Machine Learning in Action_CH2_2_使用kNN改进约会网站的配对效果

from numpy import *
import operator

# 创建数据
def createDataBase():
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]]) # numpy向量
    labels = ['A', 'A', 'B', 'B'] # 列表
    return group, labels

# kNN算法
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0] # 获得向量第一维长度
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet # 纵向扩大dataSetSize倍
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis = 1) # 按行求和
    distances = sqDistances ** 0.5
    sortedDistIndicies = distances.argsort() # 从小到大排序，返回的是索引值的列表
    classCount = {} # python字典
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1 # 数频度，每次加1
    # 对字典进行排序
    # Python 2 才能使用classCount.iteritems()
    sortedClassCount = sorted(classCount.items(), key = operator.itemgetter(1), reverse = True)
    return sortedClassCount[0][0]

# 准备数据：处理读入的数据，只取前三个特征
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines() # 将文件每一行，变成列表的每个元素
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines, 3)) # 3列，注意不能少括号
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip() # 截取所有的回车字符
        listFromLine = line.split('\t') # 返回一个列表
        returnMat[index, :] = listFromLine[0:3] # 列表赋值
        # 把datingTestSet.txt文件里的largeDoses变成3，smallDoses变成2，didntLike变成1
        classLabelVector.append(int(listFromLine[-1])) # 取最后一个
        index += 1
    return returnMat, classLabelVector

# 归一化特征值
def autoNorm(dataSet):
    minVals = dataSet.min(0) # 每一列最小值
    maxVals = dataSet.max(0) # 每一列最大值
    ranges = maxVals - minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0] # 行数（样本数）
    # 归一化公式，处理到0-1
    normDataSet = dataSet - tile(minVals, (m, 1))
    normDataSet = normDataSet / tile(ranges, (m, 1))
    # 也可以只返回矩阵
    return normDataSet, ranges, minVals

# 分类器针对约会代码的测试代码
def datingClassTest():
    hoRadio = 0.10
    # 获取数据
    datingDataMat, datingLabels = file2matrix("datingTestSet.txt")
    # 均值归一化
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m * hoRadio) # 测试向量的数量
    errorCount = 0.0
    for i in range(numTestVecs):
        # 前numTestVecs个作为测试数据，后面作为样本
        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)))

# 构建完整可用系统
def classifyPerson():
    resultList = ['完全不喜欢', '有点喜欢', '很喜欢']
    # 注意Python 3不能用raw_input
    ffMiles = float(input("frequent flier miles earned per year?  "))
    percentTats = float(input("percentage of time spent playing video games?  "))
    iceCream = float(input("liters of ice cream consumed per year?  "))
    datingDataMat, datingLabels = file2matrix("datingTestSet.txt")
    normMat, ranges, minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles, percentTats, iceCream])
    # 注意输入的测试向量也要均值归一化
    classifierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3)
    print("你大概对这个男人" + resultList[classifierResult - 1])

if __name__ == '__main__':
    # 从文本文件中解析数据
    datingDataMat, datingLabels = file2matrix('datingTestSet.txt')
    print(datingDataMat)
    print(datingLabels[0:20])

    # 用Matplotlib画散点图
    import matplotlib
    import matplotlib.pyplot as plt
    fig = plt.figure()
    ax = fig.add_subplot(111)
    # ax.scatter(datingDataMat[ : , 1], datingDataMat[ : , 2])
    # 不同的颜色，使用第2列和第3列数据
    # ax.scatter(datingDataMat[ : , 1], datingDataMat[ : , 2], 15.0 * array(datingLabels), 15.0 * array(datingLabels))
    # 使用第1列和第2列数据
    ax.scatter(datingDataMat[:, 0], datingDataMat[:, 1], 15.0 * array(datingLabels), 15.0 * array(datingLabels))
    plt.show()
    # 关闭图像，否则下面跑不出来！！！！

    # 归一化数值
    normMat, ranges, minVals = autoNorm(datingDataMat)
    print("-------------------归一化数值-----------------------")
    print(normMat)
    print(ranges)
    print(minVals)

    print("-------------------测试算法-----------------------")
    datingClassTest()

    print("-------------------构建完整可用系统-----------------------")
    classifyPerson()

    # arr = array([[1, 2, 3, 4], [5, 6, 7, 8]])
    # print(arr.shape)
    # matrix = mat(arr)
    # print(matrix.shape)

    # print(array([[1, 2],[3, 4]]))
    # print(array([(1, 2), (3, 4)]))
    # a = array([1, 2])
    # print(a.dtype)

    # a = [1, 2, 3, 4]
    # print(tile(a, 2))

    # group, labels = createDataBase()
    # print(classify0([0, 0], group, labels, 3)) # 输出B