def test_ridge():
# Ridge regression convergence test using score
# TODO: for this test to be robust, we should use a dataset instead
# of np.random.
rng = np.random.RandomState(0)
alpha = 1.0
for solver in ("svd", "sparse_cg", "cholesky", "lsqr"):
# With more samples than features
n_samples, n_features = 6, 5
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert_equal(ridge.coef_.shape, (X.shape[1], ))
assert_greater(ridge.score(X, y), 0.47)
if solver == "cholesky":
# Currently the only solver to support sample_weight.
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_greater(ridge.score(X, y), 0.47)
# With more features than samples
n_samples, n_features = 5, 10
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert_greater(ridge.score(X, y), .9)
if solver == "cholesky":
# Currently the only solver to support sample_weight.
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_greater(ridge.score(X, y), 0.9)
def test_ridge():
"""Ridge regression convergence test using score
TODO: for this test to be robust, we should use a dataset instead
of np.random.
"""
alpha = 1.0
for solver in ("sparse_cg", "dense_cholesky", "lsqr"):
# With more samples than features
n_samples, n_features = 6, 5
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert_equal(ridge.coef_.shape, (X.shape[1], ))
assert_greater(ridge.score(X, y), 0.47)
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_greater(ridge.score(X, y), 0.47)
# With more features than samples
n_samples, n_features = 5, 10
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert_greater(ridge.score(X, y), .9)
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_greater(ridge.score(X, y), 0.9)
def test_ridge():
# Ridge regression convergence test using score
# TODO: for this test to be robust, we should use a dataset instead
# of np.random.
rng = np.random.RandomState(0)
alpha = 1.0
for solver in ("svd", "sparse_cg", "cholesky", "lsqr"):
# With more samples than features
n_samples, n_features = 6, 5
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert_equal(ridge.coef_.shape, (X.shape[1], ))
assert_greater(ridge.score(X, y), 0.47)
if solver == "cholesky":
# Currently the only solver to support sample_weight.
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_greater(ridge.score(X, y), 0.47)
# With more features than samples
n_samples, n_features = 5, 10
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert_greater(ridge.score(X, y), .9)
if solver == "cholesky":
# Currently the only solver to support sample_weight.
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_greater(ridge.score(X, y), 0.9)
def test_ridge(solver):
# Ridge regression convergence test using score
# TODO: for this test to be robust, we should use a dataset instead
# of np.random.
rng = np.random.RandomState(0)
alpha = 1.0
# With more samples than features
n_samples, n_features = 6, 5
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert ridge.coef_.shape == (X.shape[1], )
assert ridge.score(X, y) > 0.47
if solver in ("cholesky", "sag"):
# Currently the only solvers to support sample_weight.
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.47
# With more features than samples
n_samples, n_features = 5, 10
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert ridge.score(X, y) > .9
if solver in ("cholesky", "sag"):
# Currently the only solvers to support sample_weight.
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.9
def test_ridge():
"""Ridge regression convergence test using score
TODO: for this test to be robust, we should use a dataset instead
of np.random.
"""
alpha = 1.0
# With more samples than features
n_samples, n_features = 6, 5
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert_equal(ridge.coef_.shape, (X.shape[1],))
assert ridge.score(X, y) > 0.5
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.5
# With more features than samples
n_samples, n_features = 5, 10
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert ridge.score(X, y) > 0.9
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.9
def test_ridge():
"""Ridge regression convergence test using score
TODO: for this test to be robust, we should use a dataset instead
of np.random.
"""
alpha = 1.0
# With more samples than features
n_samples, n_features = 6, 5
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert_equal(ridge.coef_.shape, (X.shape[1], ))
assert_true(ridge.score(X, y) > 0.5)
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_true(ridge.score(X, y) > 0.5)
# With more features than samples
n_samples, n_features = 5, 10
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert_true(ridge.score(X, y) > .9)
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_true(ridge.score(X, y) > 0.9)
def test_ridge():
"""Ridge regression convergence test using score
TODO: for this test to be robust, we should use a dataset instead
of np.random.
"""
alpha = 1.0
for solver in ("sparse_cg", "dense_cholesky", "lsqr"):
# With more samples than features
n_samples, n_features = 6, 5
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert_equal(ridge.coef_.shape, (X.shape[1], ))
assert_greater(ridge.score(X, y), 0.47)
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_greater(ridge.score(X, y), 0.47)
# With more features than samples
n_samples, n_features = 5, 10
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha, solver=solver)
ridge.fit(X, y)
assert_greater(ridge.score(X, y), .9)
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert_greater(ridge.score(X, y), 0.9)
def _test_tolerance(filter_):
ridge = Ridge(tol=1e-5)
ridge.fit(filter_(X_diabetes), y_diabetes)
score = ridge.score(filter_(X_diabetes), y_diabetes)
ridge2 = Ridge(tol=1e-3)
ridge2.fit(filter_(X_diabetes), y_diabetes)
score2 = ridge2.score(filter_(X_diabetes), y_diabetes)
assert_true(score >= score2)
def _test_tolerance(filter_):
ridge = Ridge(tol=1e-5)
ridge.fit(filter_(X_diabetes), y_diabetes)
score = ridge.score(filter_(X_diabetes), y_diabetes)
ridge2 = Ridge(tol=1e-3)
ridge2.fit(filter_(X_diabetes), y_diabetes)
score2 = ridge2.score(filter_(X_diabetes), y_diabetes)
assert_true(score >= score2)
def _test_tolerance(filter_):
ridge = Ridge(tol=1e-5, fit_intercept=False)
ridge.fit(filter_(X_diabetes), y_diabetes)
score = ridge.score(filter_(X_diabetes), y_diabetes)
ridge2 = Ridge(tol=1e-3, fit_intercept=False)
ridge2.fit(filter_(X_diabetes), y_diabetes)
score2 = ridge2.score(filter_(X_diabetes), y_diabetes)
assert score >= score2
def _test_tolerance(filter_):
ridge = Ridge(tol=1e-5, fit_intercept=False)
ridge.fit(filter_(X_diabetes), y_diabetes)
score = ridge.score(filter_(X_diabetes), y_diabetes)
ridge2 = Ridge(tol=1e-3, fit_intercept=False)
ridge2.fit(filter_(X_diabetes), y_diabetes)
score2 = ridge2.score(filter_(X_diabetes), y_diabetes)
assert score >= score2
def test_ridge_singular():
# test on a singular matrix
rng = np.random.RandomState(0)
n_samples, n_features = 6, 6
y = rng.randn(n_samples // 2)
y = np.concatenate((y, y))
X = rng.randn(n_samples // 2, n_features)
X = np.concatenate((X, X), axis=0)
ridge = Ridge(alpha=0)
ridge.fit(X, y)
assert_greater(ridge.score(X, y), 0.9)
def test_ridge_singular():
# test on a singular matrix
rng = np.random.RandomState(0)
n_samples, n_features = 6, 6
y = rng.randn(n_samples // 2)
y = np.concatenate((y, y))
X = rng.randn(n_samples // 2, n_features)
X = np.concatenate((X, X), axis=0)
ridge = Ridge(alpha=0)
ridge.fit(X, y)
assert_greater(ridge.score(X, y), 0.9)
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.Ridge
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(normalize=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.ridge import Ridge
enet_sk = Ridge(normalize=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_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.Ridge
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(normalize=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.ridge import Ridge
enet_sk = Ridge(normalize=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_ridge_diabetes(filter_):
ridge = Ridge(fit_intercept=False)
ridge.fit(filter_(X_diabetes), y_diabetes)
return np.round(ridge.score(filter_(X_diabetes), y_diabetes), 5)
def _test_ridge_diabetes(filter_):
ridge = Ridge(fit_intercept=False)
ridge.fit(filter_(X_diabetes), y_diabetes)
return np.round(ridge.score(filter_(X_diabetes), y_diabetes), 5)
