def markPos():
csvHeader = ["文件名","源文件词数","附码文件词数","词数差","差词占比"]
for subDir in os.listdir(orgDir): #子目录
data = []
pathname = os.path.join(orgDir, subDir)
if (os.path.isdir(pathname)):
new_pathname = os.path.join(tagDir, subDir)
mkdir(new_pathname)
logFile = os.path.join(new_pathname,"log.csv")
with open(logFile, "w", newline='') as f:
# with open(birth_weight_file, "w") as f:
writer = csv.writer(f)
now = time.strftime("%Y-%m-%d %H:%M:%S")
writer.writerows([[now]])
writer.writerows([csvHeader])
f.close()
for filename in os.listdir(pathname): #遍历文件
if os.path.splitext(filename)[1][1:] =='txt':
orgFile = os.path.join(pathname,filename)
targetFile = os.path.join(new_pathname,filename)
print(orgFile)
orgCount,newCount = posTagging(orgFile,targetFile)
if newCount==2:
precent = 'ERROR'
else:
precent = abs(orgCount-newCount),str(round(abs(orgCount-newCount)/newCount*100))+'%'
data.append([filename,orgCount,newCount,precent])
# with open(logFile,'a',newline='') as f:
# writer = csv.writer(f)
# writer.writerows([[filename,orgCount,newCount,abs(orgCount-newCount),str(round(abs(orgCount-newCount)/newCount*100))+'%']])
# f.close()
with open(logFile,'a',newline='') as f:
writer = csv.writer(f)
writer.writerows(data)
f.close()
def get_sentences():
data = []
orgDir = "附码语料库"
toDir = "分句语料库"
all_dirs, all_files, all_names = getdir(orgDir)
for i in all_dirs: #创建子目录
mkdir(os.path.join(toDir,i))
for i in all_files:
print(i)
file_route = i.split('\\')
file_route[0] = toDir
file = "\\".join(file_route)
data = splitSentence(i) #获取每个文章分句list
save_file(data,file)
def extract_trunk():
orgDir = "分句语料库"
toDir = "主干语料库"
vbDir = "句首动词文件"
# files=getdir(r'C:\Users\jee_s\Desktop\助研\分句语料库')
all_dirs, all_files, all_names = getdir(orgDir)
for i in all_dirs: #创建子目录
mkdir(os.path.join(toDir,i))
mkdir(os.path.join(vbDir,i))
for i in all_files:
print(i)
file_route = i.split('\\')
file_route[0] = toDir
file = "\\".join(file_route)
file_route[0] = vbDir
vbFile = "\\".join(file_route)
data = readtxt(i) #len(data)=文章句数 data[i]为每一句以空格分割后的单词List
pre_data,not_trunks = tran_sentense(data)
print(i+"文件没有主干行数：",not_trunks)
save_to_txt(pre_data, file, vbFile)
def subsection():
mkdir(sectionDir)
logFile = os.path.join(sectionDir, "log.csv")
with open(logFile, "w", newline='') as f:
writer = csv.writer(f)
now = time.strftime("%Y-%m-%d %H:%M:%S")
# writer.writerows([[now]])
writer.writerows([csvHeader])
f.close()
for subDir in os.listdir(tagDir):
pathname = os.path.join(tagDir, subDir)
if (os.path.isdir(pathname)):
new_pathname = os.path.join(sectionDir, subDir)
mkdir(new_pathname)
for filename in os.listdir(pathname):
if os.path.splitext(filename)[1] == '.txt':
orgFile = os.path.join(pathname, filename)
targetDir = os.path.join(new_pathname,
filename.split('.')[0])
mkdir(targetDir)
cutEssay(orgFile, targetDir, logFile)