《机器学习实战》(Machine Learning in Action)学习笔记（一）——k近邻算法

1-前言

    这个系列博客作为笔记用来记录学习这本书过程中遇到的问题

2-程序2-1：

    1:导入必要的包

from numpy import *
import operator

    2-规范dataSet

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

    3-实现kNN算法

         3.1- 实现核心部分，后面会调用这个函数

def classify(inX,dataSet,labels,k):
    dataSetSize = dataSet.shape[0]      #dataSet.shape 获取的结果是几行几列，shape[0]是几行
    diffMat = tile(inX,(dataSetSize,1)) - dataSet  #tile将inX变成 dataSize行
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)    #两列相加
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()    #取得distances排序后的下标变换
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]] 
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1   #记录出现了几次
    sortedClassCount = sorted(classCount.items(),key = operator.itemgetter(1),reverse = True)
    return sortedClassCount[0][0]

          3.2- 将txt文件中的数据转化成matrix

def file2matrix(fileName):
    fr = open(fileName) 
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip() #去掉回车
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

        3.3- 因为里程数数值比较大，这样会降低其他两个类别的权重，所以对整个数组归一化。

               归一化公式为：newValue = (oldValue - min) / (max - min)

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))
    return normDataSet,ranges,minVals

 

       3.4- 测试分类器性能

def datingClassTest():
    hoRatio = 0.10
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    #print(m)
    numTestVecs = int(m*hoRatio)   #将normMat中的数据以1：9划分，100到1000作为样本点，0到100作为测试点
    #print(numTestVecs)
    #print(normMat[numTestVecs:m,:])
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
        #print(classifierResult)
        print("the classifier came back with : " + str(classifierResult) + " ,the real answer is : " + str(datingLabels[i]))
    if (classifierResult != datingLabels[i]): 
        errorCount += 1.0
    print("the total error rate is " + str(errorCount/float(numTestVecs))) 

        3.5- 对输入数据进行预测

def classifyPerson():
    resultList = ['not at all','in small doses','in large doses']
    percentTats = float(input("percentage of time spent playing video game?"))
    ffMiles = float(input("frequent flier miles earned per year？"))
    iceCream = float(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])
    

 

注：其中几个函数的用法：

         1:tile(x,(n,m)) 是将 x按照 n行，m列扩展 例如：

from numpy import *

x = [[1,2],[2,3]]
result = tile(x,(2,1))
print(result)


'''输出结果为
[[1 2]
 [2 3]
 [1 2]
 [2 3]]
'''

        2:distances.argsort() 是将distances排序后输出变换的下标

distances=array([5,2,4,1])
sortedDistances = distances.argsort()
print(sortedDistances)

'''输出结果
[3 1 2 0]
'''