from numpy import *

import operator

from os import listdir

import matplotlib.pyplot as plt

"""程序清单2-1 K近邻算法"""

def classify0(inX, dataSet, labels, k):

dataSetSize = dataSet.shape[0]

diffMat = tile(inX, (dataSetSize, 1)) - dataSet

sqDiffMat = diffMat**2

sqDistances = sqDiffMat.sum(axis=1)

distances = sqDistances**0.5

sortedDistIndicies = distances.argsort()

classCount={}

for i in range(k):

voteIlabel = labels[sortedDistIndicies[i]]

classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1

sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)

return sortedClassCount[0][0]

"""程序清单2-2 将文本记录录到Numpy的解析程序"""

def file2matrix(filename):

fr = open(filename)

numberOfLines = len(fr.readlines())         #get the number of lines in the file

returnMat = zeros((numberOfLines,3))        #prepare matrix to return

classLabelVector = []                       #prepare labels return

fr = open(filename)

index = 0

line = line.strip()

listFromLine = line.split('\t')

returnMat[index, :] = listFromLine[0:3]

classLabelVector.append(int(listFromLine[-1]))

index += 1

return returnMat, classLabelVector

"""程序清单2-3 归一化特征值"""

def autoNorm(dataSet):

minVals = dataSet.min(0)

maxVals = dataSet.max(0)

ranges = maxVals - minVals

normDataSet = zeros(shape(dataSet))

m = dataSet.shape[0]

normDataSet = dataSet - tile(minVals, (m,1))

normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide

return normDataSet, ranges, minVals

"""程序清单2-4 分类器针对约会网站的测试代码"""

def datingClassTest():

hoRatio = 0.50      #hold out 10%

datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file

normMat, ranges, minVals = autoNorm(datingDataMat)

m = normMat.shape[0]

numTestVecs = int(m*hoRatio)

errorCount = 0.0

for i in range(numTestVecs):

classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)

print ("the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i]))

if (classifierResult != datingLabels[i]): errorCount += 1.0

print("the total error rate is: %f" % (errorCount/float(numTestVecs)))

print(errorCount)

"""程序清单2-5 约会网站预测函数"""

def classifyPerson():

resultList = ["not at all", "in small doses", "in large doses"]

percentTats = float(input("percentage of time spent playing video games?"))

ffMiles = float((input("frequent flier miles earned per year?")))

icecream = float(input("liters of ice cream consumed per year?"))

datingDataMat, datingLabels = file2matrix("datingTestSet2.txt")

normMat, ranges, minVals = autoNorm(datingDataMat)

inArr = array([ffMiles, percentTats, icecream])

classifierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3)

print("You will probaly like this: ", resultList[classifierResult - 1])

if __name__ == "__main__":

datingDataMat, datingLabels = file2matrix("datingTestSet2.txt") #注意教材上是错的

# print (datingDataMat)

# print(datingLabels[0:20])

"""分析数据"""

#plt.scatter(datingDataMat[:,1],datingDataMat[:,2])

"""图2-3"""

#plt.show()

# plt.scatter(datingDataMat[:,1],datingDataMat[:,2],15*array(datingLabels), 15*array(datingLabels))

# """图2-4"""

# plt.show()

"""特征值归一化"""

normat, ranges, minVals = autoNorm(datingDataMat)

# print(normat)

# print(ranges)

# print(minVals)

"""测试"""

#datingClassTest()

classifyPerson()