本文实例讲述了Python聚类算法之基本K均值运算技巧。分享给大家供大家参考,具体如下:

基本K均值 :选择 K 个初始质心,其中 K 是用户指定的参数,即所期望的簇的个数。每次循环中,每个点被指派到最近的质心,指派到同一个质心的点集构成一个。然后,根据指派到簇的点,更新每个簇的质心。重复指派和更新操作,直到质心不发生明显的变化。

# scoding=utf-8
import pylab as pl
points = [[int(eachpoint.split("#")[0]), int(eachpoint.split("#")[1])] for eachpoint in open("points","r")]
# 指定三个初始质心
currentCenter1 = [20,190]; currentCenter2 = [120,90]; currentCenter3 = [170,140]
pl.plot([currentCenter1[0]], [currentCenter1[1]],'ok')
pl.plot([currentCenter2[0]], [currentCenter2[1]],'ok')
pl.plot([currentCenter3[0]], [currentCenter3[1]],'ok')
# 记录每次迭代后每个簇的质心的更新轨迹
center1 = [currentCenter1]; center2 = [currentCenter2]; center3 = [currentCenter3]
# 三个簇
group1 = []; group2 = []; group3 = []
for runtime in range(50):
  group1 = []; group2 = []; group3 = []
  for eachpoint in points:
    # 计算每个点到三个质心的距离
    distance1 = pow(abs(eachpoint[0]-currentCenter1[0]),2) + pow(abs(eachpoint[1]-currentCenter1[1]),2)
    distance2 = pow(abs(eachpoint[0]-currentCenter2[0]),2) + pow(abs(eachpoint[1]-currentCenter2[1]),2)
    distance3 = pow(abs(eachpoint[0]-currentCenter3[0]),2) + pow(abs(eachpoint[1]-currentCenter3[1]),2)
    # 将该点指派到离它最近的质心所在的簇
    mindis = min(distance1,distance2,distance3)
    if(mindis == distance1):
      group1.append(eachpoint)
    elif(mindis == distance2):
      group2.append(eachpoint)
    else:
      group3.append(eachpoint)
  # 指派完所有的点后,更新每个簇的质心
  currentCenter1 = [sum([eachpoint[0] for eachpoint in group1])/len(group1),sum([eachpoint[1] for eachpoint in group1])/len(group1)]
  currentCenter2 = [sum([eachpoint[0] for eachpoint in group2])/len(group2),sum([eachpoint[1] for eachpoint in group2])/len(group2)]
  currentCenter3 = [sum([eachpoint[0] for eachpoint in group3])/len(group3),sum([eachpoint[1] for eachpoint in group3])/len(group3)]
  # 记录该次对质心的更新
  center1.append(currentCenter1)
  center2.append(currentCenter2)
  center3.append(currentCenter3)
# 打印所有的点,用颜色标识该点所属的簇
pl.plot([eachpoint[0] for eachpoint in group1], [eachpoint[1] for eachpoint in group1], 'or')
pl.plot([eachpoint[0] for eachpoint in group2], [eachpoint[1] for eachpoint in group2], 'oy')
pl.plot([eachpoint[0] for eachpoint in group3], [eachpoint[1] for eachpoint in group3], 'og')
# 打印每个簇的质心的更新轨迹
for center in [center1,center2,center3]:
  pl.plot([eachcenter[0] for eachcenter in center], [eachcenter[1] for eachcenter in center],'k')
pl.show()

运行效果截图如下:

Python聚类算法之基本K均值实例详解

希望本文所述对大家Python程序设计有所帮助。

华山资源网 Design By www.eoogi.com
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
华山资源网 Design By www.eoogi.com

稳了!魔兽国服回归的3条重磅消息!官宣时间再确认!

昨天有一位朋友在大神群里分享,自己亚服账号被封号之后居然弹出了国服的封号信息对话框。

这里面让他访问的是一个国服的战网网址,com.cn和后面的zh都非常明白地表明这就是国服战网。

而他在复制这个网址并且进行登录之后,确实是网易的网址,也就是我们熟悉的停服之后国服发布的暴雪游戏产品运营到期开放退款的说明。这是一件比较奇怪的事情,因为以前都没有出现这样的情况,现在突然提示跳转到国服战网的网址,是不是说明了简体中文客户端已经开始进行更新了呢?