def test_ModelHinge(self):
"""...Numerical consistency check of loss and gradient for Hinge model
"""
np.random.seed(12)
n_samples, n_features = 5000, 10
w0 = np.random.randn(n_features)
c0 = np.random.randn()
# First check with intercept
X, y = SimuLogReg(w0,
c0,
n_samples=n_samples,
verbose=False,
dtype=self.dtype).simulate()
X_spars = csr_matrix(X, dtype=self.dtype)
model = ModelHinge(fit_intercept=True).fit(X, y)
model_spars = ModelHinge(fit_intercept=True).fit(X_spars, y)
self.run_test_for_glm(model, model_spars)
self._test_glm_intercept_vs_hardcoded_intercept(model)
# Then check without intercept
X, y = SimuLogReg(w0,
None,
n_samples=n_samples,
verbose=False,
seed=2038,
dtype=self.dtype).simulate()
X_spars = csr_matrix(X)
model = ModelHinge(fit_intercept=False).fit(X, y)
model_spars = ModelHinge(fit_intercept=False).fit(X_spars, y)
self.run_test_for_glm(model, model_spars)
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 test_ModelLogReg(self):
"""...Numerical consistency check of loss and gradient for Logistic
Regression
"""
np.random.seed(12)
n_samples, n_features = 5000, 10
w0 = np.random.randn(n_features)
c0 = np.random.randn()
# First check with intercept
X, y = SimuLogReg(w0, c0, n_samples=n_samples, verbose=False,
dtype=self.dtype).simulate()
X_spars = csr_matrix(X, dtype=self.dtype)
model = ModelLogReg(fit_intercept=True).fit(X, y)
model_spars = ModelLogReg(fit_intercept=True).fit(X_spars, y)
self.run_test_for_glm(model, model_spars)
self._test_glm_intercept_vs_hardcoded_intercept(model)
# Then check without intercept
X, y = SimuLogReg(w0, None, n_samples=n_samples, verbose=False,
seed=2038, dtype=self.dtype).simulate()
X_spars = csr_matrix(X, dtype=self.dtype)
model = ModelLogReg(fit_intercept=False).fit(X, y)
model_spars = ModelLogReg(fit_intercept=False).fit(X_spars, y)
self.run_test_for_glm(model, model_spars)
self._test_glm_intercept_vs_hardcoded_intercept(model)
# Test for the Lipschitz constants without intercept
self.assertAlmostEqual(model.get_lip_best(), 0.67184209642814952,
places=self.decimal_places)
self.assertAlmostEqual(model.get_lip_mean(), 2.48961431697108,
places=self.decimal_places)
self.assertAlmostEqual(model.get_lip_max(), 13.706542412138093,
places=self.decimal_places)
self.assertAlmostEqual(model_spars.get_lip_mean(),
model.get_lip_mean(),
places=self.decimal_places)
self.assertAlmostEqual(model_spars.get_lip_max(), model.get_lip_max(),
places=self.decimal_places)
# Test for the Lipschitz constants with intercept
model = ModelLogReg(fit_intercept=True).fit(X, y)
model_spars = ModelLogReg(fit_intercept=True).fit(X_spars, y)
self.assertAlmostEqual(model.get_lip_best(), 0.671892096428,
places=self.decimal_places)
self.assertAlmostEqual(model.get_lip_mean(), 2.739614316971082,
places=self.decimal_places)
self.assertAlmostEqual(model.get_lip_max(), 13.956542412138093,
places=self.decimal_places)
self.assertAlmostEqual(model_spars.get_lip_mean(),
model.get_lip_mean(),
places=self.decimal_places)
self.assertAlmostEqual(model_spars.get_lip_max(), model.get_lip_max(),
places=self.decimal_places)
def test_ModelSmoothedHinge(self):
"""...Numerical consistency check of loss and gradient for SmoothedHinge
model
"""
np.random.seed(12)
n_samples, n_features = 5000, 10
w0 = np.random.randn(n_features)
c0 = np.random.randn()
# First check with intercept
X, y = SimuLogReg(w0, c0, n_samples=n_samples,
verbose=False).simulate()
X_spars = csr_matrix(X)
model = ModelSmoothedHinge(fit_intercept=True,
smoothness=0.2).fit(X, y)
model_spars = ModelSmoothedHinge(fit_intercept=True,
smoothness=0.2).fit(X_spars, y)
self.run_test_for_glm(model, model_spars, 1e-5, 1e-4)
self._test_glm_intercept_vs_hardcoded_intercept(model)
# Then check without intercept
X, y = SimuLogReg(w0,
None,
n_samples=n_samples,
verbose=False,
seed=2038).simulate()
X_spars = csr_matrix(X)
model = ModelSmoothedHinge(fit_intercept=False).fit(X, y)
model_spars = ModelSmoothedHinge(fit_intercept=False).fit(X_spars, y)
self.run_test_for_glm(model, model_spars, 1e-5, 1e-4)
model = ModelSmoothedHinge(fit_intercept=False,
smoothness=0.2).fit(X, y)
model_spars = ModelSmoothedHinge(fit_intercept=False,
smoothness=0.2).fit(X_spars, y)
# Test for the Lipschitz constants without intercept
self.assertAlmostEqual(model.get_lip_best(), 5 * 2.6873683857125981)
self.assertAlmostEqual(model.get_lip_mean(), 5 * 9.95845726788432)
self.assertAlmostEqual(model.get_lip_max(), 5 * 54.82616964855237)
self.assertAlmostEqual(model_spars.get_lip_mean(),
model.get_lip_mean())
self.assertAlmostEqual(model_spars.get_lip_max(), model.get_lip_max())
# Test for the Lipschitz constants with intercept
model = ModelSmoothedHinge(fit_intercept=True,
smoothness=0.2).fit(X, y)
model_spars = ModelSmoothedHinge(fit_intercept=True,
smoothness=0.2).fit(X_spars, y)
self.assertAlmostEqual(model.get_lip_best(), 5 * 2.687568385712598)
self.assertAlmostEqual(model.get_lip_mean(), 5 * 10.958457267884327)
self.assertAlmostEqual(model.get_lip_max(), 5 * 55.82616964855237)
self.assertAlmostEqual(model_spars.get_lip_mean(),
model.get_lip_mean())
self.assertAlmostEqual(model_spars.get_lip_max(), model.get_lip_max())
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_step_type_setting(self):
"""...Test that SVRG step_type parameter behaves correctly
"""
svrg = SVRG()
coeffs0 = weights_sparse_gauss(20, nnz=5, dtype=self.dtype)
interc0 = None
X, y = SimuLogReg(coeffs0,
interc0,
n_samples=3000,
verbose=False,
seed=123,
dtype=self.dtype).simulate()
model = ModelLogReg().fit(X, y)
svrg.set_model(model)
self.assertEqual(svrg.step_type, 'fixed')
self.assertEqual(svrg._solver.get_step_type(), SVRG_StepType_Fixed)
svrg = SVRG(step_type='bb')
svrg.set_model(model)
self.assertEqual(svrg.step_type, 'bb')
self.assertEqual(svrg._solver.get_step_type(),
SVRG_StepType_BarzilaiBorwein)
svrg.step_type = 'fixed'
self.assertEqual(svrg.step_type, 'fixed')
self.assertEqual(svrg._solver.get_step_type(), SVRG_StepType_Fixed)
svrg.step_type = 'bb'
self.assertEqual(svrg.step_type, 'bb')
self.assertEqual(svrg._solver.get_step_type(),
SVRG_StepType_BarzilaiBorwein)
def test_ModelSmoothedHinge_smoothness(self):
np.random.seed(12)
n_samples, n_features = 50, 2
w0 = np.random.randn(n_features)
c0 = np.random.randn()
# First check with intercept
X, y = SimuLogReg(w0, c0, n_samples=n_samples,
verbose=False).simulate()
model = ModelSmoothedHinge(smoothness=0.123).fit(X, y)
self.assertEqual(model._model.get_smoothness(), 0.123)
model.smoothness = 0.765
self.assertEqual(model._model.get_smoothness(), 0.765)
msg = '^smoothness should be between 0.01 and 1$'
with self.assertRaisesRegex(RuntimeError, msg):
model = ModelSmoothedHinge(smoothness=-1).fit(X, y)
with self.assertRaisesRegex(RuntimeError, msg):
model = ModelSmoothedHinge(smoothness=1.2).fit(X, y)
with self.assertRaisesRegex(RuntimeError, msg):
model = ModelSmoothedHinge(smoothness=0.).fit(X, y)
with self.assertRaisesRegex(RuntimeError, msg):
model.smoothness = 0.
with self.assertRaisesRegex(RuntimeError, msg):
model.smoothness = -1.
with self.assertRaisesRegex(RuntimeError, msg):
model.smoothness = 2.
def get_train_data(n_features=20, n_samples=3000, nnz=5):
np.random.seed(12)
weights0 = weights_sparse_gauss(n_features, nnz=nnz)
interc0 = 0.1
features, y = SimuLogReg(weights0,
interc0,
n_samples=n_samples,
verbose=False).simulate()
return features, y
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)
def test_variance_reduction_setting(self):
"""...SolverTest SAGA variance_reduction parameter is correctly set"""
svrg = SAGA()
coeffs0 = weights_sparse_gauss(20, nnz=5, dtype=self.dtype)
interc0 = None
X, y = SimuLogReg(coeffs0,
interc0,
n_samples=3000,
verbose=False,
seed=123,
dtype=self.dtype).simulate()
model = ModelLogReg().fit(X, y)
svrg.set_model(model)
svrg.astype(self.dtype)
self.assertEqual(svrg.variance_reduction, 'last')
self.assertEqual(svrg._solver.get_variance_reduction(),
SAGA_VarianceReductionMethod_Last)
svrg = SAGA(variance_reduction='rand')
svrg.set_model(model)
svrg.astype(self.dtype)
self.assertEqual(svrg.variance_reduction, 'rand')
self.assertEqual(svrg._solver.get_variance_reduction(),
SAGA_VarianceReductionMethod_Random)
svrg.variance_reduction = 'avg'
self.assertEqual(svrg.variance_reduction, 'avg')
self.assertEqual(svrg._solver.get_variance_reduction(),
SAGA_VarianceReductionMethod_Average)
svrg.variance_reduction = 'rand'
self.assertEqual(svrg.variance_reduction, 'rand')
self.assertEqual(svrg._solver.get_variance_reduction(),
SAGA_VarianceReductionMethod_Random)
svrg.variance_reduction = 'last'
self.assertEqual(svrg.variance_reduction, 'last')
self.assertEqual(svrg._solver.get_variance_reduction(),
SAGA_VarianceReductionMethod_Last)
with self.assertRaises(ValueError):
svrg.variance_reduction = 'wrong_name'
def test_solver_bfgs(self):
"""...Check BFGS solver for Logistic Regression with Ridge
penalization
"""
# It is the reference solver used in other unittests so we check that
# it's actually close to the true parameter of the simulated dataset
np.random.seed(12)
n_samples = 3000
n_features = 10
coeffs0 = weights_sparse_gauss(n_features, nnz=5)
interc0 = 2.
X, y = SimuLogReg(coeffs0, interc0, n_samples=n_samples,
verbose=False).simulate()
model = ModelLogReg(fit_intercept=True).fit(X, y)
prox = ProxL2Sq(strength=1e-6)
solver = BFGS(max_iter=100, print_every=1, verbose=False,
tol=1e-6).set_model(model).set_prox(prox)
coeffs = solver.solve()
err = Test.evaluate_model(coeffs, coeffs0, interc0)
self.assertAlmostEqual(err, 0., delta=5e-1)
def create_model(model_type, n_samples, n_features, with_intercept=True):
weights = np.random.randn(n_features)
intercept = None
if with_intercept:
intercept = np.random.normal()
if model_type == 'Poisson':
# we need to rescale features to avoid overflows
weights /= n_features
if intercept is not None:
intercept /= n_features
if model_type == 'Linear':
simulator = SimuLinReg(weights,
intercept=intercept,
n_samples=n_samples,
verbose=False)
elif model_type == 'Logistic':
simulator = SimuLogReg(weights,
intercept=intercept,
n_samples=n_samples,
verbose=False)
elif model_type == 'Poisson':
simulator = SimuPoisReg(weights,
intercept=intercept,
n_samples=n_samples,
verbose=False)
labels, features = simulator.simulate()
if model_type == 'Linear':
model = ModelLinReg(fit_intercept=with_intercept)
elif model_type == 'Logistic':
model = ModelLogReg(fit_intercept=with_intercept)
elif model_type == 'Poisson':
model = ModelPoisReg(fit_intercept=with_intercept)
model.fit(labels, features)
return model
from tick.solver import SVRG, SAGA
from tick.prox import ProxElasticNet
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 = []
"""
import numpy as np
import matplotlib.pyplot as plt
from cycler import cycler
from tick.simulation import weights_sparse_gauss
from tick.solver import SVRG
from tick.linear_model import SimuLogReg, ModelLogReg
from tick.prox import ProxElasticNet
from tick.plot import plot_history
n_samples, n_features, = 5000, 50
weights0 = weights_sparse_gauss(n_features, nnz=10)
intercept0 = 0.2
X, y = SimuLogReg(weights=weights0, intercept=intercept0,
n_samples=n_samples, seed=123, verbose=False).simulate()
model = ModelLogReg(fit_intercept=True).fit(X, y)
prox = ProxElasticNet(strength=1e-3, ratio=0.5, range=(0, n_features))
x0 = np.zeros(model.n_coeffs)
optimal_step = 1 / model.get_lip_max()
tested_steps = [optimal_step, 1e-2 * optimal_step, 10 * optimal_step]
solvers = []
solver_labels = []
for step in tested_steps:
svrg = SVRG(max_iter=30, tol=1e-10, verbose=False)
svrg.set_model(model).set_prox(prox)
svrg.solve(step=step)
def test_ModelQuadraticHinge(self):
"""...Numerical consistency check of loss and gradient for Quadratic
Hinge model
"""
np.random.seed(12)
n_samples, n_features = 5000, 10
w0 = np.random.randn(n_features)
c0 = np.random.randn()
# First check with intercept
X, y = SimuLogReg(w0,
c0,
n_samples=n_samples,
verbose=False,
dtype=self.dtype).simulate()
X_spars = csr_matrix(X, dtype=self.dtype)
model = ModelQuadraticHinge(fit_intercept=True).fit(X, y)
model_spars = ModelQuadraticHinge(fit_intercept=True, ).fit(X_spars, y)
self.run_test_for_glm(model, model_spars)
self._test_glm_intercept_vs_hardcoded_intercept(model)
# Then check without intercept
X, y = SimuLogReg(w0,
None,
n_samples=n_samples,
verbose=False,
seed=2038,
dtype=self.dtype).simulate()
X_spars = csr_matrix(X, dtype=self.dtype)
model = ModelQuadraticHinge(fit_intercept=False).fit(X, y)
model_spars = ModelQuadraticHinge(fit_intercept=False).fit(X_spars, y)
self.run_test_for_glm(model, model_spars)
# Test for the Lipschitz constants without intercept
self.assertAlmostEqual(model.get_lip_best(),
2.6873683857125981,
places=self.decimal_places)
self.assertAlmostEqual(model.get_lip_mean(),
9.95845726788432,
places=self.decimal_places)
self.assertAlmostEqual(model.get_lip_max(),
54.82616964855237,
places=self.decimal_places)
self.assertAlmostEqual(model_spars.get_lip_mean(),
model.get_lip_mean())
self.assertAlmostEqual(model_spars.get_lip_max(), model.get_lip_max())
# Test for the Lipschitz constants with intercept
model = ModelQuadraticHinge(fit_intercept=True).fit(X, y)
model_spars = ModelQuadraticHinge(fit_intercept=True).fit(X_spars, y)
self.assertAlmostEqual(model.get_lip_best(),
2.687568385712598,
places=self.decimal_places)
self.assertAlmostEqual(model.get_lip_mean(),
10.958457267884327,
places=self.decimal_places)
self.assertAlmostEqual(model.get_lip_max(),
55.82616964855237,
places=self.decimal_places)
self.assertAlmostEqual(model_spars.get_lip_mean(),
model.get_lip_mean(),
places=self.decimal_places)
self.assertAlmostEqual(model_spars.get_lip_max(),
model.get_lip_max(),
places=self.decimal_places)
n_features = 30
n_classes = 2
nnz = 5
w0 = np.zeros(n_features)
w0[:nnz] = 1
# TODO: Seed
n_trees = 50
# w0 = weights_sparse_exp(n_features, nnz=nnz)
X, y = SimuLogReg(weights=w0,
intercept=None,
n_samples=n_samples,
cov_corr=0.1,
features_scaling='standard',
seed=123).simulate()
y = (y + 1) / 2
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=123)
rf = RandomForestClassifier(n_estimators=n_trees,
criterion="entropy",
random_state=123)
rf.fit(X_train, y_train)
feature_importances = rf.feature_importances_
of1 = OnlineForestClassifier(n_classes=n_classes,
n_trees=n_trees,
seed=123,
def test_variance_reduction_setting(self):
"""...Test that SVRG variance_reduction parameter behaves correctly
"""
svrg = SVRG()
coeffs0 = weights_sparse_gauss(20, nnz=5, dtype=self.dtype)
interc0 = None
X, y = SimuLogReg(coeffs0,
interc0,
n_samples=3000,
verbose=False,
seed=123,
dtype=self.dtype).simulate()
model = ModelLogReg().fit(X, y)
svrg.set_model(model)
self.assertEqual(svrg.variance_reduction, 'last')
self.assertEqual(svrg._solver.get_variance_reduction(),
SVRG_VarianceReductionMethod_Last)
svrg = SVRG(variance_reduction='rand')
svrg.set_model(model)
self.assertEqual(svrg.variance_reduction, 'rand')
self.assertEqual(svrg._solver.get_variance_reduction(),
SVRG_VarianceReductionMethod_Random)
svrg.variance_reduction = 'avg'
self.assertEqual(svrg.variance_reduction, 'avg')
self.assertEqual(svrg._solver.get_variance_reduction(),
SVRG_VarianceReductionMethod_Average)
svrg.variance_reduction = 'rand'
self.assertEqual(svrg.variance_reduction, 'rand')
self.assertEqual(svrg._solver.get_variance_reduction(),
SVRG_VarianceReductionMethod_Random)
svrg.variance_reduction = 'last'
self.assertEqual(svrg.variance_reduction, 'last')
self.assertEqual(svrg._solver.get_variance_reduction(),
SVRG_VarianceReductionMethod_Last)
msg = '^variance_reduction should be one of "avg, last, rand", ' \
'got "stuff"$'
with self.assertRaisesRegex(ValueError, msg):
svrg = SVRG(variance_reduction='stuff')
svrg.set_model(model)
with self.assertRaisesRegex(ValueError, msg):
svrg.variance_reduction = 'stuff'
X, y = self.simu_linreg_data(dtype=self.dtype)
model_dense, model_spars = self.get_dense_and_sparse_linreg_model(
X, y, dtype=self.dtype)
try:
svrg.set_model(model_dense)
svrg.variance_reduction = 'avg'
svrg.variance_reduction = 'last'
svrg.variance_reduction = 'rand'
svrg.set_model(model_spars)
svrg.variance_reduction = 'last'
svrg.variance_reduction = 'rand'
except Exception:
self.fail('Setting variance_reduction in these cases should have '
'been ok')
msg = "'avg' variance reduction cannot be used with sparse datasets"
with catch_warnings(record=True) as w:
simplefilter('always')
svrg.set_model(model_spars)
svrg.variance_reduction = 'avg'
self.assertEqual(len(w), 1)
self.assertTrue(issubclass(w[0].category, UserWarning))
self.assertEqual(str(w[0].message), msg)
def check_solver(self,
solver,
fit_intercept=True,
model='logreg',
decimal=1):
"""Check solver instance finds same parameters as scipy BFGS
Parameters
----------
solver : `Solver`
Instance of a solver to be tested
fit_intercept : `bool`, default=True
Model uses intercept is `True`
model : 'linreg' | 'logreg' | 'poisreg', default='logreg'
Name of the model used to test the solver
decimal : `int`, default=1
Number of decimals required for the test
"""
# Set seed for data simulation
np.random.seed(12)
n_samples = TestSolver.n_samples
n_features = TestSolver.n_features
coeffs0 = weights_sparse_gauss(n_features, nnz=5)
if fit_intercept:
interc0 = 2.
else:
interc0 = None
if model == 'linreg':
X, y = SimuLinReg(coeffs0,
interc0,
n_samples=n_samples,
verbose=False,
seed=123).simulate()
model = ModelLinReg(fit_intercept=fit_intercept).fit(X, y)
elif model == 'logreg':
X, y = SimuLogReg(coeffs0,
interc0,
n_samples=n_samples,
verbose=False,
seed=123).simulate()
model = ModelLogReg(fit_intercept=fit_intercept).fit(X, y)
elif model == 'poisreg':
X, y = SimuPoisReg(coeffs0,
interc0,
n_samples=n_samples,
verbose=False,
seed=123).simulate()
# Rescale features to avoid overflows in Poisson simulations
X /= np.linalg.norm(X, axis=1).reshape(n_samples, 1)
model = ModelPoisReg(fit_intercept=fit_intercept).fit(X, y)
else:
raise ValueError("``model`` must be either 'linreg', 'logreg' or"
" 'poisreg'")
solver.set_model(model)
strength = 1e-2
prox = ProxL2Sq(strength, (0, model.n_features))
if type(solver) is not SDCA:
solver.set_prox(prox)
else:
solver.set_prox(ProxZero())
solver.l_l2sq = strength
coeffs_solver = solver.solve()
# Compare with BFGS
bfgs = BFGS(max_iter=100,
verbose=False).set_model(model).set_prox(prox)
coeffs_bfgs = bfgs.solve()
np.testing.assert_almost_equal(coeffs_solver,
coeffs_bfgs,
decimal=decimal)
# We ensure that reached coeffs are not equal to zero
self.assertGreater(norm(coeffs_solver), 0)
self.assertAlmostEqual(solver.objective(coeffs_bfgs),
solver.objective(coeffs_solver),
delta=1e-2)
n_samples, n_features = 150, 2
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)
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
from sklearn.datasets import make_moons, make_classification, make_circles
from sklearn.metrics import roc_auc_score
import matplotlib.pyplot as plt
from time import time
n_samples = 1000
n_features = 2
seed = 123
np.set_printoptions(precision=2)
w0 = weights_sparse_gauss(n_features, nnz=2)
X, y = SimuLogReg(w0, -1., n_samples=n_samples, seed=seed).simulate()
y = (y + 1) / 2
def plot_decisions_regression(clfs, datasets, names):
i = 1
h = .02
fig = plt.figure(figsize=(4 * (len(clfs) + 1), 4 * len(datasets)))
# iterate over datasets
for ds_cnt, ds in enumerate(datasets):
X, y = ds
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=.4, random_state=42)
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5