def runscheduler(client, username, num):
# 检索任务数量
tasklist = []
listdir('./TaskList', tasklist)
logging.info('【任务调度】: 当前任务数量' + str(len(tasklist)))
forNum = 0
for task in tasklist:
user = main.readJson()
if ('taskNum' in user[0]):
taskNum = user[0]['taskNum']
else:
logging.error('Json未配置taskNum，停止运行')
sys.exit()
logging.info('【任务统计】: 已进行' + taskNum + '个任务')
if forNum >= int(taskNum):
logging.info('【任务分配】: ' + task)
i = importlib.import_module('TaskList.' + task)
i.main(client, username, num)
resetJson('./', './', int(taskNum) + 1)
forNum = forNum + 1
dtime = random.randint(3, 30)
logging.info('【任务调度】: 延时进行' + str(dtime) + '秒')
time.sleep(dtime)
else:
logging.info('【任务跳过】: ' + task)
forNum = forNum + 1
def runscheduler(client, username, num):
# 检索任务数量
tasklist = []
listdir(resource_path('TaskList'), tasklist)
#整理数组
tasklist.sort()
logging.info('【任务调度】: 当前任务数量' + str(len(tasklist)))
user = main.readJson()
if ('taskNum' in user[0]):
taskNum = user[0]['taskNum']
else:
logging.error('Json未配置taskNum，停止运行')
sys.exit()
#日期不同重置任务
if configdate() != str(datetime.datetime.now().month) + str(
datetime.datetime.now().day):
resetJson('./', './', 0)
logging.info('【任务调度】: 日期变更重置任务')
logging.info('【任务统计】: 已进行' + taskNum + '个任务')
forNum = 0
for task in tasklist:
if forNum >= int(taskNum):
logging.info('【任务分配】: ' + task)
i = importlib.import_module('TaskList.' + task)
#启动线程处理
thread = threading.Thread(target=i.main(client, username, num))
#i.main(client,username,num)
thread.start()
time.sleep(1)
thread.join()
resetJson('./', './', int(taskNum) + 1)
forNum = forNum + 1
if forNum < len(tasklist):
dtime = random.randint(3, 10)
logging.info('【任务调度】: 延时进行' + str(dtime) + '秒')
time.sleep(dtime)
else:
print('【任务结束】: 正在尝试发送通知')
else:
logging.info('【任务跳过】: ' + task)
forNum = forNum + 1
if __name__ == '__main__':
#from main import parseDateType
#jsonfileList = parseDateType('onlynews_sort',datetype='10')
#jsonfileList.extend(parseDateType('onlynews_sort',datetype='11'))
#jsonfileList.sort()
#textfileList = parseDateType('onlynews_select_sort',datetype='10')
#textfileList.extend(parseDateType('onlynews_select_sort',datetype='11'))
#textfileList.sort()
jsonfileList = ['onlynews_sort/ptt_news_2015-10-19.json']
textfileList = ['onlynews_select_sort/ptt_news_2015-10-19.txt']
idx = 0
td_first = TopicDetection()
first_corpus = True
last_datetime = ''
for jsonfile, textfile in zip(jsonfileList, textfileList):
dataList = readJson(jsonfile)
textList = readText(textfile)
print textfile
head, tail = os.path.split(textfile)
tail = tail.split('.')[0]
matfile = "result/" + tail + ".mat"
labelfile = "result/" + tail + "_label.txt"
gendictfile = "gensim_tmp/" + tail + ".dict"
#on-the-fly
finalpredfile = "result/" + tail + "_mean.pred"
finaltopicfile = "result/" + tail + "_mean.topic"
for idx in range(len(textList)):
newtext = [textList[idx]]
if first_corpus and idx == 0:
td_first.constructTermVector(newtext,
gendictfile,
if __name__ == "__main__":
# from main import parseDateType
# jsonfileList = parseDateType('onlynews_sort',datetype='10')
# jsonfileList.extend(parseDateType('onlynews_sort',datetype='11'))
# jsonfileList.sort()
# textfileList = parseDateType('onlynews_select_sort',datetype='10')
# textfileList.extend(parseDateType('onlynews_select_sort',datetype='11'))
# textfileList.sort()
jsonfileList = ["onlynews_sort/ptt_news_2015-10-19.json"]
textfileList = ["onlynews_select_sort/ptt_news_2015-10-19.txt"]
idx = 0
td_first = TopicDetection()
first_corpus = True
last_datetime = ""
for jsonfile, textfile in zip(jsonfileList, textfileList):
dataList = readJson(jsonfile)
textList = readText(textfile)
print textfile
head, tail = os.path.split(textfile)
tail = tail.split(".")[0]
matfile = "result/" + tail + ".mat"
labelfile = "result/" + tail + "_label.txt"
gendictfile = "gensim_tmp/" + tail + ".dict"
# on-the-fly
finalpredfile = "result/" + tail + "_mean.pred"
finaltopicfile = "result/" + tail + "_mean.topic"
for idx in range(len(textList)):
newtext = [textList[idx]]
if first_corpus and idx == 0:
td_first.constructTermVector(newtext, gendictfile, outfile=matfile, update=False)
last_datetime = datetime.strptime(dataList[idx]["datetime"], "%Y-%m-%d %H:%M:%S")
max_length = -1
for label, titleList in cluster_dict.iteritems():
if len(titleList) > max_length:
max_label = label
max_length = len(titleList)
outtext = open(outtextfile, "w")
outjson = open(outjsonfile, "w")
for (title, idx) in cluster_dict[max_label]:
outtext.write("%s" % (textList[idx]))
outjson.write(json.dumps(jsonList[idx], ensure_ascii=False).encode("utf8") + "\n")
outtext.close()
outjson.close()
if __name__ == "__main__":
if len(sys.argv) != 4:
print "usage: python cluster_analysis.py textfile jsonfile outfile"
print "(e.g.) python cluster_analysis.py vectordata/total_10.txt vectordata/total_10.json cluster_title_10.txt"
exit()
clusterfile = "cluster_label.txt"
textfile = sys.argv[1]
jsonfile = sys.argv[2]
outfile = sys.argv[3]
labelList = readCluster(clusterfile)
textList = readText(textfile)
jsonList = readJson(jsonfile)
outputCluster(textList, jsonList, labelList, outfile)
# extractCluster(textList, jsonList, labelList, 'vectordata/new.txt', 'vectordata/new.json')
if len(titleList) > max_length:
max_label = label
max_length = len(titleList)
outtext = open(outtextfile, 'w')
outjson = open(outjsonfile, 'w')
for (title, idx) in cluster_dict[max_label]:
outtext.write('%s' % (textList[idx]))
outjson.write(
json.dumps(jsonList[idx], ensure_ascii=False).encode('utf8') +
"\n")
outtext.close()
outjson.close()
if __name__ == '__main__':
if len(sys.argv) != 4:
print 'usage: python cluster_analysis.py textfile jsonfile outfile'
print '(e.g.) python cluster_analysis.py vectordata/total_10.txt vectordata/total_10.json cluster_title_10.txt'
exit()
clusterfile = 'cluster_label.txt'
textfile = sys.argv[1]
jsonfile = sys.argv[2]
outfile = sys.argv[3]
labelList = readCluster(clusterfile)
textList = readText(textfile)
jsonList = readJson(jsonfile)
outputCluster(textList, jsonList, labelList, outfile)
#extractCluster(textList, jsonList, labelList, 'vectordata/new.txt', 'vectordata/new.json')
