Пример #1
0
 def split_names_corpus(self, document_class=Name):
     """Split the names corpus into training, dev, and test sets"""
     names = NamesCorpus(document_class=document_class)
     self.assertEqual(len(names), 5001 + 2943) # see names/README
     seed(hash("names"))
     shuffle(names)
     return (names[:5000], names[5000:6000], names[6000:])
Пример #2
0
 def split_names_corpus(self, document_class=Name):
     names = NamesCorpus(document_class=document_class)
     self.assertEqual(len(names), 5001 + 2943) # see names/README
     seed(hash("names"))
     shuffle(names)
     return (names[:5000], names[5000:6000], names[6000:])