def adnewsfilterM(datelist):
for tocom in datelist:
today = tocom
sentlist=[]
fb= open(rawpath+r'DATA/step8_mR/'+str(today)+r'b', 'w')
ff= open(rawpath+r'DATA/step8_mR/'+str(today)+r'f', 'w')
for item in open(rawpath+r'DATA/step8_mR/'+str(today), 'r'):
text = item
try:
print text
sentlist.append(text)
except IOError,e:
print "Something is wrong: %s" % e
pass
cl2=step3_adnewsfilter.naivebayes(step3_adnewsfilter.getwords)
step3_adnewsfilter.sampletrain(cl2,filenameing,filenameinb)
for sent in sentlist:
try:#print cl2.classify(sent)
fb.write(cl2.classify(sent)+'\n')
except IOError,e:
print "Something is wrong: %s" % e
pass
def adnewsfilterT(datelist,loclist):
#today = datetime.date.today()
#today = '2012-04-21'
for tocom in datelist:
today = tocom
for location in loclist:
print location
sentlist=[]
fb= open(rawpath+r'DATA/step7_wordsegfilter/'+str(today)+r'/'+location+r'b', 'w')
ff= open(rawpath+r'DATA/step7_wordsegfilter/'+str(today)+r'/'+location+r'f', 'w')
for item in open(rawpath+r'DATA/step7_wordsegfilter/'+str(today)+r'/'+location, 'r'):
text = item
try:
print text
sentlist.append(text)
except IOError,e:
print "Something is wrong: %s" % e
pass
cl2=step3_adnewsfilter.naivebayes(step3_adnewsfilter.getwords)
step3_adnewsfilter.sampletrain(cl2,filenameing,filenameinb)
for sent in sentlist:
try:#print cl2.classify(sent)
fb.write(cl2.classify(sent)+'\n')
except IOError,e:
print "Something is wrong: %s" % e
pass
cl2=step3_adnewsfilter.fisherclassifier(step3_adnewsfilter.getwords)
step3_adnewsfilter.sampletrain(cl2,filenameing,filenameinb)
for sent in sentlist:
try:
#print cl2.classify(sent)
ff.write(cl2.classify(sent)+'\n')
except IOError,e:
print "Something is wrong: %s" % e
pass
sentlist.append(text)
except IOError,e:
print "Something is wrong: %s" % e
pass
cl2=step3_adnewsfilter.naivebayes(step3_adnewsfilter.getwords)
step3_adnewsfilter.sampletrain(cl2,filenameing,filenameinb)
for sent in sentlist:
try:#print cl2.classify(sent)
fb.write(cl2.classify(sent)+'\n')
except IOError,e:
print "Something is wrong: %s" % e
pass
cl2=step3_adnewsfilter.fisherclassifier(step3_adnewsfilter.getwords)
step3_adnewsfilter.sampletrain(cl2,filenameing,filenameinb)
for sent in sentlist:
try:
#print cl2.classify(sent)
ff.write(cl2.classify(sent)+'\n')
except IOError,e:
print "Something is wrong: %s" % e
pass
fb.close()
ff.close()
def listtoMdb(db):
for tocom in datelist:
today = tocom
ltom1=rawpath+r'DATA/step8_mwordsegfilter/'+str(today)+'list'
