def test_8():
# "Sample from a VMHMM and then fit to it"
n_states = 2
vm = VonMisesHMM(n_states=n_states)
means = np.array([[0, 0, 0], [np.pi, np.pi, np.pi]])
kappas = np.array([[1, 2, 3], [2, 3, 4]])
transmat = np.array([[0.9, 0.1], [0.1, 0.9]])
vm.means_ = means
vm.kappas_ = kappas
vm.transmat_ = transmat
x, s = vm.sample(1000)
vm = VonMisesHMM(n_states=2)
vm.fit([x])
mappingcost = np.zeros((n_states, n_states))
for i in range(n_states):
for j in range(n_states):
mappingcost[i, j] = np.sum(
circwrap(vm.means_[i, :] - means[j, :]) ** 2)
mapping = Munkres().compute(mappingcost)
means_ = np.array([vm.means_[j, :] for i, j in mapping])
kappas_ = np.array([vm.kappas_[j, :] for i, j in mapping])
transmat_ = vm.transmat_
print('means\n', means, '\nmeans_\n', means_)
print('kappas\n', kappas, '\nkappas_\n', kappas_)
print('transmat\n', transmat, '\ntransmat_\n', transmat_)
#vm.score(x)
assert np.all(np.abs(kappas - kappas_) < 0.5)
assert np.all(circwrap(means - means_) < 0.25)
def test_3():
transmat = np.array([[0.2, 0.3, 0.5], [0.4, 0.4, 0.2], [0.8, 0.2, 0.0]])
means = np.array([[0.0], [2.0], [4.0]])
kappas = np.array([[8.0], [8.0], [6.0]])
X = [create_timeseries(means, kappas, transmat) for i in range(20)]
# For each value of various options, create a 3 state HMM and see if it is correct.
for reversible_type in ('mle', 'transpose'):
model = VonMisesHMM(n_states=3, reversible_type=reversible_type, thresh=1e-4, n_iter=30)
model.fit(X)
validate_timeseries(means, kappas, transmat, model, 0.1, 0.5, 0.1)
assert abs(model.fit_logprob_[-1]-model.score(X)) < 0.5
def test_2_state():
transmat = np.array([[0.7, 0.3], [0.4, 0.6]])
means = np.array([[0.0], [2.0]])
kappas = np.array([[4.0], [8.0]])
X = [create_timeseries(means, kappas, transmat) for i in range(10)]
# For each value of various options,
# create a 2 state HMM and see if it is correct.
for reversible_type in ('mle', 'transpose'):
model = VonMisesHMM(n_states=2, reversible_type=reversible_type,
thresh=1e-4, n_iter=30)
model.fit(X)
validate_timeseries(means, kappas, transmat, model, 0.1, 0.5, 0.05)
assert abs(model.fit_logprob_[-1] - model.score(X)) < 0.5
def test_code_works():
# creates a 4-state HMM on the ALA2 data. Nothing fancy, just makes
# sure the code runs without erroring out
trajectories = AlanineDipeptide().get_cached().trajectories
topology = trajectories[0].topology
indices = topology.select('symbol C or symbol O or symbol N')
featurizer = DihedralFeaturizer(['phi', 'psi'], trajectories[0][0])
sequences = featurizer.transform(trajectories)
hmm = VonMisesHMM(n_states=4, n_init=1)
hmm.fit(sequences)
assert len(hmm.timescales_ == 3)
assert np.any(hmm.timescales_ > 50)
def test_pipeline():
trajs = AlanineDipeptide().get_cached().trajectories
p = Pipeline([('diheds', DihedralFeaturizer(['phi', 'psi'], sincos=False)),
('hmm', VonMisesHMM(n_states=4))])
predict = p.fit_predict(trajs)
p.named_steps['hmm'].summarize()
def test_code_works():
# creates a 4-state HMM on the ALA2 data. Nothing fancy, just makes
# sure the code runs without erroring out
trajectories = AlanineDipeptide().get_cached().trajectories
topology = trajectories[0].topology
indices = topology.select('symbol C or symbol O or symbol N')
featurizer = DihedralFeaturizer(['phi', 'psi'], trajectories[0][0])
sequences = featurizer.transform(trajectories)
hmm = VonMisesHMM(n_states=4, n_init=1)
hmm.fit(sequences)
assert len(hmm.timescales_ == 3)
assert np.any(hmm.timescales_ > 50)
def test_pickle():
"""Test pickling an HMM"""
trajectories = AlanineDipeptide().get_cached().trajectories
topology = trajectories[0].topology
indices = topology.select('symbol C or symbol O or symbol N')
featurizer = DihedralFeaturizer(['phi', 'psi'], trajectories[0][0])
sequences = featurizer.transform(trajectories)
hmm = VonMisesHMM(n_states=4, n_init=1)
hmm.fit(sequences)
logprob, hidden = hmm.predict(sequences)
with tempfile.TemporaryFile() as savefile:
pickle.dump(hmm, savefile)
savefile.seek(0, 0)
hmm2 = pickle.load(savefile)
logprob2, hidden2 = hmm2.predict(sequences)
assert (logprob == logprob2)
def test_log_likelihood():
n_samples, n_states, n_features = 1000, 27, 16
obs = np.random.rand(n_samples, n_features)
vm = VonMisesHMM(n_states=n_states)
vm.fit([obs])
t0 = time.time()
from scipy.stats.distributions import vonmises
reference = np.array(
[np.sum(vonmises.logpdf(obs, vm.kappas_[i], vm.means_[i]), axis=1)
for i in range(n_states)]).T
t1 = time.time()
value = _vmhmm._compute_log_likelihood(obs, vm.means_, vm.kappas_)
t2 = time.time()
print("Log likeihood timings")
print('reference time ', t1 - t0)
print('c time ', t2 - t1)
np.testing.assert_array_almost_equal(reference, value)
def test_6():
# Test that _c_fitkappa is consistent with the two-step python implementation
np.random.seed(42)
vm = VonMisesHMM(n_states=13)
kappas = np.random.randn(13, 7)
posteriors = np.random.randn(100, 13)
obs = np.random.randn(100, 7)
means = np.random.randn(13, 7)
vm.kappas_ = kappas
vm._c_fitkappas(posteriors, obs, means)
c_kappas = np.copy(vm._kappas_)
vm._py_fitkappas(posteriors, obs, means)
py_kappas = np.copy(vm._kappas_)
np.testing.assert_array_almost_equal(py_kappas, c_kappas)
def test_1():
vm = VonMisesHMM(n_states=5)
gm = GaussianHMM(n_components=5)
X1 = np.random.randn(100, 2)
yield lambda: vm.fit([X1])
yield lambda: gm.fit([X1])
