diff --git a/bolsonaro/data/dataset.py b/bolsonaro/data/dataset.py
new file mode 100644
index 0000000000000000000000000000000000000000..b2f67c489be94791397649ba292a49f65dd604d8
--- /dev/null
+++ b/bolsonaro/data/dataset.py
@@ -0,0 +1,44 @@
+class Dataset(object):
+
+ def __init__(self, task, dataset_parameters, X_train, X_dev, X_test, y_train,
+ y_dev, y_test):
+ self._task = task
+ self._dataset_parameters = dataset_parameters
+ self._X_train = X_train
+ self._X_dev = X_dev
+ self._X_test = X_test
+ self._y_train = y_train
+ self._y_dev = y_dev
+ self._y_test = y_test
+
+ @property
+ def task(self):
+ return self._task
+
+ @property
+ def dataset_parameters(self):
+ return self._dataset_parameters
+
+ @property
+ def X_train(self):
+ return self._X_train
+
+ @property
+ def X_dev(self):
+ return self._X_dev
+
+ @property
+ def X_test(self):
+ return self._X_test
+
+ @property
+ def y_train(self):
+ return self._y_train
+
+ @property
+ def y_dev(self):
+ return self._y_dev
+
+ @property
+ def y_test(self):
+ return self._y_test
diff --git a/bolsonaro/data/dataset_loader.py b/bolsonaro/data/dataset_loader.py
new file mode 100644
index 0000000000000000000000000000000000000000..1e4264ef88d6dc595c7e5df14b678dcb95086a74
--- /dev/null
+++ b/bolsonaro/data/dataset_loader.py
@@ -0,0 +1,78 @@
+from bolsonaro.data.dataset import Dataset
+from bolsonaro.data.task import Task
+
+from sklearn.datasets import load_boston, load_iris, load_diabetes, load_digits, load_linnerud, load_wine, load_breast_cancer
+from sklearn.datasets import fetch_olivetti_faces, fetch_20newsgroups, \
+ fetch_20newsgroups_vectorized, fetch_lfw_people, fetch_lfw_pairs, \
+ fetch_covtype, fetch_rcv1, fetch_kddcup99, fetch_california_housing
+from sklearn.model_selection import train_test_split
+
+
+class DatasetLoader(object):
+
+ @staticmethod
+ def load_from_name(dataset_parameters):
+ name = dataset_parameters.name
+ if name == 'boston':
+ dataset_loading_func = load_boston
+ task = Task.REGRESSION
+ elif name == 'iris':
+ dataset_loading_func = load_iris
+ task = Task.CLASSIFICATION
+ elif name == 'diabetes':
+ dataset_loading_func = load_diabetes
+ task = Task.REGRESSION
+ elif name == 'digits':
+ dataset_loading_func = load_digits
+ task = Task.CLASSIFICATION
+ elif name == 'linnerud':
+ dataset_loading_func = load_linnerud
+ task = Task.REGRESSION
+ elif name == 'wine':
+ dataset_loading_func = load_wine
+ task = Task.CLASSIFICATION
+ elif name == 'breast_cancer':
+ dataset_loading_func = load_breast_cancer
+ task = Task.CLASSIFICATION
+ elif name == 'olivetti_faces':
+ dataset_loading_func = fetch_olivetti_faces
+ task = Task.CLASSIFICATION
+ elif name == '20newsgroups':
+ dataset_loading_func = fetch_20newsgroups
+ task = Task.CLASSIFICATION
+ elif name == '20newsgroups_vectorized':
+ dataset_loading_func = fetch_20newsgroups_vectorized
+ task = Task.CLASSIFICATION
+ elif name == 'lfw_people':
+ dataset_loading_func = fetch_lfw_people
+ task = Task.CLASSIFICATION
+ elif name == 'lfw_pairs':
+ dataset_loading_func = fetch_lfw_pairs
+ elif name == 'covtype':
+ dataset_loading_func = fetch_covtype
+ task = Task.CLASSIFICATION
+ elif name == 'rcv1':
+ dataset_loading_func = fetch_rcv1
+ task = Task.CLASSIFICATION
+ elif name == 'kddcup99':
+ dataset_loading_func = fetch_kddcup99
+ task = Task.CLASSIFICATION
+ elif name == 'california_housing':
+ dataset_loading_func = fetch_california_housing
+ task = Task.REGRESSION
+ else:
+ raise ValueError("Unsupported dataset '{}'".format(name))
+
+ X, y = dataset_loading_func(return_X_y=True)
+ X_train, X_test, y_train, y_test = train_test_split(X, y,
+ test_size=dataset_parameters.test_size,
+ random_state=dataset_parameters.seed)
+ X_train, X_dev, y_train, y_dev = train_test_split(X_train, y_train,
+ test_size=dataset_parameters.dev_size,
+ random_state=dataset_parameters.seed)
+
+ if dataset_parameters.normalize:
+ pass
+
+ return Dataset(task, dataset_parameters, X_train,
+ X_dev, X_test, y_train, y_dev, y_test)
diff --git a/bolsonaro/data/dataset_parameters.py b/bolsonaro/data/dataset_parameters.py
new file mode 100644
index 0000000000000000000000000000000000000000..e820b8f13a8502d08c7c2f679b28cef1b7262fd7
--- /dev/null
+++ b/bolsonaro/data/dataset_parameters.py
@@ -0,0 +1,28 @@
+class DatasetParameters(object):
+
+ def __init__(self, name, test_size, dev_size, random_state, normalize):
+ self._name = name
+ self._test_size = test_size
+ self._dev_size = dev_size
+ self._random_state = random_state
+ self._normalize = normalize
+
+ @property
+ def name(self):
+ return self._name
+
+ @property
+ def test_size(self):
+ return self._test_size
+
+ @property
+ def dev_size(self):
+ return self._dev_size
+
+ @property
+ def random_state(self):
+ return self._random_state
+
+ @property
+ def normalize(self):
+ return self._normalize
diff --git a/bolsonaro/data/task.py b/bolsonaro/data/task.py
new file mode 100644
index 0000000000000000000000000000000000000000..2f47fa22f472f769c075f40e1c25a7bf3de45f0d
--- /dev/null
+++ b/bolsonaro/data/task.py
@@ -0,0 +1,6 @@
+from enum import Enum
+
+
+class Task(Enum):
+ CLASSIFICATION = 1
+ REGRESSION = 2
diff --git a/bolsonaro/models/model_factory.py b/bolsonaro/models/model_factory.py
new file mode 100644
index 0000000000000000000000000000000000000000..a2f02a604d3d51c165459f3cd216033cc4ef256a
--- /dev/null
+++ b/bolsonaro/models/model_factory.py
@@ -0,0 +1,20 @@
+from bolsonaro.models.omp_forest_classifier import OmpForestClassifier
+from bolsonaro.models.omp_forest_regressor import OmpForestRegressor
+from bolsonaro.data.task import Task
+
+
+class ModelFactory(object):
+
+ @staticmethod
+ def build(task, forest_size, extracted_forest_size, seed=None):
+ if task == Task.CLASSIFICATION:
+ model_func = OmpForestClassifier
+ elif task == Task.REGRESSION:
+ model_func = OmpForestRegressor
+ else:
+ raise ValueError("Unsupported task '{}'".format(task))
+ return model_func(
+ forest_size=forest_size,
+ extracted_forest_size=extracted_forest_size,
+ seed=seed
+ )
diff --git a/bolsonaro/models/omp_forest_classifier.py b/bolsonaro/models/omp_forest_classifier.py
new file mode 100644
index 0000000000000000000000000000000000000000..12cc23fab69fc0b79ff40b1d6957db5532a8c452
--- /dev/null
+++ b/bolsonaro/models/omp_forest_classifier.py
@@ -0,0 +1,11 @@
+from sklearn.base import BaseEstimator
+from sklearn.ensemble import RandomForestClassifier
+
+
+class OmpForestClassifier(BaseEstimator):
+
+ def __init__(self):
+ raise ValueError('Classification tasks are not supported for now')
+
+ def fit(self, X, y):
+ pass
diff --git a/bolsonaro/models/omp_forest_regressor.py b/bolsonaro/models/omp_forest_regressor.py
new file mode 100644
index 0000000000000000000000000000000000000000..17d99aa452652b96990135009d1199180c2099b8
--- /dev/null
+++ b/bolsonaro/models/omp_forest_regressor.py
@@ -0,0 +1,39 @@
+from sklearn.base import BaseEstimator
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.linear_model import OrthogonalMatchingPursuit
+
+
+class OmpForestRegressor(BaseEstimator):
+
+ def __init__(self, forest_size, extracted_forest_size, seed=None):
+ self._regressor = RandomForestRegressor(n_estimators=forest_size,
+ random_state=seed)
+ self._extracted_forest_size = extracted_forest_size
+
+ def fit(self, X_train, y_train):
+ self._forest = self._train_forest(X_train, y_train)
+
+ self._weights = self._extract_subforest(X_train, y_train)
+
+ return self
+
+ @property
+ def forest(self):
+ return self._forest
+
+ @property
+ def weights(self):
+ return self._weights
+
+ def _train_forest(self, X_train, y_train):
+ self._regressor.fit(X_train, y_train)
+ forest = self._regressor.estimators_
+ return forest
+
+ def _extract_subforest(self, X_train, y_train):
+ D = [[tree.predict([elem])[0] for tree in forest] for elem in X_train]
+ omp = OrthogonalMatchingPursuit(n_nonzero_coefs=self._extracted_forest_size,
+ fit_intercept=False, normalize=False)
+ omp.fit(D, y_train)
+ weights = omp.coef_
+ return weights
diff --git a/bolsonaro/trainer.py b/bolsonaro/trainer.py
new file mode 100644
index 0000000000000000000000000000000000000000..cb9f9fedc6d71b01eb85be538280d9bd5e824c36
--- /dev/null
+++ b/bolsonaro/trainer.py
@@ -0,0 +1,26 @@
+from bolsonaro.utils import resolve_output_file_name
+
+import pickle
+
+
+class Trainer(object):
+
+ def __init__(self, dataset, model, results_dir, models_dir):
+ self._dataset = dataset
+ self._model = model
+ self._results_dir = results_dir
+ self._models_dir = models_dir
+
+ def process(self):
+ self._model.fit(self._dataset.X_train, self._dataset.y_train)
+ output_file_name = resolve_output_file_name(
+ self._dataset.dataset_parameters,
+ self._model.model_parameters,
+ self._results_dir,
+ self._models_dir
+ )
+ with open(output_file_name, 'wb') as output_file:
+ pickle.dump(output_file, {
+
+ })
+ # save forest and weights here
diff --git a/bolsonaro/utils.py b/bolsonaro/utils.py
index 6761ac86095a3420cc371a6f2b7aac0a629acc14..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 100644
--- a/bolsonaro/utils.py
+++ b/bolsonaro/utils.py
@@ -1,3 +0,0 @@
-from pathlib import Path
-
-root_directory = Path(__file__).parent.parent.absolute()
diff --git a/bolsonaro/visualization/plotter.py b/bolsonaro/visualization/plotter.py
new file mode 100644
index 0000000000000000000000000000000000000000..01f0f0388885e37b8bdefb5d9e8877a491dcdce5
--- /dev/null
+++ b/bolsonaro/visualization/plotter.py
@@ -0,0 +1,3 @@
+class Plotter(object):
+
+
\ No newline at end of file
diff --git a/train.py b/train.py
new file mode 100644
index 0000000000000000000000000000000000000000..cd6f228ce4756cfd487200589701076ffdc6b667
--- /dev/null
+++ b/train.py
@@ -0,0 +1,69 @@
+from bolsonaro.data.dataset_parameters import DatasetParameters
+from bolsonaro.data.dataset_loader import DatasetLoader
+from bolsonaro.models.model_factory import ModelFactory
+from bolsonaro.trainer import Trainer
+
+import argparse
+import pathlib
+import random
+
+
+if __name__ == "__main__":
+ default_dataset_name = 'boston'
+ default_normalize = False
+ default_forest_size = 100
+ default_extracted_forest_size = 10
+ default_results_dir = 'results'
+ default_models_dir = 'models'
+ default_dev_size = 0.2
+ default_test_size = 0.2
+ default_use_random_seed = True
+ default_random_seed_number = 1
+ begin_random_seed_range = 1
+ end_random_seed_range = 2000
+
+ 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', action='store_true', default=default_normalize, help='Normalize the data by doing the L2 division of the pred vectors.')
+ 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('--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('--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('--use_random_seed', action='store_true', default=default_use_random_seed, help='Random seed used for the data split')
+ parser.add_argument('--random_seed_number', nargs='?', type=int, default=default_random_seed_number, help='Number of random seeds used')
+ args = parser.parse_args()
+
+ pathlib.Path(args.results_dir).mkdir(parents=True, exist_ok=True)
+ pathlib.Path(args.models_dir).mkdir(parents=True, exist_ok=True)
+
+ random_seeds = [random.randint(begin_random_seed_range, end_random_seed_range) for i in range(args.random_seed_number)] \
+ if args.use_random_seed else None
+
+ for random_seed in random_seeds:
+ dataset = DatasetLoader.load_from_name(
+ DatasetParameters(
+ name=args.dataset_name,
+ test_size=args.test_size,
+ dev_size=args.dev_size,
+ random_state=random_seed,
+ normalize=args.normalize
+ )
+ )
+
+ for extracted_forest_size in args.extracted_forest_size:
+ model = ModelFactory(
+ task=dataset.task,
+ forest_size=args.forest_size,
+ extracted_forest_size=extracted_forest_size,
+ seed=random_seed
+ )
+
+ trainer = Trainer(
+ dataset=dataset,
+ model=model,
+ results_dir=args.results_dir,
+ models_dir=args.models_dir
+ )
+ trainer.process()
diff --git a/bolsonaro/notebooks/.gitkeep b/visualize.py
similarity index 100%
rename from bolsonaro/notebooks/.gitkeep
rename to visualize.py