k-近邻算法改进约会网站的配对效果

在上一篇的基础上增加如下代码：

'''
将文本记录转换到NumPy的解析程序
输入为文件名字符串
输出为训练样本矩阵和类标签向量
'''
def file2matrix(filename):
    fr = open(filename)
    arrayOLine = fr.readlines()  
    numberOfLines = len(arrayOLine)  #得到文本行数
    returnMat = zeros((numberOfLines, 3)) #创建以0填充的NumPy矩阵
    '''
    解析文本数据到列表，文本数据有4列，分别表示
    每年获得的飞行常客里程数
    玩视频游戏所消耗的时间百分比
    每周消费的冰淇淋公升数
    标签，以整型表示：不喜欢的人，魅力一般的人，极具魅力的人
    '''
    classLabelVector = []
    index = 0
    for line in arrayOLine:
        line = line.strip()  #strip，默认删除空白符（包括'\n', '\r',  '\t',  ' ')
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0: 3]  #选取前3个元素存储到特征矩阵
        classLabelVector.append(int(listFromLine[-1])) #-1表示最后一列元素，如果不用int(),将当做字符串处理
        index += 1
    return returnMat, classLabelVector


#归一化特征值
def autoNorm(dataSet):
    minVals = dataSet.min(0)  #存放每一列的最小值，min(0)参数0可以从列中选取最小值，而不是当前行最小值
    maxVals = dataSet.max(0)  #存放每一列的最大值
    ranges = maxVals - minVals #1 * 3 矩阵
    normDataSet = zeros(shape(dataSet))   #列
    m = dataSet.shape[0]      #行
    normDataSet = dataSet - tile(minVals, (m, 1))  #tile(A, (row, col))
    normDataSet = normDataSet/tile(ranges, (m, 1))
    return normDataSet, ranges, minVals


#分类器针对约会网站的测试代码
def dataingClassTest():
    hoRatio = 0.1
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)  #用于测试的数据条数
    errorCount = 0.0   #错误率
    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))

测试：

... ...
the classifier came back with: 3, the real answer is: 3
the classifier came back with: 2, the real answer is: 2
the classifier came back with: 1, the real answer is: 1
the classifier came back with: 3, the real answer is: 1
the total error rate is: 0.050000

错误率为5%
添加以下函数，进行预测

#约会网站预测函数
def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(raw_input("percentage of time spent playing video games?"))
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    iceCream = float(raw_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 probably like this person:", resultList[classifierResult-1]

>>> import KNN
>>> classifyPerson()
percentage of time spent playing video games?20
frequent flier miles earned per year?10000
liters of ice cream consumed per year?0.6
You will probably like this person: in large doses