# coding=utf-8from numpy import *
import matplotlib.pyplot as pltfrom matplotlib.pyplot import *
from collections import defaultdict
import randomclass DbScan(object):def show(self,data,color=None):if not color:color='green'group=self.createDataSet()fig = plt.figure(1)axes = fig.add_subplot(111)axes.scatter(group[:, 0], group[:, 1], s=40, c='red')axes.scatter(data[:, 0], data[:, 1], s=50, c=color)plt.show()def createDataSet(self):group = [[1.0, 1.1], [1.0, 1.0],[0, 0], [0, 0.1],[2, 1.0], [2.1, 0.9],[0.3, 0.0], [1.1, 0.9],[2.2, 1.0], [2.1, 0.8],[3.3, 3.5], [2.1, 0.9],[2, 1.0], [2.1, 0.9],[3.5, 3.4], [3.6, 3.5]]return groupdef dist(self,p1, p2):return ((p1[0]-p2[0])**2+ (p1[1]-p2[1])**2)**(0.5)def db_scan(self):all_points = self.createDataSet()E = 0.3minPts = 2# find out the core pointsother_points = []core_points = []  # 核心点集合plotted_points = []  # 使用到的点   非噪声点for point in all_points:point.append(0)  # 在点的后面加上第三维度类别，初始类别为 0total = 0for otherPoint in all_points:distance = self.dist(otherPoint, point)  # 遍历其他点并计算距离if distance <= E:total += 1  # 计算当前点的e领域内点的个数if total > minPts:core_points.append(point)  # 是核心点，添加到列表coreplotted_points.append(point)  # 将核心点添加到列表 plottedelse:other_points.append(point)  # 不是核心点，添加到其他点# find border pointsborder_points = []for core in core_points:  # 遍历核心点for other in other_points:  # 遍历非核心点if self.dist(core, other) <= E:border_points.append(other)  # 添加到非噪声点集合plotted_points.append(other)  # 添加到非噪声点集合# implement the algorithmcluster_label = 0for point in core_points:  # 遍历核心点if point[2] == 0:  # 核心点所属类别为0cluster_label += 1point[2] = cluster_label  # 每遍历一个核心点，类别栏就加1for point2 in plotted_points:  # 遍历非噪声点distance = self.dist(point2, point)if point2[2] == 0 and distance <= E:  # 非噪声点的类别为0 并且与核心点的距离小于epoint2[2] = point[2]  # 将核心点的类别赋值给非噪声点# print point, point2# after the points are asssigned correnponding labels, we group themcluster_list = defaultdict(lambda: [[], []])  # 定义一个字典，默认值是包含两个列表的列表for point in plotted_points:cluster_list[point[2]][0].append(point[0])  # 类别为键，值得第一个列表是非噪声点的xcluster_list[point[2]][1].append(point[1])  # 类别为键，值得第一个列表是非噪声点的ymarkers = ['+', '*', '.', 'd', '^', 'v', '>', '<', 'p']## plotting the clustersi = 0print cluster_listfor value in cluster_list:cluster = cluster_list[value]plot(cluster[0], cluster[1], markers[i])i = i % 10 + 1# plot the noise points as wellnoise_points = []for point in all_points:if not point in core_points and not point in border_points:noise_points.append(point)noisex = []noisey = []for point in noise_points:noisex.append(point[0])noisey.append(point[1])plot(noisex, noisey, "x")# /## title(str(len(cluster_list)) + " clusters created with E =" + str(E) + " Min Points=" + str(#     minPts) + " total points=" + str(len(all_points)) + " noise Points = " + str(len(noise_points)))axis((-1, 5, -1, 5))show()def start(self):self.db_scan()p=DbScan()
p.start()