Merge branch 'master' of ssh://delanoe.org:1979/gargantext into samuel

analysis/functions.py

@@ -243,9 +243,9 @@ def get_cooc(request=None, corpus_id=None, cooc_id=None, type='node_link', n=150
 
 def tfidf(corpus, document, ngram):
     try:
-        x = Node_Ngram.objects.get(node=document, ngram=ngram).weight
-        y = Node_Ngram.objects.filter(node=document).count()
-        tf = x/y
+        occurences_of_ngram = Node_Ngram.objects.get(node=document, ngram=ngram).weight
+        ngrams_by_document = sum([ x.weight for x in Node_Ngram.objects.filter(node=document)])
+        term_frequency = occurences_of_ngram / ngrams_by_document
     
         xx = Node.objects.filter(parent=corpus, type=NodeType.objects.get(name="Document")).count()
         yy = Node_Ngram.objects.filter(ngram=ngram).count()

parsing/FileParsers/EuropressFileParser.py

@@ -138,9 +138,9 @@ class EuropressFileParser(FileParser):
                #    metadata['language_iso2'] = 'en'
                
                
-#               metadata['publication_year']  = metadata['date'].strftime('%Y')
-#               metadata['publication_month'] = metadata['date'].strftime('%m')
-#               metadata['publication_day']  = metadata['date'].strftime('%d')
+               metadata['publication_year']  = metadata['publication_date'].strftime('%Y')
+               metadata['publication_month'] = metadata['publication_date'].strftime('%m')
+               metadata['publication_day']  = metadata['publication_date'].strftime('%d')
                metadata['publication_date'] = ""
 
                metadata['object_id'] = str(metadata['text'][-9])