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 train_model(data, target_label, duration, regressor=True):
dataframe = data.to_df()
if regressor:
model = AutoSklearnRegressor(
time_left_for_this_task=duration, memory_limit=9216
)
else:
model = AutoSklearnClassifier(
time_left_for_this_task=duration, memory_limit=9216
)
if score:
Xt, Xv, yt, yv = train_test_split(
self.preprocessor.transform(dataframe["smiles"]),
dataframe[target_label],
test_size=0.15,
random_state=18,
)
else:
Xt = self.preprocessor.transform(dataframe["smiles"])
yt = dataframe[target_label]
model.fit(Xt, yt)
if score:
print(f"Score on {target_label}: {model.score(Xv, yv)}")
return model
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
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_regression(tmp_dir, 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,
tmp_folder=tmp_dir,
dask_client=dask_client,
)
automl.fit(X_train, Y_train)
predictions = automl.predict(X_test)
assert predictions.shape == (356, )
score = mean_squared_error(Y_test, predictions)
# On average np.sqrt(30) away from the target -> ~5.5 on average
# Results with select rates drops avg score to a range of -32.40 to -37, on 30 seconds
# constraint. With more time_left_for_this_task this is no longer an issue
assert score >= -37, print_debug_information(automl)
assert count_succeses(automl.cv_results_) > 0
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
def test_type_of_target(mock_estimator):
# Test that classifier raises error for illegal target types.
X = np.array([
[1, 2],
[2, 3],
[3, 4],
[4, 5],
])
# Possible target types
y_binary = np.array([0, 0, 1, 1])
y_continuous = np.array([0.1, 1.3, 2.1, 4.0])
y_multiclass = np.array([0, 1, 2, 0])
y_multilabel = np.array([
[0, 1],
[1, 1],
[1, 0],
[0, 0],
])
y_multiclass_multioutput = np.array([
[0, 1],
[1, 3],
[2, 2],
[5, 3],
])
y_continuous_multioutput = np.array([
[0.1, 1.5],
[1.2, 3.5],
[2.7, 2.7],
[5.5, 3.9],
])
cls = AutoSklearnClassifier(ensemble_size=0)
cls.automl_ = unittest.mock.Mock()
cls.automl_.InputValidator = unittest.mock.Mock()
cls.automl_.InputValidator.target_validator = unittest.mock.Mock()
# Illegal target types for classification: continuous,
# multiclass-multioutput, continuous-multioutput.
expected_msg = r".*Classification with data of type"
" multiclass-multioutput is not supported.*"
with pytest.raises(ValueError, match=expected_msg):
cls.fit(X=X, y=y_multiclass_multioutput)
expected_msg = r".*Classification with data of type"
" continuous is not supported.*"
with pytest.raises(ValueError, match=expected_msg):
cls.fit(X=X, y=y_continuous)
expected_msg = r".*Classification with data of type"
" continuous-multioutput is not supported.*"
with pytest.raises(ValueError, match=expected_msg):
cls.fit(X=X, y=y_continuous_multioutput)
# Legal target types for classification: binary, multiclass,
# multilabel-indicator.
try:
cls.fit(X, y_binary)
except ValueError:
pytest.fail("cls.fit() raised ValueError while fitting "
"binary targets")
try:
cls.fit(X, y_multiclass)
except ValueError:
pytest.fail("cls.fit() raised ValueError while fitting "
"multiclass targets")
try:
cls.fit(X, y_multilabel)
except ValueError:
pytest.fail("cls.fit() raised ValueError while fitting "
"multilabel-indicator targets")
# Test that regressor raises error for illegal target types.
reg = AutoSklearnRegressor(ensemble_size=0)
# Illegal target types for regression: multilabel-indicator
# multiclass-multioutput
expected_msg = r".*Regression with data of type"
" multilabel-indicator is not supported.*"
with pytest.raises(ValueError, match=expected_msg):
reg.fit(
X=X,
y=y_multilabel,
)
expected_msg = r".*Regression with data of type"
" multiclass-multioutput is not supported.*"
with pytest.raises(ValueError, match=expected_msg):
reg.fit(
X=X,
y=y_multiclass_multioutput,
)
# Legal target types: continuous, multiclass,
# continuous-multioutput,
# binary
try:
reg.fit(X, y_continuous)
except ValueError:
pytest.fail("reg.fit() raised ValueError while fitting "
"continuous targets")
try:
reg.fit(X, y_multiclass)
except ValueError:
pytest.fail("reg.fit() raised ValueError while fitting "
"multiclass targets")
try:
reg.fit(X, y_continuous_multioutput)
except ValueError:
pytest.fail("reg.fit() raised ValueError while fitting "
"continuous_multioutput targets")
try:
reg.fit(X, y_binary)
except ValueError:
pytest.fail("reg.fit() raised ValueError while fitting "
"binary targets")