    data = np.array([data[:,1],data[:,2],data[:,0]]).T #list与array互换    return data#spiral_unbalancedef spiral_unbalance():    path=u'cluster_data/spiral_unbalance.mat'    spiral_unbalance=sio.loadmat(path)['spiral_unbalance']    spiral_unbalance = spiral_unbalance[0::3,:] #每隔3行取一个数据    data = spiral_unbalance    data = np.array([data[:,1],data[:,2],data[:,0]]).T #list与array互换    return data#ThreeCirclesdef ThreeCircles():    path=u'cluster_data/ThreeCircles.mat'    ThreeCircles=sio.loadmat(path)['ThreeCircles']    ThreeCircles = ThreeCircles[0::3,:] #每隔3行取一个数据    data = ThreeCircles    data = np.array([data[:,1],data[:,2],data[:,0]]).T #list与array互换    return data#Twomoonsdef Twomoons():    path=u'cluster_data/Twomoons.mat'    Twomoons=sio.loadmat(path)['Twomoons']    Twomoons = Twomoons[0::3,:] #每隔3行取一个数据    data = Twomoons    data = np.array([data[:,1],data[:,2],data[:,0]]).T #list与array互换    plt.scatter(data[:,0],data[:,1],c=data[:,2])    return data#Twomoons1def Twomoons1():    path=u'cluster_data/Twomoons.mat'    Twomoons1=sio.loadmat(path)['Twomoons']    Twomoons1 = Twomoons1[0::3,:] #每隔3行取一个数据    data = Twomoons1    data = np.array([data[:,1],data[:,2],data[:,0]]).T #list与array互换    return datadef test():    print 'test'def show_all():    plt.figure(figsize=(16,8))    #动态调用方法    func_name_list = ['two_cluster','three_cluster','five_cluster','spiral','spiral_unbalance','ThreeCircles','Twomoons','Twomoons1']    for i in range(8):        data_list.append(eval(func_name_list[i])())    #动态画图    for i in range(8):        data = data_list[i]        plt.subplot(2,4,i+1)        #plt.figure()        plt.scatter(data[:,0],data[:,1],c=data[:,2])    data_list = []show_all()

使用scikit的kmeans进行聚类

%matplotlib inlineimport scipy.io as sio#matlab文件名  two_cluster=u'cluster_data/two_cluster.mat'data=sio.loadmat(two_cluster)print data

%matplotlib inlineimport matplotlib.pyplot as pltx = data['X']cValue = x[2]plt.scatter(x[0],x[1],c=cValue)

from sklearn import cluster, datasetsb = np.array(x).Tb = b[:,0:2]y_pred = cluster.KMeans(n_clusters=2, random_state=170).fit_predict(b)cValue = x[2]plt.scatter(x[0],x[1],c=y_pred)

数据集下载

scikit-learn教程

%matplotlib inlineimport scipy.io as sio#matlab文件名  two_cluster=u'cluster_data/spiral.mat'spiral=sio.loadmat(two_cluster)['spiral']spiral = spiral[0::3,:] #每隔3行取一个数据print len(spiral),len(spiral[0])cValue = spiral[:,0]print cValue.shapecolor = ['b','y']cValue = [color[int(i)] for i in list(cValue)]plt.scatter(spiral[:,1],spiral[:,2],c=cValue)

使用kmeans结果

from sklearn import cluster, datasetsy_pred = cluster.KMeans(n_clusters=2, random_state=170).fit_predict(spiral[:,1:3])plt.scatter(spiral[:,1],spiral[:,2],c=y_pred)

使用scipy进行聚类效果

# -*- coding: utf8 -*-%matplotlib inlineimport scipy.io as sioimport matplotlib.pyplot as pltimport scipy.cluster.hierarchy as hclusterfrom sklearn.cluster import AgglomerativeClusteringimport numpy.random as random  import numpy as np  import numpy.core.fromnumeric  def loadData():    #matlab文件名      two_cluster=u'cluster_data/spiral.mat'    spiral=sio.loadmat(two_cluster)['spiral']    spiral = spiral[0::3,:] #每隔3行取一个数据    print len(spiral),len(spiral[0])    cValue = spiral[:,0]    print cValue.shape    color = ['b','y']    cValue = [color[int(i)] for i in list(cValue)]    plt.scatter(spiral[:,1],spiral[:,2],c=cValue)def spiralSample():    plt.subplot(131)    plt.title(u'origal data')    plt.scatter(spiral[:,1],spiral[:,2],c=spiral[:,0])    #scipy进行聚类,默认depth=2（可得到两类），阈值t为距离阈值，设置criterion='maxclust',找到两类之间最小距离小于t的进行合并    #http://docs.scipy.org/doc/scipy/reference/generated/scipy.cluster.hierarchy.fcluster.html#scipy.cluster.hierarchy.fcluster    y_pred=hcluster.fclusterdata(spiral[:,1:3],criterion='maxclust',t=2)        plt.subplot(132)    plt.title(u'use scipy to hierarchy cluster')    plt.scatter(spiral[:,1],spiral[:,2],c=y_pred)    #scikit进行聚类    plt.subplot(133)    plt.title(u'use scikit to hierarchy cluster')    y_pred = AgglomerativeClustering(n_clusters=2, linkage='ward').fit_predict(spiral[:,1:3])        plt.scatter(spiral[:,1],spiral[:,2],c=y_pred)    plt.show()spiralSample()