def test_simu_hawkes_multi_attrs(self):
"""...Test multiple simulations via SimuHawkesMulti vs. single Hawkes
See that multiple simulations has same attributes as a single Hawkes
simulation, but different results
"""
hawkes = SimuHawkes(kernels=self.kernels,
baseline=self.baseline,
end_time=10,
verbose=False,
seed=504)
multi = SimuHawkesMulti(hawkes, n_threads=4, n_simulations=10)
multi.simulate()
hawkes.simulate()
np.testing.assert_array_equal(hawkes.simulation_time,
multi.simulation_time)
np.testing.assert_array_equal(hawkes.n_nodes, multi.n_nodes)
np.testing.assert_array_equal(hawkes.end_time, multi.end_time)
np.testing.assert_array_equal(hawkes.max_jumps, multi.max_jumps)
np.testing.assert_array_equal(hawkes.spectral_radius(),
multi.spectral_radius)
self.assertTrue(
all(
np.array_equal(hawkes.mean_intensity(), np.array(x))
for x in multi.mean_intensity))
self.assertFalse(
np.array_equal(hawkes.n_total_jumps, multi.n_total_jumps))
def _sim_single_exposures(self):
if not self.sparse:
raise ValueError(
"'single_exposure' exposures can only be simulated"
" as sparse feature matrices")
if self.hawkes_exp_kernels is None:
np.random.seed(self.seed)
decays = .002 * np.ones((self.n_features, self.n_features))
baseline = 4 * np.random.random(self.n_features) / self.n_intervals
mult = np.random.random(self.n_features)
adjacency = mult * np.eye(self.n_features)
if self.n_correlations:
comb = list(permutations(range(self.n_features), 2))
if len(comb) > 1:
idx = itemgetter(
*np.random.choice(range(len(comb)),
size=self.n_correlations,
replace=False))
comb = idx(comb)
for i, j in comb:
adjacency[i, j] = np.random.random(1)
self._set(
'hawkes_exp_kernels',
SimuHawkesExpKernels(adjacency=adjacency,
decays=decays,
baseline=baseline,
verbose=False,
seed=self.seed))
self.hawkes_exp_kernels.adjust_spectral_radius(
.1) # TODO later: allow to change this parameter
hawkes = SimuHawkesMulti(self.hawkes_exp_kernels,
n_simulations=self.n_cases)
run_time = self.n_intervals
hawkes.end_time = [1 * run_time for _ in range(self.n_cases)]
dt = 1
self.hawkes_exp_kernels.track_intensity(dt)
hawkes.simulate()
self.hawkes_obj = hawkes
features = [[
np.min(np.floor(f)) if len(f) > 0 else -1 for f in patient_events
] for patient_events in hawkes.timestamps]
features = [
self.to_coo(feat, (run_time, self.n_features)) for feat in features
]
# Make sure patients have at least one exposure?
exposures_filter = itemgetter(
*[i for i, f in enumerate(features) if f.sum() > 0])
features = exposures_filter(features)
n_samples = len(features)
return features, n_samples
def SimExp(baseline, adjacency, decays, num_clusters, data):
hawkes = SimuHawkesExpKernels(adjacency=adjacency,
decays=decays,
baseline=baseline,
verbose=False)
#dt = 0.001 #millisecond granularity
#hawkes.track_intensity(dt) # turning this on will eat up memory
#need to compute and draw from the cluster length distrbution from the original data
cluster_lengths = ComputeClusterLengths(data)
multi = SimuHawkesMulti(hawkes, n_simulations=num_clusters)
multi.end_time = np.random.choice(cluster_lengths,
size=num_clusters,
replace=True)
multi.simulate()
sim_inner_timestamps = multi.timestamps
l = 0
for realisation in sim_inner_timestamps:
for series in realisation:
l += len(series)
print(f"Simulated {l} points")
return sim_inner_timestamps
def test_simu_hawkes_multi_time_func(self):
"""...Test that hawkes multi works correctly with HawkesKernelTimeFunc
"""
run_time = 100
t_values1 = np.array([0, 1, 1.5], dtype=float)
y_values1 = np.array([0, .2, 0], dtype=float)
tf1 = TimeFunction([t_values1, y_values1],
inter_mode=TimeFunction.InterConstRight,
dt=0.1)
kernel1 = HawkesKernelTimeFunc(tf1)
t_values2 = np.array([0, 2, 2.5], dtype=float)
y_values2 = np.array([0, .6, 0], dtype=float)
tf2 = TimeFunction([t_values2, y_values2],
inter_mode=TimeFunction.InterConstRight,
dt=0.1)
kernel2 = HawkesKernelTimeFunc(tf2)
baseline = np.array([0.1, 0.3])
hawkes = SimuHawkes(baseline=baseline,
end_time=run_time,
verbose=False,
seed=2334)
hawkes.set_kernel(0, 0, kernel1)
hawkes.set_kernel(0, 1, kernel1)
hawkes.set_kernel(1, 0, kernel2)
hawkes.set_kernel(1, 1, kernel2)
hawkes_multi = SimuHawkesMulti(hawkes, n_simulations=5, n_threads=4)
hawkes_multi.simulate()
def test_simu_hawkes_no_seed(self):
"""...Test hawkes multi can be simulated even if no seed is given
"""
T1 = np.array([0, 2, 2.5], dtype=float)
Y1 = np.array([0, .6, 0], dtype=float)
tf = TimeFunction([T1, Y1],
inter_mode=TimeFunction.InterConstRight,
dt=0.1)
kernel = HawkesKernelTimeFunc(tf)
hawkes = SimuHawkes(baseline=[.1], end_time=100, verbose=False)
hawkes.set_kernel(0, 0, kernel)
multi_hawkes_1 = SimuHawkesMulti(hawkes, n_simulations=5)
multi_hawkes_1.simulate()
multi_hawkes_2 = SimuHawkesMulti(hawkes, n_simulations=5)
multi_hawkes_2.simulate()
# If no seed are given, realizations must be different
self.assertNotEqual(multi_hawkes_1.timestamps[0][0][0],
multi_hawkes_2.timestamps[0][0][0])
def simulate_sparse_realization(self):
"""Simulate realization in which some nodes are sometimes empty
"""
baseline = np.array([0.3, 0.001])
adjacency = np.array([[0.5, 0.8], [0., 1.3]])
sim = SimuHawkesExpKernels(adjacency=adjacency,
decays=self.decay,
baseline=baseline,
verbose=False,
seed=13487,
end_time=500)
sim.adjust_spectral_radius(0.8)
multi = SimuHawkesMulti(sim, n_simulations=100)
adjacency = sim.adjacency
multi.simulate()
# Check that some but not all realizations are empty
self.assertGreater(max(map(lambda r: len(r[1]), multi.timestamps)), 1)
self.assertEqual(min(map(lambda r: len(r[1]), multi.timestamps)), 0)
return baseline, adjacency, multi.timestamps
def test_simu_hawkes_multi_seed(self):
"""...Test seeded Hawkes simu is re-seeded under multiple simulations
"""
seed = 504
hawkes = SimuHawkes(kernels=self.kernels,
baseline=self.baseline,
end_time=10,
verbose=False)
seeded_hawkes = SimuHawkes(kernels=self.kernels,
baseline=self.baseline,
end_time=10,
verbose=False,
seed=seed)
multi_1 = SimuHawkesMulti(seeded_hawkes, n_threads=4, n_simulations=1)
multi_2 = SimuHawkesMulti(hawkes, n_threads=4, n_simulations=1)
multi_2.seed = seed
hawkes.seed = seed
multi_3 = SimuHawkesMulti(hawkes, n_threads=4, n_simulations=1)
multi_1.simulate()
multi_2.simulate()
multi_3.simulate()
np.testing.assert_array_equal(multi_1.n_total_jumps,
multi_2.n_total_jumps)
np.testing.assert_array_equal(multi_1.n_total_jumps,
multi_3.n_total_jumps)
timestamps_1 = multi_1.timestamps
timestamps_2 = multi_2.timestamps
timestamps_3 = multi_3.timestamps
self.assertEqual(len(timestamps_1), len(timestamps_2))
self.assertEqual(len(timestamps_1), len(timestamps_3))
for (t1, t2, t3) in zip(timestamps_1, timestamps_2, timestamps_3):
np.testing.assert_array_equal(t1[0], t2[0])
np.testing.assert_array_equal(t1[1], t2[1])
np.testing.assert_array_equal(t1[0], t3[0])
np.testing.assert_array_equal(t1[1], t3[1])
# %% [markdown] # ### SimuHawkesMulti # %% Simulate with Multi hawkes_m1 = SimuHawkes(n_nodes=1, end_time=10000) hawkes_m1.set_baseline(0, 1.) hawkes_m2 = SimuHawkes(n_nodes=1, end_time=10000) hawkes_m2.set_baseline(0, 1.) hawkes_m1.set_kernel(0, 0, kernel_1) hawkes_m2.set_kernel(0, 0, kernel_2) # %% Run Multi multi_1 = SimuHawkesMulti(hawkes_m1, n_simulations=100) multi_1.simulate() multi_2 = SimuHawkesMulti(hawkes_m2, n_simulations=100) multi_2.simulate() # %% Get attributes from Multi multi_1_timestamps = multi_1.timestamps # multi_1_mean_intensity = multi_1.mean_intensity multi_2_timestamps = multi_2.timestamps # multi_2_mean_intensity = multi_2.mean_intensity # %% [markdown] # ## Learning # %% [markdown]
np.random.seed(7168)
n_nodes = 3
baselines = 0.3 * np.ones(n_nodes)
decays = 0.5 + np.random.rand(n_nodes, n_nodes)
adjacency = np.array([
[1, 1, -0.5],
[0, 1, 0],
[0, 0, 2],
], dtype=float)
adjacency /= 4
end_time = 1e5
integration_support = 5
n_realizations = 5
simu_hawkes = SimuHawkesExpKernels(
baseline=baselines, adjacency=adjacency, decays=decays,
end_time=end_time, verbose=False, seed=7168)
simu_hawkes.threshold_negative_intensity(True)
multi = SimuHawkesMulti(simu_hawkes, n_simulations=n_realizations, n_threads=-1)
multi.simulate()
nphc = HawkesCumulantMatching(integration_support, cs_ratio=.15, tol=1e-10,
step=0.3)
nphc.fit(multi.timestamps)
plot_hawkes_kernel_norms(nphc)