- Unignore results;

- Even if hyperparameters file is ignore with skip_best_hyperparams option, still use the same forest_size to be comparable;
- Update experiment files for stage1 wo_param experiments (using the same forest size as the with_params experiments);
- In compute_results: remove useless folder creation; temporary add extracted_forest_sizes_number option to specify the extracted forest sizes number; temporary not plotting train and dev losses in stage1 loss values figure;
- In plotter, clean-up stage1 figure generation;
- Add first unbiased losses plot (stage1: best params vs default params in california housing dataset).

.gitignore

 models/*
-results/*
 experiments/unnamed/
 
 */.kile/*
@@ -372,6 +371,3 @@ TSWLatexianTemp*
 *.lpz
 
 reports/*.pdf
-
-# Image
-*.png

code/train.py

@@ -107,7 +107,7 @@ python code/train.py --dataset_name=california_housing --seeds 1 2 3 --save_expe
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 --extraction_strategy=none --skip_best_hyperparams --save_experiment_configuration 1 none_wo_params
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 --extraction_strategy=random --skip_best_hyperparams --save_experiment_configuration 1 random_wo_params
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 --skip_best_hyperparams --save_experiment_configuration 1 omp_wo_params
-python code/compute_results.py --stage 1 --experiment_ids 1 2 3 4 5 6
+python code/compute_results.py --stage 1 --experiment_ids 1 2 3 4 5 6 --dataset_name=california_housing --extracted_forest_sizes_number=5
 """
 if __name__ == "__main__":
     load_dotenv(find_dotenv('.env'))
@@ -160,10 +160,14 @@ if __name__ == "__main__":
     logger = LoggerFactory.create(LOG_PATH, os.path.basename(__file__))
 
     hyperparameters_path = os.path.join('experiments', args.dataset_name, 'stage1', 'params.json')
-    if os.path.exists(hyperparameters_path) and not args.skip_best_hyperparams:
+    if os.path.exists(hyperparameters_path):
         logger.info("Hyperparameters found for this dataset at '{}'".format(hyperparameters_path))
         with open(hyperparameters_path, 'r+') as file_hyperparameter:
-            hyperparameters = json.load(file_hyperparameter)['best_parameters']
+            loaded_hyperparameters = json.load(file_hyperparameter)['best_parameters']
+            if args.skip_best_hyperparams:
+                hyperparameters = {'n_estimators': loaded_hyperparameters['n_estimators']}
+            else:
+                hyperparameters = loaded_hyperparameters
     else:
         hyperparameters = {}
 

experiments/california_housing/stage1/none_wo_params_4.json

@@ -27,11 +27,11 @@
     "job_number": -1,
     "extraction_strategy": "none",
     "extracted_forest_size": [
-        1,
-        3,
-        5,
-        6,
-        8
+        16,
+        33,
+        50,
+        66,
+        83
     ],
     "experiment_id": 4
 }
\ No newline at end of file

experiments/california_housing/stage1/omp_wo_params_6.json

@@ -27,11 +27,11 @@
     "job_number": -1,
     "extraction_strategy": "omp",
     "extracted_forest_size": [
-        1,
-        3,
-        5,
-        6,
-        8
+        16,
+        33,
+        50,
+        66,
+        83
     ],
     "experiment_id": 6
 }
\ No newline at end of file

experiments/california_housing/stage1/random_wo_params_5.json

@@ -27,11 +27,11 @@
     "job_number": -1,
     "extraction_strategy": "random",
     "extracted_forest_size": [
-        1,
-        3,
-        5,
-        6,
-        8
+        16,
+        33,
+        50,
+        66,
+        83
     ],
     "experiment_id": 5
 }
\ No newline at end of file