Adding split type cv-no-test for cross-validation without test split

chemprop/args.py

@@ -206,7 +206,7 @@ class TrainArgs(CommonArgs):
     """Path to separate val set, optional."""
     separate_test_path: str = None
     """Path to separate test set, optional."""
-    split_type: Literal['random', 'scaffold_balanced', 'predetermined', 'crossval', 'cv', 'index_predetermined'] = 'random'
+    split_type: Literal['random', 'scaffold_balanced', 'predetermined', 'crossval', 'cv', 'cv-no-test', 'index_predetermined'] = 'random'
     """Method of splitting the data into train/val/test."""
     split_sizes: Tuple[float, float, float] = (0.8, 0.1, 0.1)
     """Split proportions for train/validation/test sets."""

chemprop/data/utils.py

@@ -349,7 +349,7 @@ def split_data(data: MoleculeDataset,
         train, val, test = tuple(data_split)
         return MoleculeDataset(train), MoleculeDataset(val), MoleculeDataset(test)
 
-    elif split_type == 'cv':
+    elif split_type in {'cv', 'cv-no-test'}:
         if num_folds <= 1 or num_folds > len(data):
             raise ValueError('Number of folds for cross-validation must be between 2 and len(data), inclusive.')
 
@@ -362,7 +362,7 @@ def split_data(data: MoleculeDataset,
 
         train, val, test = [], [], []
         for d, index in zip(data, indices):
-            if index == test_index:
+            if index == test_index and split_type != 'cv-no-test':
                 test.append(d)
             elif index == val_index:
                 val.append(d)