GridSearch over MultiOutputRegressor?

Question

Let\'s consider a multivariate regression problem (2 response variables: Latitude and Longitude). Currently, a few machine learning model implementations like Support Vector Reg

Answer 1

Thank you, Marco.

Adding to your answer here is a short illustrative example of a Randomized Search applied to a Multi-Ouput GradientBoostingRegressor.

from sklearn.datasets import load_linnerud
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.multioutput import MultiOutputRegressor
from sklearn.model_selection import RandomizedSearchCV

x, y = load_linnerud(return_X_y=True)

model = MultiOutputRegressor(GradientBoostingRegressor(loss='ls', learning_rate=0.1, n_estimators=100, subsample=1.0,
                                                       criterion='friedman_mse', min_samples_split=2,
                                                       min_samples_leaf=1,
                                                       min_weight_fraction_leaf=0.0, max_depth=3,
                                                       min_impurity_decrease=0.0,
                                                       min_impurity_split=None, init=None, random_state=None,
                                                       max_features=None,
                                                       alpha=0.9, verbose=0, max_leaf_nodes=None, warm_start=False,
                                                       validation_fraction=0.1, n_iter_no_change=None, tol=0.0001,
                                                       ccp_alpha=0.0))

hyperparameters = dict(estimator__learning_rate=[0.05, 0.1, 0.2, 0.5, 0.9], estimator__loss=['ls', 'lad', 'huber'],
                     estimator__n_estimators=[20, 50, 100, 200, 300, 500, 700, 1000],
                     estimator__criterion=['friedman_mse', 'mse'], estimator__min_samples_split=[2, 4, 7, 10],
                     estimator__max_depth=[3, 5, 10, 15, 20, 30], estimator__min_samples_leaf=[1, 2, 3, 5, 8, 10],
                     estimator__min_impurity_decrease=[0, 0.2, 0.4, 0.6, 0.8],
                     estimator__max_leaf_nodes=[5, 10, 20, 30, 50, 100, 300])

randomized_search = RandomizedSearchCV(model, hyperparameters, random_state=0, n_iter=5, scoring=None,
                                       n_jobs=2, refit=True, cv=5, verbose=True,
                                       pre_dispatch='2*n_jobs', error_score='raise', return_train_score=True)

hyperparameters_tuning = randomized_search.fit(x, y)
print('Best Parameters = {}'.format(hyperparameters_tuning.best_params_))

tuned_model = hyperparameters_tuning.best_estimator_

print(tuned_model.predict(x))