updates + sqlite db

run.py

@@ -14,7 +14,7 @@ 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, ThreadDictExtractor, pipe1, print_answers, in_training, store_training_data, pipe2
+from classifier import get_training_threads, ThreadDictExtractor, pipe1, print_answers, in_training, store_training_data, pipe2, pipe2b
 from sklearn.pipeline import Pipeline
 from sklearn.preprocessing import LabelEncoder
 import numpy
@@ -32,6 +32,16 @@ def train_fit_pipe2():
         pipe2.fit(tt[0],tt[1])
         return pipe2,tt[2]
 
+def train_fit_pipe2b():
+        tt= get_training_threads(b"maintopic")
+        pipe2b.fit(tt[0],tt[1])
+        return pipe2b,tt[2]
+
+def predict_thread(p,l,t):
+        pre=p.predict([t])
+        print "Status is answered is estimated to be: " + str(l.inverse_transform(pre)[0])
+        return pre
+
 
 def train_single_thread(tid,p,le,key="answered"):
         if (not type(tid) is int): raise TypeError("ID must be of type int") 
@@ -43,8 +53,8 @@ def train_single_thread(tid,p,le,key="answered"):
         pre=p.predict([mth])
         answ=pre[0]
         #
-        print mth.to_text()
-        print mth.text()
+#        print mth.to_text()
+#        print mth.text()
         print "Status is answered is estimated to be: " + str(le.inverse_transform(pre)[0])
         print_answers(le)
 
@@ -104,9 +114,11 @@ if len(sys.argv)>1:
     
     if sys.argv[1] == "train_thrd2":
         p, le=train_fit_pipe2()
+        pb, lb =train_fit_pipe2b()
         train_single_thread(int(sys.argv[2]),p,le,b"maintopic")        
     if sys.argv[1] == "train_all2":
         p, labelencoder=train_fit_pipe2()
+        pb, lb=train_fit_pipe2b()
         mth=db_session.query(MailThread).all()
         print mth
         for t in mth:
@@ -115,6 +127,7 @@ if len(sys.argv)>1:
                 print "---------------------------------------------------"
                 print t.firstmail
                 print t.text()
+                predict_thread(pb,lb,t)
                 train_single_thread(t.firstmail, p, labelencoder, b"maintopic")