def test_enet_positive_constraint():
X = [[-1], [0], [1]]
y = [1, 0, -1] # just a straight line with negative slope
enet = ElasticNet(alpha=0.1, max_iter=1000, positive=True)
enet.fit(X, y)
assert min(enet.coef_) >= 0
def test_sparse_coef():
""" Check that the sparse_coef propery works """
clf = ElasticNet()
clf.coef_ = [1, 2, 3]
assert_true(sp.isspmatrix(clf.sparse_coef_))
assert_equal(clf.sparse_coef_.todense().tolist()[0], clf.coef_)
def test_sparse_enet_not_as_toy_dataset():
n_samples, n_features, max_iter = 100, 100, 1000
n_informative = 10
X, y = make_sparse_data(n_samples, n_features, 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 = SparseENet(alpha=0.1, rho=0.8, 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 = DenseENet(alpha=0.1, rho=0.8, fit_intercept=False,
max_iter=max_iter, tol=1e-7)
d_clf.fit(X_train, y_train)
assert_almost_equal(d_clf.dual_gap_, 0, 4)
assert d_clf.score(X_test, y_test) > 0.85
assert_almost_equal(s_clf.coef_, d_clf.coef_, 5)
# check that the coefs are sparse
assert np.sum(s_clf.coef_ != 0.0) < 2 * n_informative
def _test_sparse_enet_not_as_toy_dataset(alpha, fit_intercept, positive):
n_samples, n_features, max_iter = 100, 100, 1000
n_informative = 10
X, y = make_sparse_data(n_samples, n_features, n_informative,
positive=positive)
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 = SparseENet(alpha=alpha, rho=0.8, fit_intercept=fit_intercept,
max_iter=max_iter, tol=1e-7, positive=positive)
s_clf.fit(X_train, y_train)
assert_almost_equal(s_clf.dual_gap_, 0, 4)
assert_greater(s_clf.score(X_test, y_test), 0.85)
# check the convergence is the same as the dense version
d_clf = DenseENet(alpha=alpha, rho=0.8, fit_intercept=fit_intercept,
max_iter=max_iter, tol=1e-7, positive=positive)
d_clf.fit(X_train, y_train)
assert_almost_equal(d_clf.dual_gap_, 0, 4)
assert_greater(d_clf.score(X_test, y_test), 0.85)
assert_almost_equal(s_clf.coef_, d_clf.coef_, 5)
assert_almost_equal(s_clf.intercept_, d_clf.intercept_, 5)
# check that the coefs are sparse
assert_less(np.sum(s_clf.coef_ != 0.0), 2 * n_informative)
def fit(self,X,y):
'''
Fits ElasticNet Regression with kernelised features
Parameters
----------
X: array-like of size [n_samples, n_features]
Matrix of explanatory variables
y: array-like of size (n_samples,)
Vector of dependent variable
Returns
-------
obj: self
self
'''
X,y = check_X_y(X,y, dtype = np.float64)
K = get_kernel(X, X, self.gamma, self.degree, self.coef0, self.kernel,
self.kernel_params )
model = ElasticNet(self.alpha, self.l1_ratio, self.fit_intercept,
self.normalize, self.precompute, self.max_iter,
self.copy_X, self.tol, self.warm_start, self.positive,
self.random_state, self.selection)
self._model = model.fit(K,y)
self.relevant_indices_ = np.where(self._model.coef_ != 0)[0]
self.relevant_vectors_ = X[self.relevant_indices_,:]
return self
def test_sparse_coef():
# Check that the sparse_coef property works
clf = ElasticNet()
clf.coef_ = [1, 2, 3]
assert_true(sp.isspmatrix(clf.sparse_coef_))
assert_equal(clf.sparse_coef_.toarray().tolist()[0], clf.coef_)
def test_enet_toy_list_input():
# Test ElasticNet for various values of alpha and l1_ratio with list X
X = np.array([[-1], [0], [1]])
X = sp.csc_matrix(X)
Y = [-1, 0, 1] # just a straight line
T = np.array([[2], [3], [4]]) # test sample
# this should be the same as unregularized least squares
clf = ElasticNet(alpha=0, l1_ratio=1.0)
# catch warning about alpha=0.
# this is discouraged but should work.
ignore_warnings(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 = ElasticNet(alpha=0.5, l1_ratio=0.3, max_iter=1000)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_enet_float_precision():
# Generate dataset
X, y, X_test, y_test = build_dataset(n_samples=20, n_features=10)
# Here we have a small number of iterations, and thus the
# ElasticNet might not converge. This is to speed up tests
for normalize in [True, False]:
for fit_intercept in [True, False]:
coef = {}
intercept = {}
for dtype in [np.float64, np.float32]:
clf = ElasticNet(alpha=0.5,
max_iter=100,
precompute=False,
fit_intercept=fit_intercept,
normalize=normalize)
X = dtype(X)
y = dtype(y)
ignore_warnings(clf.fit)(X, y)
coef[('simple', dtype)] = clf.coef_
intercept[('simple', dtype)] = clf.intercept_
assert_equal(clf.coef_.dtype, dtype)
# test precompute Gram array
Gram = X.T.dot(X)
clf_precompute = ElasticNet(alpha=0.5,
max_iter=100,
precompute=Gram,
fit_intercept=fit_intercept,
normalize=normalize)
ignore_warnings(clf_precompute.fit)(X, y)
assert_array_almost_equal(clf.coef_, clf_precompute.coef_)
assert_array_almost_equal(clf.intercept_,
clf_precompute.intercept_)
# test multi task enet
multi_y = np.hstack((y[:, np.newaxis], y[:, np.newaxis]))
clf_multioutput = MultiTaskElasticNet(
alpha=0.5,
max_iter=100,
fit_intercept=fit_intercept,
normalize=normalize)
clf_multioutput.fit(X, multi_y)
coef[('multi', dtype)] = clf_multioutput.coef_
intercept[('multi', dtype)] = clf_multioutput.intercept_
assert_equal(clf.coef_.dtype, dtype)
for v in ['simple', 'multi']:
assert_array_almost_equal(coef[(v, np.float32)],
coef[(v, np.float64)],
decimal=4)
assert_array_almost_equal(intercept[(v, np.float32)],
intercept[(v, np.float64)],
decimal=4)
def test_enet_copy_X_True(check_input):
X, y, _, _ = build_dataset()
X = X.copy(order='F')
original_X = X.copy()
enet = ElasticNet(copy_X=True)
enet.fit(X, y, check_input=check_input)
assert_array_equal(original_X, X)
def test_enet_copy_X_True(check_input):
X, y, _, _ = build_dataset()
X = X.copy(order='F')
original_X = X.copy()
enet = ElasticNet(copy_X=True)
enet.fit(X, y, check_input=check_input)
assert_array_equal(original_X, X)
def test_warm_start():
X, y, _, _ = build_dataset()
clf = ElasticNet(alpha=0.1, max_iter=5, warm_start=True)
ignore_warnings(clf.fit)(X, y)
ignore_warnings(clf.fit)(X, y) # do a second round with 5 iterations
clf2 = ElasticNet(alpha=0.1, max_iter=10)
ignore_warnings(clf2.fit)(X, y)
assert_array_almost_equal(clf2.coef_, clf.coef_)
def test_warm_start():
X, y, _, _ = build_dataset()
clf = ElasticNet(alpha=1.0, max_iter=50, warm_start=True)
clf.fit(X, y)
clf.set_params(alpha=0.1)
clf.fit(X, y)
clf2 = ElasticNet(alpha=0.1, max_iter=500)
clf2.fit(X, y)
assert_array_almost_equal(clf2.coef_, clf.coef_)
def test_enet_copy_X_False_check_input_False():
X, y, _, _ = build_dataset()
X = X.copy(order='F')
original_X = X.copy()
enet = ElasticNet(copy_X=False)
enet.fit(X, y, check_input=False)
# No copying, X is overwritten
assert_true(np.any(np.not_equal(original_X, X)))
def test_enet_copy_X_False_check_input_False():
X, y, _, _ = build_dataset()
X = X.copy(order='F')
original_X = X.copy()
enet = ElasticNet(copy_X=False)
enet.fit(X, y, check_input=False)
# No copying, X is overwritten
assert np.any(np.not_equal(original_X, X))
def test_enet_multitarget():
n_targets = 3
X, y, _, _ = build_dataset(n_samples=10, n_features=8, n_informative_features=10, n_targets=n_targets)
estimator = ElasticNet(alpha=0.01, fit_intercept=True)
estimator.fit(X, y)
coef, intercept, dual_gap = (estimator.coef_, estimator.intercept_, estimator.dual_gap_)
for k in range(n_targets):
estimator.fit(X, y[:, k])
assert_array_almost_equal(coef[k, :], estimator.coef_)
assert_array_almost_equal(intercept[k], estimator.intercept_)
assert_array_almost_equal(dual_gap[k], estimator.dual_gap_)
def test_enet_multitarget():
n_targets = 3
X, y = make_sparse_data(n_targets=n_targets)
estimator = ElasticNet(alpha=0.01, fit_intercept=True, precompute=None)
# XXX: There is a bug when precompute is not None!
estimator.fit(X, y)
coef, intercept, dual_gap = (estimator.coef_, estimator.intercept_, estimator.dual_gap_)
for k in range(n_targets):
estimator.fit(X, y[:, k])
assert_array_almost_equal(coef[k, :], estimator.coef_)
assert_array_almost_equal(intercept[k], estimator.intercept_)
assert_array_almost_equal(dual_gap[k], estimator.dual_gap_)
def test_fit_simple_backupsklearn():
df = pd.read_csv("./open_data/simple.txt", delim_whitespace=True)
X = np.array(df.iloc[:, :df.shape[1] - 1], dtype='float32', order='C')
y = np.array(df.iloc[:, df.shape[1] - 1], dtype='float32', order='C')
Solver = h2o4gpu.ElasticNet
enet = Solver(glm_stop_early=False)
print("h2o4gpu fit()")
enet.fit(X, y)
print("h2o4gpu predict()")
print(enet.predict(X))
print("h2o4gpu score()")
print(enet.score(X,y))
enet_wrapper = Solver(positive=True, random_state=1234)
print("h2o4gpu scikit wrapper fit()")
enet_wrapper.fit(X, y)
print("h2o4gpu scikit wrapper predict()")
print(enet_wrapper.predict(X))
print("h2o4gpu scikit wrapper score()")
print(enet_wrapper.score(X, y))
from sklearn.linear_model.coordinate_descent import ElasticNet
enet_sk = ElasticNet(positive=True, random_state=1234)
print("Scikit fit()")
enet_sk.fit(X, y)
print("Scikit predict()")
print(enet_sk.predict(X))
print("Scikit score()")
print(enet_sk.score(X, y))
enet_sk_coef = csr_matrix(enet_sk.coef_, dtype=np.float32).toarray()
print(enet_sk.coef_)
print(enet_sk_coef)
print(enet_wrapper.coef_)
print(enet_sk.intercept_)
print(enet_wrapper.intercept_)
print(enet_sk.n_iter_)
print(enet_wrapper.n_iter_)
print("Coeffs, intercept, and n_iters should match")
assert np.allclose(enet_wrapper.coef_, enet_sk_coef)
assert np.allclose(enet_wrapper.intercept_, enet_sk.intercept_)
def __init__(self,
alpha=1.0,
l1_ratio=0.5,
fit_intercept=True,
normalize=False,
precompute=False,
max_iter=1000,
copy_X=True,
tol=0.0001,
warm_start=False,
positive=False,
random_state=None,
selection='cyclic'):
self._hyperparams = {
'alpha': alpha,
'l1_ratio': l1_ratio,
'fit_intercept': fit_intercept,
'normalize': normalize,
'precompute': precompute,
'max_iter': max_iter,
'copy_X': copy_X,
'tol': tol,
'warm_start': warm_start,
'positive': positive,
'random_state': random_state,
'selection': selection
}
self._wrapped_model = SKLModel(**self._hyperparams)
def test_same_multiple_output_sparse_dense():
for normalize in [True, False]:
l = ElasticNet(normalize=normalize)
X = [[0, 1, 2, 3, 4], [0, 2, 5, 8, 11], [9, 10, 11, 12, 13], [10, 11, 12, 13, 14]]
y = [[1, 2, 3, 4, 5], [1, 3, 6, 9, 12], [10, 11, 12, 13, 14], [11, 12, 13, 14, 15]]
ignore_warnings(l.fit)(X, y)
sample = np.array([1, 2, 3, 4, 5]).reshape(1, -1)
predict_dense = l.predict(sample)
l_sp = ElasticNet(normalize=normalize)
X_sp = sp.coo_matrix(X)
ignore_warnings(l_sp.fit)(X_sp, y)
sample_sparse = sp.coo_matrix(sample)
predict_sparse = l_sp.predict(sample_sparse)
assert_array_almost_equal(predict_sparse, predict_dense)
def test_check_input_false():
X, y, _, _ = build_dataset(n_samples=20, n_features=10)
X = check_array(X, order='F', dtype='float64')
y = check_array(X, order='F', dtype='float64')
clf = ElasticNet(selection='cyclic', tol=1e-8)
# Check that no error is raised if data is provided in the right format
clf.fit(X, y, check_input=False)
# With check_input=False, an exhaustive check is not made on y but its
# dtype is still cast in _preprocess_data to X's dtype. So the test should
# pass anyway
X = check_array(X, order='F', dtype='float32')
clf.fit(X, y, check_input=False)
# With no input checking, providing X in C order should result in false
# computation
X = check_array(X, order='C', dtype='float64')
assert_raises(ValueError, clf.fit, X, y, check_input=False)
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def test_enet_float_precision():
# Generate dataset
X, y, X_test, y_test = build_dataset(n_samples=20, n_features=10)
# Here we have a small number of iterations, and thus the
# ElasticNet might not converge. This is to speed up tests
for normalize in [True, False]:
for fit_intercept in [True, False]:
coef = {}
intercept = {}
clf = ElasticNet(alpha=0.5,
max_iter=100,
precompute=False,
fit_intercept=fit_intercept,
normalize=normalize)
for dtype in [np.float64, np.float32]:
X = dtype(X)
y = dtype(y)
ignore_warnings(clf.fit)(X, y)
coef[dtype] = clf.coef_
intercept[dtype] = clf.intercept_
assert_equal(clf.coef_.dtype, dtype)
assert_array_almost_equal(coef[np.float32],
coef[np.float64],
decimal=4)
assert_array_almost_equal(intercept[np.float32],
intercept[np.float64],
decimal=4)
def test_deprection_precompute_enet():
# Test that setting precompute="auto" gives a Deprecation Warning.
X, y, _, _ = build_dataset(n_samples=20, n_features=10)
clf = ElasticNet(precompute="auto")
assert_warns(DeprecationWarning, clf.fit, X, y)
clf = Lasso(precompute="auto")
assert_warns(DeprecationWarning, clf.fit, X, y)
def test_check_input_false():
X, y, _, _ = build_dataset(n_samples=20, n_features=10)
X = check_array(X, order='F', dtype='float64')
y = check_array(X, order='F', dtype='float64')
clf = ElasticNet(selection='cyclic', tol=1e-8)
# Check that no error is raised if data is provided in the right format
clf.fit(X, y, check_input=False)
X = check_array(X, order='F', dtype='float32')
clf.fit(X, y, check_input=True)
# Check that an error is raised if data is provided in the wrong dtype,
# because of check bypassing
assert_raises(ValueError, clf.fit, X, y, check_input=False)
# With no input checking, providing X in C order should result in false
# computation
X = check_array(X, order='C', dtype='float64')
assert_raises(ValueError, clf.fit, X, y, check_input=False)
def test_overrided_gram_matrix():
X, y, _, _ = build_dataset(n_samples=20, n_features=10)
Gram = X.T.dot(X)
clf = ElasticNet(selection='cyclic', tol=1e-8, precompute=Gram)
assert_warns_message(
UserWarning, "Gram matrix was provided but X was centered"
" to fit intercept, "
"or X was normalized : recomputing Gram matrix.", clf.fit, X, y)
def test_enet_positive_constraint():
X = [[-1], [0], [1]]
y = [1, 0, -1] # just a straight line with negative slope
enet = ElasticNet(alpha=0.1, max_iter=1000, positive=True)
enet.fit(X, y)
assert_true(min(enet.coef_) >= 0)
enet = ElasticNet(alpha=0.1, max_iter=1000, precompute=True, positive=True)
enet.fit(X, y)
assert_true(min(enet.coef_) >= 0)
def test_normalize_option():
""" Check that the normalize option in enet works """
X = sp.csc_matrix([[-1], [0], [1]])
y = [-1, 0, 1]
clf_dense = ElasticNet(fit_intercept=True, normalize=True)
clf_sparse = ElasticNet(fit_intercept=True, normalize=True)
clf_dense.fit(X, y)
X = sp.csc_matrix(X)
clf_sparse.fit(X, y)
assert_almost_equal(clf_dense.dual_gap_, 0)
assert_array_almost_equal(clf_dense.coef_, clf_sparse.coef_)
def test_warm_start():
X, y, _, _ = build_dataset()
with warnings.catch_warnings():
warnings.simplefilter("ignore", UserWarning)
clf = ElasticNet(alpha=0.1, max_iter=5, warm_start=True)
clf.fit(X, y)
clf.fit(X, y) # do a second round with 5 iterations
clf2 = ElasticNet(alpha=0.1, max_iter=10)
clf2.fit(X, y)
assert_array_almost_equal(clf2.coef_, clf.coef_)
def test_precompute_invalid_argument():
X, y, _, _ = build_dataset()
for clf in [ElasticNetCV(precompute="invalid"),
LassoCV(precompute="invalid")]:
assert_raises_regex(ValueError, ".*should be.*True.*False.*auto.*"
"array-like.*Got 'invalid'", clf.fit, X, y)
# Precompute = 'auto' is not supported for ElasticNet
assert_raises_regex(ValueError, ".*should be.*True.*False.*array-like.*"
"Got 'auto'", ElasticNet(precompute='auto').fit, X, y)
def _test_sparse_enet_not_as_toy_dataset(alpha, fit_intercept, positive):
n_samples, n_features, max_iter = 100, 100, 1000
n_informative = 10
X, y = make_sparse_data(n_samples,
n_features,
n_informative,
positive=positive)
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 = ElasticNet(alpha=alpha,
l1_ratio=0.8,
fit_intercept=fit_intercept,
max_iter=max_iter,
tol=1e-7,
positive=positive,
warm_start=True)
s_clf.fit(X_train, y_train)
assert_almost_equal(s_clf.dual_gap_, 0, 4)
assert_greater(s_clf.score(X_test, y_test), 0.85)
# check the convergence is the same as the dense version
d_clf = ElasticNet(alpha=alpha,
l1_ratio=0.8,
fit_intercept=fit_intercept,
max_iter=max_iter,
tol=1e-7,
positive=positive,
warm_start=True)
d_clf.fit(X_train.toarray(), y_train)
assert_almost_equal(d_clf.dual_gap_, 0, 4)
assert_greater(d_clf.score(X_test, y_test), 0.85)
assert_almost_equal(s_clf.coef_, d_clf.coef_, 5)
assert_almost_equal(s_clf.intercept_, d_clf.intercept_, 5)
# check that the coefs are sparse
assert_less(np.sum(s_clf.coef_ != 0.0), 2 * n_informative)
def test_warm_start_convergence_with_regularizer_decrement():
X, y = load_boston(return_X_y=True)
# Train a model to converge on a lightly regularized problem
final_alpha = 1e-5
low_reg_model = ElasticNet(alpha=final_alpha).fit(X, y)
# Fitting a new model on a more regularized version of the same problem.
# Fitting with high regularization is easier it should converge faster
# in general.
high_reg_model = ElasticNet(alpha=final_alpha * 10).fit(X, y)
assert low_reg_model.n_iter_ > high_reg_model.n_iter_
# Fit the solution to the original, less regularized version of the
# problem but from the solution of the highly regularized variant of
# the problem as a better starting point. This should also converge
# faster than the original model that starts from zero.
warm_low_reg_model = deepcopy(high_reg_model)
warm_low_reg_model.set_params(warm_start=True, alpha=final_alpha)
warm_low_reg_model.fit(X, y)
assert low_reg_model.n_iter_ > warm_low_reg_model.n_iter_
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
class ElasticNetImpl():
def __init__(self,
alpha=1.0,
l1_ratio=0.5,
fit_intercept=True,
normalize=False,
precompute=False,
max_iter=1000,
copy_X=True,
tol=0.0001,
warm_start=False,
positive=False,
random_state=None,
selection='cyclic'):
self._hyperparams = {
'alpha': alpha,
'l1_ratio': l1_ratio,
'fit_intercept': fit_intercept,
'normalize': normalize,
'precompute': precompute,
'max_iter': max_iter,
'copy_X': copy_X,
'tol': tol,
'warm_start': warm_start,
'positive': positive,
'random_state': random_state,
'selection': selection
}
self._wrapped_model = SKLModel(**self._hyperparams)
def fit(self, X, y=None):
if (y is not None):
self._wrapped_model.fit(X, y)
else:
self._wrapped_model.fit(X)
return self
def predict(self, X):
return self._wrapped_model.predict(X)
def test_check_input_false():
X, y, _, _ = build_dataset(n_samples=20, n_features=10)
X = check_array(X, order='F', dtype='float64')
y = check_array(X, order='F', dtype='float64')
clf = ElasticNet(selection='cyclic', tol=1e-8)
# Check that no error is raised if data is provided in the right format
clf.fit(X, y, check_input=False)
X = check_array(X, order='F', dtype='float32')
clf.fit(X, y, check_input=True)
# Check that an error is raised if data is provided in the wrong format,
# because of check bypassing
assert_raises(ValueError, clf.fit, X, y, check_input=False)
# With no input checking, providing X in C order should result in false
# computation
X = check_array(X, order='C', dtype='float64')
clf.fit(X, y, check_input=False)
coef_false = clf.coef_
clf.fit(X, y, check_input=True)
coef_true = clf.coef_
assert_raises(AssertionError, assert_array_almost_equal, coef_true,
coef_false)
def test_enet_toy_explicit_sparse_input():
"""Test ElasticNet for various values of alpha and l1_ratio with sparse
X"""
f = ignore_warnings
# training samples
X = sp.lil_matrix((3, 1))
X[0, 0] = -1
# X[1, 0] = 0
X[2, 0] = 1
Y = [-1, 0, 1] # just a straight line (the identity function)
# test samples
T = sp.lil_matrix((3, 1))
T[0, 0] = 2
T[1, 0] = 3
T[2, 0] = 4
# this should be the same as lasso
clf = ElasticNet(alpha=0, l1_ratio=1.0)
f(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 = ElasticNet(alpha=0.5, l1_ratio=0.3, max_iter=1000)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_warm_start():
X, y, _, _ = build_dataset()
with warnings.catch_warnings():
warnings.simplefilter("ignore", UserWarning)
clf = ElasticNet(alpha=0.1, max_iter=5, warm_start=True)
clf.fit(X, y)
clf.fit(X, y) # do a second round with 5 iterations
clf2 = ElasticNet(alpha=0.1, max_iter=10)
clf2.fit(X, y)
assert_array_almost_equal(clf2.coef_, clf.coef_)
def test_normalize_option():
""" Check that the normalize option in enet works """
X = sp.csc_matrix([[-1], [0], [1]])
y = [-1, 0, 1]
clf_dense = ElasticNet(fit_intercept=True, normalize=True)
clf_sparse = ElasticNet(fit_intercept=True, normalize=True)
clf_dense.fit(X, y)
X = sp.csc_matrix(X)
clf_sparse.fit(X, y)
assert_almost_equal(clf_dense.dual_gap_, 0)
assert_array_almost_equal(clf_dense.coef_, clf_sparse.coef_)
def test_warm_start_convergence():
X, y, _, _ = build_dataset()
model = ElasticNet(alpha=1e-3, tol=1e-3).fit(X, y)
n_iter_reference = model.n_iter_
# This dataset is not trivial enough for the model to converge in one pass.
assert_greater(n_iter_reference, 2)
# Check that n_iter_ is invariant to multiple calls to fit
# when warm_start=False, all else being equal.
model.fit(X, y)
n_iter_cold_start = model.n_iter_
assert_equal(n_iter_cold_start, n_iter_reference)
# Fit the same model again, using a warm start: the optimizer just performs
# a single pass before checking that it has already converged
model.set_params(warm_start=True)
model.fit(X, y)
n_iter_warm_start = model.n_iter_
assert_equal(n_iter_warm_start, 1)
def test_enet_multitarget():
n_targets = 3
X, y, _, _ = build_dataset(n_samples=10, n_features=8,
n_informative_features=10, n_targets=n_targets)
estimator = ElasticNet(alpha=0.01, fit_intercept=True)
estimator.fit(X, y)
coef, intercept, dual_gap = (estimator.coef_, estimator.intercept_,
estimator.dual_gap_)
for k in range(n_targets):
estimator.fit(X, y[:, k])
assert_array_almost_equal(coef[k, :], estimator.coef_)
assert_array_almost_equal(intercept[k], estimator.intercept_)
assert_array_almost_equal(dual_gap[k], estimator.dual_gap_)
def test_enet_multitarget():
n_targets = 3
X, y = make_sparse_data(n_targets=n_targets)
estimator = ElasticNet(alpha=0.01, fit_intercept=True, precompute=None)
# XXX: There is a bug when precompute is not None!
estimator.fit(X, y)
coef, intercept, dual_gap = (estimator.coef_, estimator.intercept_,
estimator.dual_gap_)
for k in range(n_targets):
estimator.fit(X, y[:, k])
assert_array_almost_equal(coef[k, :], estimator.coef_)
assert_array_almost_equal(intercept[k], estimator.intercept_)
assert_array_almost_equal(dual_gap[k], estimator.dual_gap_)
def test_fit_simple_backupsklearn():
df = pd.read_csv("./open_data/simple.txt", delim_whitespace=True)
X = np.array(df.iloc[:, :df.shape[1] - 1], dtype='float32', order='C')
y = np.array(df.iloc[:, df.shape[1] - 1], dtype='float32', order='C')
Solver = h2o4gpu.ElasticNet
enet = Solver(glm_stop_early=False)
print("h2o4gpu fit()")
enet.fit(X, y)
print("h2o4gpu predict()")
print(enet.predict(X))
print("h2o4gpu score()")
print(enet.score(X, y))
enet_wrapper = Solver(positive=True, random_state=1234)
print("h2o4gpu scikit wrapper fit()")
enet_wrapper.fit(X, y)
print("h2o4gpu scikit wrapper predict()")
print(enet_wrapper.predict(X))
print("h2o4gpu scikit wrapper score()")
print(enet_wrapper.score(X, y))
from sklearn.linear_model.coordinate_descent import ElasticNet
enet_sk = ElasticNet(positive=True, random_state=1234)
print("Scikit fit()")
enet_sk.fit(X, y)
print("Scikit predict()")
print(enet_sk.predict(X))
print("Scikit score()")
print(enet_sk.score(X, y))
enet_sk_coef = csr_matrix(enet_sk.coef_, dtype=np.float32).toarray()
print(enet_sk.coef_)
print(enet_sk_coef)
print(enet_wrapper.coef_)
print(enet_sk.intercept_)
print(enet_wrapper.intercept_)
print(enet_sk.n_iter_)
print(enet_wrapper.n_iter_)
print("Coeffs, intercept, and n_iters should match")
assert np.allclose(enet_wrapper.coef_, enet_sk_coef)
assert np.allclose(enet_wrapper.intercept_, enet_sk.intercept_)
def test_check_input_false():
X, y, _, _ = build_dataset(n_samples=20, n_features=10)
X = check_array(X, order='F', dtype='float64')
y = check_array(X, order='F', dtype='float64')
clf = ElasticNet(selection='cyclic', tol=1e-8)
# Check that no error is raised if data is provided in the right format
clf.fit(X, y, check_input=False)
# With check_input=False, an exhaustive check is not made on y but its
# dtype is still cast in _preprocess_data to X's dtype. So the test should
# pass anyway
X = check_array(X, order='F', dtype='float32')
clf.fit(X, y, check_input=False)
# With no input checking, providing X in C order should result in false
# computation
X = check_array(X, order='C', dtype='float64')
assert_raises(ValueError, clf.fit, X, y, check_input=False)
def test_warm_start_convergence():
X, y, _, _ = build_dataset()
model = ElasticNet(alpha=1e-3, tol=1e-3).fit(X, y)
n_iter_reference = model.n_iter_
# This dataset is not trivial enough for the model to converge in one pass.
assert_greater(n_iter_reference, 2)
# Check that n_iter_ is invariant to multiple calls to fit
# when warm_start=False, all else being equal.
model.fit(X, y)
n_iter_cold_start = model.n_iter_
assert_equal(n_iter_cold_start, n_iter_reference)
# Fit the same model again, using a warm start: the optimizer just performs
# a single pass before checking that it has already converged
model.set_params(warm_start=True)
model.fit(X, y)
n_iter_warm_start = model.n_iter_
assert_equal(n_iter_warm_start, 1)
def test_same_multiple_output_sparse_dense():
for normalize in [True, False]:
l = ElasticNet(normalize=normalize)
X = [[0, 1, 2, 3, 4], [0, 2, 5, 8, 11], [9, 10, 11, 12, 13],
[10, 11, 12, 13, 14]]
y = [[1, 2, 3, 4, 5], [1, 3, 6, 9, 12], [10, 11, 12, 13, 14],
[11, 12, 13, 14, 15]]
ignore_warnings(l.fit)(X, y)
sample = np.array([1, 2, 3, 4, 5]).reshape(1, -1)
predict_dense = l.predict(sample)
l_sp = ElasticNet(normalize=normalize)
X_sp = sp.coo_matrix(X)
ignore_warnings(l_sp.fit)(X_sp, y)
sample_sparse = sp.coo_matrix(sample)
predict_sparse = l_sp.predict(sample_sparse)
assert_array_almost_equal(predict_sparse, predict_dense)
def _test_sparse_enet_not_as_toy_dataset(alpha, fit_intercept, positive):
n_samples, n_features, max_iter = 100, 100, 1000
n_informative = 10
X, y = make_sparse_data(n_samples, n_features, n_informative,
positive=positive)
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 = SparseENet(alpha=alpha, rho=0.8, fit_intercept=fit_intercept,
max_iter=max_iter, tol=1e-7, positive=positive,
warm_start=True)
s_clf.fit(X_train, y_train)
assert_almost_equal(s_clf.dual_gap_, 0, 4)
assert_greater(s_clf.score(X_test, y_test), 0.85)
# check the convergence is the same as the dense version
d_clf = DenseENet(alpha=alpha, rho=0.8, fit_intercept=fit_intercept,
max_iter=max_iter, tol=1e-7, positive=positive,
warm_start=True)
d_clf.fit(X_train, y_train)
assert_almost_equal(d_clf.dual_gap_, 0, 4)
assert_greater(d_clf.score(X_test, y_test), 0.85)
assert_almost_equal(s_clf.coef_, d_clf.coef_, 5)
assert_almost_equal(s_clf.intercept_, d_clf.intercept_, 5)
# check that the coefs are sparse
assert_less(np.sum(s_clf.coef_ != 0.0), 2 * n_informative)
# check that warm restart leads to the same result with
# sparse and dense versions
rng = np.random.RandomState(seed=0)
coef_init = rng.randn(n_features)
d_clf.fit(X_train, y_train, coef_init=coef_init)
s_clf.fit(X_train, y_train, coef_init=coef_init)
assert_almost_equal(s_clf.coef_, d_clf.coef_, 5)
assert_almost_equal(s_clf.intercept_, d_clf.intercept_, 5)
def test_random_descent():
# Test that both random and cyclic selection give the same results.
# Ensure that the test models fully converge and check a wide
# range of conditions.
# This uses the coordinate descent algo using the gram trick.
X, y, _, _ = build_dataset(n_samples=50, n_features=20)
clf_cyclic = ElasticNet(selection='cyclic', tol=1e-8)
clf_cyclic.fit(X, y)
clf_random = ElasticNet(selection='random', tol=1e-8, random_state=42)
clf_random.fit(X, y)
assert_array_almost_equal(clf_cyclic.coef_, clf_random.coef_)
assert_almost_equal(clf_cyclic.intercept_, clf_random.intercept_)
# This uses the descent algo without the gram trick
clf_cyclic = ElasticNet(selection='cyclic', tol=1e-8)
clf_cyclic.fit(X.T, y[:20])
clf_random = ElasticNet(selection='random', tol=1e-8, random_state=42)
clf_random.fit(X.T, y[:20])
assert_array_almost_equal(clf_cyclic.coef_, clf_random.coef_)
assert_almost_equal(clf_cyclic.intercept_, clf_random.intercept_)
# Sparse Case
clf_cyclic = ElasticNet(selection='cyclic', tol=1e-8)
clf_cyclic.fit(sparse.csr_matrix(X), y)
clf_random = ElasticNet(selection='random', tol=1e-8, random_state=42)
clf_random.fit(sparse.csr_matrix(X), y)
assert_array_almost_equal(clf_cyclic.coef_, clf_random.coef_)
assert_almost_equal(clf_cyclic.intercept_, clf_random.intercept_)
# Multioutput case.
new_y = np.hstack((y[:, np.newaxis], y[:, np.newaxis]))
clf_cyclic = MultiTaskElasticNet(selection='cyclic', tol=1e-8)
clf_cyclic.fit(X, new_y)
clf_random = MultiTaskElasticNet(selection='random', tol=1e-8,
random_state=42)
clf_random.fit(X, new_y)
assert_array_almost_equal(clf_cyclic.coef_, clf_random.coef_)
assert_almost_equal(clf_cyclic.intercept_, clf_random.intercept_)
# Raise error when selection is not in cyclic or random.
clf_random = ElasticNet(selection='invalid')
assert_raises(ValueError, clf_random.fit, X, y)
def test_enet_small():
"""Toy tests with generated X and Y"""
# TODO: add \theta prior knowledge here and test the output
X = np.array([[-1.], [0.], [1.]])
Y = [-1, 0, 1] # a straight line
T = [[2.], [3.], [4.]] # test sample
# this should be the same as lasso
clf = ElasticNet(alpha=1e-8, l1_ratio=1.0)
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 = ElasticNet(alpha=0.5, l1_ratio=0.3, max_iter=100,
precompute=False)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf.set_params(max_iter=100, precompute=True)
clf.fit(X, Y) # with Gram
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf.set_params(max_iter=100, precompute=np.dot(X.T, X))
clf.fit(X, Y) # with Gram
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_random_descent():
# Test that both random and cyclic selection give the same results.
# Ensure that the test models fully converge and check a wide
# range of conditions.
# This uses the coordinate descent algo using the gram trick.
X, y, _, _ = build_dataset(n_samples=50, n_features=20)
clf_cyclic = ElasticNet(selection='cyclic', tol=1e-8)
clf_cyclic.fit(X, y)
clf_random = ElasticNet(selection='random', tol=1e-8, random_state=42)
clf_random.fit(X, y)
assert_array_almost_equal(clf_cyclic.coef_, clf_random.coef_)
assert_almost_equal(clf_cyclic.intercept_, clf_random.intercept_)
# This uses the descent algo without the gram trick
clf_cyclic = ElasticNet(selection='cyclic', tol=1e-8)
clf_cyclic.fit(X.T, y[:20])
clf_random = ElasticNet(selection='random', tol=1e-8, random_state=42)
clf_random.fit(X.T, y[:20])
assert_array_almost_equal(clf_cyclic.coef_, clf_random.coef_)
assert_almost_equal(clf_cyclic.intercept_, clf_random.intercept_)
# Sparse Case
clf_cyclic = ElasticNet(selection='cyclic', tol=1e-8)
clf_cyclic.fit(sparse.csr_matrix(X), y)
clf_random = ElasticNet(selection='random', tol=1e-8, random_state=42)
clf_random.fit(sparse.csr_matrix(X), y)
assert_array_almost_equal(clf_cyclic.coef_, clf_random.coef_)
assert_almost_equal(clf_cyclic.intercept_, clf_random.intercept_)
# Multioutput case.
new_y = np.hstack((y[:, np.newaxis], y[:, np.newaxis]))
clf_cyclic = MultiTaskElasticNet(selection='cyclic', tol=1e-8)
clf_cyclic.fit(X, new_y)
clf_random = MultiTaskElasticNet(selection='random', tol=1e-8,
random_state=42)
clf_random.fit(X, new_y)
assert_array_almost_equal(clf_cyclic.coef_, clf_random.coef_)
assert_almost_equal(clf_cyclic.intercept_, clf_random.intercept_)
# Raise error when selection is not in cyclic or random.
clf_random = ElasticNet(selection='invalid')
assert_raises(ValueError, clf_random.fit, X, y)
def test_enet_toy():
# Test ElasticNet for various parameters of alpha and l1_ratio.
# Actually, the parameters alpha = 0 should not be allowed. However,
# we test it as a border case.
# ElasticNet is tested with and without precomputed Gram matrix
X = np.array([[-1.], [0.], [1.]])
Y = [-1, 0, 1] # just a straight line
T = [[2.], [3.], [4.]] # test sample
# this should be the same as lasso
clf = ElasticNet(alpha=1e-8, l1_ratio=1.0)
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 = ElasticNet(alpha=0.5, l1_ratio=0.3, max_iter=100,
precompute=False)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf.set_params(max_iter=100, precompute=True)
clf.fit(X, Y) # with Gram
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf.set_params(max_iter=100, precompute=np.dot(X.T, X))
clf.fit(X, Y) # with Gram
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_enet_toy_list_input():
"""Test ElasticNet for various values of alpha and l1_ratio with list X"""
X = np.array([[-1], [0], [1]])
X = sp.csc_matrix(X)
Y = [-1, 0, 1] # just a straight line
T = np.array([[2], [3], [4]]) # test sample
# this should be the same as unregularized least squares
clf = ElasticNet(alpha=0, l1_ratio=1.0)
# catch warning about alpha=0.
# this is discouraged but should work.
ignore_warnings(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 = ElasticNet(alpha=0.5, l1_ratio=0.3, max_iter=1000)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_enet_toy_list_input():
"""Test ElasticNet for various parameters of alpha and rho with list X"""
X = np.array([[-1], [0], [1]])
X = sp.csc_matrix(X)
Y = [-1, 0, 1] # just a straight line
T = np.array([[2], [3], [4]]) # test sample
# this should be the same as unregularized least squares
clf = ElasticNet(alpha=0, rho=1.0)
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 = ElasticNet(alpha=0.5, rho=0.3, max_iter=1000)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, rho=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_enet_toy_list_input():
"""Test ElasticNet for various parameters of alpha and rho with list X"""
X = np.array([[-1], [0], [1]])
X = sp.csc_matrix(X)
Y = [-1, 0, 1] # just a straight line
T = np.array([[2], [3], [4]]) # test sample
# this should be the same as unregularized least squares
clf = ElasticNet(alpha=0, rho=1.0)
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 = ElasticNet(alpha=0.5, rho=0.3, max_iter=1000)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, rho=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_warm_start():
X, y, _, _ = build_dataset()
# Test that explicit warm restart...
clf = ElasticNet(alpha=1.0, max_iter=50)
clf.fit(X, y)
clf2 = ElasticNet(alpha=0.1, max_iter=50)
clf2.fit(X, y, coef_init=clf.coef_.copy())
# ... and implicit warm restart are equivalent.
clf3 = ElasticNet(alpha=1.0, max_iter=50, warm_start=True)
clf3.fit(X, y)
assert_array_almost_equal(clf3.coef_, clf.coef_)
clf3.set_params(alpha=0.1)
clf3.fit(X, y)
assert_array_almost_equal(clf3.coef_, clf2.coef_)
def test_warm_start():
X, y, _, _ = build_dataset()
# Test that explicit warm restart...
clf = ElasticNet(alpha=1.0, max_iter=50)
clf.fit(X, y)
clf2 = ElasticNet(alpha=0.1, max_iter=50)
clf2.fit(X, y, coef_init=clf.coef_.copy())
#... and implicit warm restart are equivalent.
clf3 = ElasticNet(alpha=1.0, max_iter=50, warm_start=True)
clf3.fit(X, y)
assert_array_almost_equal(clf3.coef_, clf.coef_)
clf3.set_params(alpha=0.1)
clf3.fit(X, y)
assert_array_almost_equal(clf3.coef_, clf2.coef_)
print X_train[123,:]
'''
norm1 = np.linalg.norm(y_train)
if norm1 != 0:
y_train, y_test = y_train/norm1, y_test/norm1
print norm1
'''
print y_train.shape
model = SVR(C=1.0, gamma=1.0)
model = LinearRegression()
lasso = Lasso(alpha=0.1).fit(X_train, y_train)
enet = ElasticNet(alpha=0.1, l1_ratio=0.7).fit(X_train, y_train)
y_pred = lasso.predict(X_test)
print "MSE", mean_squared_error(y_test, y_pred)
m = np.mean(y_test)
print "MSE (Mean)",mean_squared_error(y_test, m*np.ones(len(y_test)))
print "r^2 on test data", r2_score(y_test, y_pred)
plt.plot(enet.coef_, label='Elastic net coefficients')
plt.plot(lasso.coef_, label='Lasso coefficients')
plt.legend(loc='best')
plt.title("Lasso R^2: %f, Elastic Net R^2: %f"
% (r2_score(y_test, lasso.predict(X_test)), r2_score(y_test, enet.predict(X_test))))
def test_enet_toy():
# Test ElasticNet for various parameters of alpha and l1_ratio.
# Actually, the parameters alpha = 0 should not be allowed. However,
# we test it as a border case.
# ElasticNet is tested with and without precomputed Gram matrix
X = np.array([[-1.], [0.], [1.]])
Y = [-1, 0, 1] # just a straight line
T = [[2.], [3.], [4.]] # test sample
# this should be the same as lasso
clf = ElasticNet(alpha=1e-8, l1_ratio=1.0)
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 = ElasticNet(alpha=0.5, l1_ratio=0.3, max_iter=100,
precompute=False)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf.set_params(max_iter=100, precompute=True)
clf.fit(X, Y) # with Gram
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf.set_params(max_iter=100, precompute=np.dot(X.T, X))
clf.fit(X, Y) # with Gram
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_enet_toy_explicit_sparse_input():
"""Test ElasticNet for various values of alpha and l1_ratio with sparse
X"""
f = ignore_warnings
# training samples
X = sp.lil_matrix((3, 1))
X[0, 0] = -1
# X[1, 0] = 0
X[2, 0] = 1
Y = [-1, 0, 1] # just a straight line (the identity function)
# test samples
T = sp.lil_matrix((3, 1))
T[0, 0] = 2
T[1, 0] = 3
T[2, 0] = 4
# this should be the same as lasso
clf = ElasticNet(alpha=0, l1_ratio=1.0)
f(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 = ElasticNet(alpha=0.5, l1_ratio=0.3, max_iter=1000)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
