[python函数学习]机器学习实战 - 手写数字识别的测试代码
from numpy import *
import operator #运算符模块 可执行排序操作
from os import listdir
# 将图像转换为向量 img to vector
def img2vector(filename):
returnVect = zeros((1, 1024)) #一维 1024个0 二维图形存储为一维数据 失去结构化信息
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
# 测试代码
def handwritingClassTest():
hwLabels = []
pathTrain = "E:\\machine Learning in Action\\machinelearninginaction\\Ch02\\digits\\trainingDigits"
trainingFileList = listdir(pathTrain) # 返回目录下文件名列表
m = len(trainingFileList) # 文件个数
trainingMat = zeros((m, 1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0] # 以 . 为分隔符,将数据分为两列 只取第一列数据,即删除后缀.txt
classNumStr = int(fileStr.split('_')[0]) # 取0-9分类
hwLabels.append(classNumStr)
trainingMat[i, : ] = img2vector(pathTrain + '/' + fileNameStr) # img to vector
# 测试集
pathTest = "E:\\machine Learning in Action\\machinelearninginaction\\Ch02\\digits\\testDigits"
testFileList = listdir(pathTest)
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0] # 以 . 为分隔符,将数据分为两列 只取第一列数据,即删除后缀.txt
classNumStr = int(fileStr.split('_')[0]) # 取0-9分类
vectorUnderTest = img2vector(pathTest + '/' + fileNameStr) #img to vector
classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3) # 计算欧式距离 选择距离最小的3个点
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)))
os.listdir(path)
返回指定路径下的文件和文件夹列表
path – 是目录路径
eg:
from os import listdir
# 打开文件
path = ""
dirs = os.listdir(path)
# 输出所有文件和文件夹
for file in dirs
print file
输出结果:
test.htm
stamp
faq.htm
_vti_txt
robots.txt
itemlisting
resumelisting
writing_effective_resume.htm
advertisebusiness.htm
papers
resume