机器学习实战2-2KNN识别手写数字

from numpy import *
from os import listdir
import KNN
"""
将32*32的二进制图像矩阵转换为1*1024的向量
"""
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

testVector = img2vector('digits/testDigits/0_13.txt')  # 文件存放在项目中的路径
#print(testVector[0,0:124])

# 使用K-近邻算法识别手写数字
def handwritingClassTest():
    hwLables = []
    trainingFilelist = listdir('digits/trainingDigits')  # 返回指定路径下的文件和文件夹列表
    m = len(trainingFilelist)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFilelist[i]
        fileStr = fileNameStr.split('.')[0]  # 通过指定的分隔符：，对字符串进行切片。参数num表示返回num+1个参数列表。take off .txt
        classNumStr = int(fileStr.split('_')[0])  # 得到二进制图像对应的数字
        hwLables.append(classNumStr)  # 得到训练集标签
        trainingMat[i,:] = img2vector('digits/trainingDigits/%s'%fileNameStr)  # 该路径下依次向被调函数传递
    testFileList = listdir('digits/testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileNameStr.split('_')[0])
        vectorUnderTest = img2vector('digits/testDigits/%s'%fileNameStr)  # 单个测试向量，1*1024
        classifierReuslt = KNN.classify0(vectorUnderTest,trainingMat,hwLables,3)  # 得到分类器给出的训练结果，即标签
        print("the classifier came back with: %d, the real answer is: %d"\
              %(classifierReuslt, classNumStr))
        if(classNumStr != classifierReuslt): errorCount += 1.0
    print("\nthe total number of errors is: %d"%errorCount)
    print("\nthe total error rate is: %f" %(errorCount/float(mTest)))

handwritingClassTest()