- Split train function in three distinct functions;

- Update TODO list.

TODO.md

-* Trouver des jeux de données pertinents
-* Entraîner et tester des forêts de différentes tailles
-* Entraîner et tester en regression et classification
-* Entraîner et tester sur différentes modalités (pas seulement des datasets d'images)
-* Entraîner avec différents hyperparamètres (d, profondeur, epsilon)
-* Appliquer OMP avec différentes valeurs de k (notamment un petit k)
-* Faire des figures
-* Implémenter et comparer les systèmes concurrents
+* Fix pickle loading of ModelRawResults, because saving the model_object leads import issues.
+* Fix ModelFactory.load function.
+* Fix model results loading in compute_results.py.
+* Check that omp multiclasses classifier is working as expected.
+* In the bayesian search computation, output a different file name depending on the task of the trained model.
+* Check the best params scores of the regressors (neg_mean_squared_error leads to huge negative values).
+* Prepare the json experiment files to run.
\ No newline at end of file
\ No newline at end of file

code/bolsonaro/trainer.py

@@ -20,48 +20,51 @@ class Trainer(object):
         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()
-
+    def init(self, model):
         if model.models_parameters.subsets_used == 'train,dev':
-            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._X_forest = self._dataset.X_train
+            self._y_forest = self._dataset.y_train
+            self._X_omp = self._dataset.X_dev
+            self._y_omp = self._dataset.y_dev
             self._logger.debug('Fitting the forest on train subset and OMP on dev subset.')
         elif model.models_parameters.subsets_used == 'train+dev,train+dev':
-            X_forest = np.concatenate([self._dataset.X_train, self._dataset.X_dev])
-            X_omp = X_forest
-            y_forest = np.concatenate([self._dataset.y_train, self._dataset.y_dev])
-            y_omp = y_forest
+            self._X_forest = np.concatenate([self._dataset.X_train, self._dataset.X_dev])
+            self._X_omp = self._X_forest
+            self._y_forest = np.concatenate([self._dataset.y_train, self._dataset.y_dev])
+            self._y_omp = self._y_forest
             self._logger.debug('Fitting both the forest and OMP on train+dev subsets.')
         elif model.models_parameters.subsets_used == 'train,train+dev':
-            X_forest = self._dataset.X_train
-            y_forest = self._dataset.y_train
-            X_omp = np.concatenate([self._dataset.X_train, self._dataset.X_dev])
-            y_omp = np.concatenate([self._dataset.y_train, self._dataset.y_dev])
+            self._X_forest = self._dataset.X_train
+            self._y_forest = self._dataset.y_train
+            self._X_omp = np.concatenate([self._dataset.X_train, self._dataset.X_dev])
+            self._y_omp = np.concatenate([self._dataset.y_train, self._dataset.y_dev])
         else:
             raise ValueError("Unknown specified subsets_used parameter '{}'".format(model.models_parameters.subsets_used))
 
+    def train(self, model):
+        """
+        :param model: Object with
+        :return:
+        """
+        
+        self._logger.debug('Training model using train set...')
+        self._begin_time = time.time()
         model.fit(
-            X_forest=X_forest,
-            y_forest=y_forest,
-            X_omp=X_omp,
-            y_omp=y_omp
+            X_forest=self._X_forest,
+            y_forest=self._y_forest,
+            X_omp=self._X_omp,
+            y_omp=self._y_omp
         )
-        end_time = time.time()
+        self._end_time = time.time()
 
+    def compute_results(self, model, models_dir):
+        """
+        :param model: Object with
+        :param models_dir: Where the results will be saved
+        """
         results = ModelRawResults(
             model_object=model,
-            training_time=end_time - begin_time,
+            training_time=self._end_time - self._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),

code/train.py

@@ -69,7 +69,9 @@ def process_job(seed, parameters, experiment_id, hyperparameters):
 
         model = ModelFactory.build(dataset.task, model_parameters)
 
-        trainer.train(model, sub_models_dir)
+        trainer.init(model)
+        trainer.train(model)
+        trainer.compute_results(model, sub_models_dir)
     logger.info('Training done')
 
 if __name__ == "__main__":