- Add result of stage3 for breast_cancer;

- Add diamonds in experiment scripts and add factorize run_compute_results.sh script;
- Add best params for diamonds dataset.

experiments/diamonds/stage1/params.json

+{
+    "scorer": "neg_mean_squared_error",
+    "best_score_train": -627872.5455188936,
+    "best_score_test": -551230.808602097,
+    "best_parameters": {
+        "max_features": "auto",
+        "min_samples_leaf": 1,
+        "max_depth": 12,
+        "n_estimators": 429
+    },
+    "random_seed": [
+        83,
+        1000,
+        1262,
+        1117,
+        1899,
+        1378,
+        1904,
+        1661,
+        57,
+        1143,
+        1350,
+        871,
+        1030,
+        1585,
+        745
+    ]
+}
\ No newline at end of file

scripts/run_compute_results.sh

-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=california_housing --models_dir=models/california_housing/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=boston --models_dir=models/boston/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=iris --models_dir=models/iris/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=diabetes --models_dir=models/diabetes/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=digits --models_dir=models/digits/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=linnerud --models_dir=models/linnerud/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=wine --models_dir=models/wine/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=breast_cancer --models_dir=models/breast_cancer/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=olivetti_faces --models_dir=models/olivetti_faces/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=20newsgroups_vectorized --models_dir=models/20newsgroups_vectorized/stage1
-python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=lfw_pairs --models_dir=models/lfw_pairs/stage1
-
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=california_housing --models_dir=models/california_housing/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=boston --models_dir=models/boston/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=iris --models_dir=models/iris/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=diabetes --models_dir=models/diabetes/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=digits --models_dir=models/digits/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=linnerud --models_dir=models/linnerud/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=wine --models_dir=models/wine/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=breast_cancer --models_dir=models/breast_cancer/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=olivetti_faces --models_dir=models/olivetti_faces/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=20newsgroups_vectorized --models_dir=models/20newsgroups_vectorized/stage2
-python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=lfw_pairs --models_dir=models/lfw_pairs/stage2
-
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=california_housing --models_dir=models/california_housing/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=boston --models_dir=models/boston/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=iris --models_dir=models/iris/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=diabetes --models_dir=models/diabetes/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=digits --models_dir=models/digits/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=linnerud --models_dir=models/linnerud/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=wine --models_dir=models/wine/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=breast_cancer --models_dir=models/breast_cancer/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=olivetti_faces --models_dir=models/olivetti_faces/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=20newsgroups_vectorized --models_dir=models/20newsgroups_vectorized/stage3
-python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=lfw_pairs --models_dir=models/lfw_pairs/stage3
+for dataset in california_housing boston iris diabetes digits linnerud wine breast_cancer olivetti_faces 20newsgroups_vectorized lfw_pairs diamonds
+do
+    python code/compute_results.py --stage=1 --experiment_ids 1 2 3 4 5 6 --dataset_name=$dataset --models_dir=models/$dataset/stage1
+    python code/compute_results.py --stage=2 --experiment_ids 1 2 3 4 --dataset_name=$dataset --models_dir=models/$dataset/stage2
+    python code/compute_results.py --stage=3 --experiment_ids 1 2 3 --dataset_name=$dataset --models_dir=models/$dataset/stage3
+done

scripts/run_stage1_experiments.sh

@@ -3,7 +3,7 @@ core_number=5
 walltime=1:00
 seeds='1 2 3 4 5'
 
-for dataset in california_housing boston iris diabetes digits linnerud wine breast_cancer olivetti_faces 20newsgroups_vectorized lfw_pairs
+for dataset in california_housing boston iris diabetes digits linnerud wine breast_cancer olivetti_faces 20newsgroups_vectorized lfw_pairs diamonds
 do
     oarsub -p "(gpu is null)" -l /core=$core_number,walltime=1:00 "conda activate test_env && python code/train.py --dataset_name=$dataset --seeds $seeds --extraction_strategy=none --save_experiment_configuration 1 none_with_params --extracted_forest_size_stop=0.05 --experiment_id=1 --models_dir=models/$dataset/stage1"
     oarsub -p "(gpu is null)" -l /core=$core_number,walltime=1:00 "conda activate test_env && python code/train.py --dataset_name=$dataset --seeds $seeds --extraction_strategy=random --save_experiment_configuration 1 random_with_params --extracted_forest_size_stop=0.05 --experiment_id=2 --models_dir=models/$dataset/stage1"

scripts/run_stage2_experiments.sh

@@ -3,7 +3,7 @@ core_number=5
 walltime=1:00
 seeds='1 2 3 4 5'
 
-for dataset in california_housing boston iris diabetes digits linnerud wine breast_cancer olivetti_faces 20newsgroups_vectorized lfw_pairs
+for dataset in california_housing boston iris diabetes digits linnerud wine breast_cancer olivetti_faces 20newsgroups_vectorized lfw_pairs diamonds
 do
     oarsub -p "(gpu is null)" -l /core=$core_number,walltime=1:00 "conda activate test_env && python code/train.py --dataset_name=$dataset --seeds $seeds --save_experiment_configuration 2 no_normalization --extracted_forest_size_stop=0.05 --experiment_id=1 --models_dir=models/$dataset/stage2"
     oarsub -p "(gpu is null)" -l /core=$core_number,walltime=1:00 "conda activate test_env && python code/train.py --dataset_name=$dataset --seeds $seeds --save_experiment_configuration 2 normalize_D --normalize_D --extracted_forest_size_stop=0.05 --experiment_id=2 --models_dir=models/$dataset/stage2"

scripts/run_stage3_experiments.sh

@@ -3,7 +3,7 @@ core_number=5
 walltime=1:00
 seeds='1 2 3 4 5'
 
-for dataset in california_housing boston iris diabetes digits linnerud wine breast_cancer olivetti_faces 20newsgroups_vectorized lfw_pairs
+for dataset in california_housing boston iris diabetes digits linnerud wine breast_cancer olivetti_faces 20newsgroups_vectorized lfw_pairs diamonds
 do
     oarsub -p "(gpu is null)" -l /core=$core_number,walltime=1:00 "conda activate test_env && python code/train.py --dataset_name=$dataset --seeds $seeds --save_experiment_configuration 3 train-dev_subset --extracted_forest_size_stop=0.05 --subsets_used=train,dev --experiment_id=1 --models_dir=models/$dataset/stage3"
     oarsub -p "(gpu is null)" -l /core=$core_number,walltime=1:00 "conda activate test_env && python code/train.py --dataset_name=$dataset --seeds $seeds --save_experiment_configuration 3 train-dev_train-dev_subset --extracted_forest_size_stop=0.05 --subsets_used=train+dev,train+dev --experiment_id=2 --models_dir=models/$dataset/stage3"