【P19 机器学习-分类算法及应用实践】手写数字识别

手写字识别

1 手写字的识别 （KNN）

通过0,1二值化把手写数字，变化成矩阵
32*32

1.1 读取训练集

import numpy as np 
from os import listdir  # 读取文件夹下的所有文件，形成一个文件列表

# 图片转矩阵
def img2vector(filename):
    returnVect = np.zeros((1,1024)) # 每个图片矩阵32*32，存为1行
    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

#读取数据
hwLabels = []
trainingFileList = listdir('E:\\Progarm\\Py_Program\\HandwritingRecognition\\trainingDigits')
m = len(trainingFileList)
trainingMat = np.zeros((m,1024))
for i in  range(m):
    fileNameStr=trainingFileList[i]
    fileStr = fileNameStr.split('.')[0]
    classNumStr = int(fileStr.split('_')[0])
    hwLabels.append(classNumStr)
    trainingMat[i,:] = img2vector('E:\\Progarm\\Py_Program\\HandwritingRecognition\\trainingDigits\\%s' % fileNameStr)

print(trainingFileList)
print(hwLabels)
print(trainingMat)

1.2 读取测试集

# 读取测试集,执行KNN分类
testFileList = listdir('E:\\Progarm\\Py_Program\\HandwritingRecognition\\testDigits')
k = 3
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('E:\\Progarm\\Py_Program\\HandwritingRecognition\\testDigits\\%s' % fileNameStr)
    classifierResult = K.knn(vectorUnderTest,trainingMat,hwLabels,k)
    print('KNN识别的结果是： %d , 实际是： %d' % (classifierResult,classNumStr))
    if classifierResult != classNumStr:
        errorCount +=1.0

print('训练集数量： %d ,测试集数量： %d' % (m,mTest))
print('错误识别数 : %d , 正确率 ： %f ' % (errorCount , (1-errorCount/float(mTest))*100))

1.3 完整程序

import numpy as np 
from os import listdir # 读取文件夹下的所有文件
import knn as K

# 图片转矩阵
def img2vector(filename):
    returnVect = np.zeros((1,1024)) # 每个图片矩阵32*32，存为1行
    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

#读取训练集数据
hwLabels = []
trainingFileList = listdir('E:\\Progarm\\Py_Program\\HandwritingRecognition\\trainingDigits')
m = len(trainingFileList)
trainingMat = np.zeros((m,1024))
for i in  range(m):
    fileNameStr = trainingFileList[i]
    fileStr = fileNameStr.split('.')[0]
    classNumStr = int(fileStr.split('_')[0])
    hwLabels.append(classNumStr)
    trainingMat[i,:] = img2vector('E:\\Progarm\\Py_Program\\HandwritingRecognition\\trainingDigits\\%s' % fileNameStr)


#print(trainingFileList)
#print(hwLabels)
#print(trainingMat)


# 读取测试集,执行KNN分类
testFileList = listdir('E:\\Progarm\\Py_Program\\HandwritingRecognition\\testDigits')
k = 3
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('E:\\Progarm\\Py_Program\\HandwritingRecognition\\testDigits\\%s' % fileNameStr)
    classifierResult = K.knn(vectorUnderTest,trainingMat,hwLabels,k)
    print('KNN识别的结果是： %d , 实际是： %d' % (classifierResult,classNumStr))
    if classifierResult != classNumStr:
        errorCount +=1.0
  
print('训练集数量： %d ,测试集数量： %d' % (m,mTest))
print('错误识别数 : %d , 正确率 ： %f ' % (errorCount , (1-errorCount/float(mTest))*100))