机器学习/深度学习入门：python实现KNN

《机器学习实战》kNN

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/4/5 16:58
# @Author  : HJH
# @Site    : 
# @File    : kNN.py
# @Software: PyCharm

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

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    #计算欧式距离
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    #argsort函数返回的是数组值从小到大的索引值
    sortedDistIndicies = distances.argsort()
    classCount={}
    #选择距离最小的k个节点
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    #排序
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

#将手写数字图像转换为向量的形式
def img2vector(filename):
    returnVect = zeros((1,1024))
    with open(filename,'r') as fr:
        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 = []
    trainingFileList = listdir('trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        #从文件名中分析数字
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        # print(fileStr)
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        # print(classNumStr)
        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()

手写数字的数据集：链接：https://pan.baidu.com/s/1R5e5BTbVu8jo2nzIuBO_Gw 密码：qfkb