encoding update, bugfix in notebook

aparrish · Aug 21, 2019 · 8421204 · 8421204
1 parent eea1fc9
commit 8421204
Show file tree

Hide file tree

Showing 2 changed files with 150 additions and 150 deletions.
diff --git a/data/text_data.py b/data/text_data.py
@@ -86,7 +86,7 @@ def _read_corpus(self, fname, label, max_length, vocab):
 
         # if it looks like a gzip file, use gzip.open
         if fname.endswith('.gz'):
-            opener = lambda x: gzip.open(fname, 'rt')
+            opener = lambda x: gzip.open(fname, 'rt', encoding='utf8')
         else:
             opener = lambda x: open(x)