add better off topic detection

feature_extractor.py

@@ -44,6 +44,9 @@ class FeatureExtractor(object):
                 self._spell_errors_per_character=sum(e_set._spelling_errors)/float(sum([len(t) for t in e_set._text]))
                 self._grammar_errors_per_character=1-(sum(self._get_grammar_errors
                     (e_set._pos,e_set._text,e_set._tokens))/float(sum([len(t) for t in e_set._text])))
+                bag_feats=self.gen_bag_feats(e_set)
+                f_row_sum=numpy.sum(bag_feats[:,:])/bag_feats.shape[0]
+                self._mean_f_prop=f_row_sum/float(sum([len(t) for t in e_set._text]))
                 ret = "ok"
             else:
                 raise util_functions.InputError(e_set, "needs to be an essay set of the train type.")
@@ -165,14 +168,14 @@ class FeatureExtractor(object):
         all_feedback=[]
         for m in xrange(0,len(e_set._text)):
             individual_feedback=[]
-            if set_grammar_per_character[m]>self._grammar_errors_per_character:
-                individual_feedback.append("Potential grammatical errors.")
-            if set_spell_errors_per_character[m]>self._spell_errors_per_character:
+            if set_grammar_per_character[m]>(self._grammar_errors_per_character):
+                individual_feedback.append("Potential grammar errors.")
+            if set_spell_errors_per_character[m]>(self._spell_errors_per_character):
                 individual_feedback.append("Potential spelling errors.")
             if features is not None:
                 f_row_sum=numpy.sum(features[m,12:])
                 f_row_prop=f_row_sum/len(e_set._text[m])
-                if f_row_prop<.05:
+                if f_row_prop<(self._mean_f_prop):
                     individual_feedback.append("Essay may be off topic.")
             all_feedback.append(individual_feedback)
 

tests/tmpfile

- in order to replicate this experiment , we would need to know the temperature of the vinegar as well as how much vinegar to put in . both of these could vary and therefore change the result of the experiment . 
\ No newline at end of file
+the self employed person variable be the marble , limestone natalie wood , charge plate .the marble bug out designate wa . deoxyguanosine monophosphate . the limestone be . thousand and sir henry joseph wood come out full point . .the stop of the try out comprise that you give birth to limit the hoi polloi of to each one sample distribution .
\ No newline at end of file