def test_regression_pandas_support(tmp_dir, dask_client):
X, y = sklearn.datasets.fetch_openml(
data_id=41514, # diabetes
return_X_y=True,
as_frame=True,
)
# This test only make sense if input is dataframe
assert isinstance(X, pd.DataFrame)
assert isinstance(y, pd.Series)
automl = AutoSklearnRegressor(
time_left_for_this_task=40,
per_run_time_limit=5,
dask_client=dask_client,
tmp_folder=tmp_dir,
)
# Make sure we error out because y is not encoded
automl.fit(X, y)
# Make sure that at least better than random.
# We use same X_train==X_test to test code quality
assert automl.score(X, y) >= 0.5, print_debug_information(automl)
automl.refit(X, y)
# Make sure that at least better than random.
assert r2(y, automl.predict(X)) > 0.5, print_debug_information(automl)
assert count_succeses(
automl.cv_results_) > 0, print_debug_information(automl)
def regression(self, metric="r2"):
"""
Perform auto_regression.
Args:
metric (str): The evaluation metric of regression.
This will be mapped by AutoSklearnML.get_regression_metric
to an instance of :class:`autosklearn.metrics.Scorer` as
created by :meth:`autosklearn.metrics.make_scorer`.
Default metric: "r2".
Other supported metrics: "mean_squared_error",
"mean_absolute_error",
"median_absolute_error"
Returns:
"""
auto_regressor = AutoSklearnRegressor(**self.auto_sklearn_kwargs)
regression_metric = AutoSklearnML.get_regression_metric(metric)
auto_regressor.fit(self._X_train,
self._y_train,
metric=regression_metric,
dataset_name=self.dataset_name)
print(auto_regressor.show_models())
if self.auto_sklearn_kwargs["resampling_strategy"] == "cv":
auto_regressor.refit(self._X_train.copy(), self._y_train.copy())
prediction_train = auto_regressor.predict(self._X_train)
print("training set {} score: {}".format(
metric,
regression_metric._score_func(self._y_train, prediction_train)))
prediction_test = auto_regressor.predict(self._X_test)
print("test set {} score: {}".format(
metric, regression_metric._score_func(self._y_test,
prediction_test)))
with open(
os.path.join(self.auto_sklearn_kwargs['output_folder'],
'best_auto_sklearn_output.log'), 'a+') as wf:
wf.write('The best model is : \n')
wf.write(auto_regressor.show_models())
wf.write("\ntraining set {} score: {}\n".format(
metric,
regression_metric._score_func(self._y_train,
prediction_train)))
wf.write('\n')
wf.write("test set {} score: {}".format(
metric,
regression_metric._score_func(self._y_test, prediction_test)))
dump_file = os.path.join(self.auto_sklearn_kwargs['output_folder'],
'automl_regressor.dump.pkl')
with open(dump_file, 'wb') as f:
pickle.dump(auto_regressor, f)
return auto_regressor
def test_autosklearn_regression_methods_returns_self(dask_client):
X_train, y_train, X_test, y_test = putil.get_dataset('boston')
automl = AutoSklearnRegressor(time_left_for_this_task=30,
per_run_time_limit=5,
dask_client=dask_client,
ensemble_size=0)
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