From b62b7df7d6eed466d0e095511ccc8096b2512f8b Mon Sep 17 00:00:00 2001
From: Luc Giffon <luc.giffon@lis-lab.fr>
Date: Mon, 4 Nov 2019 16:42:11 +0100
Subject: [PATCH] support for normalize parameter + optimisation on train (wtf
was that for loop)
---
code/bolsonaro/models/model_parameters.py | 10 ++++++++--
code/bolsonaro/models/omp_forest_regressor.py | 20 +++++++++++++++++++
code/train.py | 3 ++-
3 files changed, 30 insertions(+), 3 deletions(-)
diff --git a/code/bolsonaro/models/model_parameters.py b/code/bolsonaro/models/model_parameters.py
index b1fec8c..2d8dba5 100644
--- a/code/bolsonaro/models/model_parameters.py
+++ b/code/bolsonaro/models/model_parameters.py
@@ -4,10 +4,11 @@ import os
class ModelParameters(object):
- def __init__(self, forest_size, extracted_forest_size, seed=None):
+ def __init__(self, forest_size, extracted_forest_size, normalize, seed=None):
self._forest_size = forest_size
self._extracted_forest_size = extracted_forest_size
self._seed = seed
+ self._normalize = normalize
@property
def forest_size(self):
@@ -21,12 +22,17 @@ class ModelParameters(object):
def seed(self):
return self._seed
+ @property
+ def normalize(self):
+ return self._normalize
+
def save(self, directory_path, experiment_id):
with open(directory_path + os.sep + 'model_parameters_{}.json'.format(experiment_id), 'w') as output_file:
json.dump({
'forest_size': self._forest_size,
'extracted_forest_size': self._extracted_forest_size,
- 'seed': self._seed
+ 'seed': self._seed,
+ 'normalize': self._normalize
},
output_file,
indent=4)
diff --git a/code/bolsonaro/models/omp_forest_regressor.py b/code/bolsonaro/models/omp_forest_regressor.py
index 9de6c74..7813da9 100644
--- a/code/bolsonaro/models/omp_forest_regressor.py
+++ b/code/bolsonaro/models/omp_forest_regressor.py
@@ -3,12 +3,17 @@ from sklearn.linear_model import OrthogonalMatchingPursuit
from sklearn.base import BaseEstimator
import numpy as np
+from bolsonaro import LOG_PATH
+from bolsonaro.error_handling.logger_factory import LoggerFactory
+
+
class OmpForestRegressor(BaseEstimator):
def __init__(self, models_parameters):
self._regressor = RandomForestRegressor(n_estimators=models_parameters.forest_size,
random_state=models_parameters.seed)
self._models_parameters = models_parameters
+ self._logger = LoggerFactory.create(LOG_PATH, __name__)
def fit(self, X_train, y_train):
self._forest = self._train_forest(X_train, y_train)
@@ -45,10 +50,25 @@ class OmpForestRegressor(BaseEstimator):
:param y_train: (n_sample,) array
:return:
"""
+ self._logger.debug("Forest make prediction on X_train")
D = np.array([tree.predict(X_train) for tree in self._forest]).T
+
+ if self._models_parameters.normalize:
+ self._logger.debug("Compute norm of predicted vectors on X_train")
+ 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))
omp.fit(D, y_train)
weights = omp.coef_ # why not to use directly the omp estimator and bypass it using the coefs?
return weights
+
+ def predict(self):
+ raise NotImplementedError("TODO: implement predict function")
+ # todo don't forget to deal with the normalize parameter
+ # should the norm used on train or the new norms be used for normalization?
diff --git a/code/train.py b/code/train.py
index 74d90a5..9a50283 100644
--- a/code/train.py
+++ b/code/train.py
@@ -92,7 +92,8 @@ if __name__ == "__main__":
model_parameters = ModelParameters(
forest_size=args.forest_size,
extracted_forest_size=extracted_forest_size,
- seed=random_seed
+ seed=random_seed,
+ normalize=args.normalize
)
model_parameters.save(sub_models_dir, experiment_id)
--
GitLab