机器学习实战之K-Means算法

test10.py

#-*- coding:utf-8

import sys
sys.path.append("kMeans.py") import kMeans
from numpy import * # datMat = mat(kMeans.loadDataSet('testSet.txt'))
# mindata = min(datMat[:, 0])
# print(mindata)
#
#
# ranCentK = kMeans.randCent(datMat, 2)
# print(ranCentK)
#
# dis = kMeans.distEclud(datMat[0], datMat[1])
# print(dis) # datMat3 = mat(kMeans.loadDataSet('testSet2.txt'))
# centList, myNewAssments = kMeans.biKmeans(datMat3, 3)
# print(centList) geoResults = kMeans.geoGrab('1 VA Center', 'Augusta, ME')
print(geoResults) res = geoResults['ResultSet']['Error']
print(res) print('over!!!')

kMeans.py

'''
Created on Feb 16, 2011
k Means Clustering for Ch10 of Machine Learning in Action
@author: Peter Harrington
'''
from numpy import * def loadDataSet(fileName): #general function to parse tab -delimited floats
dataMat = [] #assume last column is target value
fr = open(fileName)
for line in fr.readlines():
curLine = line.strip().split('\t')
fltLine = list(map(float,curLine)) #map all elements to float()
dataMat.append(fltLine)
return dataMat def distEclud(vecA, vecB):
return sqrt(sum(power(vecA - vecB, 2))) #la.norm(vecA-vecB) def randCent(dataSet, k):
n = shape(dataSet)[1]
centroids = mat(zeros((k,n)))#create centroid mat
for j in range(n):#create random cluster centers, within bounds of each dimension
minJ = min(dataSet[:,j])
rangeJ = float(max(dataSet[:,j]) - minJ)
centroids[:,j] = mat(minJ + rangeJ * random.rand(k,1))
return centroids def kMeans(dataSet, k, distMeas=distEclud, createCent=randCent):
m = shape(dataSet)[0]
clusterAssment = mat(zeros((m,2)))#create mat to assign data points
#to a centroid, also holds SE of each point
centroids = createCent(dataSet, k)
clusterChanged = True
while clusterChanged:
clusterChanged = False
for i in range(m):#for each data point assign it to the closest centroid
minDist = inf; minIndex = -1
for j in range(k):
distJI = distMeas(centroids[j,:],dataSet[i,:])
if distJI < minDist:
minDist = distJI; minIndex = j
if clusterAssment[i,0] != minIndex: clusterChanged = True
clusterAssment[i,:] = minIndex,minDist**2
print(centroids)
for cent in range(k):#recalculate centroids
ptsInClust = dataSet[nonzero(clusterAssment[:,0].A==cent)[0]]#get all the point in this cluster
centroids[cent,:] = mean(ptsInClust, axis=0) #assign centroid to mean
return centroids, clusterAssment def biKmeans(dataSet, k, distMeas=distEclud):
m = shape(dataSet)[0]
clusterAssment = mat(zeros((m,2)))
centroid0 = mean(dataSet, axis=0).tolist()[0]
centList =[centroid0] #create a list with one centroid
for j in range(m):#calc initial Error
clusterAssment[j,1] = distMeas(mat(centroid0), dataSet[j,:])**2
while (len(centList) < k):
lowestSSE = inf
for i in range(len(centList)):
ptsInCurrCluster = dataSet[nonzero(clusterAssment[:,0].A==i)[0],:]#get the data points currently in cluster i
centroidMat, splitClustAss = kMeans(ptsInCurrCluster, 2, distMeas)
sseSplit = sum(splitClustAss[:,1])#compare the SSE to the currrent minimum
sseNotSplit = sum(clusterAssment[nonzero(clusterAssment[:,0].A!=i)[0],1])
print("sseSplit, and notSplit: ",sseSplit,sseNotSplit)
if (sseSplit + sseNotSplit) < lowestSSE:
bestCentToSplit = i
bestNewCents = centroidMat
bestClustAss = splitClustAss.copy()
lowestSSE = sseSplit + sseNotSplit
bestClustAss[nonzero(bestClustAss[:,0].A == 1)[0],0] = len(centList) #change 1 to 3,4, or whatever
bestClustAss[nonzero(bestClustAss[:,0].A == 0)[0],0] = bestCentToSplit
print('the bestCentToSplit is: ',bestCentToSplit)
print('the len of bestClustAss is: ', len(bestClustAss))
centList[bestCentToSplit] = bestNewCents[0,:].tolist()[0]#replace a centroid with two best centroids
centList.append(bestNewCents[1,:].tolist()[0])
clusterAssment[nonzero(clusterAssment[:,0].A == bestCentToSplit)[0],:]= bestClustAss#reassign new clusters, and SSE
return mat(centList), clusterAssment import urllib import json
def geoGrab(stAddress, city):
apiStem = 'http://where.yahooapis.com/geocode?' #create a dict and constants for the goecoder
params = {}
params['flags'] = 'J'#JSON return type
params['appid'] = 'aaa0VN6k'
params['location'] = '%s %s' % (stAddress, city)
url_params = urllib.parse.urlencode(params)
yahooApi = apiStem + url_params #print url_params
print(yahooApi)
c = urllib.request.urlopen(yahooApi)
return json.loads(c.read()) from time import sleep
def massPlaceFind(fileName):
fw = open('places.txt', 'w')
for line in open(fileName).readlines():
line = line.strip()
lineArr = line.split('\t')
retDict = geoGrab(lineArr[1], lineArr[2])
if retDict['ResultSet']['Error'] == 0:
lat = float(retDict['ResultSet']['Results'][0]['latitude'])
lng = float(retDict['ResultSet']['Results'][0]['longitude'])
print("%s\t%f\t%f" % (lineArr[0], lat, lng))
fw.write('%s\t%f\t%f\n' % (line, lat, lng))
else: print("error fetching")
sleep(1)
fw.close() def distSLC(vecA, vecB):#Spherical Law of Cosines
a = sin(vecA[0,1]*pi/180) * sin(vecB[0,1]*pi/180)
b = cos(vecA[0,1]*pi/180) * cos(vecB[0,1]*pi/180) * cos(pi * (vecB[0,0]-vecA[0,0]) /180)
return arccos(a + b)*6371.0 #pi is imported with numpy import matplotlib
import matplotlib.pyplot as plt
def clusterClubs(numClust=5):
datList = []
for line in open('places.txt').readlines():
lineArr = line.split('\t')
datList.append([float(lineArr[4]), float(lineArr[3])])
datMat = mat(datList)
myCentroids, clustAssing = biKmeans(datMat, numClust, distMeas=distSLC)
fig = plt.figure()
rect=[0.1,0.1,0.8,0.8]
scatterMarkers=['s', 'o', '^', '', 'p', 'd', 'v', 'h', '>', '<']
axprops = dict(xticks=[], yticks=[])
ax0=fig.add_axes(rect, label='ax0', **axprops)
imgP = plt.imread('Portland.png')
ax0.imshow(imgP)
ax1=fig.add_axes(rect, label='ax1', frameon=False)
for i in range(numClust):
ptsInCurrCluster = datMat[nonzero(clustAssing[:,0].A==i)[0],:]
markerStyle = scatterMarkers[i % len(scatterMarkers)]
ax1.scatter(ptsInCurrCluster[:,0].flatten().A[0], ptsInCurrCluster[:,1].flatten().A[0], marker=markerStyle, s=90)
ax1.scatter(myCentroids[:,0].flatten().A[0], myCentroids[:,1].flatten().A[0], marker='+', s=300)
plt.show()

机器学习10—K-均值聚类学习笔记的更多相关文章

  1. 机器学习实战---K均值聚类算法

    一:一般K均值聚类算法实现 (一)导入数据 import numpy as np import matplotlib.pyplot as plt def loadDataSet(filename): ...

  2. 机器学习之K均值聚类

      聚类的核心概念是相似度或距离,有很多相似度或距离的方法,比如欧式距离.马氏距离.相关系数.余弦定理.层次聚类和K均值聚类等 1. K均值聚类思想   K均值聚类的基本思想是,通过迭代的方法寻找K个 ...

  3. 100天搞定机器学习|day44 k均值聚类数学推导与python实现

    [如何正确使用「K均值聚类」? 1.k均值聚类模型 给定样本,每个样本都是m为特征向量,模型目标是将n个样本分到k个不停的类或簇中,每个样本到其所属类的中心的距离最小,每个样本只能属于一个类.用C表示 ...

  4. 机器学习2—K近邻算法学习笔记

    Python3.6.3下修改代码中def classify0(inX,dataSet,labels,k)函数的classCount.iteritems()为classCount.items(),另外p ...

  5. 机器学习算法与Python实践之(六)二分k均值聚类

    http://blog.csdn.net/zouxy09/article/details/17590137 机器学习算法与Python实践之(六)二分k均值聚类 zouxy09@qq.com http ...

  6. 机器学习之路:python k均值聚类 KMeans 手写数字

    python3 学习使用api 使用了网上的数据集,我把他下载到了本地 可以到我的git中下载数据集: https://github.com/linyi0604/MachineLearning 代码: ...

  7. 机器学习实战5:k-means聚类:二分k均值聚类+地理位置聚簇实例

    k-均值聚类是非监督学习的一种,输入必须指定聚簇中心个数k.k均值是基于相似度的聚类,为没有标签的一簇实例分为一类. 一 经典的k-均值聚类 思路: 1 随机创建k个质心(k必须指定,二维的很容易确定 ...

  8. 探索sklearn | K均值聚类

    1 K均值聚类 K均值聚类是一种非监督机器学习算法,只需要输入样本的特征 ,而无需标记. K均值聚类首先需要随机初始化K个聚类中心,然后遍历每一个样本,将样本归类到最近的一个聚类中,一个聚类中样本特征 ...

  9. 5-Spark高级数据分析-第五章 基于K均值聚类的网络流量异常检测

    据我们所知,有‘已知的已知’,有些事,我们知道我们知道:我们也知道,有 ‘已知的未知’,也就是说,有些事,我们现在知道我们不知道.但是,同样存在‘不知的不知’——有些事,我们不知道我们不知道. 上一章 ...

随机推荐

  1. adb 查看android手机中应用的包名和安装位置

    1. 查看是否连接手机 adb devices 2. 进入指定的device的shell adb shell 或者 adb -s ********* shell 3. adb 查看所有安装的包 pm ...

  2. iOS 获取当前经纬度

    一般说来LBS功能一般分为两块:一块是地理定位,就是获取当前精度.纬度和地理位置的功能,这一部分功能主要用到CoreLocation.Frameworks.一部分就是显示地图信息.丰富地图内容等,这一 ...

  3. 前端福利:一套UI框架

    阅读目录 背景 预览效果 表单组件 普通文本框 多行文本框 复选框 切换滑块 单选框 下拉选择框 数字输入框 时间选择 文件选择 显示文本 按钮 开源地址 背景 目前市场上有很多表单美化的UI,做的都 ...

  4. 【ASP.NET】 中 system.math 函数使用

    1 /* 字段 */ 2 Math.E; //2.71828182845905 3 Math.PI; //3.14159265358979 4 5 /* 静态方法 */ 6 Math.Abs; //绝 ...

  5. codeigniter与swfupload完整解决方案

    转自:http://blog.sina.com.cn/s/blog_6d8dc8eb0100s4bv.html codeigniter(简称ci)有研究了一段时间了,看重的是ci的轻量,便捷,最近公司 ...

  6. 新人补钙系列教程之:AS 与 JS 相互通信

    比较常用的,AS 调用 JS private function callJS():void{ ExternalInterface.addCallback("callbackQQPay&quo ...

  7. MyEclipse导入Hibernate出现Path must include project and resource;/project name

    如图,在MyEclipse 2014以下版本中都没遇见这个问题. 在导入Hibernate框架的时候,可以说真的随缘,运气不好,明明配置全都没问题,还是连续几次失败,这个时候除了烧高香拜拜,也只能靠百 ...

  8. hadoop2.4 支持snappy

    我们hadoop2,4集群默认不支持snappy压缩,可是近期有业务方说他们的部分数据是snappy压缩的(这部分数据由另外一个集群提供给他们时就是snappy压缩格式的)想迁移到到我们集群上面来进行 ...

  9. POJ 2029 Get Many Persimmon Trees (二维树状数组)

    Get Many Persimmon Trees Time Limit:1000MS    Memory Limit:30000KB    64bit IO Format:%I64d & %I ...

  10. Linux——vi命令的使用

    vi的基本操作 a) 进入vi 在系统提示符号输入vi及文件名称后,就进入vi全屏幕编辑画面: $ vi myfile 不过有一点要特别注意,就是您进入vi之后,是处于「命令行模式(command m ...