removed matching model fields, automatic classifier reloading, added autmatic_classification field to matching model

src/documents/management/commands/document_create_classifier.py

@@ -42,9 +42,14 @@ class Command(Renderable, BaseCommand):
 
         # Step 2: vectorize data
         logging.getLogger(__name__).info("Vectorizing data...")
-        clf.data_vectorizer = CountVectorizer(analyzer='char', ngram_range=(1, 5), min_df=0.05)
+        clf.data_vectorizer = CountVectorizer(analyzer='char', ngram_range=(2, 6), min_df=0.1)
         data_vectorized = clf.data_vectorizer.fit_transform(data)
 
+        print(clf.data_vectorizer.vocabulary_)
+
+        logging.getLogger(__name__).info("Shape of vectorized data: {}".format(data_vectorized.shape))
+
+
         clf.tags_binarizer = MultiLabelBinarizer()
         labels_tags_vectorized = clf.tags_binarizer.fit_transform(labels_tags)
 

src/documents/management/commands/document_retagger.py

@@ -46,7 +46,11 @@ class Command(Renderable, BaseCommand):
             documents = Document.objects.all().exclude(tags__is_archived_tag=True).distinct()
 
         logging.getLogger(__name__).info("Loading classifier")
-        clf = DocumentClassifier.load_classifier()
+        try:
+            clf = DocumentClassifier.load_classifier()
+        except FileNotFoundError:
+            logging.getLogger(__name__).fatal("Cannot classify documents, classifier model file was not found.")
+            return
 
 
         for document in documents: