def test1():
datMat = mat(kMeans.loadDataSet('testSet.txt'))
print(min(datMat[:, 0]))
print(kMeans.randCent(datMat, 2))
print(kMeans.distEclud(datMat[0], datMat[1]))
#myCentroids, clustAssing = kMeans.kMeans(datMat,3)
myCentroids, clustAssing = kMeans.biKmeans(datMat, 4)
print(myCentroids)
kMeans.plot1(datMat, myCentroids)
'''
Created on 2016. 2. 9.
@author: TaijinKim
'''
import kMeans
from numpy import *
dataMat = mat(kMeans.loadDataSet('../data/testSet.txt'))
# print(min(dataMat[:, 0]))
# print(min(dataMat[:, 1]))
# print(max(dataMat[:, 1]))
# print(max(dataMat[:, 0]))
#
print(kMeans.randCent(dataMat, 2))
#
# print(kMeans.distEclud(dataMat[0], dataMat[1]))
# myCentroids, clustAssing = kMeans.kMeans(dataMat, 4)
#!/usr/bin/env python
__coding__ = "utf-8"
__author__ = "Ng WaiMing"
from kMeans import kMeans
from kMeans import loadDataSet
from kMeans import randCent
from kMeans import distEclud
from kMeans import biKmeans
from numpy import *
if __name__ == '__main__':
dataMat = mat(loadDataSet('testSet.txt'))
print('min(dataMat[:, 0])', min(dataMat[:, 0]), '\n')
print('min(dataMat[:, 1])', min(dataMat[:, 1]), '\n')
print('max(dataMat[:, 0])', max(dataMat[:, 0]), '\n')
print('max(dataMat[:, 1])', max(dataMat[:, 1]), '\n')
print(randCent(dataMat, 2), '\n')
print(distEclud(dataMat[0], dataMat[1]))
centroids, clusterAssment = kMeans(dataMat, 4)
print('centroids:\n', centroids, '\n')
print('clusterAssment:\n', clusterAssment, '\n')
dataMat3 = mat(loadDataSet('testSet2.txt'))
centList, myNewAssments = biKmeans(dataMat3, 3)
print('centList: \n', centList, '\n')
# fileName = '../../../../data/k-means/places.txt'
# imgName = '../../../../data/k-means/Portland.png'
# kMeans.clusterClubs(fileName=fileName, imgName=imgName, numClust=5)
#!/usr/bin/env python
#-*- coding: UTF-8 -*-
import kMeans
from numpy import *
dataMat=mat(kMeans.loadDataSet('testSet.txt'))
kMeansRandCenter=kMeans.randCent(dataMat,2) # 两个中心
print(kMeansRandCenter)
centroids,clusterAssment=kMeans.kMeans(dataMat,5)
import matplotlib.pyplot as plt
fig=plt.figure(1)
plt.plot(centroids[:,0],centroids[:,1],'ro')
plt.plot(dataMat[:,0],dataMat[:,1],'bo')
plt.axis([-8,8,-8,8])
# plt.show()
kMeans.binaryKeans(dataMat,3)
dataMat3=mat(kMeans.loadDataSet('testSet2.txt'))
centList,Assments=kMeans.binaryKeans(dataMat3,3)
print("centList:",centList)
print("Assments:",Assments)
fig=plt.figure(2)
plt.plot(dataMat3[:,0],dataMat3[:,1],'bo')
plt.plot(centList[:,0],centList[:,1],'ro')
plt.axis([-10,10,-10,10])
# plt.show()
# 对每个质心
# 计算质心与数据点之间的距离
# 将数据点分配到距其最近的簇
# 对每一个簇，计算簇中所有点的均值并将均值作为质心
import kMeans
from numpy import *
import matplotlib
import matplotlib.pyplot as plt
import time
st = time.time()
k = 3
dataMat = mat(kMeans.loadDataSet('testSet2.txt'))
oldClassLabel = zeros(len(dataMat), int)
newClassLabel = ones(len(dataMat), int)
center = kMeans.randCent(dataMat, k)
dist = []
m = 0
while newClassLabel.tolist().__eq__(
oldClassLabel.tolist()) != True: # 所有的点的新分类的标签和旧分类的标签不一致时就继续进行划分
m += 1 # 迭代次数
for di in range(len(dataMat)): # 对数据集中的每个数据点
dist = []
for ci in range(len(center)): # 对每个质心，计算某个点到质心的距离
dist.append(kMeans.distEclud(dataMat[di],
center[ci])) # dist 用于记录一个点到所有簇点的距离
distsort = array(dist).argsort() # 对距离排序，返回从小到大的索引
oldClassLabel = newClassLabel.copy() # ！！！！注意这里是引用不能直接用等号，否则将会使得两个值一起变
newClassLabel[di] = distsort[0] # 取出索引的最小值，就是距离最近的点
for j in range(k):
x = mean(array(dataMat)[kMeans.find_all_index(newClassLabel, j),
import kMeans
from numpy import *
datMat = mat(kMeans.loadDataSet('testSet.txt'))
print min(datMat[:, 0])
print min(datMat[:, 1])
print max(datMat[:, 0])
print max(datMat[:, 1])
print kMeans.randCent(datMat, 2)
print kMeans.distEclud(datMat[0], datMat[1])
myCentroids, clustAssing = kMeans.kMeans(datMat, 4)
#print myCentroids, clustAssing
datMat3 = mat(kMeans.loadDataSet('testSet2.txt'))
centList, myNewAssments = kMeans.biKmeans(datMat3, 3)
print centList
import kMeans
from numpy import *
dataMat = mat(kMeans.loadDataSet('testSet.txt'))
# print dataMat
randMat = kMeans.randCent(dataMat, 2)
# print dataMat[:, 0]
# print randMat
res = kMeans.kMeans(dataMat, 4)
# print res
dataMat3 = mat(kMeans.loadDataSet('testSet2.txt'))
kMeans.biKmeans(dataMat3, 3)
# centList, myNewAssments =
import kMeans
from numpy import *
# 导入txt数据
datMat = mat(kMeans.loadDataSet('data2.txt'))
# datMat矩阵的第2-4列分别对应半长轴、偏心率和轨道倾角
datMat[0, 2:5]
# 计算距离
delta_v = kMeans.distdeltaV(datMat[0, 2:5], datMat[1, 2:5])
# 随机生成k个质心
centroids = kMeans.randCent(datMat[:, 2:5], 4)
# k-均值聚类
myCentroids, clustAssing = kMeans.kMeans(datMat[:, 2:5], 5, kMeans.distdeltaV)
# 二分 k-均值聚类
centList, myNewAssments = kMeans.biKmeans(datMat[:, 2:5], 5, kMeans.distdeltaV)
# 画图
kMeans.showCluster_SRQ(datMat[:, 2:5], myNewAssments)
Created on Sun May 14 11:57:07 2017
@author: 凯风
"""
import kMeans
import numpy as np
from imp import reload
reload(kMeans)
datMat = np.mat(kMeans.loadDataSet('testSet.txt'))
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
import kMeans
from numpy import *
datMat = mat(kMeans.loadDataSet('testSet.txt'))
print min(datMat[:,0])
print min(datMat[:,1])
print max(datMat[:,0])
print max(datMat[:,1])
print kMeans.randCent(datMat, 2)
print kMeans.distEclud(datMat[0], datMat[1])
myCentroids, clustAssing = kMeans.kMeans(datMat, 4)
#print myCentroids, clustAssing
datMat3 = mat(kMeans.loadDataSet('testSet2.txt'))
centList, myNewAssments = kMeans.biKmeans(datMat3, 3)
print centList
import kMeans import os import sys from numpy import * project_path = os.path.abspath(os.path.dirname(__file__)) text_path = os.path.join(project_path, "../chapter10/testSet.txt") datMat = mat(kMeans.loadDataSet(text_path)) print(min(datMat[:, 0])) print(min(datMat[:, 1])) print(max(datMat[:, 1])) print(max(datMat[:, 0])) print(kMeans.randCent(datMat, 2)) print(kMeans.distEclud(datMat[0], datMat[1]))
from time import sleep
import urllib
import json
# homedir= os.getcwd()+'/machinelearninginaction/ch10/' #绝对路径
homedir = '' #相对路径
#10.1 k均值聚类算法
datMat = mat(kMeans.loadDataSet(homedir + 'testSet.txt'))
myCentroids, clustAssing = kMeans.kMeans(datMat, 4)
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
import kMeans
from numpy import *
# 构建矩阵
datMat = mat(kMeans.loadDataSet('testSet.txt'))
min(datMat[:, 0])
min(datMat[:, 1])
max(datMat[:, 1])
max(datMat[:, 0])
# 支持函数
kMeans.randCent(datMat, 2)
kMeans.distEclud(datMat[0], datMat[1])
# 聚类
from importlib import reload
reload(kMeans)
datMat = mat(kMeans.loadDataSet('testSet.txt'))
myCentroids, clustAssing = kMeans.kMeans(datMat, 4)
# 二分
from importlib import reload
reload(kMeans)
datMat3 = mat(kMeans.loadDataSet('testSet2.txt'))
centList, myNewAssments = kMeans.biKmeans(datMat3, 3)
centList
# 示例
from importlib import reload
reload(kMeans)
geoResults = kMeans.geoGrab('1 VA Center', 'Augusta, ME')
geoResults['ResultSet']['Error']
def test1():
dataMat = np.mat(kMeans.loadDataSet('testSet.txt'))
print kMeans.randCent(dataMat, 2)
print kMeans.distEclud(dataMat[0], dataMat[1])
