机器学习实战 k-近邻算法（kNN）

概述

准备Python导入数据

from numpy import *
import operator

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

查看

import kNN
group,labels = kNN.createDataSet()
print(group)
print(labels)

实施kNN分类算法

from numpy import *
import operator

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

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]#行数
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)#行相加
    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]


if __name__ == '__main__':
    group, labels = createDataSet()
    print(group)
    print(labels)
    print(classify0([0,0],group,labels,3))

示例：使用kMM算法改进约会网站的配对效果

准备数据：从文本中解析数据

文件所在地址->

import kNN

def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)  # 得到文件的行数
    returnMat = kNN.zeros((numberOfLines, 3))  # 创建返回的矩阵--行列

    classLabelVector = []  # 分类标签向量
    index = 0
    for line in arrayOLines:
        line = line.strip()  # 去掉回车符
        listFromLine = line.split('\t')  # 根据'\t'进行分割，成元素列表
        returnMat[index,:] = listFromLine[0:3]  # 前三个元素存入矩阵
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector

if __name__ == '__main__':
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    print(datingDataMat)
    print(datingLabels)

分析数据：使用Matplotlib创建散点图

PyCharm不能直接安装MAtplotlib，可以用终端在Scripts位置pip install matplotlib安装。

import kNN
import matplotlib
import matplotlib.pyplot as plt


def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)  # 得到文件的行数
    returnMat = kNN.zeros((numberOfLines, 3))  # 创建返回的矩阵--行列

    classLabelVector = []  # 分类标签向量
    index = 0
    for line in arrayOLines:
        line = line.strip()  # 去掉回车符
        listFromLine = line.split('\t')  # 根据'\t'进行分割，成元素列表
        returnMat[index,:] = listFromLine[0:3]  # 前三个元素存入矩阵
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector

if __name__ == '__main__':
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    print(datingDataMat)
    print(datingLabels)
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2])
    plt.show()

结果如下图所示（第二、第三行数据）：

使用参数ax.scatter(datingDataMat[:,1], datingDataMat[:,2], 15.0*kNN.array(datingLabels), 15.0*kNN.array(datingLabels))

结果如下图所示（第二、第三行数据）：

结果如下图所示（第一、第二行数据）：

准备数据：归一化数值

from numpy import *
import date

def autoNorm(dataSet):
    minVals = dataSet.min(0)#0代表从列中取值
    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

if __name__ == '__main__':
    datingDataMat, datingLabels = date.file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    print(normMat)
    print(ranges)
    print(minVals)

测试算法：作为完整程序验证分类器

（不在编写独立文件了太麻烦）

def datingClassTest():
    hoRatio = 0.10
    datingDataMat,datingLabels = file2matrix('datingTestSet.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 ckassifier 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)))

使用算法：构建完整可用系统

def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percenTats = float(input("percentage of time spent playing video games?"))
    ffMiles = float(input("frequent fliter miles earned per year?"))
    iceCream = float(input("liter of ice cream consumed per year?"))
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges , minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles, percenTats, iceCream])
    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)
    print("You will probably like this person:",resultList[classifierResult - 1])

使用K-近邻算法识别手写数字

from numpy import *
from os import listdir
import operator

def img2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect
def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]#行数
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis=1)#行相加
    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 handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('trainingDigits')#listdir() 方法用于返回指定的文件夹包含的文件或文件夹的名字的列表。
    m = len(trainingFileList)#数目
    trainingMat = zeros((m,1024))#创建训练集矩阵
    for i in range(m):
        #获取文件名
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        #将数据加入训练集
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print("the classifier came back with : %d,the real answer is: %d" % (classifierResult,classNumStr))
        if(classifierResult != classNumStr):
            errorCount += 1.0
    print("\nthe total number of errors is: %d" % errorCount)
    print("\nthe total error rate is: %f" % (errorCount/float(mTest)))

if __name__ == '__main__':
    handwritingClassTest()