k-近邻算法改进约会网站配对效果

from numpy import *
import operator

def createDataSet():
    group = array([[1.0, 1.1], [1.1, 1.0], [0, 0], [0, 0.1]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]

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


    sqdiffMat = diffMat**2

    sqdistance = sqdiffMat.sum(axis = 1)
    distances = sqdistance**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]

def file2matrix(filename):
    '''
    分析数据
    将文件数据转化成分类器能处理的形式
    :param filename:
    :return:
    '''
    '''
    :param filename: 
    :return: 
    '''
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector

def autoNorm(dataSet):
    '''
    准备数据
    归一化特征值
    :param dataSet:
    :return:
    '''
    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))
    return normDataSet,ranges, minVals

def datingClassTest():
    '''
    测试分类器，这里选用前10%的数据测试，后10%的数据训练
    :return:
    '''
    hoRatio = 0.10
    datingDataMat, datingLabels = file2matrix(r'f:\python\datingTestSet2.txt')
    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)))

def classifyPerson():
    '''
    使用算法
    :return:
    '''
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(input("percentage of time spent playing video games:"))
    iceCream = float(input("liters of ice cream consumed per year:"))
    ffMiles = float(input("frequent flier miles earned per year:"))
    datingDataMat ,datingLabels = file2matrix(r'f:\python\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])

以上是kNN.py中对的内容，核心是classify0（）函数

from kNN import *
import matplotlib.pyplot as plt
'''

classifyPerson()

以上是_main_模块中的内容