1.背景
无监督学习的定义就不多说了，不懂得可以google。因为项目需要，需要进行无监督的分类学习。
K-means里面的K指的是将数据分成的份数，基本上用的就是算距离的方法。
大致的思路就是给定一个矩阵，假设K的值是2，也就是分成两个部分，那么我们首先确定两个质心。一开始是找矩阵每一列的最大值max，最小值min，算出range=max-min，然后设质心就是min+range*random。之后在逐渐递归跟进，其实要想明白还是要跟一遍代码，自己每一步都输出一下看看跟自己想象的是否一样。
（顺便吐槽一下，网上好多人在写文章的事后拿了书上的代码就粘贴上，也不管能不能用，博主改了一下午才改好。。。，各种bug）
2.代码
'''
@author: hakuri
'''
from numpy import *
import matplotlib.pyplot as plt
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 = 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(array(dataSet)[:,j])
rangeJ = float(max(array(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(array(centroids)[j,:],array(dataSet)[i,:])
if distJI < minDist:
minDist = distJI; minIndex = j
if clusterAssment[i,0] != minIndex: clusterChanged = True
clusterAssment[i,:] = minIndex,minDist**2
print centroids
# print nonzero(array(clusterAssment)[:,0]
for cent in range(k):#recalculate centroids
ptsInClust = dataSet[nonzero(array(clusterAssment)[:,0]==cent)[0][0]]#get all the point in this cluster
centroids[cent,:] = mean(ptsInClust, axis=0) #assign centroid to mean
id=nonzero(array(clusterAssment)[:,0]==cent)[0]
return centroids, clusterAssment,id
def plotBestFit(dataSet,id,centroids):
dataArr = array(dataSet)
cent=array(centroids)
n = shape(dataArr)[0]
n1=shape(cent)[0]
xcord1 = []; ycord1 = []
xcord2 = []; ycord2 = []
xcord3=[];ycord3=[]
j=0
for i in range(n):
if j in id:
xcord1.append(dataArr[i,0]); ycord1.append(dataArr[i,1])
else:
xcord2.append(dataArr[i,0]); ycord2.append(dataArr[i,1])
j=j+1
for k in range(n1):
xcord3.append(cent[k,0]);ycord3.append(cent[k,1])
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')
ax.scatter(xcord2, ycord2, s=30, c='green')
ax.scatter(xcord3, ycord3, s=50, c='black')
plt.xlabel('X1'); plt.ylabel('X2');
plt.show()
if __name__=='__main__':
dataSet=loadDataSet('/Users/hakuri/Desktop/testSet.txt')
# # print randCent(dataSet,2)
# print dataSet
#
# print kMeans(dataSet,2)
a=[]
b=[]
a, b,id=kMeans(dataSet,2)
plotBestFit(dataSet,id,a)
用的时候直接看最后的main，dataSet是数据集输入，我会在下载地址提供给大家。
kmeans函数第一个参数是输入矩阵、第二个是K的值，也就是分几份。
plotBestFit是画图函数，需要加plot库，而且目前只支持二维且K=2的情况。
3.效果图
里面黑色的大点是两个质心，怎么样，效果还可以吧！
测试的时候一定要多用一点数据才会明显。
测试的时候一定要多用一点数据才会明显。
4.下载地址
我的github地址https://github.com/jimenbian，喜欢就点个starO(∩_∩)O哈！
/********************************
* 本文来自博客 “李博Garvin“
* 转载请标明出处:http://blog.csdn.net/buptgshengod
******************************************/
