def test_standard_fit_regression_stacker_no_bagging_free_weights(self):
"""Test regression stacking with metric mean absolute error, no bagging"""
stacker = LinearPredictorStacker(
metric=metric_mae,
algorithm=LinearPredictorStacker.STANDARD,
normed_weights=False,
max_iter=200,
n_bags=1,
colsample=1.,
subsample=1.,
verbose=2,
eps=1e-3,
seed=0)
stacker.add_predictors_by_filename(files=[
get_path('noid_OOF_predictions_2.csv'),
get_path('noid_OOF_predictions_3.csv'),
get_path('noid_OOF_predictions_4.csv')
])
self.assertEqual(len(stacker.target), 1000)
self.assertEqual(len(stacker.predictors), 1000)
self.assertEqual(stacker.predictors.shape[1], 22)
stacker.fit()
print(stacker.get_weights())
self.assertAlmostEqual(stacker.score, 1185.0745095110819, places=4)
self.assertAlmostEqual(stacker.mean_score,
1188.5725272161117,
places=4)
def test_fit_with_predictors_and_target(self):
data = pd.read_csv(get_path('noid_OOF_predictions_2.csv'))
target = data.loss
data.drop(['loss'], axis=1, inplace=True)
stacker = LinearPredictorStacker(
metric=metric_rmse,
algorithm=LinearPredictorStacker.SWAPPING,
max_iter=200,
n_bags=1,
colsample=1.,
subsample=1.,
verbose=0)
stacker.fit(predictors=data, target=target)
self.assertAlmostEqual(stacker.score, 1969.3946377360355, places=4)
self.assertAlmostEqual(stacker.mean_score,
2033.0404650725116,
places=4)
# test weights
self.assertTupleEqual(
stacker.get_weights(),
(-0.75000000000000011, 0.050000000000000003, -0.44999999999999996,
2.4499999999999993, 0.050000000000000003, -1.2500000000000004,
0.050000000000000003, -1.7500000000000009, 0.050000000000000003,
0.44999999999999996, 0.25, 3.099999999999997,
-0.75000000000000011, -0.39999999999999997, 2.5499999999999989,
-2.3999999999999995, -1.850000000000001, 0.050000000000000003,
1.5000000000000007, 0.050000000000000003))
def test_fit_swapping_regression_stacker_no_bagging_normed_weights(self):
"""Test regression stacking with metric mean absolute error, no bagging"""
stacker = LinearPredictorStacker(
metric=metric_mae,
algorithm=LinearPredictorStacker.SWAPPING,
normed_weights=True,
max_iter=2000,
n_bags=1,
colsample=1.,
subsample=1.,
verbose=2,
eps=1e-3,
seed=11)
stacker.add_predictors_by_filename(files=[
get_path('noid_OOF_predictions_2.csv'),
get_path('noid_OOF_predictions_3.csv'),
get_path('noid_OOF_predictions_4.csv')
])
self.assertEqual(len(stacker.target), 1000)
self.assertEqual(len(stacker.predictors), 1000)
self.assertEqual(stacker.predictors.shape[1], 22)
stacker.fit()
self.assertAlmostEqual(stacker.score, 1156.3066, places=4)
self.assertAlmostEqual(stacker.mean_score,
1188.5725272161117,
places=4)
def test_fit_regression_stacker_mae_ten_bags(self):
"""Test regression stacking with metric mean absolute error and 20 bags"""
stacker = LinearPredictorStacker(metric=metric_mae,
max_iter=10,
n_bags=20,
colsample=.8,
subsample=.8,
seed=24698537)
stacker.add_predictors_by_filename(files=[
get_path('noid_OOF_predictions_2.csv'),
get_path('noid_OOF_predictions_3.csv'),
get_path('noid_OOF_predictions_4.csv')
])
self.assertEqual(len(stacker.target), 1000)
self.assertEqual(len(stacker.predictors), 1000)
self.assertEqual(stacker.predictors.shape[1], 22)
stacker.fit()
self.assertAlmostEqual(stacker.score, 1179.2406088734808, places=4)
# Old version self.assertAlmostEqual(stacker.score, 1187.6537373418842, places=4)
self.assertAlmostEqual(stacker.mean_score,
1188.5725272161117,
places=4)
def test_fit_regression_stacker_rmse_no_bagging_step_decrease(self):
"""Test regression stacking with metric root mean squared error, no bagging"""
stacker = LinearPredictorStacker(metric=metric_rmse,
max_iter=250,
n_bags=1,
colsample=1.,
subsample=1.,
verbose=0)
stacker.add_predictors_by_filename(files=[
get_path('noid_OOF_predictions_2.csv'),
get_path('noid_OOF_predictions_3.csv'),
get_path('noid_OOF_predictions_4.csv')
])
self.assertEqual(len(stacker.target), 1000)
self.assertEqual(len(stacker.predictors), 1000)
self.assertEqual(stacker.predictors.shape[1], 22)
stacker.fit()
self.assertAlmostEqual(stacker.score, 1972.574584232116, places=4)
# Old version self.assertAlmostEqual(stacker.score, 2030.5021340510675, places=4)
self.assertAlmostEqual(stacker.mean_score,
2032.2110846499691,
places=4)
def test_fit_regression_stacker_mae_no_bagging(self):
"""Test regression stacking with metric mean absolute error, no bagging"""
stacker = LinearPredictorStacker(metric=metric_mae,
max_iter=20,
n_bags=1,
colsample=1.,
subsample=1.,
verbose=0)
stacker.add_predictors_by_filename(files=[
get_path('noid_OOF_predictions_2.csv'),
get_path('noid_OOF_predictions_3.csv'),
get_path('noid_OOF_predictions_4.csv')
])
self.assertEqual(len(stacker.target), 1000)
self.assertEqual(len(stacker.predictors), 1000)
self.assertEqual(stacker.predictors.shape[1], 22)
stacker.fit()
self.assertAlmostEqual(stacker.score, 1176.295406, places=4)
# Old version self.assertAlmostEqual(stacker.score, 1187.1916616561432, places=4)
self.assertAlmostEqual(stacker.mean_score,
1188.5725272161117,
places=4)
def test_swapping_fit_regression_stacker_rmse_no_bagging(self):
"""Test regression stacking with metric root mean squared error, no bagging"""
stacker = LinearPredictorStacker(
metric=metric_rmse,
algorithm=LinearPredictorStacker.SWAPPING,
max_iter=20,
n_bags=1,
colsample=1.,
subsample=1.,
verbose=0)
stacker.add_predictors_by_filename(files=[
get_path('noid_OOF_predictions_2.csv'),
get_path('noid_OOF_predictions_3.csv'),
get_path('noid_OOF_predictions_4.csv')
])
self.assertEqual(len(stacker.target), 1000)
self.assertEqual(len(stacker.predictors), 1000)
self.assertEqual(stacker.predictors.shape[1], 22)
stacker.fit()
self.assertAlmostEqual(stacker.score, 2008.0897782026507, places=4)
self.assertAlmostEqual(stacker.mean_score,
2032.2110846499691,
places=4)
def test_regression_r2_score_maximization(self):
stacker = LinearPredictorStacker(
metric=r2_score,
maximize=True,
algorithm=LinearPredictorStacker.STANDARD,
normed_weights=False,
max_iter=200,
n_bags=1,
colsample=1.,
subsample=1.,
verbose=2,
eps=1e-4,
seed=0)
stacker.add_predictors_by_filename(files=[
get_path('noid_OOF_predictions_2.csv'),
get_path('noid_OOF_predictions_3.csv'),
get_path('noid_OOF_predictions_4.csv')
])
self.assertEqual(len(stacker.target), 1000)
self.assertEqual(len(stacker.predictors), 1000)
self.assertEqual(stacker.predictors.shape[1], 22)
stacker.fit()
self.assertAlmostEqual(stacker.score, 0.5478882, places=4)
self.assertAlmostEqual(stacker.mean_score, 0.537271112149033, places=4)