By default, compute the hyperparams of the whole dataset list.

code/bolsonaro/data/dataset_loader.py

@@ -26,6 +26,10 @@ class DatasetLoader(object):
     DEFAULT_SUBSETS_USED = 'train,dev'
     DEFAULT_NORMALIZE_WEIGHTS = False
 
+    dataset_names = ['boston', 'iris', 'diabetes', 'digits', 'linnerud', 'wine',
+        'breast_cancer', 'olivetti_faces', '20newsgroups_vectorized', 'lfw_people',
+        'lfw_pairs', 'covtype', 'rcv1', 'california_housing']
+
     @staticmethod
     def load(dataset_parameters):
         name = dataset_parameters.name

code/compute_hyperparameters.py

@@ -45,14 +45,12 @@ if __name__ == "__main__":
                         'min_samples_leaf': Integer(1, 1000),
                         'max_depth': Integer(1, 20),
                         'max_features': Categorical(['auto', 'sqrt', 'log2'], [0.5, 0.25, 0.25])}
-    DATASET_LIST = ['boston', 'iris', 'diabetes']
-    # , 'digits', 'linnerud', 'wine']
 
     parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     parser.add_argument('--cv', nargs='?', type=int, default=DEFAULT_CV, help='Specify the size of the cross-validation.')
     parser.add_argument('--n_iter', nargs='?', type=int, default=DEFAULT_N_ITER, help='Specify the number of iterations for the bayesian search.')
     parser.add_argument('--seed', nargs='?', type=int, default=None, help='Specify a seed instead of generate it randomly.')
-    parser.add_argument('--datasets', nargs='+', type=str, default=DATASET_LIST, help='Specify the dataset used by the estimator.')
+    parser.add_argument('--datasets', nargs='+', type=str, default=DatasetLoader.dataset_names, help='Specify the dataset used by the estimator.')
     parser.add_argument('--verbose', action='store_true', default=False, help='Print information during the bayesian search.')
     args = parser.parse_args()