fix parser for test_dataset and update version

Author: Nicolas Béreux

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "rbms"
-version = "0.4.0"
+version = "0.4.1"
 authors = [
   {name="Nicolas Béreux", email="nicolas.bereux@gmail.com"},
   {name="Aurélien Decelle"},

rbms/dataset/parser.py

@@ -8,10 +8,17 @@ def add_args_dataset(parser: argparse.ArgumentParser) -> argparse.ArgumentParser
     dataset_args = parser.add_argument_group("Dataset")
     dataset_args.add_argument(
         "-d",
-        "--data",
+        "--dataset",
         type=str,
         required=True,
-        help="Name of the dataset ('HGD', 'MNIST', 'BKACE', 'PF00072', 'PF13354'), or path to a data file (type should be .h5 or .fasta)",
+        help="Path to a data file (type should be .h5 or .fasta)",
+    )
+    dataset_args.add_argument(
+        "--test_dataset",
+        type=str,
+        required=False,
+        default=None,
+        help="Path to test dataset file (type should be .h5 or .fasta)",
     )
     dataset_args.add_argument(
         "--subset_labels",

rbms/scripts/train_rbm.py

@@ -36,7 +36,8 @@ def train_rbm(args: dict):
         num_updates=args["num_updates"], n_save=args["n_save"], spacing=args["spacing"]
     )
     train_dataset, test_dataset = load_dataset(
-        dataset_name=args["data"],
+        dataset_name=args["dataset"],
+        test_dataset_name=args["test_dataset"],
         subset_labels=args["subset_labels"],
         use_weights=args["use_weights"],
         alphabet=args["alphabet"],