#2-2约会网站配对

#将文本记录转换为NumPy

def file2matrix(filename):

    love_dictionary = {'largeDoses':3, 'smallDoses':2, 'didntLike':1}

    fr = open(filename)     #打开文件

    arrayOLines = fr.readlines()    #行组成的数组

    numberOfLines = len(arrayOLines)    #返回数组元素个数

    returnMat = zeros((numberOfLines, 3))   #生成numberOfLines*3的0数组

    classLabelVector = []   #数组

    index = 0

    for line in arrayOLines:

        line = line.strip()     #除去头尾空格

        listFromLine = line.split('\t')     #按'\t'分割成数组

        returnMat[index, :] = listFromLine[0:3]     #从0开始截取3个

        if(listFromLine[-1].isdigit()):

            classLabelVector.append(int(listFromLine[-1]))  #是数字就放数字，存入类型

        else:

            classLabelVector.append(love_dictionary.get(listFromLine[-1]))  #是字符串就转成数字，存入类型

        index += 1

    return returnMat, classLabelVector

import matplotlib

import matplotlib.pyplot as plt

fig = plt.figure() #返回一个图像窗口

ax = fig.add_subplot(111) #在1行1列1号位画子图

datingDataMat,datingLabels=file2matrix("E:/Python/《机器学*实战》代码/Ch02/datingTestSet2.txt")

# print(datingLabels)

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

#scatter(x, y, 点的大小, 颜色，标记)

ax.scatter(datingDataMat[:,1], datingDataMat[:,2], 15.0*array(datingLabels),15.0*array(datingLabels),"*")

ax.axis([-2,25,-0.2,2.0]) #[x轴min,x轴max,y轴min,y轴max]

plt.xlabel('game')

plt.ylabel('ice')

# plt.show()

# 归一化特征值

# newVal=(oldVal-minVal)/(maxVal-minVal)

def autoNorm(dataSet):

    minVals=dataSet.min(0) #得到每一列的最小值（列1min，列2min，列3min）

    maxVals=dataSet.max(0) #得到每一列的最大值

    ranges=maxVals-minVals

    normDataSet=zeros(shape(dataSet))# 建立一个和dataSet一样大小的0矩阵

    m=dataSet.shape[0]

    normDataSet=dataSet-tile(minVals,(m,1))# tile建立矩阵tile(重复的内容,(在高度上重复,在长度上重复))

    normDataSet=normDataSet/tile(ranges,(m,1))

    return normDataSet,ranges,minVals

normMat,ranges,minVals=autoNorm(datingDataMat)

#分类器

def datingClassTest():

    hoRatio=0.10 #0.1的数据作为测试

    datingDataMat,datingLabels=file2matrix("E:/Python/《机器学*实战》代码/Ch02/datingTestSet2.txt")

    normMat,ranges,minVals=autoNorm(datingDataMat)#归一化的特征值，特征值原本范围，特征值最小值

    m=normMat.shape[0]

    numTestVecs=int(m*hoRatio)#测试数据的数量

    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)))

#约会网站预测函数

def classifyPerson():

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

    percentTats=float(input("游戏时间百分比"))

    ffMiles=float(input("每年飞行常客里程数"))

    iceCream=float(input("每年吃冰淇淋多少升"))

    datingDataMat,datingLabels=file2matrix("E:/Python/《机器学*实战》代码/Ch02/datingTestSet2.txt")

    normMat,ranges,minVals=autoNorm(datingDataMat)

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

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

    print(resultList[classifierResult-1])

# classifyPerson()