Uppercased default consts

code/bolsonaro/models/omp_forest_regressor.py

@@ -9,7 +9,7 @@ import numpy as np
 
 class OmpForestRegressor(BaseEstimator):
 
-    default_score_metric = 'mse'
+    DEFAULT_SCORE_METRIC = 'mse'
 
     def __init__(self, models_parameters):
         self._regressor = RandomForestRegressor(n_estimators=models_parameters.forest_size,
@@ -60,7 +60,7 @@ class OmpForestRegressor(BaseEstimator):
 
         return predictions
 
-    def score(self, X, y, metric=default_score_metric):
+    def score(self, X, y, metric=DEFAULT_SCORE_METRIC):
         """
         Evaluate OMPForestRegressor on (`X`, `y`) using `metric`
 

code/bolsonaro/trainer.py

@@ -34,7 +34,7 @@ class Trainer(object):
             train_score=model.score(self._dataset.X_train, self._dataset.y_train),
             dev_score=model.score(self._dataset.X_dev, self._dataset.y_dev),
             test_score=model.score(self._dataset.X_test, self._dataset.y_test),
-            score_metric=model.default_score_metric,
+            score_metric=model.DEFAULT_SCORE_METRIC, # TODO: resolve the used metric in a proper way
             train_score_regressor=model.score_regressor(self._dataset.X_train, self._dataset.y_train),
             dev_score_regressor=model.score_regressor(self._dataset.X_dev, self._dataset.y_dev),
             test_score_regressor=model.score_regressor(self._dataset.X_test, self._dataset.y_test)

code/compute_results.py

@@ -14,14 +14,14 @@ if __name__ == "__main__":
     # get environment variables in .env
     load_dotenv(find_dotenv('.env.example'))
 
-    default_results_dir = os.environ["project_dir"] + os.sep + 'results'
-    default_models_dir = os.environ["project_dir"] + os.sep + 'models'
-    default_experiment_ids = None
+    DEFAULT_RESULTS_DIR = os.environ["project_dir"] + os.sep + 'results'
+    DEFAULT_MODELS_DIR = os.environ["project_dir"] + os.sep + 'models'
+    DEFAULT_EXPERIMENT_IDS = None
 
     parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-    parser.add_argument('--results_dir', nargs='?', type=str, default=default_results_dir, help='The output directory of the results.')
-    parser.add_argument('--models_dir', nargs='?', type=str, default=default_models_dir, help='The output directory of the trained models.')
-    parser.add_argument('--experiment_ids', nargs='+', type=int, default=default_experiment_ids, help='Compute the results of the specified experiment id(s)')
+    parser.add_argument('--results_dir', nargs='?', type=str, default=DEFAULT_RESULTS_DIR, help='The output directory of the results.')
+    parser.add_argument('--models_dir', nargs='?', type=str, default=DEFAULT_MODELS_DIR, help='The output directory of the trained models.')
+    parser.add_argument('--experiment_ids', nargs='+', type=int, default=DEFAULT_EXPERIMENT_IDS, help='Compute the results of the specified experiment id(s)')
     args = parser.parse_args()
 
     pathlib.Path(args.results_dir).mkdir(parents=True, exist_ok=True)

code/train.py

@@ -19,33 +19,33 @@ if __name__ == "__main__":
     # get environment variables in .env
     load_dotenv(find_dotenv('.env.example'))
 
-    default_dataset_name = 'boston'
-    default_normalize = True
-    default_normalize_D = False
-    default_dataset_normalizer = None
-    default_forest_size = 100
-    default_extracted_forest_size = 10
+    DEFAULT_DATASET_NAME = 'boston'
+    DEFAULT_NORMALIZE_D = False
+    DEFAULT_DATASET_NORMALIZER = None
+    DEFAULT_FOREST_SIZE = 100
+    DEFAULT_EXTRACTED_FOREST_SIZE = 10
     # the models will be stored in a directory structure like: models/{experiment_id}/seeds/{seed_nb}/extracted_forest_size/{nb_extracted_trees}
-    default_models_dir = os.environ["project_dir"] + os.sep + 'models'
-    default_dev_size = 0.2
-    default_test_size = 0.2
-    default_random_seed_number = 1
+    DEFAULT_MODELS_DIR = os.environ["project_dir"] + os.sep + 'models'
+    DEFAULT_DEV_SIZE = 0.2
+    DEFAULT_TEST_SIZE = 0.2
+    DEFAULT_RANDOM_SEED_NUMBER = 1
+    DEFAULT_TRAIN_ON_SUBSET = 'train'
+
     begin_random_seed_range = 1
     end_random_seed_range = 2000
-    default_train_on_subset = 'train'
 
     parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-    parser.add_argument('--dataset_name', nargs='?', type=str, default=default_dataset_name, help='Specify the dataset. Regression: boston, diabetes, linnerud, california_housing. Classification: iris, digits, wine, breast_cancer, olivetti_faces, 20newsgroups, 20newsgroups_vectorized, lfw_people, lfw_pairs, covtype, rcv1, kddcup99.')
-    parser.add_argument('--normalize_D', action='store_true', default=default_normalize_D, help='Specify if we want to normalize the prediction of the forest by doing the L2 division of the pred vectors.')
-    parser.add_argument('--dataset_normalizer', nargs='?', type=str, default=default_dataset_normalizer, help='Specify which dataset normalizer use (either standard, minmax, robust or normalizer).')
-    parser.add_argument('--forest_size', nargs='?', type=int, default=default_forest_size, help='The number of trees of the random forest.')
-    parser.add_argument('--extracted_forest_size', nargs='+', type=int, default=default_extracted_forest_size, help='The number of trees selected by OMP.')
-    parser.add_argument('--models_dir', nargs='?', type=str, default=default_models_dir, help='The output directory of the trained models.')
-    parser.add_argument('--dev_size', nargs='?', type=float, default=default_dev_size, help='Dev subset ratio.')
-    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('--dataset_name', nargs='?', type=str, default=DEFAULT_DATASET_NAME, help='Specify the dataset. Regression: boston, diabetes, linnerud, california_housing. Classification: iris, digits, wine, breast_cancer, olivetti_faces, 20newsgroups, 20newsgroups_vectorized, lfw_people, lfw_pairs, covtype, rcv1, kddcup99.')
+    parser.add_argument('--normalize_D', action='store_true', default=DEFAULT_NORMALIZE_D, help='Specify if we want to normalize the prediction of the forest by doing the L2 division of the pred vectors.')
+    parser.add_argument('--dataset_normalizer', nargs='?', type=str, default=DEFAULT_DATASET_NORMALIZER, help='Specify which dataset normalizer use (either standard, minmax, robust or normalizer).')
+    parser.add_argument('--forest_size', nargs='?', type=int, default=DEFAULT_FOREST_SIZE, help='The number of trees of the random forest.')
+    parser.add_argument('--extracted_forest_size', nargs='+', type=int, default=DEFAULT_EXTRACTED_FOREST_SIZE, help='The number of trees selected by OMP.')
+    parser.add_argument('--models_dir', nargs='?', type=str, default=DEFAULT_MODELS_DIR, help='The output directory of the trained models.')
+    parser.add_argument('--dev_size', nargs='?', type=float, default=DEFAULT_DEV_SIZE, help='Dev subset ratio.')
+    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('--train_on_subset', nargs='?', type=str, default=default_train_on_subset, help='Specify on witch subset the model will be trained (either train or dev).')
+    parser.add_argument('--train_on_subset', nargs='?', type=str, default=DEFAULT_TRAIN_ON_SUBSET, help='Specify on witch subset the model will be trained (either train or dev).')
     args = parser.parse_args()
 
     pathlib.Path(args.models_dir).mkdir(parents=True, exist_ok=True)