added flask interface

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, pipe2b
+from classifier import get_training_threads, ThreadDictExtractor,  print_answers, in_training, store_training_data, get_pipe, test_pipe # , pipe2, pipe2b
 from sklearn.pipeline import Pipeline
 from sklearn.preprocessing import LabelEncoder
 import numpy
@@ -23,8 +23,8 @@ import numpy
 
 def train_fit_pipe():
         tt= get_training_threads(b"answered")
-        print tt[1]
-        print tt[0]
+#        print tt[1]
+#        print tt[0]
         pipe1.fit(tt[0],tt[1])
         return pipe1,tt[2]
 def train_fit_pipe2():
@@ -80,13 +80,15 @@ def train_single_thread(tid,p,le,key="answered"):
         else:
                 print "couldn't handle %s" % ca 
     
-
+from flaskapp import app
+                
 #print "arg1:"+sys.argv[1]
 if len(sys.argv)>1:
     if sys.argv[1] == "fetch_threads":
         print flatten_threads(fetch_threads())
 
-
+    if sys.argv[1] == "run_server":
+            app.run(port=3000,debug=True)
     if sys.argv[1] == "print_threads":
         mth=db_session.query(MailThread).all()
         for t in mth:
@@ -104,6 +106,10 @@ if len(sys.argv)>1:
             print t.firstmail
             print t.subject()
             print t.text()
+    if sys.argv[1] == "compile_threads":
+        mth=db_session.query(MailThread).all()
+        for t in mth:
+                t.compile()
             
         
     if sys.argv[1] == "print_threads2":
@@ -113,8 +119,9 @@ if len(sys.argv)>1:
             print "---------------\n"
     
     if sys.argv[1] == "train_thrd2":
-        p, le=train_fit_pipe2()
-        pb, lb =train_fit_pipe2b()
+        p, le=get_pipe("pipe2", "maintopic")
+        pb, lb =get_pipe("pipe2b", "maintopic")
+        
         train_single_thread(int(sys.argv[2]),p,le,b"maintopic")        
     if sys.argv[1] == "train_all2":
         p, labelencoder=train_fit_pipe2()
@@ -130,7 +137,9 @@ if len(sys.argv)>1:
                 predict_thread(pb,lb,t)
                 train_single_thread(t.firstmail, p, labelencoder, b"maintopic") 
 
-        
+    if sys.argv[1] == "benchpipe2":
+        test_pipe(["pipe2","pipe2b","pipe2c"],"maintopic")
+
     if sys.argv[1] == "testpipe2":
         from classifier import ThreadSubjectExtractor, ThreadTextExtractor
         pipe2,le=train_fit_pipe2()