fixes for tox21 dataset (#163)

* fixes for tox21 dataset

* ruff fixes

Author: schnamo

chebai/preprocessing/datasets/pubchem.py

@@ -106,6 +106,7 @@ def _load_dict(input_file_path: str) -> Generator[dict, None, None]:
         Yields:
             dict: Dictionary containing 'features', 'labels' (None), and 'ident' fields.
         """
+        # pubchem IDs are here
         with open(input_file_path, "r") as input_file:
             for row in input_file:
                 ident, smiles = row.split("\t")

chebai/preprocessing/datasets/tox21.py

@@ -161,7 +161,7 @@ def _load_dict(self, input_file_path: str) -> List[Dict]:
             for row in reader:
                 smiles = row["smiles"]
                 labels = [
-                    bool(int(float(label))) if len(label) > 1 else None
+                    bool(int(float(label))) if len(label) >= 1 else None
                     for label in (row[k] for k in self.HEADERS)
                 ]
                 # group = int(row["group"])

chebai/preprocessing/reader.py

@@ -98,8 +98,11 @@ def _read_components(self, row: Dict[str, Any]) -> Dict[str, Any]:
         under the additional `missing_labels` keyword."""
         labels = self._get_raw_label(row)
         additional_kwargs = self._get_additional_kwargs(row)
-        if any(label is None for label in labels):
-            additional_kwargs["missing_labels"] = [label is None for label in labels]
+        if labels is not None:
+            if any(label is None for label in labels):
+                additional_kwargs["missing_labels"] = [
+                    label is None for label in labels
+                ]
         return dict(
             features=self._get_raw_data(row),
             labels=labels,