labelType, labelNum = createMoreMatch(LABEL_PATH)
matchHead = u.create_file_head(SOURCE_PATH, 'right', [LABEL_FILE.split('.')[0]])
print u.utf8_2_gbk('标签个数:' + str(labelNum) + '个')
for key, value in labelType.items():
count += 1
print u.utf8_2_gbk('当前执行到第' + str(count) + '个')
words = value.strip().split('|')
if len(words) == 1:
c = createPattern(words[0], ACCURATE)
p = re.compile(c)
for num, line in enumerate(source_file_body):
content = u.create_content(line, COLUNM)
if p.match(content):
source_file_body[num] = source_file_body[num].strip() + key + '|' + '\n'
keyWordCount[key] = keyWordCount.get(key, 0) + 1
if len(words) == 2:
c = createPattern(words[0], ACCURATE)
f = createPattern(words[1], ACCURATE)
cp = re.compile(c)
fp = re.compile(f)
for num, line in enumerate(source_file_body):
content = u.create_content(line, COLUNM)
if cp.match(content) and not fp.match(content):
source_file_body[num] = source_file_body[num].strip() + key + '|' + '\n'
keyWordCount[key] = keyWordCount.get(key, 0) + 1
u.create_result_file(u.setFileName(SOURCE_FILE, LABEL_FILE), matchHead, source_file_body)
u.writeDictFile(u.changeFileName(combinefileName(SOURCE_FILE, LABEL_FILE), '统计.txt'), keyWordCount, 1)
except:
traceback.print_exc(file=open('error.txt', 'w+'))
matchHead = u.utf8_2_gbk('内容' + ',' + LABEL_FILE.split('.')[0] + '\n')
print u.utf8_2_gbk('标签个数:' + str(labelNum) + '个')
for key, value in labelType.items():
count += 1
print u.utf8_2_gbk('当前执行到第' + str(count) + '个')
words = value.strip().split('|')
if len(words) == 1:
c = createPattern(words[0])
p = re.compile(c)
for num, line in enumerate(source_file_body):
if p.match(line):
source_file_body[num] = source_file_body[num].strip(
) + key + '|' + '\n'
keyWordCount[key] = keyWordCount.get(key, 0) + 1
if len(words) == 2:
c = createPattern(words[0])
f = createPattern(words[1])
cp = re.compile(c)
fp = re.compile(f)
for num, line in enumerate(source_file_body):
if cp.match(line) and not fp.match(line):
source_file_body[num] = source_file_body[num].strip(
) + key + '|' + '\n'
keyWordCount[key] = keyWordCount.get(key, 0) + 1
u.create_result_file(u.setFileName(SOURCE_FILE, LABEL_FILE), matchHead,
source_file_body)
u.writeDictFile(u.changeFileName(LABEL_FILE, '统计.csv'), keyWordCount, 1)
print u.utf8_2_gbk('开始执行')
file_list = u.GetFileList(FILE_PATH, [])
for f in file_list:
file_dict[f.encode('gbk')] = rm_repeat(u.create_file_body(f.encode('utf-8')))
total_file = file('total.csv', 'w+')
for key, value in file_dict.items():
total_file.writelines(value)
total_file.close()
count_file = open('total.csv', 'rb')
for line in count_file:
content = u.create_content(line, 1)
count_dict[content] = count_dict.get(content, 0) + 1
count_file.close()
u.writeDictFile(RESULT_FILE, count_dict, 1)
print u.utf8_2_gbk('执行完毕')
print u.utf8_2_gbk('输出文件路径:') + sys.path[0] + u.utf8_2_gbk('\\' + RESULT_FILE)
except:
traceback.print_exc()
print '=============================================================='
print u.utf8_2_gbk('运行出错')
print u.utf8_2_gbk('常见错误')
print u.utf8_2_gbk('IndexError: list index out of range')
print u.utf8_2_gbk('匹配列选择错误或source文件夹为空或label文件夹为空')
print '=============================================================='
raw_input('Press Enter to exit...')
os.remove('total.csv')
head = linecache.getline(u.utf8_2_gbk(SOURCE_FILE), 1).strip()
TOTALCOLUNM = len(head.split(','))
print u.utf8_2_gbk('标签词个数:') + u.printDictLen(labelWordp)
source_file_body = u.create_file_body(SOURCE_FILE)
for key, value in labelWordp.items():
i += 1
print u.utf8_2_gbk('当前执行到{0}个'.format(i))
for num, line in enumerate(source_file_body):
data = line.strip().split(',')
if len(data) == TOTALCOLUNM + 1:
continue
content = data[COLUNM - 1]
p = re.compile(value)
if p.match(content):
source_file_body[num] = source_file_body[num].strip() + ',' + key + '\n'
keyWordCount[key] = keyWordCount.get(key, 0) + 1
# 补全格式
for num, line in enumerate(source_file_body):
data = line.strip().split(',')
if len(data) == TOTALCOLUNM + 1:
continue
source_file_body[num] = source_file_body[num].strip() + ',' + '' + '\n'
result_file_head = u.create_file_head(SOURCE_FILE, 'right', [u.gbk_2_utf8(columnName)])
u.create_result_file(RESULT_FILE, result_file_head, source_file_body)
KEYWORD_FILE = LABELWORD.split('.')[0] + '统计.txt'
u.writeDictFile(KEYWORD_FILE, keyWordCount) # 输出统计结果
print u.utf8_2_gbk('开始执行聚类')
for num, line in enumerate(source_file_body):
content = re.sub(pattern, '', u.create_content(line, COLUMN))
if len(content) <= 20:
keywords = jieba.analyse.extract_tags(content, topK=2)
else:
keywords = jieba.analyse.extract_tags(content, topK=TOPKET)
keywords.sort()
key = ','.join(keywords)
cluster[key] = str(cluster.get(key, 0)) + "," + str(num + 1)
print u.utf8_2_gbk('聚类完成,生成输出文件')
for num, value in enumerate(cluster.itervalues()):
cluster_list = value[2:].split(',')
count_file_dict[num] = len(cluster_list)
for n in cluster_list:
result_file_body.append(
str(num) + ',' + source_file_body[int(n) - 1])
u.create_result_file(u.changeFileName(SOURCENAME, '-聚类.csv'),
source_file_head, result_file_body)
u.writeDictFile(u.changeFileName(SOURCENAME, '-聚类统计.txt'),
count_file_dict, 1)
except:
traceback.print_exc()
print '=============================================================='
print u.utf8_2_gbk('运行出错')
print u.utf8_2_gbk('常见错误')
print u.utf8_2_gbk('IndexError: list index out of range')
print u.utf8_2_gbk('匹配列选择错误或source文件夹为空或label文件夹为空')
print '=============================================================='
raw_input('Press Enter to exit...')