机器学习-python实现DBSCAN

本文主要介绍的是DBSCAN.是一种著名的密度聚类算法。其原理这里就不详细介绍了，详细请看周志华西瓜书P211-P214。这里主要介绍它的python代码。

import xlrd
import numpy as np
import numpy.random as random
import math 
import copy
import Queue
from random import choice
import matplotlib.pyplot as plt
from collections import Counter 
class DataSet():
    def __init__(self):
        self.DataMat=[]
        self.DataNum=0
        self.FinalSub=[]
        
        print "Creat a Class"
def ReadData(ob):
    data=xlrd.open_workbook("kmeans.xlsx")
    table=data.sheets()[0]
    for i in range(table.nrows-1):
        ob.DataMat.append(table.row_values(i+1))
    ob.DataMat=np.array(ob.DataMat)
    ob.DataNum=np.shape(ob.DataMat)[0]
    print "Your Data Mat is \n",ob.DataMat
    print "Your Data Set Num is",ob.DataNum
def DrawPicture(ob):
    plt.figure('test')
    Signal=['xb','xr','xg','xy','xm','xk','xw','xc']
    for x in range(len(ob.FinalSub)):
        for y in list(ob.FinalSub[x]):
            plt.plot(ob.DataMat[y][0],ob.DataMat[y][1],Signal[x]) 
    plt.savefig("My.jpg")
def CalculataSeed(ob,epsen,MinPts):
    dist=0
    epsenNum=0
    epsenSet=[]
    SeedSet=set()
     
    for i in range(ob.DataNum):
        epsenSet.append(set([-1]))
        for j in range(ob.DataNum):
            if i!=j:
                dist=round(np.linalg.norm(ob.DataMat[i]-ob.DataMat[j]),3)
                if dist<=epsen :
                    epsenNum+=1
                    epsenSet[i].add(j)
            else :
                continue
        if len(epsenSet[i])>=MinPts:
            SeedSet.add(i)
    for i in range(len(epsenSet)):
        print epsenSet[i]
    print "The core seed set is ",SeedSet
    k=0
    NoViSet=set(range(ob.DataNum))
    print "NoviSet is ",NoViSet
    Olde_NoviSet=set()
    Q=Queue.Queue()
    randomStep=0
    deta=set()
    Qnum=0
    while SeedSet != set() :
        Olde_NoviSet=copy.deepcopy(NoViSet) 
        randomStep=choice(list(SeedSet))
        Q.put(randomStep)
        print "random seed is ",randomStep
        NoViSet=NoViSet-set([randomStep])
        while Q.empty() != True:
            Qnum=Q.get()
            if len(epsenSet[Qnum]) >= MinPts :
                deta=epsenSet[Qnum]&NoViSet
                NoViSet=NoViSet-deta
                while deta != set():
                    Q.put(deta.pop())
        k+=1
        ob.FinalSub.append(Olde_NoviSet-NoViSet)
        print "Class is", ob.FinalSub[k-1]
        SeedSet=SeedSet-ob.FinalSub[k-1]   
        print "SeedSet is ",SeedSet		
        print "NoviSet is ",NoViSet
    ob.FinalSub.append(NoViSet)    
def main():
    A=DataSet()
    ReadData(A)
    CalculataSeed(A,0.11,5)
    DrawPicture(A)
main()

数据如下：把它存放在excel表格中。

density	sweet
0.697	0.46
0.774	0.376
0.634	0.264
0.608	0.318
0.556	0.215
0.403	0.237
0.481	0.149
0.437	0.211
0.666	0.091
0.243	0.267
0.245	0.057
0.343	0.099
0.639	0.161
0.657	0.198
0.36	0.37
0.593	0.042
0.719	0.103
0.359	0.188
0.339	0.241
0.282	0.257
0.748	0.232
0.714	0.346
0.483	0.312
0.478	0.437
0.525	0.369
0.751	0.489
0.532	0.472
0.473	0.376
0.725	0.445
0.446	0.459

得到结果如图：