机器学习之K-近邻算法

    上学期险些挂了孙大圣的PRML（pattern recognition and machine learning）课之后，决定本学期重新学一遍机器学习的经典算法，为接下来的寻找论文方向铺路，经过2个礼拜的颓废之后，终于写下了这篇knn算法，虽然此类文章已经在网上烂大街了，不过还是决定重新梳理一下自己的思路。

    首先定义一下K-邻近算法，它的工作原理是：存在一个样本数据集合，也称作数据集，并且样本集中每个数据都存在标签，即我们知道样本集中每一数据与所属分类的对应关系。输入没有标签的新数据后，将新数据的每个特征与样本集中数据对应的特征进行比较，然后算法提取样本集中特征最相似数据（最近邻）的分类标签。一般来说，我们只选择样本数据集中前k个最相似的数据，这就是k-近邻算法中k的出处。通常k是不大于20的整数。最后，选择k个最相似数据中出现次数最多的分类，作为新数据的分类。一般在学习过程中k会取2-5比较合适。

    以机器学习实战中约会的例子为例，实现KNN算法，KNN的思想很简单，k-近邻算法是分类数据最简单最有效的算法，但是k-近邻算法需要保存全部数据集，如果训练集很大，则必须使用大量的存储空间，同时它必须对数据集中的每个数据计算距离值，实际使用会非常耗时。

from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt
from os import listdir
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]

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
    for line in fr.readlines():
        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):
    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

def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('D:\Program Files\PycharmProjects\MLIA\KNN\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)

if __name__ == '__main__':
    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('D:\Program Files\PycharmProjects\MLIA\KNN\datingTestSet2.txt')
    inArr = array([ffMiles,percentTats,iceCream])
    normMat, ranges, minVals = autoNorm(datingDataMat)
    classifierResult =classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print("You will probably like this person: ",resultList[classifierResult -1])
    # fig = plt.figure()
    # ax = fig.add_subplot(111)
    # ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
    # plt.show()
    # print(normMat)
    # print(ranges)
    # print(minVals)
    #datingClassTest()