diff --git a/code/bolsonaro/data/dataset_parameters.py b/code/bolsonaro/data/dataset_parameters.py
index e251c7536f0814a5839f71532201abd827312b00..9854a75eb27ec83990b8ae032c58e7dec52a5e8c 100644
--- a/code/bolsonaro/data/dataset_parameters.py
+++ b/code/bolsonaro/data/dataset_parameters.py
@@ -5,12 +5,11 @@ import os
class DatasetParameters(object):
- def __init__(self, name, test_size, dev_size, random_state, train_on_subset, dataset_normalizer):
+ def __init__(self, name, test_size, dev_size, random_state, dataset_normalizer):
self._name = name
self._test_size = test_size
self._dev_size = dev_size
self._random_state = random_state
- self._train_on_subset = train_on_subset
self._dataset_normalizer = dataset_normalizer
@property
@@ -29,10 +28,6 @@ class DatasetParameters(object):
def random_state(self):
return self._random_state
- @property
- def train_on_subset(self):
- return self._train_on_subset
-
@property
def dataset_normalizer(self):
return self._dataset_normalizer
diff --git a/code/bolsonaro/models/model_parameters.py b/code/bolsonaro/models/model_parameters.py
index 7198dceb9f2677dbd44767baa9f308edc5953e90..450d97bc01fe8f02ccd399d2c47a0c7397b4cb13 100644
--- a/code/bolsonaro/models/model_parameters.py
+++ b/code/bolsonaro/models/model_parameters.py
@@ -5,11 +5,12 @@ import os
class ModelParameters(object):
- def __init__(self, forest_size, extracted_forest_size, normalize_D, seed=None):
+ def __init__(self, forest_size, extracted_forest_size, normalize_D, use_dev_subset, seed=None):
self._forest_size = forest_size
self._extracted_forest_size = extracted_forest_size
- self._seed = seed
self._normalize_D = normalize_D
+ self._use_dev_subset = use_dev_subset
+ self._seed = seed
@property
def forest_size(self):
@@ -19,14 +20,18 @@ class ModelParameters(object):
def extracted_forest_size(self):
return self._extracted_forest_size
- @property
- def seed(self):
- return self._seed
-
@property
def normalize_D(self):
return self._normalize_D
+ @property
+ def use_dev_subset(self):
+ return self._use_dev_subset
+
+ @property
+ def seed(self):
+ return self._seed
+
def save(self, directory_path, experiment_id):
save_obj_to_json(directory_path + os.sep + 'model_parameters_{}.json'.format(experiment_id),
self.__dict__)
diff --git a/code/bolsonaro/models/omp_forest_regressor.py b/code/bolsonaro/models/omp_forest_regressor.py
index cd26f92acc89725e4f6cc64b69bad8d2e8d2cbc3..50754246abc13e0282e4cbd6aa1e917a0e3544ed 100644
--- a/code/bolsonaro/models/omp_forest_regressor.py
+++ b/code/bolsonaro/models/omp_forest_regressor.py
@@ -36,9 +36,9 @@ class OmpForestRegressor(BaseEstimator):
def models_parameters(self):
return self._models_parameters
- def fit(self, X, y):
- self._forest = self._train_forest(X, y)
- self._weights = self._extract_subforest(X, y)
+ def fit(self, X_forest, y_forest, X_omp, y_omp):
+ self._forest = self._train_forest(X_forest, y_forest)
+ self._weights = self._extract_subforest(X_omp, y_omp)
return self
def score_regressor(self, X, y):
diff --git a/code/bolsonaro/trainer.py b/code/bolsonaro/trainer.py
index 91480dd944f077668494dfedf252756ec0511898..e5ca49b4bef86a4386f314801d9c36ec8ea2fa7f 100644
--- a/code/bolsonaro/trainer.py
+++ b/code/bolsonaro/trainer.py
@@ -4,6 +4,7 @@ from . import LOG_PATH
import time
import datetime
+import numpy as np
class Trainer(object):
@@ -15,15 +16,26 @@ class Trainer(object):
def train(self, model, models_dir):
self._logger.debug('Training model using train set...')
begin_time = time.time()
- train_on_subset = self._dataset.dataset_parameters.train_on_subset
- if train_on_subset == 'train':
- X, y = self._dataset.X_train, self._dataset.y_train
- elif train_on_subset == 'dev':
- X, y = self._dataset.X_dev, self._dataset.y_dev
+
+ if model.models_parameters.use_dev_subset:
+ X_forest = self._dataset.X_train
+ y_forest = self._dataset.y_train
+ X_omp = self._dataset.X_dev
+ y_omp = self._dataset.y_dev
+ self._logger.debug('Fitting the forest on train subset and OMP on dev subset.')
else:
- raise ValueError("Unsupported train_on_subset value '{}'".format(train_on_subset))
- self._logger.debug('Fitting on {} subset'.format(train_on_subset))
- model.fit(X, y)
+ X_forest = np.concatenate([self._dataset.X_train, self._dataset.X_dev])
+ X_omp = np.concatenate([self._dataset.X_train, self._dataset.X_dev])
+ y_forest = np.concatenate([self._dataset.y_train, self._dataset.y_dev])
+ y_omp = np.concatenate([self._dataset.y_train, self._dataset.y_dev])
+ self._logger.debug('Fitting both the forest and OMP on train+dev subsets.')
+
+ model.fit(
+ X_forest=X_forest,
+ y_forest=y_forest,
+ X_omp=X_omp,
+ y_omp=y_omp
+ )
end_time = time.time()
ModelRawResults(
diff --git a/code/train.py b/code/train.py
index 475843c9dbd005935fe7e61d77b7467a781af1fc..5783fef4bd32d75f62f5dcf05c9812e82f9c0338 100644
--- a/code/train.py
+++ b/code/train.py
@@ -29,7 +29,7 @@ if __name__ == "__main__":
DEFAULT_DEV_SIZE = 0.2
DEFAULT_TEST_SIZE = 0.2
DEFAULT_RANDOM_SEED_NUMBER = 1
- DEFAULT_TRAIN_ON_SUBSET = 'train'
+ DEFAULT_USE_DEV_SUBSET = False
DEFAULT_DISABLE_PROGRESS = False
begin_random_seed_range = 1
@@ -46,7 +46,7 @@ if __name__ == "__main__":
parser.add_argument('--test_size', nargs='?', type=float, default=DEFAULT_TEST_SIZE, help='Test subset ratio.')
parser.add_argument('--random_seed_number', nargs='?', type=int, default=DEFAULT_RANDOM_SEED_NUMBER, help='Number of random seeds used.')
parser.add_argument('--seeds', nargs='+', type=int, default=None, help='Specific a list of seeds instead of generate them randomly')
- parser.add_argument('--train_on_subset', nargs='?', type=str, default=DEFAULT_TRAIN_ON_SUBSET, help='Specify on witch subset the model will be trained (either train or dev).')
+ parser.add_argument('--use_dev_subset', action='store_true', default=DEFAULT_USE_DEV_SUBSET, help='If specify the forest will be trained on train subset and OMP on dev subset. Otherwise both the forest and OMP will be trained on train+dev subsets.')
parser.add_argument('--disable_progress', action='store_true', default=DEFAULT_DISABLE_PROGRESS, help='Disable the progress bars.')
args = parser.parse_args()
@@ -83,8 +83,7 @@ if __name__ == "__main__":
test_size=args.test_size,
dev_size=args.dev_size,
random_state=seed,
- dataset_normalizer=args.dataset_normalizer,
- train_on_subset=args.train_on_subset
+ dataset_normalizer=args.dataset_normalizer
)
dataset_parameters.save(models_dir, experiment_id_str)
@@ -101,8 +100,9 @@ if __name__ == "__main__":
model_parameters = ModelParameters(
forest_size=args.forest_size,
extracted_forest_size=extracted_forest_size,
- seed=seed,
- normalize_D=args.normalize_D
+ normalize_D=args.normalize_D,
+ use_dev_subset=args.use_dev_subset,
+ seed=seed
)
model_parameters.save(sub_models_dir, experiment_id)