def test_gpx_regression(self):
INSTANCE: int = 13
reg = RandomForestRegressor()
x, y = load_boston(return_X_y=True)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
train_size=.8,
test_size=.2,
random_state=42)
reg.fit(x_train, y_train)
gpx = Gpx(predict=reg.predict,
x_train=x_train,
y_train=y_train,
problem='regression',
random_state=42)
gpx.explaining(x_test[INSTANCE, :])
y_hat = reg.predict(x_test)
mse = mean_squared_error(y_test, y_hat)
d = gpx.features_distribution()
# self.assertEqual(max(list(d.values())), d['x_2'])
self.assertLess(
gpx.understand(metric='mse'), mse,
'{} mse greater than understand (local mse)'.format(
self.test_gpx_regression.__name__))
def test_features_distribution(self):
x_varied, y_varied = make_moons(n_samples=500, random_state=170)
model = MLPClassifier()
model.fit(x_varied, y_varied)
my_predict = model.predict_proba
gpx = Gpx(my_predict,
x_train=x_varied,
y_train=y_varied,
random_state=42,
num_samples=250)
gpx.explaining(x_varied[13, :])
d = gpx.features_distribution()
gpx.logger.info('distribution-> program:{} / x_0: {} / x_1: {}'.format(
gpx.gp_model._program, d['x_0'], d['x_1']))
self.assertLess(
d['x_0'], d['x_1'],
'Method features_distributions() output unexpected, x_0 greater than x_1!'
)