import kMeans
'''
geoResults = kMeans.geoGrab('1 VA Center', 'Augusta, ME')
print geoResults
print geoResults['ResultSet']['Error']
print geoResults['ResultSet']['Results'][0]['longitude']
print geoResults['ResultSet']['Results'][0]['latitude']
kMeans.massPlaceFind('portlandClubs.txt')
'''
kMeans.clusterClubs(5)
def test2():
#kMeans.geoGrab('1 VA Center', 'Augusta, ME1')
#kMeans.testURLLib()
kMeans.clusterClubs(5)
'''
myCentroids, clustAssing = kMeans.kMeans(datMat, 4)
print
print
print myCentroids
print
print
print clustAssing
'''
#datMat3 = mat(kMeans.loadDataSet('testSet2.txt'))
#datMat3 = mat(kMeans.loadDataSet('baidu_poi.txt'))
#myCentroids, clustAssing = kMeans.kMeans(datMat3, 2)
#print myCentroids
#print
#print clustAssing
#centList, myNewAssessments = kMeans.biKmeans(datMat3, 3)
#print
#print
#print centList
#print
#print
#print myNewAssessments
kMeans.clusterClubs(9)
min(datMat[:,0])
max(datMat[:,0])
min(datMat[:,1])
max(datMat[:,1])
kMeans.randCent(datMat,2) # 看一下初始化的质心是否在取值范围内
kMeans.distEclud(datMat[0],datMat[1])
# 在实际数据上看下K-means
reload(kMeans)
datMat = np.mat(kMeans.loadDataSet('testSet.txt'))
myCentroids,clustAssing = kMeans.kMeans(datMat,4) # 不一定是全局最优解
# 二分k-means
reload(kMeans)
datMat3 = np.mat(kMeans.loadDataSet('testSet2.txt'))
centList,myNewAssments = kMeans.biKmeans(datMat3,3) # 其实依然无法保证全局最优解，只能是局部最优解
centList
myNewAssments
# 利用二分k-means在图上画出簇
reload(kMeans)
kMeans.clusterClubs(4)
# This Python file uses the following encoding: utf-8
import os, sys
import kMeans
from numpy import *
reload(kMeans)
'''
datMat=mat(kMeans.loadDataSet("C:\Users\YAN\Desktop\Kmeans/testSet.txt"))
print (kMeans.randCent(datMat,2))
print (kMeans.distEclud(datMat[0],datMat[1]))
myCentroids,clustAssing=kMeans.kMeans(datMat,4)
print ("the centroids are:",myCentroids)
print ("the assignment is:",clustAssing)
'''
'''
#-----------二分法Kmeans-------------#
datMat3=mat(kMeans.loadDataSet("C:\Users\YAN\Desktop\Kmeans/testSet2.txt"))
centList,myNewAssments=kMeans.biKmeans(datMat3,3)
print [centList[0],centList[1],centList[2]]
'''
#geoResults=kMeans.geoGrab('1 VA Center','Augusta, ME')
kMeans.clusterClubs(5)
print "datMat:", datMat
print "min(datMat[:,0]):", min(datMat[:, 0])
print "min(datMat[:,1]):", min(datMat[:, 1])
print "max(datMat[:,0]):", max(datMat[:, 0])
print "max(datMat[:,1]):", max(datMat[:, 1])
print "randCent(datMat,2):", kMeans.randCent(datMat, 2)
print "distEclud( datMat[ 0], datMat[ 1]):", kMeans.distEclud(
datMat[0], datMat[1])
print "myCentroids:", myCentroids
print "clustAssing:", clustAssing
print ":",
print ":",
#10.3 二分k均值算法
datMat3 = mat(kMeans.loadDataSet(homedir + 'testSet2.txt'))
centList, myNewAssments = kMeans.biKmeans(datMat3, 3)
print "datMat3:", datMat3
print "centList:", centList
print "myNewAssments:", myNewAssments
#10.4.1 Yahoo!PlaceFinder API
# geoResults=kMeans.geoGrab('1 VA Center', 'Augusta, ME')
# print "geoResults:",geoResults
# print "geoResults['ResultSet']['Error']:",geoResults['ResultSet']['Error']
# print "geoResults['ResultSet']['Results'][0]['longitude']:",geoResults['ResultSet']['Results'][0]['longitude']
# print "kMeans.massPlaceFind(homedir+'portlandClubs.txt'):",kMeans.massPlaceFind(homedir+'portlandClubs.txt')
#10.4.2 对地理坐标进行聚类
print "kMeans.clusterClubs(5):", kMeans.clusterClubs(5)
import kMeans
from numpy import *
datMat = mat(kMeans.loadDataSet('testSet2.txt'))
print('datMat = ', datMat)
#centroids = kMeans.randCent(datMat, 2)
#print('centroids = ',centroids)
#centroids, clusterAssment = kMeans.biKmeans(datMat, 3)
#kMeans.Draw(datMat, centroids)
distance = kMeans.clusterClubs()