def test_lasso_zero():
# Check that the lasso can handle zero data without crashing
X = [[0], [0], [0]]
y = [0, 0, 0]
clf = Lasso(alpha=0.1).fit(X, y)
pred = clf.predict([[1], [2], [3]])
assert_array_almost_equal(clf.coef_, [0])
assert_array_almost_equal(pred, [0, 0, 0])
assert_almost_equal(clf.dual_gap_, 0)
def test_lasso_zero():
# Check that the sparse lasso can handle zero data without crashing
X = sp.csc_matrix((3, 1))
y = [0, 0, 0]
T = np.array([[1], [2], [3]])
clf = Lasso().fit(X, y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0])
assert_array_almost_equal(pred, [0, 0, 0])
assert_almost_equal(clf.dual_gap_, 0)
def test_lasso_readonly_data():
X = np.array([[-1], [0], [1]])
Y = np.array([-1, 0, 1]) # just a straight line
T = np.array([[2], [3], [4]]) # test sample
with TempMemmap((X, Y)) as (X, Y):
clf = Lasso(alpha=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [.25])
assert_array_almost_equal(pred, [0.5, 0.75, 1.])
assert_almost_equal(clf.dual_gap_, 0)
def test_sparse_enet_coordinate_descent():
"""Test that a warning is issued if model does not converge"""
clf = Lasso(max_iter=2)
n_samples = 5
n_features = 2
X = sp.csc_matrix((n_samples, n_features)) * 1e50
y = np.ones(n_samples)
assert_warns(ConvergenceWarning, clf.fit, X, y)
def test_lasso_positive_constraint():
X = [[-1], [0], [1]]
y = [1, 0, -1] # just a straight line with negative slope
lasso = Lasso(alpha=0.1, max_iter=1000, positive=True)
lasso.fit(X, y)
assert min(lasso.coef_) >= 0
lasso = Lasso(alpha=0.1, max_iter=1000, precompute=True, positive=True)
lasso.fit(X, y)
assert min(lasso.coef_) >= 0
def test_sparse_input_convergence_warning():
X, y, _, _ = build_dataset(n_samples=1000, n_features=500)
with pytest.warns(ConvergenceWarning):
ElasticNet(max_iter=1,
tol=0).fit(sparse.csr_matrix(X, dtype=np.float32), y)
# check that the model converges w/o warnings
with pytest.warns(None) as record:
Lasso(max_iter=1000).fit(sparse.csr_matrix(X, dtype=np.float32), y)
assert not record.list
def test_sparse_lasso_not_as_toy_dataset():
n_samples = 100
max_iter = 1000
n_informative = 10
X, y = make_sparse_data(n_samples=n_samples, n_informative=n_informative)
X_train, X_test = X[n_samples // 2:], X[:n_samples // 2]
y_train, y_test = y[n_samples // 2:], y[:n_samples // 2]
s_clf = Lasso(alpha=0.1, fit_intercept=False, max_iter=max_iter, tol=1e-7)
s_clf.fit(X_train, y_train)
assert_almost_equal(s_clf.dual_gap_, 0, 4)
assert s_clf.score(X_test, y_test) > 0.85
# check the convergence is the same as the dense version
d_clf = Lasso(alpha=0.1, fit_intercept=False, max_iter=max_iter, tol=1e-7)
d_clf.fit(X_train.toarray(), y_train)
assert_almost_equal(d_clf.dual_gap_, 0, 4)
assert d_clf.score(X_test, y_test) > 0.85
# check that the coefs are sparse
assert np.sum(s_clf.coef_ != 0.0) == n_informative
def test_coef_shape_not_zero():
est_no_intercept = Lasso(fit_intercept=False)
est_no_intercept.fit(np.c_[np.ones(3)], np.ones(3))
assert est_no_intercept.coef_.shape == (1, )
def test_lasso_toy():
# Test Lasso on a toy example for various values of alpha.
# When validating this against glmnet notice that glmnet divides it
# against nobs.
X = [[-1], [0], [1]]
Y = [-1, 0, 1] # just a straight line
T = [[2], [3], [4]] # test sample
clf = Lasso(alpha=1e-8)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [1])
assert_array_almost_equal(pred, [2, 3, 4])
assert_almost_equal(clf.dual_gap_, 0)
clf = Lasso(alpha=0.1)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [.85])
assert_array_almost_equal(pred, [1.7, 2.55, 3.4])
assert_almost_equal(clf.dual_gap_, 0)
clf = Lasso(alpha=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [.25])
assert_array_almost_equal(pred, [0.5, 0.75, 1.])
assert_almost_equal(clf.dual_gap_, 0)
clf = Lasso(alpha=1)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [.0])
assert_array_almost_equal(pred, [0, 0, 0])
assert_almost_equal(clf.dual_gap_, 0)
def test_lasso_alpha_warning():
X = [[-1], [0], [1]]
Y = [-1, 0, 1] # just a straight line
clf = Lasso(alpha=0)
assert_warns(UserWarning, clf.fit, X, Y)