- Remove extracted_forest_sizes_number parameter from compute_results.py and...

- Remove extracted_forest_sizes_number parameter from compute_results.py and retreive the value instead;
- Add almost all remaining experiment config files of stages 1, 2 and 3;
- Add almost all remaining result plots of stages 1, 2 and 3;
- Add some temporary scripts to run all stages experiments.

code/compute_results.py

@@ -9,6 +9,14 @@ from dotenv import find_dotenv, load_dotenv
 import os
 
 
+def retreive_extracted_forest_sizes_number(models_dir, experiment_id):
+    experiment_id_path = models_dir + os.sep + str(experiment_id) # models/{experiment_id}
+    experiment_seed_root_path = experiment_id_path + os.sep + 'seeds' # models/{experiment_id}/seeds
+    seed = os.listdir(experiment_seed_root_path)[0]
+    experiment_seed_path = experiment_seed_root_path + os.sep + seed # models/{experiment_id}/seeds/{seed}
+    extracted_forest_sizes_root_path = experiment_seed_path + os.sep + 'extracted_forest_sizes'
+    return len(os.listdir(extracted_forest_sizes_root_path))
+
 def extract_scores_across_seeds_and_extracted_forest_sizes(models_dir, results_dir, experiment_id):
     experiment_id_path = models_dir + os.sep + str(experiment_id) # models/{experiment_id}
     experiment_seed_root_path = experiment_id_path + os.sep + 'seeds' # models/{experiment_id}/seeds
@@ -120,7 +128,6 @@ if __name__ == "__main__":
         'stage=2: {{no_normalization}} {{normalize_D}} {{normalize_weights}} {{normalize_D_and_weights}}' + \
         'stage=3: {{train-dev_subset}} {{train-dev_train-dev_subset}} {{train-train-dev_subset}}')
     parser.add_argument('--dataset_name', nargs='?', type=str, required=True, help='Specify the dataset name. TODO: read it from models dir directly.')
-    parser.add_argument('--extracted_forest_sizes_number', nargs='?', type=int, required=True, help='Specify the number of extracted forest sizes. TODO: read it from models dir directly.')
     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.')
     args = parser.parse_args()
@@ -130,6 +137,9 @@ if __name__ == "__main__":
 
     logger = LoggerFactory.create(LOG_PATH, os.path.basename(__file__))
 
+    logger.info('Compute results of with stage:{} - experiment_ids:{} - dataset_name:{} - results_dir:{} - models_dir:{}'.format(
+        args.stage, args.experiment_ids, args.dataset_name, args.results_dir, args.models_dir))
+
     # Create recursively the results dir tree
     pathlib.Path(args.results_dir).mkdir(parents=True, exist_ok=True)
 
@@ -137,6 +147,9 @@ if __name__ == "__main__":
         if len(args.experiment_ids) != 6:
             raise ValueError('In the case of stage 1, the number of specified experiment ids must be 6.')
 
+        # Retreive the extracted forest sizes number used in order to have a base forest axis as long as necessary
+        extracted_forest_sizes_number = retreive_extracted_forest_sizes_number(args.models_dir, args.experiment_ids[1])
+
         # Experiments that used the best hyperparameters found for this dataset
 
         # base_with_params
@@ -144,7 +157,7 @@ if __name__ == "__main__":
         base_with_params_train_scores, base_with_params_dev_scores, base_with_params_test_scores, \
             base_with_params_experiment_score_metric = \
             extract_scores_across_seeds_and_forest_size(args.models_dir, args.results_dir, args.experiment_ids[0],
-            args.extracted_forest_sizes_number)
+            extracted_forest_sizes_number)
         # random_with_params
         logger.info('Loading random_with_params experiment scores...')
         random_with_params_train_scores, random_with_params_dev_scores, random_with_params_test_scores, \
@@ -163,7 +176,7 @@ if __name__ == "__main__":
         base_wo_params_train_scores, base_wo_params_dev_scores, base_wo_params_test_scores, \
             base_wo_params_experiment_score_metric = extract_scores_across_seeds_and_forest_size(
                 args.models_dir, args.results_dir, args.experiment_ids[3],
-            args.extracted_forest_sizes_number)
+            extracted_forest_sizes_number)
         # random_wo_params
         logger.info('Loading random_wo_params experiment scores...')
         random_wo_params_train_scores, random_wo_params_dev_scores, random_wo_params_test_scores, \
@@ -292,6 +305,16 @@ if __name__ == "__main__":
         pathlib.Path(output_path).mkdir(parents=True, exist_ok=True)
 
         Plotter.plot_stage2_losses(
+            file_path=output_path + os.sep + 'losses.png',
+            all_experiment_scores=[train_dev_subset_test_scores, train_dev_train_dev_subset_test_scores,
+                train_train_dev_subset_test_scores],
+            all_labels=['train,dev', 'train+dev,train+dev', 'train,train+dev'],
+            x_value=extracted_forest_sizes,
+            xlabel='Number of trees extracted',
+            ylabel=experiments_score_metric,
+            title='Loss values of {}\nusing different training subsets'.format(args.dataset_name))
+
+        """Plotter.plot_stage2_losses(
             file_path=output_path + os.sep + 'losses.png',
             all_experiment_scores=[train_dev_subset_train_scores, train_train_dev_subset_train_scores,
                 train_train_dev_subset_train_scores, train_dev_subset_dev_scores, train_dev_train_dev_subset_dev_scores,
@@ -303,10 +326,12 @@ if __name__ == "__main__":
             x_value=extracted_forest_sizes,
             xlabel='Number of trees extracted',
             ylabel=experiments_score_metric,
-            title='Loss values of {}\nusing different training subsets'.format(args.dataset_name))
+            title='Loss values of {}\nusing different training subsets'.format(args.dataset_name))"""
     else:
         raise ValueError('This stage number is not supported yet, but it will be!')
 
+    logger.info('Done.')
+
     """
     TODO:
     For each dataset:

code/train.py

@@ -105,23 +105,23 @@ Command lines example for stage 1:
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --extraction_strategy=none --save_experiment_configuration 1 none_with_params --extracted_forest_size_stop=0.05
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --extraction_strategy=random --save_experiment_configuration 1 random_with_params --extracted_forest_size_stop=0.05
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --save_experiment_configuration 1 omp_with_params --extracted_forest_size_stop=0.05
-python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --extraction_strategy=none --skip_best_hyperparams --save_experiment_configuration 1 none_wo_params --forest_size=1000 --extracted_forest_size_stop=0.05
-python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --extraction_strategy=random --skip_best_hyperparams --save_experiment_configuration 1 random_wo_params --forest_size=1000 --extracted_forest_size_stop=0.05
-python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --skip_best_hyperparams --save_experiment_configuration 1 omp_wo_params --forest_size=1000 --extracted_forest_size_stop=0.05
-python code/compute_results.py --stage 1 --experiment_ids 1 2 3 4 5 6 --dataset_name=california_housing --extracted_forest_sizes_number=5
+python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --extraction_strategy=none --skip_best_hyperparams --save_experiment_configuration 1 none_wo_params --extracted_forest_size_stop=0.05
+python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --extraction_strategy=random --skip_best_hyperparams --save_experiment_configuration 1 random_wo_params --extracted_forest_size_stop=0.05
+python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --skip_best_hyperparams --save_experiment_configuration 1 omp_wo_params --extracted_forest_size_stop=0.05
+python code/compute_results.py --stage 1 --experiment_ids 1 2 3 4 5 6 --dataset_name=california_housing
 
 Command lines example for stage 2:
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --save_experiment_configuration 2 no_normalization --extracted_forest_size_stop=0.05
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --save_experiment_configuration 2 normalize_D --normalize_D --extracted_forest_size_stop=0.05
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --save_experiment_configuration 2 normalize_weights --normalize_weights --extracted_forest_size_stop=0.05
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --save_experiment_configuration 2 normalize_D_and_weights --normalize_D --normalize_weights --extracted_forest_size_stop=0.05
-python code/compute_results.py --stage 2 --experiment_ids 7 8 9 10 --dataset_name=california_housing --extracted_forest_sizes_number=5
+python code/compute_results.py --stage 2 --experiment_ids 7 8 9 10 --dataset_name=california_housing
 
 Command lines example for stage 3:
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --save_experiment_configuration 3 train-dev_subset --extracted_forest_size_stop=0.05 --subsets_used train,dev
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --save_experiment_configuration 3 train-dev_train-dev_subset --extracted_forest_size_stop=0.05 --subsets_used train+dev,train+dev
 python code/train.py --dataset_name=california_housing --seeds 1 2 3 4 5 --save_experiment_configuration 3 train-train-dev_subset --extracted_forest_size_stop=0.05 --subsets_used train,train+dev
-python code/compute_results.py --stage 3 --experiment_ids 11 12 13 --dataset_name=california_housing --extracted_forest_sizes_number=5
+python code/compute_results.py --stage 3 --experiment_ids 11 12 13 --dataset_name=california_housing
 """
 if __name__ == "__main__":
     load_dotenv(find_dotenv('.env'))

experiments/20newsgroups_vectorized/stage1/none_with_params.json

+{
+    "experiment_id": 1,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "1",
+        "none_with_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "none",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage1/none_wo_params.json

+{
+    "experiment_id": 4,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": true,
+    "save_experiment_configuration": [
+        "1",
+        "none_wo_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "none",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage1/omp_with_params.json

+{
+    "experiment_id": 3,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "1",
+        "omp_with_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage1/omp_wo_params.json

+{
+    "experiment_id": 6,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": true,
+    "save_experiment_configuration": [
+        "1",
+        "omp_wo_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage1/random_with_params.json

+{
+    "experiment_id": 2,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "1",
+        "random_with_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "random",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage1/random_wo_params.json

+{
+    "experiment_id": 5,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": true,
+    "save_experiment_configuration": [
+        "1",
+        "random_wo_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "random",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage2/no_normalization.json

+{
+    "experiment_id": 1,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage2",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "2",
+        "no_normalization"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage2/normalize_D.json

+{
+    "experiment_id": 2,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": true,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage2",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "2",
+        "normalize_D"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage2/normalize_D_and_weights.json

+{
+    "experiment_id": 4,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": true,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage2",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": true,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "2",
+        "normalize_D_and_weights"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage2/normalize_weights.json

+{
+    "experiment_id": 3,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage2",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": true,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "2",
+        "normalize_weights"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage3/train-dev_subset.json

+{
+    "experiment_id": 1,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage3",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "3",
+        "train-dev_subset"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage3/train-dev_train-dev_subset.json

+{
+    "experiment_id": 2,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage3",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train+dev,train+dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "3",
+        "train-dev_train-dev_subset"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/20newsgroups_vectorized/stage3/train-train-dev_subset.json

+{
+    "experiment_id": 3,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "20newsgroups_vectorized",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/20newsgroups_vectorized/stage3",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,train+dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "3",
+        "train-train-dev_subset"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        7,
+        13,
+        20,
+        27,
+        34
+    ]
+}
\ No newline at end of file

experiments/boston/stage1/none_with_params.json

+{
+    "experiment_id": 1,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "boston",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/boston/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "1",
+        "none_with_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "none",
+    "extracted_forest_size": [
+        8,
+        17,
+        25,
+        33,
+        42
+    ]
+}
\ No newline at end of file

experiments/boston/stage1/none_wo_params.json

+{
+    "experiment_id": 4,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "boston",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/boston/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": true,
+    "save_experiment_configuration": [
+        "1",
+        "none_wo_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "none",
+    "extracted_forest_size": [
+        8,
+        17,
+        25,
+        33,
+        42
+    ]
+}
\ No newline at end of file

experiments/boston/stage1/omp_with_params.json

+{
+    "experiment_id": 3,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "boston",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/boston/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "1",
+        "omp_with_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        8,
+        17,
+        25,
+        33,
+        42
+    ]
+}
\ No newline at end of file

experiments/boston/stage1/omp_wo_params.json

+{
+    "experiment_id": 6,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "boston",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/boston/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": true,
+    "save_experiment_configuration": [
+        "1",
+        "omp_wo_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "omp",
+    "extracted_forest_size": [
+        8,
+        17,
+        25,
+        33,
+        42
+    ]
+}
\ No newline at end of file

experiments/boston/stage1/random_with_params.json

+{
+    "experiment_id": 2,
+    "experiment_configuration": null,
+    "experiment_configuration_path": "experiments",
+    "dataset_name": "boston",
+    "normalize_D": false,
+    "dataset_normalizer": "standard",
+    "forest_size": null,
+    "extracted_forest_size_samples": 5,
+    "extracted_forest_size_stop": 0.05,
+    "models_dir": "models/boston/stage1",
+    "dev_size": 0.2,
+    "test_size": 0.2,
+    "random_seed_number": 1,
+    "seeds": [
+        1,
+        2,
+        3,
+        4,
+        5
+    ],
+    "subsets_used": "train,dev",
+    "normalize_weights": false,
+    "verbose": false,
+    "skip_best_hyperparams": false,
+    "save_experiment_configuration": [
+        "1",
+        "random_with_params"
+    ],
+    "job_number": -1,
+    "extraction_strategy": "random",
+    "extracted_forest_size": [
+        8,
+        17,
+        25,
+        33,
+        42
+    ]
+}
\ No newline at end of file