def test_return_incumbent(self):
X_train, X_test, y_train, y_test = load_benchmark(return_split=True)
linear_basis_fn = 'ridge'
n_regressors = 1
boosting_loss = 'ls'
line_search_options = dict(init_guess=1,
opt_method='minimize',
method='Nelder-Mead',
tol=1e-7,
options={"maxiter": 10000},
niter=None,
T=None,
loss='lad',
regularization=0.1)
base_boosting_options = dict(n_regressors=n_regressors,
boosting_loss=boosting_loss,
line_search_options=line_search_options)
index = 3
reg = Regressor(regressor_choice=linear_basis_fn,
params=dict(alpha=0.1),
target_index=index,
base_boosting_options=base_boosting_options)
reg.baseboostcv(X_train.iloc[:10, :], y_train.iloc[:10, :])
self.assertHasAttr(reg, 'return_incumbent_')
def test_baseboostcv_score(self):
X_train, X_test, y_train, y_test = load_benchmark(return_split=True)
stack = dict(regressors=['ridge', 'lgbmregressor'],
final_regressor='ridge')
line_search_options = dict(init_guess=1,
opt_method='minimize',
method='Nelder-Mead',
tol=1e-7,
options={"maxiter": 10000},
niter=None,
T=None,
loss='lad',
regularization=0.1)
base_boosting_options = dict(n_regressors=3,
boosting_loss='ls',
line_search_options=line_search_options)
reg = Regressor(regressor_choice='stackingregressor',
target_index=0,
stacking_options=dict(layers=stack),
base_boosting_options=base_boosting_options)
y_pred = reg.baseboostcv(X_train, y_train).predict(X_test)
score = reg.score(y_test, y_pred)
self.assertNotHasAttr(reg, 'return_incumbent_')
self.assertGreaterEqual(score['mae'].values, 0.0)
self.assertGreaterEqual(score['mse'].values, 0.0)
self.assertLess(score['mae'].values, 2.0)
self.assertLess(score['mse'].values, 6.2)
base_boosting_options=options_with_lad)
else:
# We make an instance of Regressor with our choice of ridge
# regression for the single-target regression subtask: 3.
# The parameter alpha denotes the regularization strength
# in ridge regression, where the Tikhonov matrix is the
# scalar alpha times the identity matrix.
reg = Regressor(regressor_choice=linear_basis_fn,
params=dict(alpha=0.1),
target_index=index,
base_boosting_options=options_with_huber)
# We use the baseboostcv method, which utilizes a private
# inbuilt model selection method to choose either the
# incumbent or the candidate.
y_pred = reg.baseboostcv(X_train, y_train).predict(X_test)
# We can check if the incumbent won model selection with
# the return_incumbent_ attribute.
if hasattr(reg, 'return_incumbent_'):
print(f'Incumbent was chosen in subtask {index + 1}')
# We compute the single-target test error.
score = reg.score(y_test, y_pred)
test_error.append(score)
test_error = pd.concat(test_error)
print('Finished building the scoring DataFrame.')
print(test_error.round(decimals=2))
print('Finished computing the multi-target scores.')
print(test_error.mean().round(decimals=2))
