Python实现knn

#coding:utf-8
import numpy as np
import operator
import os

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX,(dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis = 1)
    distances = sqDistances**0.5
    sortedDistanceIndices = distances.argsort()
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistanceIndices[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) +1
    sortedClassCount = sorted(classCount.items(),key = operator.itemgetter(1), reverse = True)
    return sortedClassCount[0][0]
    

def file2matric(filename):
    fr = open(filename)
    arrayOLine = fr.readlines()
    numberOfLines = len(arrayOLine)
    returnMat = np.zeros((numberOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLine:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        if listFromLine[-1] == 'largeDoses':
            temp = 3
        if listFromLine[-1] == 'smallDoses':
            temp = 2
        if listFromLine[-1] == 'didntLike':
            temp = 1
        classLabelVector.append(temp)
        index += 1
    return returnMat, classLabelVector
    
def autoNormal(dataset):
    minVals = dataset.min(0)
    maxVals = dataset.max(0)
    ranges = maxVals - minVals
    normDataset = np.zeros(np.shape(dataset))
    m = dataset.shape[0]
    normDataset = dataset - np.tile(minVals,(m,1))
    normDataset = normDataset/np.tile(ranges,(m,1))
    return normDataset, ranges, minVals

def classifyPersion():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(raw_input("percentage of time spent play video games?"))
    ffMiles = float(raw_input("frequent filer niles earned per year?"))
    iceCream = float(raw_input("liters of ice cream consumed per year?"))
    datingDataMat, datingLabels = file2matric(r".\datingTestSet.txt")
    normalMat , ranges, minVals = autoNormal(datingDataMat)
    inArr = np.array([ffMiles,percentTats,iceCream])
    classifierResult = classify0((inArr - minVals)/ranges, normalMat, datingLabels,3)
    print "You will probably like this persion :" , resultList[classifierResult - 1]

def img2vertor(filename):
    returnVect = np.zeros((1,1024))
    fr = open(filename,'r+')
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect    
    
def handwritingclasstest():
    hwLabels = []
    traingFileList = os.listdir(r".\digits\trainingDigits")
    m = len(traingFileList)
    trainingMat = np.zeros((m,1024))
    for i in range(m):
        fileNameStr = traingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vertor(r".\digits\trainingDigits\%s" % fileNameStr)
    testFileList = os.listdir(r".\digits\testDigits")
    mtest = len(testFileList)
    errorCount = 0.0
    for i in range(mtest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split(".")[0]
        classNumStr = fileStr.split("_")[0]
        vectorUnderTest = img2vertor(r".\digits\testDigits\%s" % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print "the classifier came back with: %d ,the real answer is :%s " % (classifierResult,classNumStr)
        if(classifierResult != int(classNumStr)):
            errorCount += 1.0
    print "\n the total number of error is %d" % errorCount
    print "\n the total error rate is %f" % (errorCount/float(mtest))

以上代码包含两个小项目：

第一个是使用knn算法改进约会网站的配对效果，使用Python交互界面运行

先后输入参数10   10000    0.5      结果为in small doses

数据点此出下载  提取码：ue4a

 

第二个小项目是手写数字识别系统

同样是使用交互界面运行

import knn

knn.handwritingclasstest()

数据点此处下载  提取码：9qd1

 

本代码是依据《机器学习实战》这本书编写。