diff --git a/code/bolsonaro/data/dataset_loader.py b/code/bolsonaro/data/dataset_loader.py
index d706b7a07751f715b6398b1f451ec9f337d00f60..dd11da7f322ebce2d8ac62fabf180a86d0978046 100644
--- a/code/bolsonaro/data/dataset_loader.py
+++ b/code/bolsonaro/data/dataset_loader.py
@@ -8,6 +8,13 @@ from sklearn.datasets import fetch_olivetti_faces, fetch_20newsgroups, \
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
+def change_binary_func_load(base_load_function):
+ def func_load(return_X_y):
+ X, y = base_load_function(return_X_y=return_X_y)
+ assert len(set(y).difference({0, 1})) == 0, "Classes for binary classifier should be {-1, +1}"
+ y[y==0] = -1
+ return X, y
+ return func_load
class DatasetLoader(object):
@@ -33,7 +40,7 @@ class DatasetLoader(object):
dataset_loading_func = load_wine
task = Task.CLASSIFICATION
elif name == 'breast_cancer':
- dataset_loading_func = load_breast_cancer
+ dataset_loading_func = change_binary_func_load(load_breast_cancer)
task = Task.CLASSIFICATION
elif name == 'olivetti_faces':
dataset_loading_func = fetch_olivetti_faces
diff --git a/code/bolsonaro/models/model_factory.py b/code/bolsonaro/models/model_factory.py
index fb6b32cb26727d2221367f208598f04e1a19dfb1..1fa46385a884d82b74b44a5b8227b5b3dbfb0286 100644
--- a/code/bolsonaro/models/model_factory.py
+++ b/code/bolsonaro/models/model_factory.py
@@ -1,4 +1,4 @@
-from bolsonaro.models.omp_forest_classifier import OmpForestClassifier
+from bolsonaro.models.omp_forest_classifier import OmpForestBinaryClassifier
from bolsonaro.models.omp_forest_regressor import OmpForestRegressor
from bolsonaro.data.task import Task
from bolsonaro.models.model_parameters import ModelParameters
@@ -12,7 +12,7 @@ class ModelFactory(object):
@staticmethod
def build(task, model_parameters):
if task == Task.CLASSIFICATION:
- model_func = OmpForestClassifier
+ model_func = OmpForestBinaryClassifier
elif task == Task.REGRESSION:
model_func = OmpForestRegressor
else:
@@ -21,8 +21,10 @@ class ModelFactory(object):
@staticmethod
def load(task, directory_path, experiment_id, model_raw_results):
+ raise NotImplementedError
model_parameters = ModelParameters.load(directory_path, experiment_id)
model = ModelFactory.build(task, model_parameters)
- model.set_forest(model_raw_results.forest)
- model.set_weights(model_raw_results.weights)
+ # todo faire ce qu'il faut ici pour rétablir correctement le modèle
+ # model.set_forest(model_raw_results.forest)
+ # model.set_weights(model_raw_results.weights)
return model
diff --git a/code/bolsonaro/models/model_raw_results.py b/code/bolsonaro/models/model_raw_results.py
index 673cb0fc65b7378e95c03b186d246cb70b384a07..df8b2ec0b10704a8a8c397b9012298e8b901e14b 100644
--- a/code/bolsonaro/models/model_raw_results.py
+++ b/code/bolsonaro/models/model_raw_results.py
@@ -6,13 +6,12 @@ import datetime
class ModelRawResults(object):
- def __init__(self, forest, weights, training_time,
+ def __init__(self, model_object, training_time,
datetime, train_score, dev_score, test_score,
score_metric, train_score_regressor, dev_score_regressor,
test_score_regressor):
- self._forest = forest
- self._weights = weights
+ self._model_object = model_object
self._training_time = training_time
self._datetime = datetime
self._train_score = train_score
@@ -24,12 +23,8 @@ class ModelRawResults(object):
self._test_score_regressor = test_score_regressor
@property
- def forest(self):
- return self._forest
-
- @property
- def weights(self):
- return self._weights
+ def model_object(self):
+ return self.model_object
@property
def training_time(self):
diff --git a/code/bolsonaro/models/omp_forest.py b/code/bolsonaro/models/omp_forest.py
new file mode 100644
index 0000000000000000000000000000000000000000..1962d78eaa670035d9cb4bd283d513aa700e7d84
--- /dev/null
+++ b/code/bolsonaro/models/omp_forest.py
@@ -0,0 +1,116 @@
+from abc import abstractmethod, ABCMeta
+
+import numpy as np
+from sklearn.linear_model import OrthogonalMatchingPursuit
+
+from bolsonaro import LOG_PATH
+from bolsonaro.error_handling.logger_factory import LoggerFactory
+from sklearn.base import BaseEstimator
+
+
+class OmpForest(BaseEstimator, metaclass=ABCMeta):
+ def __init__(self, models_parameters, base_forest_estimator):
+ self._base_forest_estimator = base_forest_estimator
+ self._models_parameters = models_parameters
+ self._logger = LoggerFactory.create(LOG_PATH, __name__)
+
+ @property
+ def models_parameters(self):
+ return self._models_parameters
+
+ def score_base_estimator(self, X, y):
+ return self._base_forest_estimator.score(X, y)
+
+
+ def _base_estimator_predictions(self, X):
+ return np.array([tree.predict(X) for tree in self._base_forest_estimator.estimators_]).T
+
+ @property
+ def forest(self):
+ return self._base_forest_estimator.estimators_
+
+ # sklearn baseestimator api methods
+ @abstractmethod
+ def fit(self, X_forest, y_forest, X_omp, y_omp):
+ pass
+
+ @abstractmethod
+ def predict(self, X):
+ pass
+
+ @abstractmethod
+ def score(self, X, y):
+ pass
+
+class SingleOmpForest(OmpForest):
+ def __init__(self, models_parameters, base_forest_estimator):
+ # fit_intercept shouldn't be set to False as the data isn't necessarily centered here
+ # normalization is handled outsite OMP
+ self._omp = OrthogonalMatchingPursuit(
+ n_nonzero_coefs=models_parameters.extracted_forest_size,
+ fit_intercept=True, normalize=False)
+
+ super().__init__(models_parameters, base_forest_estimator)
+
+ def fit(self, X_forest, y_forest, X_omp, y_omp):
+ self._base_forest_estimator.fit(X_forest, y_forest)
+ self._extract_subforest(X_omp, y_omp) # type: OrthogonalMatchingPursuit
+ return self
+
+ def _extract_subforest(self, X, y):
+ """
+ Given an already estimated regressor: apply OMP to get the weight of each tree.
+
+ The X data is used for interrogation of every tree in the forest. The y data
+ is used for finding the weights in OMP.
+
+ :param X: (n_sample, n_features) array
+ :param y: (n_sample,) array
+ :return:
+ """
+ self._logger.debug("Forest make prediction on X")
+ D = self._base_estimator_predictions(X)
+
+ if self._models_parameters.normalize_D:
+ # question: maybe consider other kinds of normalization.. centering?
+ self._logger.debug("Compute norm of predicted vectors on X")
+ self._forest_norms = np.linalg.norm(D, axis=0)
+ D /= self._forest_norms
+
+ self._logger.debug("Apply orthogonal maching pursuit on forest for {} extracted trees."
+ .format(self._models_parameters.extracted_forest_size))
+
+ return self._omp.fit(D, y)
+
+ def predict(self, X):
+ """
+ Apply the SingleOmpForest to X.
+
+ Make all the base tree predictions then apply the OMP weights for pruning.
+
+ :param X:
+ :return:
+ """
+ forest_predictions = self._base_estimator_predictions(X)
+
+ if self._models_parameters.normalize_D:
+ forest_predictions /= self._forest_norms
+
+ if self._models_parameters.normalize_weights:
+ # we can normalize weights (by their sum) so that they sum to 1
+ # and they can be interpreted as impact percentages for interpretability.
+ # this necessits to remove the (-) in weights, e.g. move it to the predictions (use unsigned_coef)
+
+ # question: je comprend pas le truc avec nonszero?
+ # predictions = self._omp.predict(forest_predictions) * (1 / (np.sum(self._omp.coef_) / len(np.nonzero(self._omp.coef_))))
+ coef_signs = np.sign(self._omp.coef_)[np.newaxis, :] # add axis to make sure it will be broadcasted line-wise (there might be a confusion when forest_prediction is square)
+ unsigned_coef = (coef_signs * self._omp.coef_).squeeze()
+ intercept = self._omp.intercept_
+
+ adjusted_forest_predictions = forest_predictions * coef_signs
+ predictions = adjusted_forest_predictions.dot(unsigned_coef) + intercept
+
+ else:
+ predictions = self._omp.predict(forest_predictions)
+
+ return predictions
\ No newline at end of file
diff --git a/code/bolsonaro/models/omp_forest_classifier.py b/code/bolsonaro/models/omp_forest_classifier.py
index 12cc23fab69fc0b79ff40b1d6957db5532a8c452..fb602ce401c086a2dba77714bc6530d69df10898 100644
--- a/code/bolsonaro/models/omp_forest_classifier.py
+++ b/code/bolsonaro/models/omp_forest_classifier.py
@@ -1,11 +1,65 @@
+from collections import namedtuple
+
from sklearn.base import BaseEstimator
from sklearn.ensemble import RandomForestClassifier
+from sklearn.linear_model import OrthogonalMatchingPursuit
+
+from bolsonaro import LOG_PATH
+from bolsonaro.error_handling.logger_factory import LoggerFactory
+from bolsonaro.models.omp_forest import OmpForest, SingleOmpForest
+import numpy as np
+
+class OmpForestBinaryClassifier(SingleOmpForest):
+
+ DEFAULT_SCORE_METRIC = 'indicator'
+
+ def __init__(self, models_parameters):
+ estimator = RandomForestClassifier(n_estimators=models_parameters.forest_size,
+ random_state=models_parameters.seed, n_jobs=-1)
+ super().__init__(models_parameters, estimator)
+
+ def _check_classes(self, y):
+ assert len(set(y).difference({-1, 1})) == 0, "Classes for binary classifier should be {-1, +1}"
+
+ def fit(self, X_forest, y_forest, X_omp, y_omp):
+ self._check_classes(y_forest)
+ self._check_classes(y_omp)
+
+ return super().fit(X_forest, y_forest, X_omp, y_omp)
+
+
+ def score(self, X, y, metric=DEFAULT_SCORE_METRIC):
+ """
+ Evaluate OMPForestClassifer on (`X`, `y`) using `metric`
+
+ :param X:
+ :param y:
+ :param metric: might be "indicator"
+ :return:
+ """
+ predictions = self.predict(X)
+
+ if metric == 'indicator':
+ evaluation = np.abs(np.mean(np.abs(np.sign(predictions) - y) - 1))
+ else:
+ raise ValueError("Unsupported metric '{}'.".format(metric))
+
+ return evaluation
+
+
+class OmpForestMulticlassClassifier(BaseEstimator):
+ def __init__(self, models_parameters):
+ self._models_parameters = models_parameters
+ self._base_forest_estimators = RandomForestClassifier(n_estimators=models_parameters.forest_size,
+ random_state=models_parameters.seed, n_jobs=-1)
+ self._logger = LoggerFactory.create(LOG_PATH, __name__)
-class OmpForestClassifier(BaseEstimator):
- def __init__(self):
- raise ValueError('Classification tasks are not supported for now')
- def fit(self, X, y):
- pass
+if __name__ == "__main__":
+ forest = RandomForestClassifier(n_estimators=10)
+ X = np.random.rand(10, 5)
+ y = np.random.choice([-1, +1], 10)
+ forest.fit(X, y)
+ print(forest.predict(np.random.rand(10, 5)))
\ No newline at end of file
diff --git a/code/bolsonaro/models/omp_forest_regressor.py b/code/bolsonaro/models/omp_forest_regressor.py
index 65193e1ad32260ad55ff885f2f663aaf9dfeea77..c1404fc2564a0611b072bdd79921f1179680ec93 100644
--- a/code/bolsonaro/models/omp_forest_regressor.py
+++ b/code/bolsonaro/models/omp_forest_regressor.py
@@ -1,67 +1,22 @@
-from bolsonaro import LOG_PATH
-from bolsonaro.error_handling.logger_factory import LoggerFactory
+
from sklearn.ensemble import RandomForestRegressor
-from sklearn.linear_model import OrthogonalMatchingPursuit
-from sklearn.base import BaseEstimator
import numpy as np
+from bolsonaro.models.omp_forest import SingleOmpForest
+
-class OmpForestRegressor(BaseEstimator):
+class OmpForestRegressor(SingleOmpForest):
DEFAULT_SCORE_METRIC = 'mse'
def __init__(self, models_parameters):
- self._regressor = RandomForestRegressor(n_estimators=models_parameters.forest_size,
- random_state=models_parameters.seed, n_jobs=-1)
- self._models_parameters = models_parameters
- self._logger = LoggerFactory.create(LOG_PATH, __name__)
-
- @property
- def forest(self):
- return self._forest
-
- def set_forest(self, forest):
- self._forest = forest
- self._regressor.estimators_ = forest
-
- @property
- def weights(self):
- return self._weights
-
- def set_weights(self, weights):
- self._weights = weights
-
- @property
- def models_parameters(self):
- return self._models_parameters
-
- def fit(self, X_forest, y_forest, X_omp, y_omp):
- self._forest = self._train_forest(X_forest, y_forest)
- self._omp = self._extract_subforest(X_omp, y_omp)
- self._weights = self._omp.coef_
- return self
-
- def score_regressor(self, X, y):
- return self._regressor.score(X, y)
-
- def predict(self, X):
- """
- Apply the OMPForestRegressor to X.
-
- :param X:
- :return:
- """
- forest_predictions = self._forest_prediction(X)
+ estimator = RandomForestRegressor(n_estimators=models_parameters.forest_size,
+ random_state=models_parameters.seed, n_jobs=-1)
- if self._models_parameters.normalize_D:
- forest_predictions /= self._forest_norms
- predictions = self._omp.predict(forest_predictions) * (1 / (np.sum(self._omp.coef_) / len(np.nonzero(self._omp.coef_)))) \
- if self._models_parameters.normalize_weights \
- else self._omp.predict(forest_predictions)
+ super().__init__(models_parameters, estimator)
- return predictions
def score(self, X, y, metric=DEFAULT_SCORE_METRIC):
"""
@@ -79,39 +34,4 @@ class OmpForestRegressor(BaseEstimator):
else:
raise ValueError("Unsupported metric '{}'.".format(metric))
- return evaluation
-
- def _train_forest(self, X, y):
- self._regressor.fit(X, y)
- forest = self._regressor.estimators_
- return forest
-
- def _extract_subforest(self, X, y):
- """
- Given an already estimated regressor: apply OMP to get the weight of each tree.
-
- The X data is used for interrogation of every tree in the forest. The y data
- is used for finding the weights in OMP.
-
- :param X: (n_sample, n_features) array
- :param y: (n_sample,) array
- :return:
- """
- self._logger.debug("Forest make prediction on X")
- D = self._forest_prediction(X)
-
- 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)
- D /= self._forest_norms
-
- omp = OrthogonalMatchingPursuit(
- n_nonzero_coefs=self._models_parameters.extracted_forest_size,
- fit_intercept=False, normalize=False)
- self._logger.debug("Apply orthogonal maching pursuit on forest for {} extracted trees."
- .format(self._models_parameters.extracted_forest_size))
- return omp.fit(D, y)
-
- def _forest_prediction(self, X):
- return np.array([tree.predict(X) for tree in self._forest]).T
+ return evaluation
\ No newline at end of file
diff --git a/code/bolsonaro/trainer.py b/code/bolsonaro/trainer.py
index b586914166cf80f274a502d8d44b83f6b6f97484..e615ca8c97facd1b8e033e60eec11c1cc8de922e 100644
--- a/code/bolsonaro/trainer.py
+++ b/code/bolsonaro/trainer.py
@@ -8,12 +8,26 @@ import numpy as np
class Trainer(object):
+ """
+ Class capable of fitting any model object to some prepared data then evaluate and save results through the `train` method.
+ """
def __init__(self, dataset):
+ """
+
+ :param dataset: Object with X_train, y_train, X_dev, y_dev, X_test and Y_test attributes
+ """
self._dataset = dataset
self._logger = LoggerFactory.create(LOG_PATH, __name__)
def train(self, model, models_dir):
+ """
+
+ :param model: Object with
+ :param models_dir: Where the results will be saved
+ :return:
+ """
+ # todo cette fonction ne fait pas que "train", elle choisit le jeu de données, train et evalue le modèle -> nom à changer
self._logger.debug('Training model using train set...')
begin_time = time.time()
@@ -45,16 +59,18 @@ class Trainer(object):
)
end_time = time.time()
- ModelRawResults(
- forest=model.forest,
- weights=model.weights,
+ results = ModelRawResults(
+ model_object=model,
training_time=end_time - begin_time,
datetime=datetime.datetime.now(),
train_score=model.score(self._dataset.X_train, self._dataset.y_train),
dev_score=model.score(self._dataset.X_dev, self._dataset.y_dev),
test_score=model.score(self._dataset.X_test, self._dataset.y_test),
score_metric=model.DEFAULT_SCORE_METRIC, # TODO: resolve the used metric in a proper way
- train_score_regressor=model.score_regressor(self._dataset.X_train, self._dataset.y_train),
- dev_score_regressor=model.score_regressor(self._dataset.X_dev, self._dataset.y_dev),
- test_score_regressor=model.score_regressor(self._dataset.X_test, self._dataset.y_test)
- ).save(models_dir)
+ train_score_regressor=model.score_base_estimator(self._dataset.X_train, self._dataset.y_train),
+ dev_score_regressor=model.score_base_estimator(self._dataset.X_dev, self._dataset.y_dev),
+ test_score_regressor=model.score_base_estimator(self._dataset.X_test, self._dataset.y_test)
+ )
+ results.save(models_dir)
+ self._logger.info("Base performance on test: {}".format(results.test_score_regressor))
+ self._logger.info("Performance on test: {}".format(results.test_score))
diff --git a/code/train.py b/code/train.py
index 4faff6e970da3600cc9f00714759ba2c9df7f73d..73bf6ab688ab647fd1cf4f9e40e234a2a805d703 100644
--- a/code/train.py
+++ b/code/train.py
@@ -18,9 +18,20 @@ import json
def process_job(seed, parameters, experiment_id):
+ """
+ Experiment function.
+
+ Will be used as base function for worker in multithreaded application.
+
+ :param seed:
+ :param parameters:
+ :param experiment_id:
+ :return:
+ """
logger = LoggerFactory.create(LOG_PATH, 'training_seed{}_ti{}'.format(
seed, threading.get_ident()))
logger.info('seed={}'.format(seed))
+
seed_str = str(seed)
experiment_id_str = str(experiment_id)
models_dir = parameters['models_dir'] + os.sep + experiment_id_str + os.sep + 'seeds' + \
@@ -35,12 +46,12 @@ def process_job(seed, parameters, experiment_id):
dataset_normalizer=parameters['dataset_normalizer']
)
dataset_parameters.save(models_dir, experiment_id_str)
-
dataset = DatasetLoader.load(dataset_parameters)
trainer = Trainer(dataset)
for extracted_forest_size in parameters['extracted_forest_size']:
+ # question if training is too long, one may also split experiments for different forest sizes into different workers
logger.info('extracted_forest_size={}'.format(extracted_forest_size))
sub_models_dir = models_dir + os.sep + 'extracted_forest_size' + os.sep + str(extracted_forest_size)
pathlib.Path(sub_models_dir).mkdir(parents=True, exist_ok=True)
@@ -62,7 +73,7 @@ def process_job(seed, parameters, experiment_id):
if __name__ == "__main__":
# get environment variables in .env
- load_dotenv(find_dotenv('.env.example'))
+ load_dotenv(find_dotenv('.env'))
DEFAULT_EXPERIMENT_CONFIGURATION_PATH = 'experiments'
DEFAULT_DATASET_NAME = 'boston'
@@ -109,6 +120,7 @@ if __name__ == "__main__":
logger = LoggerFactory.create(LOG_PATH, os.path.basename(__file__))
+ # The number of tree to extract from forest (K)
parameters['extracted_forest_size'] = parameters['extracted_forest_size'] \
if type(parameters['extracted_forest_size']) == list \
else [parameters['extracted_forest_size']]
@@ -116,6 +128,7 @@ if __name__ == "__main__":
if parameters['seeds'] != None and parameters['random_seed_number'] > 1:
logger.warning('seeds and random_seed_number parameters are both specified. Seeds will be used.')
+ # Seeds are either provided as parameters or generated at random
seeds = parameters['seeds'] if parameters['seeds'] is not None \
else [random.randint(begin_random_seed_range, end_random_seed_range) \
for i in range(parameters['random_seed_number'])]