-1
}
if __name__ == '__main__':
# Extract paths
data_path, results_path, _ = generate_paths()
# Load lucas dataset
datasets = load_datasets(data_path=data_path, data_type='csv')
# Extract oversamplers
oversamplers = CONFIG['oversamplers']
# Generate oversamplers
for oversampler in oversamplers:
# Define and fit experiment
experiment = ImbalancedExperiment(
oversamplers=[oversampler],
classifiers=CONFIG['classifiers'],
scoring=CONFIG['scoring'],
n_splits=CONFIG['n_splits'],
n_runs=CONFIG['n_runs'],
random_state=CONFIG['rnd_seed'],
n_jobs=CONFIG['n_jobs']).fit(datasets)
# Save results
file_name = f'{oversampler[0].replace("-", "").lower()}.pkl'
experiment.results_.to_pickle(join(results_path, file_name))
summarize_datasets,
calculate_optimal,
calculate_wide_optimal,
calculate_ranking,
calculate_mean_sem_ranking,
calculate_mean_sem_scores,
calculate_mean_sem_perc_diff_scores,
apply_friedman_test,
apply_holms_test,
)
from rlearn.model_selection import ModelSearchCV
from rlearn.tools.tests import DATASETS, CLASSIFIERS, OVERSAMPLERS
EXPERIMENT = ImbalancedExperiment(OVERSAMPLERS,
CLASSIFIERS,
scoring=None,
n_splits=3,
n_runs=3,
random_state=0).fit(DATASETS)
@pytest.mark.parametrize(
'scoring,sort_results',
[
(None, None),
(None, 'mean_fit_time'),
(None, 'mean_test_score'),
('accuracy', None),
('recall', 'mean_fit_time'),
('recall', 'mean_test_score'),
(['accuracy', 'recall'], None),
(['accuracy', 'recall'], 'mean_fit_time'),