black

Author: svnv-svsv-jm

pytorch_forecasting/data/timeseries.py

@@ -1569,9 +1569,9 @@ def __getitem__(self, idx: int) -> Tuple[Dict[str, torch.Tensor], torch.Tensor]:
 
             # switch some variables to nan if encode length is 0
             if encoder_length == 0 and len(self.dropout_categoricals) > 0:
-                data_cat[:, [self.flat_categoricals.index(c) for c in self.dropout_categoricals]] = (
-                    0  # zero is encoded nan
-                )
+                fc = self.flat_categoricals
+                dc = self.dropout_categoricals
+                data_cat[:, [fc.index(c) for c in dc]] = 0  # zero is encoded nan
 
         assert decoder_length > 0, "Decoder length should be greater than 0"
         assert encoder_length >= 0, "Encoder length should be at least 0"