def test_regression_pandas_support(self):
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
self.assertTrue(isinstance(X, pd.DataFrame))
self.assertTrue(isinstance(y, pd.Series))
automl = AutoSklearnRegressor(
time_left_for_this_task=30,
per_run_time_limit=5,
)
# 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
self.assertTrue(automl.score(X, y) > 0.5)
automl.refit(X, y)
# Make sure that at least better than random.
self.assertTrue(r2(y, automl.predict(X)) > 0.5)
def test_cv_regression(self):
"""
Makes sure that when using a cv strategy, we are able to fit
a regressor
"""
tmp = os.path.join(self.test_dir, '..', '.tmp_regression_fit_cv')
output = os.path.join(self.test_dir, '..', '.out_regression_fit_cv')
self._setUp(tmp)
self._setUp(output)
X_train, Y_train, X_test, Y_test = putil.get_dataset(
'boston', train_size_maximum=300)
automl = AutoSklearnRegressor(time_left_for_this_task=60,
per_run_time_limit=10,
resampling_strategy='cv',
tmp_folder=tmp,
output_folder=output)
automl.fit(X_train, Y_train)
predictions = automl.predict(X_test)
self.assertEqual(predictions.shape, (206, ))
score = r2(Y_test, predictions)
print(Y_test)
print(predictions)
self.assertGreaterEqual(score, 0.1)
self.assertGreater(self._count_succeses(automl.cv_results_), 0)
self._tearDown(tmp)
self._tearDown(output)
def test_cv_regression(tmp_dir, output_dir, dask_client):
"""
Makes sure that when using a cv strategy, we are able to fit
a regressor
"""
X_train, Y_train, X_test, Y_test = putil.get_dataset(
'boston', train_size_maximum=300)
automl = AutoSklearnRegressor(time_left_for_this_task=60,
per_run_time_limit=10,
resampling_strategy='cv',
tmp_folder=tmp_dir,
dask_client=dask_client,
output_folder=output_dir)
automl.fit(X_train, Y_train)
# Log file path
log_file_path = glob.glob(os.path.join(tmp_dir, 'AutoML*.log'))[0]
predictions = automl.predict(X_test)
assert predictions.shape == (206, )
score = r2(Y_test, predictions)
assert score >= 0.1, extract_msg_from_log(log_file_path)
assert count_succeses(
automl.cv_results_) > 0, extract_msg_from_log(log_file_path)
def test_regression_pandas_support(tmp_dir, output_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,
output_folder=output_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 test_cv_regression(tmp_dir, dask_client):
"""
Makes sure that when using a cv strategy, we are able to fit
a regressor
"""
X_train, Y_train, X_test, Y_test = putil.get_dataset(
'boston', train_size_maximum=300)
automl = AutoSklearnRegressor(
time_left_for_this_task=60,
per_run_time_limit=10,
resampling_strategy='cv',
tmp_folder=tmp_dir,
dask_client=dask_client,
)
automl.fit(X_train, Y_train)
predictions = automl.predict(X_test)
assert predictions.shape == (206, )
score = r2(Y_test, predictions)
assert score >= 0.1, print_debug_information(automl)
assert count_succeses(
automl.cv_results_) > 0, print_debug_information(automl)
assert includes_train_scores(automl.performance_over_time_.columns) is True
assert performance_over_time_is_plausible(
automl.performance_over_time_) is True