X_test, y_test = X[n_samples // 2:], y[n_samples // 2:]
print("test data sparsity: %f" % sparsity_ratio(X_test))
###############################################################################
clf = SGDRegressor(penalty="l1", alpha=0.2, max_iter=2000, tol=None)
clf.fit(X_train, y_train)
print("model sparsity: %f" % sparsity_ratio(clf.coef_))
def benchmark_dense_predict():
for _ in range(300):
clf.predict(X_test)
def benchmark_sparse_predict():
X_test_sparse = csr_matrix(X_test)
for _ in range(300):
clf.predict(X_test_sparse)
def score(y_test, y_pred, case):
r2 = r2_score(y_test, y_pred)
print("r^2 on test data (%s) : %f" % (case, r2))
score(y_test, clf.predict(X_test), "dense model")
benchmark_dense_predict()
clf.sparsify()
score(y_test, clf.predict(X_test), "sparse model")
benchmark_sparse_predict()
