Replace use_dev_subset by subsets_used parameter, in order to specify more...

Replace use_dev_subset by subsets_used parameter, in order to specify more clearly which combination of train dev to used to train the forest and OMP

code/bolsonaro/models/model_parameters.py

@@ -5,11 +5,11 @@ import os
 
 class ModelParameters(object):
 
-    def __init__(self, forest_size, extracted_forest_size, normalize_D, use_dev_subset, seed=None):
+    def __init__(self, forest_size, extracted_forest_size, normalize_D, subsets_used, seed=None):
         self._forest_size = forest_size
         self._extracted_forest_size = extracted_forest_size
         self._normalize_D = normalize_D
-        self._use_dev_subset = use_dev_subset
+        self._subsets_used = subsets_used
         self._seed = seed
 
     @property
@@ -25,8 +25,8 @@ class ModelParameters(object):
         return self._normalize_D
 
     @property
-    def use_dev_subset(self):
-        return self._use_dev_subset
+    def subsets_used(self):
+        return self._subsets_used
 
     @property
     def seed(self):

code/bolsonaro/trainer.py

@@ -17,20 +17,25 @@ class Trainer(object):
         self._logger.debug('Training model using train set...')
         begin_time = time.time()
 
-        if model.models_parameters.use_dev_subset:
+        if model.models_parameters.subsets_used == 'train,dev':
             X_forest = self._dataset.X_train
             y_forest = self._dataset.y_train
             X_omp = self._dataset.X_dev
             y_omp = self._dataset.y_dev
             self._logger.debug('Fitting the forest on train subset and OMP on dev subset.')
-        else:
+        elif model.models_parameters.subsets_used == 'train+dev,train+dev':
             X_forest = np.concatenate([self._dataset.X_train, self._dataset.X_dev])
             X_omp = X_forest
             y_forest = np.concatenate([self._dataset.y_train, self._dataset.y_dev])
             y_omp = y_forest
             self._logger.debug('Fitting both the forest and OMP on train+dev subsets.')
-
-        # TODO: add an option to train forest to train+dev and OMP to dev
+        elif model.models_parameters.subsets_used == 'train,train+dev':
+            X_forest = self._dataset.X_train
+            y_forest = self._dataset.y_train
+            X_omp = np.concatenate([self._dataset.X_train, self._dataset.X_dev])
+            y_omp = np.concatenate([self._dataset.y_train, self._dataset.y_dev])
+        else:
+            raise ValueError("Unknown specified subsets_used parameter '{}'".format(model.models_parameters.subsets_used))
 
         model.fit(
             X_forest=X_forest,

code/train.py

@@ -29,7 +29,7 @@ if __name__ == "__main__":
     DEFAULT_DEV_SIZE = 0.2
     DEFAULT_TEST_SIZE = 0.2
     DEFAULT_RANDOM_SEED_NUMBER = 1
-    DEFAULT_USE_DEV_SUBSET = False
+    DEFAULT_SUBSETS_USED = 'train,dev'
     DEFAULT_DISABLE_PROGRESS = False
 
     begin_random_seed_range = 1
@@ -46,7 +46,7 @@ if __name__ == "__main__":
     parser.add_argument('--test_size', nargs='?', type=float, default=DEFAULT_TEST_SIZE, help='Test subset ratio.')
     parser.add_argument('--random_seed_number', nargs='?', type=int, default=DEFAULT_RANDOM_SEED_NUMBER, help='Number of random seeds used.')
     parser.add_argument('--seeds', nargs='+', type=int, default=None, help='Specific a list of seeds instead of generate them randomly')
-    parser.add_argument('--use_dev_subset', action='store_true', default=DEFAULT_USE_DEV_SUBSET, help='If specify the forest will be trained on train subset and OMP on dev subset. Otherwise both the forest and OMP will be trained on train+dev subsets.')
+    parser.add_argument('--subsets_used', nargs='+', type=str, default=DEFAULT_SUBSETS_USED, help='train,dev: forest on train, OMP on dev. train+dev,train+dev: both forest and OMP on train+dev. train,train+dev: forest on train+dev and OMP on dev.')
     parser.add_argument('--disable_progress', action='store_true', default=DEFAULT_DISABLE_PROGRESS, help='Disable the progress bars.')
     args = parser.parse_args()
 
@@ -101,7 +101,7 @@ if __name__ == "__main__":
                         forest_size=args.forest_size,
                         extracted_forest_size=extracted_forest_size,
                         normalize_D=args.normalize_D,
-                        use_dev_subset=args.use_dev_subset,
+                        subsets_used=args.subsets_used,
                         seed=seed
                     )
                     model_parameters.save(sub_models_dir, experiment_id)