def _unit_test_params(cls):
yield {
"models": [
linear_model.LogisticRegression(),
tree.HoeffdingTreeClassifier(),
naive_bayes.GaussianNB(),
]
}
@pytest.mark.parametrize(
"estimator, check",
[
pytest.param(estimator, check, id=f"{estimator}:{check.__name__}")
for estimator in list(get_all_estimators()) + [
feature_extraction.TFIDF(),
linear_model.LogisticRegression(),
preprocessing.StandardScaler() | linear_model.LinearRegression(),
preprocessing.StandardScaler() | linear_model.PAClassifier(),
(preprocessing.StandardScaler()
| multiclass.OneVsRestClassifier(
linear_model.LogisticRegression())),
(preprocessing.StandardScaler()
| multiclass.OneVsRestClassifier(linear_model.PAClassifier())),
naive_bayes.GaussianNB(),
preprocessing.StandardScaler(),
cluster.KMeans(n_clusters=5, seed=42),
preprocessing.MinMaxScaler(),
preprocessing.MinMaxScaler() + preprocessing.StandardScaler(),
feature_extraction.PolynomialExtender(),
(feature_extraction.PolynomialExtender()
| preprocessing.StandardScaler()
| linear_model.LinearRegression()),
feature_selection.VarianceThreshold(),
feature_selection.SelectKBest(similarity=stats.PearsonCorr()),
] for check in utils.estimator_checks.yield_checks(estimator)
if check.__name__ not in estimator._unit_test_skips()
],
)
def test_check_estimator(estimator, check):
sampling_rate=SAMPLING_RATE)),
('EvoAutoML Bagging Best',
EvolutionaryBaggingClassifier(population_size=POPULATION_SIZE,
model=AUTOML_CLASSIFICATION_PIPELINE,
param_grid=CLASSIFICATION_PARAM_GRID,
sampling_rate=SAMPLING_RATE)),
('ARF', ensemble.AdaptiveRandomForestClassifier()),
('Leveraging Bagging',
ensemble.LeveragingBaggingClassifier(model=ENSEMBLE_CLASSIFIER())),
('Bagging',
ensemble.BaggingClassifier(model=ENSEMBLE_CLASSIFIER(), n_models=10)),
('SRPC', ensemble.SRPClassifier(n_models=10)),
('Hoeffding Tree', tree.HoeffdingTreeClassifier()),
('Logistic Regression', linear_model.LogisticRegression()),
('HAT', tree.HoeffdingAdaptiveTreeClassifier()),
('GaussianNB', naive_bayes.GaussianNB()),
('KNN', neighbors.KNNClassifier()),
]
if __name__ == '__main__':
RESULT_PATH.mkdir(parents=True, exist_ok=True)
#output = evaluate_ensemble(CLASSIFICATION_TRACKS[1], ENSEMBLE_EVALUATION_MODELS[2])
pool = Pool(60) # Create a multiprocessing Pool
output = pool.starmap(
evaluate_ensemble,
list(
itertools.product(CLASSIFICATION_TRACKS,
ENSEMBLE_EVALUATION_MODELS)))
pool.close()
