Fixed encoding for MovieLens data

ankane · Sep 30, 2023 · af04f3c · af04f3c
1 parent f91b3f5
commit af04f3c
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/lib/disco/data.rb b/lib/disco/data.rb
@@ -9,7 +9,7 @@ def load_movielens
         file_hash: "06416e597f82b7342361e41163890c81036900f418ad91315590814211dca490")
 
       # convert u.item to utf-8
-      movies_str = File.read(item_path).encode("UTF-8", "binary", invalid: :replace, undef: :replace, replace: "")
+      movies_str = File.read(item_path).encode("UTF-8", "ISO-8859-1")
 
       movies = {}
       CSV.parse(movies_str, col_sep: "|") do |row|