def test_SimuLogReg(self):
"""...Test simulation of a Logistic Regression
"""
n_samples = 10
n_features = 3
idx = np.arange(n_features)
weights = np.exp(-idx / 10.)
weights[::2] *= -1
seed = 123
simu = SimuLogReg(weights,
None,
n_samples=n_samples,
seed=seed,
verbose=False)
X, y = simu.simulate()
X_truth = np.array([[1.4912667, 0.80881799, 0.26977298],
[1.23227551, 0.50697013, 1.9409132],
[1.8891494, 1.49834791, 2.41445794],
[0.19431319, 0.80245126, 1.02577552],
[-1.61687582, -1.08411865, -0.83438387],
[2.30419894, -0.68987056, -0.39750262],
[-0.28826405, -1.23635074, -0.76124386],
[-1.32869473, -1.8752391, -0.182537],
[0.79464218, 0.65055633, 1.57572506],
[0.71524202, 1.66759831, 0.88679047]])
y_truth = np.array([-1., -1., -1., -1., 1., -1., 1., -1., -1., 1.])
np.testing.assert_array_almost_equal(X_truth, X)
np.testing.assert_array_almost_equal(y_truth, y)
def generate_logistic_data(n_features, n_samples, use_intercept=False):
""" Function to generate labels features y and X that corresponds
to w, c
"""
if n_features <= 5:
raise ValueError("``n_features`` must be larger than 5")
np.random.seed(12)
coeffs0 = weights_sparse_gauss(n_features, nnz=5)
if use_intercept:
interc0 = 2.
else:
interc0 = None
simu = SimuLogReg(coeffs0, interc0, n_samples=n_samples, verbose=False)
X, y = simu.simulate()
return y, X, coeffs0, interc0
def test_asaga_solver(self):
"""...Check ASAGA solver for a Logistic Regression with Elastic net
penalization
"""
seed = 1398
np.random.seed(seed)
n_samples = 4000
n_features = 30
weights = weights_sparse_gauss(n_features, nnz=3).astype(self.dtype)
intercept = 0.2
penalty_strength = 1e-3
sparsity = 1e-4
features = sparse.rand(n_samples, n_features, density=sparsity,
format='csr', random_state=8).astype(self.dtype)
simulator = SimuLogReg(weights, n_samples=n_samples, features=features,
verbose=False, intercept=intercept,
dtype=self.dtype)
features, labels = simulator.simulate()
model = ModelLogReg(fit_intercept=True)
model.fit(features, labels)
prox = ProxElasticNet(penalty_strength, ratio=0.1, range=(0,
n_features))
solver_step = 1. / model.get_lip_max()
saga = SAGA(step=solver_step, max_iter=100, tol=1e-10, verbose=False,
n_threads=1, record_every=10, seed=seed)
saga.set_model(model).set_prox(prox)
saga.solve()
asaga = SAGA(step=solver_step, max_iter=100, tol=1e-10, verbose=False,
n_threads=2, record_every=10, seed=seed)
asaga.set_model(model).set_prox(prox)
asaga.solve()
np.testing.assert_array_almost_equal(saga.solution, asaga.solution,
decimal=4)
self.assertGreater(np.linalg.norm(saga.solution[:-1]), 0)
weights0 = np.array([0.3, 1.2])
intercept0 = 0.5
simu_linreg = SimuLinReg(weights0,
intercept0,
n_samples=n_samples,
seed=123,
verbose=False)
X_linreg, y_linreg = simu_linreg.simulate()
simu_logreg = SimuLogReg(weights0,
intercept0,
n_samples=n_samples,
seed=123,
verbose=False)
X_logreg, y_logreg = simu_logreg.simulate()
simu_poisreg = SimuPoisReg(weights0,
intercept0,
n_samples=n_samples,
link='exponential',
seed=123,
verbose=False)
X_poisreg, y_poisreg = simu_poisreg.simulate()
plt.figure(figsize=(12, 3))
plt.subplot(1, 3, 1)
plt.scatter(*X_linreg.T, c=y_linreg, cmap='RdBu')
plt.colorbar()
plt.title('Linear', fontsize=16)
seed = 1398
np.random.seed(seed)
n_samples = 40000
n_features = 20000
sparsity = 1e-4
penalty_strength = 1e-5
weights = weights_sparse_gauss(n_features, nnz=1000)
intercept = 0.2
features = sparse.rand(n_samples, n_features, density=sparsity, format='csr')
simulator = SimuLogReg(weights, n_samples=n_samples, features=features,
verbose=False, intercept=intercept)
features, labels = simulator.simulate()
model = ModelLogReg(fit_intercept=True)
model.fit(features, labels)
prox = ProxElasticNet(penalty_strength, ratio=0.5, range=(0, n_features))
svrg_step = 1. / model.get_lip_max()
test_n_threads = [1, 2, 4]
fig, axes = plt.subplots(1, 2, figsize=(8, 4))
for ax, SolverClass in zip(axes, [SVRG, SAGA]):
solver_list = []
solver_labels = []
for n_threads in test_n_threads: