Using SGDClassifier

In this final coding exercise, you'll do a hyperparameter search over the regularization strength and the loss (logistic regression vs. linear SVM) using SGDClassifier().

Cet exercice fait partie du cours

Linear Classifiers in Python

Afficher le cours

Instructions

Instantiate an SGDClassifier instance with random_state=0.
Search over the regularization strength and the hinge vs. log_loss losses.

Exercice interactif pratique

Essayez cet exercice en complétant cet exemple de code.

# We set random_state=0 for reproducibility 
linear_classifier = ____(random_state=0)

# Instantiate the GridSearchCV object and run the search
parameters = {'alpha':[0.00001, 0.0001, 0.001, 0.01, 0.1, 1], 
             'loss':[____]}
searcher = GridSearchCV(linear_classifier, parameters, cv=10)
searcher.fit(X_train, y_train)

# Report the best parameters and the corresponding score
print("Best CV params", searcher.best_params_)
print("Best CV accuracy", searcher.best_score_)
print("Test accuracy of best grid search hypers:", searcher.score(X_test, y_test))

Modifier et exécuter le code