import tms
tms.tms_train("../data/Traindata_noseg.txt",main_save_path="./",seg=1)
tms.tms_predict("../data/Testdata.txt","./model/tms.config",result_save_path="./tms.result")
def predicting(filename, configfile, savepath):
tms.tms_predict(filename, configfile, result_save_path=savepath, seg=1)
# -*- coding: utf-8 -*-
import tms
import datetime
import time
def timediff(timestart, timestop):
t = timestop - timestart
time_day = t.days
s_time = t.seconds
ms_time = t.microseconds / 1000000
usedtime = int(s_time + ms_time)
time_hour = usedtime / 60 / 60
time_minute = (usedtime - time_hour * 3600) / 60
time_second = usedtime - time_hour * 3600 - time_minute * 60
time_micsecond = (t.microseconds - t.microseconds / 1000000) / 1000
retstr = "%d天%d小时%d分%d秒%d毫秒" % (time_day, time_hour, time_minute, time_second, time_micsecond)
return retstr
if __name__ == "__main__":
beginTime = datetime.datetime.now()
tms.tms_train("../twitterData/twitterTrain.txt", main_save_path="./", seg=1, global_fun="idf")
tms.tms_segment("../twitterData/twitterTestData.txt", [1], "../twitterData/twitterTestData1.txt", "^", "\t", 1)
tms.tms_predict(
"../twitterData/twitterTestData1.txt", "./model/tms.config", result_save_path="../twitterData/tms.result"
)
endTime = datetime.datetime.now()
d = timediff(beginTime, endTime)
print d
#!/usr/bin/python
import sys
sys.path.insert(
0,
"D:\\09Limited_buffer\\earlywarningbyci\\classification\\trainmodel\\src")
sys.path.insert(
0, "D:\\09Limited_buffer\\earlywarningbyci\\classification\\trainmodel\\")
import tms
#_*_ coding: utf-8 _*_
tms.tms_train("D:\\09Limited_buffer\\earlywarningbyci\\classification\\trainmodel\\data\\ad.txt",\
main_save_path="./data/",\
seg=1,indexes=[2],\
str_splitTag=" ",\
stopword_filename="./chinese_stopword.txt",\
ratio=1)
tms.tms_predict("D:\\09Limited_buffer\\earlywarningbyci\\classification\\trainmodel\\data\\adtrain3.txt","D:\\09Limited_buffer\\earlywarningbyci\\classification\\trainmodel\\data\\model\\tms.config",\
result_save_path="./data/pre.result",\
seg=1,\
indexes=[2])
tms.tms_analysis(".\\data\\pre.result")
#-*- coding: utf-8 -*-
import tms
import datetime
import time
def timediff(timestart, timestop):
t = (timestop-timestart)
time_day = t.days
s_time = t.seconds
ms_time = t.microseconds / 1000000
usedtime = int(s_time + ms_time)
time_hour = usedtime / 60 / 60
time_minute = (usedtime - time_hour * 3600 ) / 60
time_second = usedtime - time_hour * 3600 - time_minute * 60
time_micsecond = (t.microseconds - t.microseconds / 1000000) / 1000
retstr = "%d天%d小时%d分%d秒%d毫秒" %(time_day, time_hour, time_minute, time_second, time_micsecond)
return retstr
if __name__ == '__main__':
beginTime = datetime.datetime.now()
tms.tms_train("../twitterData/twitterTrain.txt",main_save_path="./",seg=1,global_fun ='idf')
tms.tms_segment("../twitterData/twitterTestData.txt",[1],"../twitterData/twitterTestData1.txt","^","\t",1)
tms.tms_predict("../twitterData/twitterTestData1.txt","./model/tms.config",result_save_path="../twitterData/tms.result")
endTime = datetime.datetime.now()
d = timediff(beginTime , endTime)
print d
def predicting(filename, configfile, savepath):
tms.tms_predict(filename, configfile, result_save_path=savepath, seg=1)
import tms
tms.tms_train("../data/Traindata_noseg.txt", main_save_path="./", seg=1)
tms.tms_predict("../data/Testdata.txt",
"./model/tms.config",
result_save_path="./tms.result")
fout=open("before_predict.txt","wt")
for i in MicroBlog.objects:
print >>fout,i.mid.encode('utf-8')," ".encode('utf-8'),\
i.content.encode('utf-8')," ".encode('utf-8'),\
i.n_likes+i.n_forwards+i.n_comments," ".encode('utf-8'),\
i.created," ".encode('utf-8'),\
i.content.encode('utf-8')
fout.close()
import tms
#tms.tms_segment("before_predict.txt",out_filename="before_predict_seg.txt",\
# seg=1,indexes=[1],str_splitTag=" ",)
tms.tms_predict("before_predict.txt","D:\\09Limited_buffer\\earlywarningbyci\\classification\\trainmodel\\data\\model\\tms.config",\
result_save_path="predicted.txt",\
seg=1,str_splitTag=" ",\
indexes=[1],\
result_indexes=[0,2,3,4])
#result_indexes=[0,1,2])
filterout=open("predicted.txt","r")
afterfilter=open("filter.csv","wt")
print >>afterfilter,"mid,focus,created,content"
lines=filterout.readlines()
for i in lines:
list=i.split()
label=list[0]
mic_id=list[2]
mic_focus=list[3]
mic_created=list[4]+" "+list[5]
list_length = len(list)
fout = open("before_predict.txt", "wt")
for i in MicroBlog.objects:
print >>fout,i.mid.encode('utf-8')," ".encode('utf-8'),\
i.content.encode('utf-8')," ".encode('utf-8'),\
i.n_likes+i.n_forwards+i.n_comments," ".encode('utf-8'),\
i.created," ".encode('utf-8'),\
i.content.encode('utf-8')
fout.close()
import tms
#tms.tms_segment("before_predict.txt",out_filename="before_predict_seg.txt",\
# seg=1,indexes=[1],str_splitTag=" ",)
tms.tms_predict("before_predict.txt","D:\\09Limited_buffer\\earlywarningbyci\\classification\\trainmodel\\data\\model\\tms.config",\
result_save_path="predicted.txt",\
seg=1,str_splitTag=" ",\
indexes=[1],\
result_indexes=[0,2,3,4])
#result_indexes=[0,1,2])
filterout = open("predicted.txt", "r")
afterfilter = open("filter.csv", "wt")
print >> afterfilter, "mid,focus,created,content"
lines = filterout.readlines()
for i in lines:
list = i.split()
label = list[0]
mic_id = list[2]
mic_focus = list[3]
mic_created = list[4] + " " + list[5]
list_length = len(list)
