updates + sqlite db

classifier.py

@@ -4,6 +4,7 @@ from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer
 from sklearn.preprocessing import LabelEncoder
 from sklearn.pipeline import Pipeline, FeatureUnion
 from sklearn.naive_bayes import MultinomialNB
+from sklearn.neural_network import MLPClassifier
 
 import numpy as np
 import yaml
@@ -100,7 +101,28 @@ pipe2 = Pipeline([
     ], transformer_weights={
         'subject': 1,
         'text': 0.7,
-        'envelope': 0.5
+        'envelope': 0.7
     } )),
     ('clf', MultinomialNB())
 ])
+
+pipe2b = Pipeline([
+    ('union', FeatureUnion(transformer_list=[
+        ('subject', Pipeline([('tse', ThreadSubjectExtractor()),
+                              ('cv',CountVectorizer()),
+                              ('tfidf', TfidfTransformer())
+        ])),
+        ('text',    Pipeline([('tte',ThreadTextExtractor()),
+                              ('cv',CountVectorizer()),
+                              ('tfidf', TfidfTransformer())
+        ])),
+        ('envelope', Pipeline([('tde', ThreadDictExtractor()),
+                               ('dv',DictVectorizer())
+        ]))
+    ], transformer_weights={
+        'subject': 1,
+        'text': 0.7,
+        'envelope': 0.7
+    } )),
+    ('mlc', MLPClassifier())
+])