机器学习第二章 k-means

python3的约会网站k-means代码：
三点修改：
由于string无法转换float ：采用dataset2.txt
由于定义了range 在for循环处又使用了同名的range函数：故range改为range1
由于raw_input被取代：使用input（）

import matplotlib.pyplot as plt
from numpy import *
import  numpy as np
import operator


# 准备使用python导入数据

def createDataSet():
	group = array( [[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 1.0]] )
	label = ['A', 'A', 'B', 'B']
	return group, label


# 从文本文件中解析数据
def classify(inX, dataSet, labels, k):
	# 计算欧式距离 sqrt（（x1-x2）**2+（y1-y2）**2）
	dataSetSize = dataSet.shape[0]
	# tile为将inx复制成形状为(dataSetSize,1)的矩阵
	diffMat = tile( inX, (dataSetSize, 1) ) - dataSet
	sqDiffMat = diffMat ** 2
	sqDistances = sqDiffMat.sum( axis=1 )
	distances = sqDistances ** 0.5
	sortedDistIndices = distances.argsort()
	# 选择欧式距离最小的前k个点
	classCount = {}
	for i in range( k ):
		voteIlabel = labels[sortedDistIndices[i]]
		classCount[voteIlabel] = classCount.get( voteIlabel, 0 ) + 1
	# 排序 输出最多的分类
	# argsort是numpy中的函数，返回从小到大排序的索引值
	# sort则是对数组进行排序 sorted对原数组没有影响，sort则是作用于原数组 reverse=True降序 =False升序 默认为False
	sortClassCOunt = sorted( classCount.items(), key=operator.itemgetter( 1 ), reverse=True )
	return sortClassCOunt[0][0]


# 从文本文件中解析数据
def file2matrix(filename):
	fr = open( filename, encoding='UTF-8' )
	arrayOLines = fr.readlines()
	# 获取文件行数
	numberOfLines = len( arrayOLines )
	# 创建返回的Numpy矩阵
	returnMat = zeros( (numberOfLines, 3) )
	classLaberVector = []
	index = 0
	# 解析文件数据到列表
	for line in arrayOLines:
		# 截掉所有回车字符
		line = line.strip()
		# 使用\t将整行数据分割成元素列表
		listFromLine = line.split( '\t' )
		# 样本训练矩阵
		returnMat[index, :] = listFromLine[0:3]
		# 标签向量
		classLaberVector.append( int( listFromLine[-1] ) )
		index += 1
	return returnMat, classLaberVector

# 归一化特征值
def autoNorm(dataset):
	minVals = dataset.min(0)
	maxVals = dataset.max(0)
	range1=maxVals-minVals
	normDataSet = zeros(shape(dataset))
	m = dataset.shape[0]
	normDataSet = dataset - tile( minVals,(m,1))
	normDataSet = normDataSet / np.tile(range1, (m, 1))
	return normDataSet,range1,minVals

# 分类器针对约会网站的测试代码
def datingClassTest():
	hoRatio=0.1
	datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
	normMat,range1,minvals = autoNorm(datingDataMat)
	m = normMat.shape[0]
	numTestVecs = int(m*hoRatio)
	errorCount = 0.0
	for i in range(numTestVecs):
		classifierResult = classify(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
		print("the c  is:%d,%f" %(classifierResult,datingLabels[i]))
		if(classifierResult !=datingLabels[i]):errorCount +=1.0
	print("the total id : %f"%(errorCount/float(numTestVecs)))

# 预测
def classifyPerson():
	resultList = ['not at all','in small does','in large doses']
	percentTats = float(input("video games?"))
	ffMiles = float(input("enered per year?"))
	iceCream = float(input("ice ceream per year"))
	datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
	normMat,range1,minvals = autoNorm(datingDataMat)
	inArr = array([ffMiles , percentTats , iceCream])
	classifierResult = classify((inArr-minvals)/range1,normMat,datingLabels , 3)
	print("the person :",resultList[classifierResult - 1])
if __name__ == "__main__":
	group, label = createDataSet()
	datingDataMat,datingLabels = file2matrix( 'datingTestSet2.txt' )
	normMat,range1,minvals=autoNorm(datingDataMat)
	# print(datingClassTest())
	print(classifyPerson())
    # 使用matplotlib创建散点图
	fig = plt.figure()
	ax = fig.add_subplot(111)
	ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
	plt.show()