#-*- coding:utf-8 -*-

import math

import numpy as np

import pylab as pl

 #数据集：每三个是一组分别是西瓜的编号，密度，含糖量

data = """

1,0.697,0.46,2,0.774,0.376,3,0.634,0.264,4,0.608,0.318,5,0.556,0.215,

6,0.403,0.237,7,0.481,0.149,8,0.437,0.211,9,0.666,0.091,10,0.243,0.267,

11,0.245,0.057,12,0.343,0.099,13,0.639,0.161,14,0.657,0.198,15,0.36,0.37,

16,0.593,0.042,17,0.719,0.103,18,0.359,0.188,19,0.339,0.241,20,0.282,0.257,

21,0.748,0.232,22,0.714,0.346,23,0.483,0.312,24,0.478,0.437,25,0.525,0.369,

26,0.751,0.489,27,0.532,0.472,28,0.473,0.376,29,0.725,0.445,30,0.446,0.459"""

#数据处理 dataset是30个样本（密度，含糖量）的列表

a = data.split(',')

dataset = [(float(a[i]), float(a[i+1])) for i in range(1, len(a)-1, 3)]

#计算欧几里得距离,a,b分别为两个元组

def dist(a, b):

    return math.sqrt(math.pow(a[0]-b[0], 2)+math.pow(a[1]-b[1], 2))

#算法模型

def DBSCAN(D, e, Minpts):

    #初始化核心对象集合T,聚类个数k,聚类集合C, 未访问集合P,

    T = set(); k = 0; C = []; P = set(D)

    for d in D:

        if len([ i for i in D if dist(d, i) <= e]) >= Minpts:

            T.add(d)

    #开始聚类

    while len(T):

        P_old = P

        o = list(T)[np.random.randint(0, len(T))]

        P = P - set(o)

        Q = []; Q.append(o)

        while len(Q):

            q = Q[0]

            Nq = [i for i in D if dist(q, i) <= e]

            if len(Nq) >= Minpts:

                S = P & set(Nq)

                Q += (list(S))

                P = P - S

            Q.remove(q)

        k += 1

        Ck = list(P_old - P)

        T = T - set(Ck)

        C.append(Ck)

    return C

#画图

def draw(C):

    colValue = ['r', 'y', 'g', 'b', 'c', 'k', 'm']

    for i in range(len(C)):

        coo_X = []    #x坐标列表

        coo_Y = []    #y坐标列表

        for j in range(len(C[i])):

            coo_X.append(C[i][j][0])

            coo_Y.append(C[i][j][1])

        pl.scatter(coo_X, coo_Y, marker='x', color=colValue[i%len(colValue)], label=i)

    pl.legend(loc='upper right')

    pl.show()

C = DBSCAN(dataset, 0.11, 5)

draw(C)

1.初始化核心对象集合T为空，遍历一遍样本集D中所有的样本，计算每个样本点的ε-邻域中包含样本的个数，如果个数大于等于MinPts，则将该样本点加入到核心对象集合中。初始化聚类簇数k = 0， 初始化未访问样本集和为P = D。

2.当T集合中存在样本时执行如下步骤：

2.1记录当前未访问集合P_old = P

2.2从T中随机选一个核心对象o,初始化一个队列Q = [o]

2.3P = P-o(从T中删除o)

2.4当Q中存在样本时执行：

2.4.1取出队列中的首个样本q

2.4.2计算q的ε-邻域中包含样本的个数，如果大于等于MinPts，则令S为q的ε-邻域与P的交集，

Q = Q+S, P = P-S

2.5 k = k + 1,生成聚类簇为Ck = P_old - P

2.6 T = T - Ck

3.划分为C= {C1, C2, ……, Ck}