small rewrites

run.py

@@ -15,7 +15,7 @@ from storage.fetch_mail import fetch_threads, flatten_threads
 from storage import Mail, MailThread, db_session
 #import yaml
 #import email
-from classifier import get_training_threads,  print_answers, in_training, store_training_data, get_pipe, test_pipe, train_single_thread # , pipe2, pipe2b
+from classifier import get_training_threads,  print_answers,get_pipe, test_pipe, train_single_thread # , pipe2, pipe2b
 from classifier import predict_threads
 maintopic_values=["studium", "information","ausleihen","jobausschreibung", "umfragen"]
 
@@ -30,31 +30,8 @@ if len(sys.argv)>1:
 
     if sys.argv[1] == "fetch_threads":
         print flatten_threads(fetch_threads())
-    if sys.argv[1] == "predict_threads2":
-        predict_threads()
     if sys.argv[1] == "predict_threads":
-        print "predicting threads"
-        pipe1,le=get_pipe("pipe1",b"answered",["db"])
-        pipe2,le2=get_pipe("pipe2g", b"maintopic",["db"])
-        pipe3,le3=get_pipe("pipe2b", b"lang",["db"])
-        q=db_session.query(MailThread).filter(MailThread.istrained.op("IS NOT")(True))
-        
-        mail_threads=q.all()
-        
-        if len(mail_threads) ==0:
-                raise ValueError("no untrained threads found")
-        answered=le.inverse_transform(pipe1.predict(mail_threads))
-        maintopic=le2.inverse_transform(pipe2.predict(mail_threads))
-        lang=le3.inverse_transform(pipe3.predict(mail_threads))
-
-        for i, t in enumerate(mail_threads):
-                t.answered=bool(answered[i])
-                t.opened=bool(answered[i])
-
-                t.maintopic=str(maintopic[i])
-                t.lang=str(lang[i])
-                db_session.add(t)
-                db_session.commit()
+        predict_threads()
     if sys.argv[1]=="stats":
             for topic in maintopic_values:
                     print topic
@@ -70,20 +47,6 @@ if len(sys.argv)>1:
             from flaskapp import app
             app.run(port=3000,debug=True)
 
-
-    if  sys.argv[1] == "trained_threads_from_yml":
-        from classifier.classifier import train
-        for k in train:
-                print k
-                t=db_session.query(MailThread).filter(MailThread.firstmail==k).first()
-                t.istrained=True
-                db_session.add(t)
-        db_session.commit()
-    if sys.argv[1] == "print_threads2":
-        mth=db_session.query(MailThread).all()
-        for t in mth:
-            print t.to_text()
-            print "---------------\n"
     
     if sys.argv[1] == "train_thrd2":
         p, le=get_pipe("pipe2", "maintopic",["db"])
@@ -207,37 +170,7 @@ if len(sys.argv)>1:
         db_session.commit()
     
 
-    if sys.argv[1] == "fetch_mail":
-        print "fetching mail %d " % int(sys.argv[2])
-        m=fetch_mail(int(sys.argv[2]))
-        hd=decode_header(m['ENVELOPE'].subject)
-        hd2=[]
-        #    print hd
-        for h in hd:
-            if not h[1] is None:
-                hd2.append(h[0].decode(h[1]))
-                #            print h[0].decode(h[1])
-            else:
-                hd2.append(h[0])
-        print "\nBetreff:"
-        for h in hd2:
-            print h
-        print "FROM:"
-        for t in m['ENVELOPE'].from_:
-            print t
-        print "TO:"
-        for t in m['ENVELOPE'].to:
-            print t
-        em=email.message_from_string(m['RFC822'])
-        for p in em.walk():
-            if p.get_content_maintype()=="text":
-                print p.get_payload()
-            elif p.get_content_maintype()=="multipart":
-                print p.get_payload()
-            else:
-                print p.get_content_maintype()
-
-    
+   
 
     if sys.argv[1] == "initdb":
         from storage import init_db