diff --git a/code/bolsonaro/data/dataset_loader.py b/code/bolsonaro/data/dataset_loader.py
index b76f7408fe8c0b7937bc5d84d0bab397e441ff09..d706b7a07751f715b6398b1f451ec9f337d00f60 100644
--- a/code/bolsonaro/data/dataset_loader.py
+++ b/code/bolsonaro/data/dataset_loader.py
@@ -6,6 +6,7 @@ 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
+from sklearn import preprocessing
class DatasetLoader(object):
@@ -71,9 +72,20 @@ class DatasetLoader(object):
test_size=dataset_parameters.dev_size,
random_state=dataset_parameters.random_state)
- # TODO?
- if dataset_parameters.normalize:
- pass
+ if dataset_parameters.dataset_normalizer is not None:
+ if dataset_parameters.dataset_normalizer == 'standard':
+ scaler = preprocessing.StandardScaler()
+ elif dataset_parameters.dataset_normalizer == 'minmax':
+ scaler = preprocessing.MinMaxScaler()
+ elif dataset_parameters.dataset_normalizer == 'robust':
+ scaler = preprocessing.RobustScaler()
+ elif dataset_parameters.dataset_normalizer == 'normalizer':
+ scaler = preprocessing.Normalizer()
+ else:
+ raise ValueError("Unsupported normalizer '{}'".format(dataset_parameters.dataset_normalizer))
+ X_train = scaler.fit_transform(X_train)
+ X_dev = scaler.transform(X_dev)
+ X_test = scaler.transform(X_test)
return Dataset(task, dataset_parameters, X_train,
X_dev, X_test, y_train, y_dev, y_test)
diff --git a/code/bolsonaro/data/dataset_parameters.py b/code/bolsonaro/data/dataset_parameters.py
index d5a1145d3dc4a3796dbdd1b38aa50325262b7e3e..9e7e7def56f205e342257bcb8849ece952177042 100644
--- a/code/bolsonaro/data/dataset_parameters.py
+++ b/code/bolsonaro/data/dataset_parameters.py
@@ -4,13 +4,13 @@ import os
class DatasetParameters(object):
- def __init__(self, name, test_size, dev_size, random_state, normalize, train_on_subset):
+ def __init__(self, name, test_size, dev_size, random_state, train_on_subset, dataset_normalizer):
self._name = name
self._test_size = test_size
self._dev_size = dev_size
self._random_state = random_state
- self._normalize = normalize
self._train_on_subset = train_on_subset
+ self._dataset_normalizer = dataset_normalizer
@property
def name(self):
@@ -28,14 +28,14 @@ class DatasetParameters(object):
def random_state(self):
return self._random_state
- @property
- def normalize(self):
- return self._normalize
-
@property
def train_on_subset(self):
return self._train_on_subset
+ @property
+ def dataset_normalizer(self):
+ return self._dataset_normalizer
+
def save(self, directory_path, experiment_id):
with open(directory_path + os.sep + 'dataset_parameters_{}.json'.format(experiment_id), 'w') as output_file:
json.dump({
@@ -43,7 +43,7 @@ class DatasetParameters(object):
'test_size': self._test_size,
'dev_size': self._dev_size,
'random_state': self._random_state,
- 'normalize': self._normalize,
+ 'dataset_normalizer': self._dataset_normalizer,
'train_on_subset': self._train_on_subset
},
output_file,
@@ -58,6 +58,6 @@ class DatasetParameters(object):
test_size=parameters['test_size'],
dev_size=parameters['dev_size'],
random_state=parameters['random_state'],
- normalize=parameters['normalize'],
+ dataset_normalizer=parameters['dataset_normalizer'],
train_on_subset=parameters['train_on_subset']
)
diff --git a/code/bolsonaro/models/model_parameters.py b/code/bolsonaro/models/model_parameters.py
index 838253255e2a9a71290633e026090b70e680e201..93bb177270bb1d261234664a5b9ee06898e00165 100644
--- a/code/bolsonaro/models/model_parameters.py
+++ b/code/bolsonaro/models/model_parameters.py
@@ -4,11 +4,11 @@ import os
class ModelParameters(object):
- def __init__(self, forest_size, extracted_forest_size, normalize, seed=None):
+ def __init__(self, forest_size, extracted_forest_size, normalize_D, seed=None):
self._forest_size = forest_size
self._extracted_forest_size = extracted_forest_size
self._seed = seed
- self._normalize = normalize
+ self._normalize_D = normalize_D
@property
def forest_size(self):
@@ -23,8 +23,8 @@ class ModelParameters(object):
return self._seed
@property
- def normalize(self):
- return self._normalize
+ def normalize_D(self):
+ return self._normalize_D
def save(self, directory_path, experiment_id):
with open(directory_path + os.sep + 'model_parameters_{}.json'.format(experiment_id), 'w') as output_file:
@@ -32,7 +32,7 @@ class ModelParameters(object):
'forest_size': self._forest_size,
'extracted_forest_size': self._extracted_forest_size,
'seed': self._seed,
- 'normalize': self._normalize
+ 'normalize_D': self._normalize_D
},
output_file,
indent=4)
@@ -45,5 +45,5 @@ class ModelParameters(object):
forest_size=parameters['forest_size'],
extracted_forest_size=parameters['extracted_forest_size'],
seed=parameters['seed'],
- normalize=parameters['normalize']
+ normalize_D=parameters['normalize_D']
)
diff --git a/code/bolsonaro/models/omp_forest_regressor.py b/code/bolsonaro/models/omp_forest_regressor.py
index f5e2b35f23f931a06ca88ce181434f4ff98cce23..5c79c2a4623c0dabe2dd4bdaf47329174f605f3e 100644
--- a/code/bolsonaro/models/omp_forest_regressor.py
+++ b/code/bolsonaro/models/omp_forest_regressor.py
@@ -53,7 +53,7 @@ class OmpForestRegressor(BaseEstimator):
"""
D = self._forest_prediction(X)
- if self._models_parameters.normalize:
+ if self._models_parameters.normalize_D:
D /= self._forest_norms
predictions = D @ self.weights
@@ -97,7 +97,7 @@ class OmpForestRegressor(BaseEstimator):
self._logger.debug("Forest make prediction on X")
D = self._forest_prediction(X)
- if self._models_parameters.normalize:
+ if self._models_parameters.normalize_D:
# question: maybe consider other kinds of normalization
self._logger.debug("Compute norm of predicted vectors on X")
self._forest_norms = np.linalg.norm(D, axis=0)
diff --git a/code/train.py b/code/train.py
index a410e53bb4ccefc90f5f976617da37e8b709cb40..5f854b68afedea8574001d7c26ef4deaee46f248 100644
--- a/code/train.py
+++ b/code/train.py
@@ -21,7 +21,8 @@ if __name__ == "__main__":
default_dataset_name = 'boston'
default_normalize = True
- default_wo_normalization = False
+ default_normalize_D = False
+ default_dataset_normalizer = None
default_forest_size = 100
default_extracted_forest_size = 10
# the models will be stored in a directory structure like: models/{experiment_id}/seeds/{seed_nb}/extracted_forest_size/{nb_extracted_trees}
@@ -35,7 +36,8 @@ if __name__ == "__main__":
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('--wo_normalization', action='store_true', default=default_wo_normalization, help='Withouyt normalize the data by doing the L2 division of the pred vectors.')
+ parser.add_argument('--normalize_D', action='store_true', default=default_normalize_D, help='Specify if we want to normalize the prediction of the forest by doing the L2 division of the pred vectors.')
+ parser.add_argument('--dataset_normalizer', nargs='?', type=str, default=default_dataset_normalizer, help='Specify which dataset normalizer use (either standard, minmax, robust or normalizer).')
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('--models_dir', nargs='?', type=str, default=default_models_dir, help='The output directory of the trained models.')
@@ -61,9 +63,6 @@ if __name__ == "__main__":
else [random.randint(begin_random_seed_range, end_random_seed_range) \
for i in range(args.random_seed_number)]
- normalize = default_normalize and args.wo_normalization is False
- logger.debug('normalize={}'.format(normalize))
-
experiment_id = resolve_experiment_id(args.models_dir)
experiment_id_str = str(experiment_id)
@@ -80,7 +79,7 @@ if __name__ == "__main__":
test_size=args.test_size,
dev_size=args.dev_size,
random_state=seed,
- normalize=normalize,
+ dataset_normalizer=args.dataset_normalizer,
train_on_subset=args.train_on_subset
)
dataset_parameters.save(models_dir, experiment_id_str)
@@ -99,7 +98,7 @@ if __name__ == "__main__":
forest_size=args.forest_size,
extracted_forest_size=extracted_forest_size,
seed=seed,
- normalize=normalize
+ normalize_D=args.normalize_D
)
model_parameters.save(sub_models_dir, experiment_id)