From 13900d04256fb192b33c33f9488ee1a6c0cddcac Mon Sep 17 00:00:00 2001 From: sfluegel Date: Fri, 24 Jul 2026 10:06:27 +0200 Subject: [PATCH] cast chebi ids to string to ensure that they can be compared to splits_df --- chebai/preprocessing/datasets/base.py | 1 + 1 file changed, 1 insertion(+) diff --git a/chebai/preprocessing/datasets/base.py b/chebai/preprocessing/datasets/base.py index 24655b0d..d5cd5653 100644 --- a/chebai/preprocessing/datasets/base.py +++ b/chebai/preprocessing/datasets/base.py @@ -1111,6 +1111,7 @@ def _retrieve_splits_from_csv(self) -> None: filename = self.processed_file_names_dict["data"] data = self.load_processed_data_from_file(filename) df_data = pd.DataFrame(data) + df_data["ident"] = df_data["ident"].astype(str) if self.apply_id_filter: print(f"Applying ID filter from {self.apply_id_filter}...")