- Add progress bar during training;

- Update requirements packages.

code/train.py

@@ -12,7 +12,7 @@ import argparse
 import pathlib
 import random
 import os
-import errno
+from tqdm import tqdm
 
 
 if __name__ == "__main__":
@@ -67,16 +67,13 @@ if __name__ == "__main__":
     experiment_id = resolve_experiment_id(args.models_dir)
     experiment_id_str = str(experiment_id)
 
-    for seed in seeds:
-        logger.debug('Seed={}'.format(seed))
+    with tqdm(seeds) as seed_bar:
+        for seed in seed_bar:
+            seed_bar.set_description('seed={}'.format(seed))
             seed_str = str(seed)
             models_dir = args.models_dir + os.sep + experiment_id_str + os.sep + 'seeds' + \
                 os.sep + seed_str
-        try:
-            os.makedirs(models_dir)
-        except OSError as e:
-            if e.errno != errno.EEXIST:
-                raise
+            pathlib.Path(models_dir).mkdir(parents=True, exist_ok=True)
 
             dataset_parameters = DatasetParameters(
                 name=args.dataset_name,
@@ -92,14 +89,11 @@ if __name__ == "__main__":
 
             trainer = Trainer(dataset)
 
-        for extracted_forest_size in args.extracted_forest_size:
-            logger.debug('extracted_forest_size={}'.format(extracted_forest_size))
+            with tqdm(args.extracted_forest_size) as extracted_forest_size_bar:
+                for extracted_forest_size in extracted_forest_size_bar:
+                    extracted_forest_size_bar.set_description('extracted_forest_size={}'.format(extracted_forest_size))
                     sub_models_dir = models_dir + os.sep + 'extracted_forest_size' + os.sep + str(extracted_forest_size)
-            try:
-                os.makedirs(sub_models_dir)
-            except OSError as e:
-                if e.errno != errno.EEXIST:
-                    raise
+                    pathlib.Path(sub_models_dir).mkdir(parents=True, exist_ok=True)
 
                     model_parameters = ModelParameters(
                         forest_size=args.forest_size,
@@ -112,6 +106,3 @@ if __name__ == "__main__":
                     model = ModelFactory.build(dataset.task, model_parameters)
 
                     trainer.train(model, sub_models_dir)
-
-            logger.info('Error on test set: {}'.format(model.score(dataset.X_test, dataset.y_test)))
-            logger.info('Accuracy on test set: {}'.format(model.score_regressor(dataset.X_test, dataset.y_test)))

requirements.txt

@@ -9,3 +9,5 @@ awscli
 flake8
 python-dotenv>=0.5.1
 scikit-learn
+python-dotenv
+tqdm
\ No newline at end of file