一步一步实现KNN分类算法

参考机器学习实战第二章，自己实现了一遍

from numpy import *
import operator
import pandas as pd
from os import listdir

#inX是测试数据，dataSet是训练数据集，labels是标签，返回的是概率最大的标签
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
    sorted(classCount.items(), key=lambda e: e[1], reverse=True)
    return sorted(classCount.items(), key=lambda e: e[1], reverse=True)[0][0]

#自己生成的数据，仅作测试用
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

#从txt文件中提取训练集和标签
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
    classLabel = []                       #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]
        classLabel.append(listFromLine[-1])
        index += 1
    classLabelVector = pd.Categorical(classLabel)
    return returnMat,(classLabelVector.labels+1)

#对训练集中的每个维度数据进行归一化
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

#测试txt文件中的准确率
def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('C:/Users/new/Desktop/datingTestSet.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)

#把手写字符转换成一维向量
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

#手写字符测试
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('C:/Users/new/Desktop/trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('C:/Users/new/Desktop/trainingDigits/%s' % fileNameStr)
    testFileList = listdir('C:/Users/new/Desktop/testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('C:/Users/new/Desktop/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)))




handwritingClassTest()

# returnMat,classLabel=file2matrix('C:/Users/new/Desktop/datingTestSet.txt')
# print(autoNorm(returnMat)[0])
# group,labels=createDataSet()
# print(group,labels)
# s=classify0([0,0],group,labels,2)
# print(s)

the total number of errors is: 11

the total error rate is: 0.011628

代码可以直接使用，实验数据可以从这里下载~~~