improve error handling in deepSMILES reader

ChEB-AI · Nov 24, 2023 · 46852e4 · 46852e4
1 parent c615f17
commit 46852e4
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/chebai/preprocessing/reader.py b/chebai/preprocessing/reader.py
@@ -124,15 +124,15 @@ def name(cls):
     def _read_data(self, raw_data):
         try:
             tokenized = _tokenize(self.converter.encode(raw_data))
+            tokenized = [self._get_token_index(v[1]) for v in tokenized]
         except ValueError as e:
             print(f'could not process {raw_data}')
+            print(f'Corresponding deepSMILES: {self.converter.encode(raw_data)}')
             print(f'\t{e}')
             self.error_count += 1
             print(f'\terror count: {self.error_count}')
             tokenized = []
-        return [
-            self._get_token_index(v[1]) for v in tokenized
-        ]
+        return tokenized
 
 
 class ChemDataUnlabeledReader(ChemDataReader):