From 3c309a5cc8dfc39ffe604916b4757588ab102c7f Mon Sep 17 00:00:00 2001
From: Charly Lamothe <charly.lamothe@univ-amu.fr>
Date: Sun, 22 Mar 2020 02:54:28 +0100
Subject: [PATCH] set random results linear to ease the read of coherence preds
plot reading
---
.../models/kmeans_forest_regressor.py | 6 +--
code/bolsonaro/trainer.py | 3 +-
code/compute_results.py | 48 +++++++++----------
code/train.py | 2 +-
4 files changed, 30 insertions(+), 29 deletions(-)
diff --git a/code/bolsonaro/models/kmeans_forest_regressor.py b/code/bolsonaro/models/kmeans_forest_regressor.py
index d0d6412..81801ef 100644
--- a/code/bolsonaro/models/kmeans_forest_regressor.py
+++ b/code/bolsonaro/models/kmeans_forest_regressor.py
@@ -19,7 +19,7 @@ class KMeansForestRegressor(BaseEstimator, metaclass=ABCMeta):
def __init__(self, models_parameters, score_metric=mean_squared_error):
self._models_parameters = models_parameters
self._estimator = RandomForestRegressor(**self._models_parameters.hyperparameters,
- random_state=self._models_parameters.seed, n_jobs=2)
+ random_state=self._models_parameters.seed, n_jobs=1)
self._extracted_forest_size = self._models_parameters.extracted_forest_size
self._score_metric = score_metric
self._selected_trees = list()
@@ -46,7 +46,7 @@ class KMeansForestRegressor(BaseEstimator, metaclass=ABCMeta):
# For each cluster select the best tree on the validation set
extracted_forest_sizes = list(range(self._extracted_forest_size))
with tqdm_joblib(tqdm(total=self._extracted_forest_size, disable=True)) as prune_forest_job_pb:
- pruned_forest = Parallel(n_jobs=2)(delayed(self._prune_forest_job)(prune_forest_job_pb,
+ pruned_forest = Parallel(n_jobs=1)(delayed(self._prune_forest_job)(prune_forest_job_pb,
extracted_forest_sizes[i], labels, X_val, y_val, self._score_metric)
for i in range(self._extracted_forest_size))
@@ -56,7 +56,7 @@ class KMeansForestRegressor(BaseEstimator, metaclass=ABCMeta):
def _prune_forest_job(self, prune_forest_job_pb, c, labels, X_val, y_val, score_metric):
index = np.where(labels == c)[0]
with tqdm_joblib(tqdm(total=len(index), disable=True)) as cluster_job_pb:
- cluster = Parallel(n_jobs=2)(delayed(self._cluster_job)(cluster_job_pb, index[i], X_val,
+ cluster = Parallel(n_jobs=1)(delayed(self._cluster_job)(cluster_job_pb, index[i], X_val,
y_val, score_metric) for i in range(len(index)))
best_tree_index = np.argmax(cluster)
prune_forest_job_pb.update()
diff --git a/code/bolsonaro/trainer.py b/code/bolsonaro/trainer.py
index 9d4911e..5cea2bd 100644
--- a/code/bolsonaro/trainer.py
+++ b/code/bolsonaro/trainer.py
@@ -77,7 +77,7 @@ class Trainer(object):
else:
raise ValueError("Unknown specified subsets_used parameter '{}'".format(model.models_parameters.subsets_used))
- def train(self, model, extracted_forest_size=None):
+ def train(self, model, extracted_forest_size=None, seed=None):
"""
:param model: An instance of either RandomForestRegressor, RandomForestClassifier, OmpForestRegressor,
OmpForestBinaryClassifier, OmpForestMulticlassClassifier.
@@ -88,6 +88,7 @@ class Trainer(object):
if type(model) in [RandomForestRegressor, RandomForestClassifier]:
if extracted_forest_size is not None:
estimators_index = np.arange(len(model.estimators_))
+ np.random.seed(seed)
np.random.shuffle(estimators_index)
choosen_estimators = estimators_index[:extracted_forest_size]
model.estimators_ = np.array(model.estimators_)[choosen_estimators]
diff --git a/code/compute_results.py b/code/compute_results.py
index e05fff6..9e276e6 100644
--- a/code/compute_results.py
+++ b/code/compute_results.py
@@ -521,7 +521,7 @@ if __name__ == "__main__":
ylabel=base_with_params_experiment_score_metric,
title='Loss values of {}\nusing best params of previous stages'.format(args.dataset_name))
- if args.plot_weight_density or args.plot_preds_coherence:
+ """if args.plot_weight_density or args.plot_preds_coherence:
root_output_path = os.path.join(args.results_dir, args.dataset_name, f'stage{args.stage}')
if args.stage == 1:
@@ -551,28 +551,28 @@ if __name__ == "__main__":
continue
current_experiment_id = int(args.experiment_ids[i].split('=')[1])
- omp_experiment_ids.append((label, current_experiment_id))
-
- for (experiment_label, experiment_id) in omp_experiment_ids:
- if args.plot_weight_density:
- logger.info(f'Computing weight density plot for experiment {experiment_label}...')
- experiment_weights = extract_weights_across_seeds(args.models_dir, args.results_dir, experiment_id)
- Plotter.weight_density(experiment_weights, os.path.join(root_output_path, f'weight_density_{experiment_label}.png'))
- if args.plot_preds_coherence:
- all_labels = ['random', 'omp']
- random_with_params_train_scores, random_with_params_dev_scores, random_with_params_test_scores, \
- with_params_extracted_forest_sizes, random_with_params_experiment_score_metric = \
- extract_scores_across_seeds_and_extracted_forest_sizes(args.models_dir, args.results_dir, int(args.experiment_ids[1]))
- coherence_values = [extract_coherences_across_seeds(args.models_dir, args.results_dir, i) for i in range(2, 4)]
- print(coherence_values[1])
- Plotter.plot_stage2_losses(
- file_path=root_output_path + os.sep + f"coherences_{'-'.join(all_labels)}.png",
- all_experiment_scores=coherence_values,
- all_labels=all_labels,
- x_value=with_params_extracted_forest_sizes,
- xlabel='Number of trees extracted',
- ylabel='Coherence',
- title='Coherence values of {}'.format(args.dataset_name))
- logger.info(f'Computing preds coherence plot for experiment {experiment_label}...')
+ omp_experiment_ids.append((label, current_experiment_id))"""
+
+ #for (experiment_label, experiment_id) in omp_experiment_ids:
+ if args.plot_weight_density:
+ logger.info(f'Computing weight density plot for experiment {experiment_label}...')
+ experiment_weights = extract_weights_across_seeds(args.models_dir, args.results_dir, experiment_id)
+ Plotter.weight_density(experiment_weights, os.path.join(root_output_path, f'weight_density_{experiment_label}.png'))
+ if args.plot_preds_coherence:
+ root_output_path = os.path.join(args.results_dir, args.dataset_name, f'stage4')
+ all_labels = ['random', 'omp', 'omp_normalize_D']
+ random_with_params_train_scores, random_with_params_dev_scores, random_with_params_test_scores, \
+ with_params_extracted_forest_sizes, random_with_params_experiment_score_metric = \
+ extract_scores_across_seeds_and_extracted_forest_sizes(args.models_dir, args.results_dir, 2)
+ coherence_values = [extract_coherences_across_seeds(args.models_dir, args.results_dir, i) for i in [2, 3, 4]]
+ Plotter.plot_stage2_losses(
+ file_path=root_output_path + os.sep + f"coherences_{'-'.join(all_labels)}_30_all.png",
+ all_experiment_scores=coherence_values,
+ all_labels=all_labels,
+ x_value=with_params_extracted_forest_sizes,
+ xlabel='Number of trees extracted',
+ ylabel='Coherence',
+ title='Coherence values of {}'.format(args.dataset_name))
+ logger.info(f'Computing preds coherence plot...')
logger.info('Done.')
diff --git a/code/train.py b/code/train.py
index ad80795..9708b71 100644
--- a/code/train.py
+++ b/code/train.py
@@ -169,7 +169,7 @@ def extracted_forest_size_job(extracted_forest_size_job_pb, extracted_forest_siz
pretrained_model_parameters.save(sub_models_dir, experiment_id)
trainer.init(model, subsets_used=parameters['subsets_used'])
- trainer.train(model, extracted_forest_size=extracted_forest_size)
+ trainer.train(model, extracted_forest_size=extracted_forest_size, seed=seed)
#trainer.compute_preds_coherence(model)
trainer.compute_results(model, sub_models_dir)
--
GitLab