def test_optimizable_threshold_enabled(mock_fit, mock_score,
mock_predict_proba, mock_encode_targets,
mock_optimize_threshold, X_y_binary,
caplog):
mock_optimize_threshold.return_value = 0.8
X, y = X_y_binary
automl = AutoMLSearch(X_train=X,
y_train=y,
problem_type='binary',
objective='precision',
max_iterations=1,
optimize_thresholds=True)
mock_score.return_value = {'precision': 1.0}
automl.search()
mock_fit.assert_called()
mock_score.assert_called()
mock_predict_proba.assert_called()
mock_optimize_threshold.assert_called()
assert automl.best_pipeline.threshold == 0.8
assert automl.results['pipeline_results'][0]['cv_data'][0].get(
'binary_classification_threshold') == 0.8
assert automl.results['pipeline_results'][0]['cv_data'][1].get(
'binary_classification_threshold') == 0.8
assert automl.results['pipeline_results'][0]['cv_data'][2].get(
'binary_classification_threshold') == 0.8
automl.describe_pipeline(0)
out = caplog.text
assert "Objective to optimize binary classification pipeline thresholds for" in out
def test_describe_pipeline_objective_ordered(X_y_binary, caplog):
X, y = X_y_binary
automl = AutoMLSearch(X_train=X, y_train=y, problem_type='binary', objective='AUC', max_iterations=2, n_jobs=1)
automl.search()
automl.describe_pipeline(0)
out = caplog.text
out_stripped = " ".join(out.split())
objectives = [get_objective(obj) for obj in automl.additional_objectives]
objectives_names = [obj.name for obj in objectives]
expected_objective_order = " ".join(objectives_names)
assert expected_objective_order in out_stripped
def test_additional_objectives(X_y_binary):
X, y = X_y_binary
objective = FraudCost(retry_percentage=.5,
interchange_fee=.02,
fraud_payout_percentage=.75,
amount_col=10)
automl = AutoMLSearch(X_train=X, y_train=y, problem_type='binary', objective='F1', max_iterations=2, additional_objectives=[objective],
n_jobs=1)
automl.search()
results = automl.describe_pipeline(0, return_dict=True)
assert 'Fraud Cost' in list(results["cv_data"][0]["all_objective_scores"].keys())
def test_get_pipeline_none(X_y_binary):
X, y = X_y_binary
automl = AutoMLSearch(X_train=X, y_train=y, problem_type='binary')
with pytest.raises(PipelineNotFoundError, match="Pipeline not found"):
automl.describe_pipeline(0)
