def test_HawkesSumExpKern_solver_step(self):
"""...Test HawkesSumExpKern setting of step parameter
of solver
"""
for solver in solvers:
if solver in ['bfgs']:
msg = '^Solver "%s" has no settable step$' % solver
with self.assertWarnsRegex(RuntimeWarning, msg):
learner = HawkesSumExpKern(
self.decays,
solver=solver,
step=1,
**Test.specific_solver_kwargs(solver))
self.assertIsNone(learner.step)
else:
learner = HawkesSumExpKern(
self.decays,
solver=solver,
step=self.float_1,
**Test.specific_solver_kwargs(solver))
self.assertEqual(learner.step, self.float_1)
self.assertEqual(learner._solver_obj.step, self.float_1)
learner.step = self.float_2
self.assertEqual(learner.step, self.float_2)
self.assertEqual(learner._solver_obj.step, self.float_2)
if solver in ['sgd']:
msg = '^SGD step needs to be tuned manually$'
with self.assertWarnsRegex(RuntimeWarning, msg):
learner = HawkesSumExpKern(self.decays,
solver='sgd',
max_iter=1)
learner.fit(self.events, 0.3)
def test_corresponding_simu(self):
"""...Test that the corresponding simulation object is correctly
built
"""
learner = HawkesSumExpKern(self.decays, max_iter=10)
learner.fit(self.events)
corresponding_simu = learner._corresponding_simu()
np.testing.assert_array_equal(corresponding_simu.decays,
learner.decays)
np.testing.assert_array_equal(corresponding_simu.baseline,
learner.baseline)
np.testing.assert_array_equal(corresponding_simu.adjacency,
learner.adjacency)
learner = HawkesSumExpKern(self.decays,
n_baselines=3,
period_length=1,
max_iter=10)
learner.fit(self.events)
corresponding_simu = learner._corresponding_simu()
np.testing.assert_array_equal(corresponding_simu.decays,
learner.decays)
np.testing.assert_array_equal(corresponding_simu.baseline,
learner.baseline)
np.testing.assert_array_equal(corresponding_simu.adjacency,
learner.adjacency)
def test_HawkesSumExpKern_fit(self):
"""...Test HawkesSumExpKern fit with different solvers
and penalties
"""
sto_seed = 179312
n_nodes = 2
events, baseline, adjacency = Test.get_train_data(
self.decays, n_nodes=n_nodes, n_decays=self.n_decays)
start = 0.01
initial_adjacency_error = \
Test.estimation_error(start * np.ones((n_nodes, n_nodes)),
adjacency)
for penalty in penalties:
for solver in solvers:
solver_kwargs = {
'penalty': penalty,
'tol': 1e-10,
'solver': solver,
'verbose': False,
'max_iter': 1000
}
if penalty != 'none':
solver_kwargs['C'] = 50
if solver in ['sgd', 'svrg']:
solver_kwargs['random_state'] = sto_seed
# manually set step
if solver == 'sgd':
solver_kwargs['step'] = 1e-5
elif solver == 'svrg':
continue
if solver == 'bfgs':
# BFGS only accepts ProxZero and ProxL2sq for now
if penalty != 'l2':
continue
if penalty == 'nuclear':
# Nuclear penalty only compatible with batch solvers
if solver in \
HawkesSumExpKern._solvers_stochastic:
continue
learner = HawkesSumExpKern(self.decays, **solver_kwargs)
learner.fit(events, start=start)
adjacency_error = Test.estimation_error(
learner.adjacency, adjacency)
self.assertLess(
adjacency_error, initial_adjacency_error * 0.8,
"solver %s with penalty %s "
"reached too high baseline error" % (solver, penalty))
def test_sparse(self):
"""...Test that original coeffs are correctly retrieved when some
realizations are empty
"""
baseline, adjacency, events = self.simulate_sparse_realization()
learner = HawkesSumExpKern(self.decays, verbose=False)
learner.fit(events)
np.testing.assert_array_almost_equal(learner.baseline,
baseline,
decimal=1)
np.testing.assert_array_almost_equal(learner.adjacency,
adjacency,
decimal=1)
def test_plot_hawkes_kernels(self):
"""...Test plot_hawkes_history rendering given a fitted Hawkes
learner
"""
decays = np.array([1.5, 3.5])
hawkes_sumexp = HawkesSumExpKern(decays, max_iter=0)
# We set some specific coeffs to be free from any future learner
# modifications
# With 0 iteration and coeffs as start point it should remain there
coeffs = np.array(
[0.99, 0.99, 0.55, 0.37, 0.39, 0.16, 0.63, 0.49, 0.49, 0.30])
hawkes_sumexp.fit(self.hawkes_simu.timestamps, start=coeffs)
n_points = 10
for support in [None, 4]:
fig = plot_hawkes_kernels(hawkes_sumexp,
hawkes=self.hawkes_simu,
show=False,
n_points=n_points,
support=support)
if support is None:
max_support = hawkes_sumexp.get_kernel_supports().max() * 1.2
else:
max_support = support
for i, j in itertools.product(range(self.n_nodes), repeat=2):
index = i * self.n_nodes + j
ax = fig.axes[index]
ax_t_axis, ax_estimated_kernel = ax.lines[0].get_xydata().T
t_axis = np.linspace(0, max_support, n_points)
np.testing.assert_array_equal(ax_t_axis, t_axis)
estimated_kernel = hawkes_sumexp.get_kernel_values(
i, j, t_axis)
np.testing.assert_array_equal(ax_estimated_kernel,
estimated_kernel)
_, ax_true_kernel = ax.lines[1].get_xydata().T
true_kernel = self.hawkes_simu.kernels[i, j].get_values(t_axis)
np.testing.assert_array_equal(ax_true_kernel, true_kernel)
def test_HawkesSumExpKern_score(self):
"""...Test HawkesSumExpKern score method
"""
n_nodes = 2
n_realizations = 3
train_events = [[
np.cumsum(np.random.rand(4 + i)) for i in range(n_nodes)
] for _ in range(n_realizations)]
test_events = [[
np.cumsum(np.random.rand(4 + i)) for i in range(n_nodes)
] for _ in range(n_realizations)]
learner = HawkesSumExpKern(self.decays)
msg = '^You must either call `fit` before `score` or provide events$'
with self.assertRaisesRegex(ValueError, msg):
learner.score()
given_baseline = np.random.rand(n_nodes)
given_adjacency = np.random.rand(n_nodes, n_nodes, self.n_decays)
learner.fit(train_events)
train_score_current_coeffs = learner.score()
self.assertAlmostEqual(train_score_current_coeffs, 1.684827141)
train_score_given_coeffs = learner.score(baseline=given_baseline,
adjacency=given_adjacency)
self.assertAlmostEqual(train_score_given_coeffs, 1.16247892)
test_score_current_coeffs = learner.score(test_events)
self.assertAlmostEqual(test_score_current_coeffs, 1.66494295)
test_score_given_coeffs = learner.score(test_events,
baseline=given_baseline,
adjacency=given_adjacency)
self.assertAlmostEqual(test_score_given_coeffs, 1.1081362)
def test_HawkesSumExpKern_fit_start(self):
"""...Test HawkesSumExpKern starting point of fit method
"""
n_nodes = len(self.events)
n_coefs = n_nodes + n_nodes * n_nodes * self.n_decays
# Do not step
learner = HawkesSumExpKern(self.decays, max_iter=-1)
learner.fit(self.events)
np.testing.assert_array_equal(learner.coeffs, np.ones(n_coefs))
learner.fit(self.events, start=self.float_1)
np.testing.assert_array_equal(learner.coeffs,
np.ones(n_coefs) * self.float_1)
learner.fit(self.events, start=self.int_1)
np.testing.assert_array_equal(learner.coeffs,
np.ones(n_coefs) * self.int_1)
random_coeffs = np.random.rand(n_coefs)
learner.fit(self.events, start=random_coeffs)
np.testing.assert_array_equal(learner.coeffs, random_coeffs)
decays = [0.1, 0.5, 1.]
baseline = [0.12, 0.07]
adjacency = [[[0, .1, .4], [.2, 0., .2]],
[[0, 0, 0], [.6, .3, 0]]]
hawkes_exp_kernels = SimuHawkesSumExpKernels(
adjacency=adjacency, decays=decays, baseline=baseline,
end_time=end_time, verbose=False, seed=1039)
hawkes_exp_kernels.track_intensity(0.1)
hawkes_exp_kernels.simulate()
learner = HawkesSumExpKern(decays, penalty='elasticnet',
elastic_net_ratio=0.8)
learner.fit(hawkes_exp_kernels.timestamps)
t_min = 100
t_max = 200
fig, ax_list = plt.subplots(2, 1, figsize=(10, 6))
learner.plot_estimated_intensity(hawkes_exp_kernels.timestamps,
t_min=t_min, t_max=t_max,
ax=ax_list)
plot_point_process(hawkes_exp_kernels, plot_intensity=True,
t_min=t_min, t_max=t_max, ax=ax_list)
# Enhance plot
for ax in ax_list:
# Set labels to both plots
ax.lines[0].set_label('estimated')
from tick.inference import HawkesSumExpKern
end_time = 1000
n_realizations = 10
decays = [.5, 2., 6.]
baseline = [0.12, 0.07]
adjacency = [[[0, .1, .4], [.2, 0., .2]], [[0, 0, 0], [.6, .3, 0]]]
hawkes_exp_kernels = SimuHawkesSumExpKernels(adjacency=adjacency,
decays=decays,
baseline=baseline,
end_time=end_time,
verbose=False,
seed=1039)
multi = SimuHawkesMulti(hawkes_exp_kernels, n_simulations=n_realizations)
multi.end_time = [(i + 1) / 10 * end_time for i in range(n_realizations)]
multi.simulate()
learner = HawkesSumExpKern(decays, penalty='elasticnet', elastic_net_ratio=0.8)
learner.fit(multi.timestamps)
fig = plot_hawkes_kernels(learner, hawkes=hawkes_exp_kernels, show=False)
for ax in fig.axes:
ax.set_ylim([0., 1.])
plt.show()