def test_autosklearn_classification_methods_returns_self(dask_client):
"""
Currently this method only tests that the methods of AutoSklearnClassifier
is able to fit using fit(), fit_ensemble() and refit()
"""
X_train, y_train, X_test, y_test = putil.get_dataset('iris')
automl = AutoSklearnClassifier(time_left_for_this_task=60,
per_run_time_limit=10,
ensemble_size=0,
dask_client=dask_client,
exclude_preprocessors=['fast_ica'])
automl_fitted = automl.fit(X_train, y_train)
assert automl is automl_fitted
automl_ensemble_fitted = automl.fit_ensemble(y_train, ensemble_size=5)
assert automl is automl_ensemble_fitted
automl_refitted = automl.refit(X_train.copy(), y_train.copy())
assert automl is automl_refitted
def test_autosklearn_anneal(as_frame):
"""
This test makes sure that anneal dataset can be fitted and scored.
This dataset is quite complex, with NaN, categorical and numerical columns
so is a good testcase for unit-testing
"""
X, y = sklearn.datasets.fetch_openml(data_id=2,
return_X_y=True,
as_frame=as_frame)
automl = AutoSklearnClassifier(time_left_for_this_task=60,
ensemble_size=0,
delete_tmp_folder_after_terminate=False,
initial_configurations_via_metalearning=0,
smac_scenario_args={'runcount_limit': 6},
resampling_strategy='holdout-iterative-fit')
if as_frame:
# Let autosklearn calculate the feat types
automl_fitted = automl.fit(X, y)
else:
X_, y_ = sklearn.datasets.fetch_openml(data_id=2,
return_X_y=True,
as_frame=True)
feat_type = [
'categorical' if X_[col].dtype.name == 'category' else 'numerical'
for col in X_.columns
]
automl_fitted = automl.fit(X, y, feat_type=feat_type)
assert automl is automl_fitted
automl_ensemble_fitted = automl.fit_ensemble(y, ensemble_size=5)
assert automl is automl_ensemble_fitted
# We want to make sure we can learn from this data.
# This is a test to make sure the data format (numpy/pandas)
# can be used in a meaningful way -- not meant for generalization,
# hence we use the train dataset
assert automl_fitted.score(X, y) > 0.75