def ChapmanKolmogorovTest(assignments,
klist=[1, 2, 3, 4, 5],
lagtime=50,
states=None):
msm = MarkovStateModel(lag_time=lagtime, n_timescales=10)
msm.fit(assignments)
p_tau = msm.populations_
T_tau = msm.transmat_
mapping_tau = msm.mapping_
prob_tau_all = []
prob_ktau_all = []
if states == "all" or states is None:
states = range(len(p_tau))
for k in klist:
lagtime_long = k * lagtime
print "long lagtime:", lagtime_long
msm = MarkovStateModel(lag_time=lagtime_long, n_timescales=10)
msm.fit(assignments)
p_ktau = msm.populations_
T_ktau = msm.transmat_
mapping_ktau = msm.mapping_
probability_tau, probability_ktau = CalculateStatesProbability(
T_tau, T_ktau, p_tau, p_ktau, mapping_tau, mapping_ktau, k, states)
prob_tau_all.append(probability_tau)
prob_ktau_all.append(probability_ktau)
return prob_tau_all, prob_ktau_all
def test_counts_no_trim():
# test counts matrix without trimming
model = MarkovStateModel(reversible_type=None, ergodic_cutoff=0)
model.fit([[1, 1, 1, 1, 1, 1, 1, 1, 1]])
eq(model.countsmat_, np.array([[8.0]]))
eq(model.mapping_, {1: 0})
def test_1():
# test counts matrix without trimming
model = MarkovStateModel(reversible_type=None, ergodic_cutoff=0)
model.fit([[1, 1, 1, 1, 1, 1, 1, 1, 1]])
eq(model.countsmat_, np.array([[8.0]]))
eq(model.mapping_, {1: 0})
def test_13():
model = MarkovStateModel(n_timescales=2)
model.fit([[0, 0, 0, 1, 2, 1, 0, 0, 0, 1, 3, 3, 3, 1, 1, 2, 2, 0, 0]])
left_right = np.dot(model.left_eigenvectors_.T, model.right_eigenvectors_)
# check biorthonormal
np.testing.assert_array_almost_equal(
left_right,
np.eye(3))
# check that the stationary left eigenvector is normalized to be 1
np.testing.assert_almost_equal(model.left_eigenvectors_[:, 0].sum(), 1)
# the left eigenvectors satisfy <\phi_i, \phi_i>_{\mu^{-1}} = 1
for i in range(3):
np.testing.assert_almost_equal(
np.dot(model.left_eigenvectors_[:, i],
model.left_eigenvectors_[:, i] / model.populations_), 1)
# and that the right eigenvectors satisfy <\psi_i, \psi_i>_{\mu} = 1
for i in range(3):
np.testing.assert_almost_equal(
np.dot(model.right_eigenvectors_[:, i],
model.right_eigenvectors_[:, i] *
model.populations_), 1)
def test_both():
sequences = [np.random.randint(20, size=1000) for _ in range(10)]
lag_times = [1, 5, 10]
models_ref = []
for tau in lag_times:
msm = MarkovStateModel(reversible_type='mle', lag_time=tau,
n_timescales=10)
msm.fit(sequences)
models_ref.append(msm)
timescales_ref = [m.timescales_ for m in models_ref]
model = MarkovStateModel(reversible_type='mle', lag_time=1, n_timescales=10)
models = param_sweep(model, sequences, {'lag_time': lag_times}, n_jobs=2)
timescales = implied_timescales(sequences, lag_times, msm=model,
n_timescales=10, n_jobs=2)
print(timescales)
print(timescales_ref)
if np.abs(models[0].transmat_ - models[1].transmat_).sum() < 1E-6:
raise Exception("you wrote a bad test.")
for i in range(len(lag_times)):
npt.assert_array_almost_equal(models[i].transmat_,
models_ref[i].transmat_)
npt.assert_array_almost_equal(timescales_ref[i], timescales[i])
def test_both():
model = MarkovStateModel(
reversible_type='mle', lag_time=1, n_timescales=1)
# note this might break it if we ask for more than 1 timescale
sequences = np.random.randint(20, size=(10, 1000))
lag_times = [1, 5, 10]
models_ref = []
for tau in lag_times:
msm = MarkovStateModel(
reversible_type='mle', lag_time=tau, n_timescales=10)
msm.fit(sequences)
models_ref.append(msm)
timescales_ref = [m.timescales_ for m in models_ref]
models = param_sweep(msm, sequences, {'lag_time' : lag_times}, n_jobs=2)
timescales = implied_timescales(sequences, lag_times, msm=msm,
n_timescales=10, n_jobs=2)
print(timescales)
print(timescales_ref)
if np.abs(models[0].transmat_ - models[1].transmat_).sum() < 1E-6:
raise Exception("you wrote a bad test.")
for i in range(len(lag_times)):
models[i].lag_time = lag_times[i]
npt.assert_array_almost_equal(models[i].transmat_, models_ref[i].transmat_)
npt.assert_array_almost_equal(timescales_ref[i], timescales[i])
def test_partial_transform():
model = MarkovStateModel()
model.fit([['a', 'a', 'b', 'b', 'c', 'c', 'a', 'a']])
assert model.mapping_ == {'a': 0, 'b': 1, 'c': 2}
v = model.partial_transform(['a', 'b', 'c'])
assert isinstance(v, list)
assert len(v) == 1
assert v[0].dtype == np.int
np.testing.assert_array_equal(v[0], [0, 1, 2])
v = model.partial_transform(['a', 'b', 'c', 'd'], 'clip')
assert isinstance(v, list)
assert len(v) == 1
assert v[0].dtype == np.int
np.testing.assert_array_equal(v[0], [0, 1, 2])
v = model.partial_transform(['a', 'b', 'c', 'd'], 'fill')
assert isinstance(v, np.ndarray)
assert len(v) == 4
assert v.dtype == np.float
np.testing.assert_array_equal(v, [0, 1, 2, np.nan])
v = model.partial_transform(['a', 'a', 'SPLIT', 'b', 'b', 'b'], 'clip')
assert isinstance(v, list)
assert len(v) == 2
assert v[0].dtype == np.int
assert v[1].dtype == np.int
np.testing.assert_array_equal(v[0], [0, 0])
np.testing.assert_array_equal(v[1], [1, 1, 1])
def case1():
map_id = 40
for p_id in range(6383, 6391):
assignments = np.load('Assignments-%d.fixed.Map%d.npy' %
(p_id, map_id))
cv = KFold(len(assignments), n_folds=10)
lagtime = 50
msm = MarkovStateModel(lag_time=lagtime)
pops = []
msmts = []
for fold, (train_index, test_index) in enumerate(cv):
assignments_train = assignments[train_index]
msm.fit(assignments_train)
if len(msm.populations_) == 40:
pops.append(msm.populations_)
msmts.append(msm.timescales_)
output_dir = "Data-%d-macro%d" % (p_id, map_id)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
fn_populations = os.path.join(output_dir, "Populations-10fold.npy")
fn_msmts = os.path.join(output_dir, "ImpliedTimescales-10fold.npy")
np.save(fn_populations, pops)
np.save(fn_msmts, msmts)
print "Saved: {},{}".format(fn_populations, fn_msmts)
def test_10():
# test inverse transform
model = MarkovStateModel(reversible_type=None, ergodic_cutoff=0)
model.fit([['a', 'b', 'c', 'a', 'a', 'b']])
v = model.inverse_transform([[0, 1, 2]])
assert len(v) == 1
np.testing.assert_array_equal(v[0], ['a', 'b', 'c'])
def test_10():
# test inverse transform
model = MarkovStateModel(reversible_type=None, ergodic_cutoff=0)
model.fit([['a', 'b', 'c', 'a', 'a', 'b']])
v = model.inverse_transform([[0, 1, 2]])
assert len(v) == 1
np.testing.assert_array_equal(v[0], ['a', 'b', 'c'])
def test_fluxes_1():
# depends on tpt.committors
msm = MarkovStateModel(lag_time=1)
assignments = np.random.randint(3, size=(10, 1000))
msm.fit(assignments)
tprob = msm.transmat_
pop = msm.populations_
# forward committors
qplus = tpt.committors(0, 2, msm)
ref_fluxes = np.zeros((3, 3))
ref_net_fluxes = np.zeros((3, 3))
for i in range(3):
for j in range(3):
if i != j:
# Eq. 2.24 in Metzner et al. Transition Path Theory.
# Multiscale Model. Simul. 2009, 7, 1192-1219.
ref_fluxes[i, j] = (pop[i] * tprob[i, j] *
(1 - qplus[i]) * qplus[j])
for i in range(3):
for j in range(3):
ref_net_fluxes[i, j] = np.max([0, ref_fluxes[i, j] -
ref_fluxes[j, i]])
fluxes = tpt.fluxes(0, 2, msm)
net_fluxes = tpt.net_fluxes(0, 2, msm)
npt.assert_array_almost_equal(ref_fluxes, fluxes)
npt.assert_array_almost_equal(ref_net_fluxes, net_fluxes)
def test_harder_hubscore():
# depends on tpt.committors and tpt.conditional_committors
assignments = np.random.randint(10, size=(10, 1000))
msm = MarkovStateModel(lag_time=1)
msm.fit(assignments)
hub_scores = tpt.hub_scores(msm)
ref_hub_scores = np.zeros(10)
for A in range(10):
for B in range(10):
committors = tpt.committors(A, B, msm)
denom = msm.transmat_[A, :].dot(committors)
for C in range(10):
if A == B or A == C or B == C:
continue
cond_committors = tpt.conditional_committors(A, B, C, msm)
temp = 0.0
for i in range(10):
if i in [A, B]:
continue
temp += cond_committors[i] * msm.transmat_[A, i]
temp /= denom
ref_hub_scores[C] += temp
ref_hub_scores /= (9 * 8)
npt.assert_array_almost_equal(ref_hub_scores, hub_scores)
def test_harder_hubscore():
# depends on tpt.committors and tpt.conditional_committors
assignments = np.random.randint(10, size=(10, 1000))
msm = MarkovStateModel(lag_time=1)
msm.fit(assignments)
hub_scores = tpt.hub_scores(msm)
ref_hub_scores = np.zeros(10)
for A in xrange(10):
for B in xrange(10):
committors = tpt.committors(A, B, msm)
denom = msm.transmat_[A, :].dot(committors) #+ msm.transmat_[A, B]
for C in xrange(10):
if A == B or A == C or B == C:
continue
cond_committors = tpt.conditional_committors(A, B, C, msm)
temp = 0.0
for i in xrange(10):
if i in [A, B]:
continue
temp += cond_committors[i] * msm.transmat_[A, i]
temp /= denom
ref_hub_scores[C] += temp
ref_hub_scores /= (9 * 8)
#print(ref_hub_scores, hub_scores)
npt.assert_array_almost_equal(ref_hub_scores, hub_scores)
def test_cond_committors():
# depends on tpt.committors
msm = MarkovStateModel(lag_time=1)
assignments = np.random.randint(4, size=(10, 1000))
msm.fit(assignments)
tprob = msm.transmat_
for_committors = tpt.committors(0, 3, msm)
cond_committors = tpt.conditional_committors(0, 3, 2, msm)
# The committor for state one can be decomposed into paths that
# do and do not visit state 2 along the way. The paths that do not
# visit state 1 must look like 1, 1, 1, ..., 1, 1, 3. So we can
# compute them with a similar approximation as the forward committor
# Since we want the other component of the forward committor, we
# subtract that probability from the forward committor
ref = for_committors[1] - np.power(tprob[1, 1], np.arange(5000)).sum() * tprob[1, 3]
#print (ref / for_committors[1])
ref = [0, ref, for_committors[2], 0]
#print(cond_committors, ref)
npt.assert_array_almost_equal(ref, cond_committors)
def test_cond_committors():
# depends on tpt.committors
msm = MarkovStateModel(lag_time=1)
assignments = np.random.randint(4, size=(10, 1000))
msm.fit(assignments)
tprob = msm.transmat_
for_committors = tpt.committors(0, 3, msm)
cond_committors = tpt.conditional_committors(0, 3, 2, msm)
# The committor for state one can be decomposed into paths that
# do and do not visit state 2 along the way. The paths that do not
# visit state 1 must look like 1, 1, 1, ..., 1, 1, 3. So we can
# compute them with a similar approximation as the forward committor
# Since we want the other component of the forward committor, we
# subtract that probability from the forward committor
ref = for_committors[1] - np.power(tprob[1, 1],
np.arange(5000)).sum() * tprob[1, 3]
#print (ref / for_committors[1])
ref = [0, ref, for_committors[2], 0]
#print(cond_committors, ref)
npt.assert_array_almost_equal(ref, cond_committors)
def test_fluxes():
# depends on tpt.committors
msm = MarkovStateModel(lag_time=1)
assignments = np.random.randint(3, size=(10, 1000))
msm.fit(assignments)
tprob = msm.transmat_
pop = msm.populations_
# forward committors
qplus = tpt.committors(0, 2, msm)
ref_fluxes = np.zeros((3, 3))
ref_net_fluxes = np.zeros((3, 3))
for i in xrange(3):
for j in xrange(3):
if i != j:
# Eq. 2.24 in Metzner et al. Transition Path Theory.
# Multiscale Model. Simul. 2009, 7, 1192-1219.
ref_fluxes[i, j] = (pop[i] * tprob[i, j] * (1 - qplus[i]) *
qplus[j])
for i in xrange(3):
for j in xrange(3):
ref_net_fluxes[i, j] = np.max(
[0, ref_fluxes[i, j] - ref_fluxes[j, i]])
fluxes = tpt.fluxes(0, 2, msm)
net_fluxes = tpt.net_fluxes(0, 2, msm)
# print(fluxes)
# print(ref_fluxes)
npt.assert_array_almost_equal(ref_fluxes, fluxes)
npt.assert_array_almost_equal(ref_net_fluxes, net_fluxes)
def test_13():
model = MarkovStateModel(n_timescales=2)
model.fit([[0, 0, 0, 1, 2, 1, 0, 0, 0, 1, 3, 3, 3, 1, 1, 2, 2, 0, 0]])
left_right = np.dot(model.left_eigenvectors_.T, model.right_eigenvectors_)
# check biorthonormal
np.testing.assert_array_almost_equal(
left_right,
np.eye(3))
# check that the stationary left eigenvector is normalized to be 1
np.testing.assert_almost_equal(model.left_eigenvectors_[:, 0].sum(), 1)
# the left eigenvectors satisfy <\phi_i, \phi_i>_{\mu^{-1}} = 1
for i in range(3):
np.testing.assert_almost_equal(
np.dot(model.left_eigenvectors_[:, i],
model.left_eigenvectors_[:, i] / model.populations_), 1)
# and that the right eigenvectors satisfy <\psi_i, \psi_i>_{\mu} = 1
for i in range(3):
np.testing.assert_almost_equal(
np.dot(model.right_eigenvectors_[:, i],
model.right_eigenvectors_[:, i] *
model.populations_), 1)
def test_counts_2():
# test counts matrix with trimming
model = MarkovStateModel(reversible_type=None, ergodic_cutoff=1)
model.fit([[1, 1, 1, 1, 1, 1, 1, 1, 1, 2]])
eq(model.mapping_, {1: 0})
eq(model.countsmat_, np.array([[8]]))
def test_partial_transform():
model = MarkovStateModel()
model.fit([['a', 'a', 'b', 'b', 'c', 'c', 'a', 'a']])
assert model.mapping_ == {'a': 0, 'b': 1, 'c': 2}
v = model.partial_transform(['a', 'b', 'c'])
assert isinstance(v, list)
assert len(v) == 1
assert v[0].dtype == np.int
np.testing.assert_array_equal(v[0], [0, 1, 2])
v = model.partial_transform(['a', 'b', 'c', 'd'], 'clip')
assert isinstance(v, list)
assert len(v) == 1
assert v[0].dtype == np.int
np.testing.assert_array_equal(v[0], [0, 1, 2])
v = model.partial_transform(['a', 'b', 'c', 'd'], 'fill')
assert isinstance(v, np.ndarray)
assert len(v) == 4
assert v.dtype == np.float
np.testing.assert_array_equal(v, [0, 1, 2, np.nan])
v = model.partial_transform(['a', 'a', 'SPLIT', 'b', 'b', 'b'], 'clip')
assert isinstance(v, list)
assert len(v) == 2
assert v[0].dtype == np.int
assert v[1].dtype == np.int
np.testing.assert_array_equal(v[0], [0, 0])
np.testing.assert_array_equal(v[1], [1, 1, 1])
def test_counts_2():
# test counts matrix with trimming
model = MarkovStateModel(reversible_type=None, ergodic_cutoff=1)
model.fit([[1, 1, 1, 1, 1, 1, 1, 1, 1, 2]])
eq(model.mapping_, {1: 0})
eq(model.countsmat_, np.array([[8]]))
def test_both():
model = MarkovStateModel(reversible_type="mle", lag_time=1, n_timescales=1)
# note this might break it if we ask for more than 1 timescale
sequences = np.random.randint(20, size=(10, 1000))
lag_times = [1, 5, 10]
models_ref = []
for tau in lag_times:
msm = MarkovStateModel(reversible_type="mle", lag_time=tau, n_timescales=10)
msm.fit(sequences)
models_ref.append(msm)
timescales_ref = [m.timescales_ for m in models_ref]
models = param_sweep(msm, sequences, {"lag_time": lag_times}, n_jobs=2)
timescales = implied_timescales(sequences, lag_times, msm=msm, n_timescales=10, n_jobs=2)
print(timescales)
print(timescales_ref)
if np.abs(models[0].transmat_ - models[1].transmat_).sum() < 1e-6:
raise Exception("you wrote a bad test.")
for i in range(len(lag_times)):
models[i].lag_time = lag_times[i]
npt.assert_array_almost_equal(models[i].transmat_, models_ref[i].transmat_)
npt.assert_array_almost_equal(timescales_ref[i], timescales[i])
def test_51():
# test score_ll
model = MarkovStateModel(reversible_type='mle')
sequence = ['a', 'a', 'b', 'b', 'a', 'a', 'b', 'b', 'c', 'c', 'c', 'a', 'a']
model.fit([sequence])
assert model.mapping_ == {'a': 0, 'b': 1, 'c': 2}
score_ac = model.score_ll([['a', 'c']])
assert score_ac == np.log(model.transmat_[0, 2])
def test_mle_eq():
seq = [[0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1]]
mle_mdl = MarkovStateModel(lag_time=1)
b_mdl = BootStrapMarkovStateModel(n_samples=10, n_procs=2, msm_args={'lag_time': 1})
mle_mdl.fit(seq)
b_mdl.fit(seq)
#make sure we have good model
eq(mle_mdl.populations_, b_mdl.mle_.populations_)
eq(mle_mdl.timescales_, b_mdl.mle_.timescales_)
def test_from_msm():
assignments, _ = _metastable_system()
msm = MarkovStateModel()
msm.fit(assignments)
pcca = PCCA.from_msm(msm, 2)
msm = MarkovStateModel()
msm.fit(assignments)
pccaplus = PCCAPlus.from_msm(msm, 2)
def test_51():
# test score_ll
model = MarkovStateModel(reversible_type='mle')
sequence = ['a', 'a', 'b', 'b', 'a', 'a', 'b', 'b', 'c', 'c', 'c', 'a', 'a']
model.fit([sequence])
assert model.mapping_ == {'a': 0, 'b': 1, 'c': 2}
score_ac = model.score_ll([['a', 'c']])
assert score_ac == np.log(model.transmat_[0, 2])
def test_6():
# test score_ll with novel entries
model = MarkovStateModel(reversible_type='mle')
sequence = ['a', 'a', 'b', 'b', 'a', 'a', 'b', 'b']
model.fit([sequence])
assert not np.isfinite(model.score_ll([['c']]))
assert not np.isfinite(model.score_ll([['c', 'c']]))
assert not np.isfinite(model.score_ll([['a', 'c']]))
def test_from_msm():
assignments, _ = _metastable_system()
msm = MarkovStateModel()
msm.fit(assignments)
pcca = PCCA.from_msm(msm, 2)
msm = MarkovStateModel()
msm.fit(assignments)
pccaplus = PCCAPlus.from_msm(msm, 2)
def test_6():
# test score_ll with novel entries
model = MarkovStateModel(reversible_type='mle')
sequence = ['a', 'a', 'b', 'b', 'a', 'a', 'b', 'b']
model.fit([sequence])
assert not np.isfinite(model.score_ll([['c']]))
assert not np.isfinite(model.score_ll([['c', 'c']]))
assert not np.isfinite(model.score_ll([['a', 'c']]))
def at_lagtime(lt):
msm = MarkovStateModel(lag_time=lt, n_timescales=10, verbose=False)
msm.fit(list(ktrajs.values()))
ret = {
'lag_time': lt,
'percent_retained': msm.percent_retained_,
}
for i in range(msm.n_timescales):
ret['timescale_{}'.format(i)] = msm.timescales_[i]
return ret
def test_plot_implied_timescales(self):
lag_times = [1, 50, 100, 250, 500, 1000, 5000]
msm_objs = []
for lag in lag_times:
# Construct MSM
msm = MarkovStateModel(lag_time=lag, n_timescales=5)
msm.fit(data)
msm_objs.append(msm)
ax = plot_implied_timescales(msm_objs)
assert isinstance(ax, SubplotBase)
def test_plot_implied_timescales():
lag_times = [1, 50, 100, 250, 500, 1000, 5000]
msm_objs = []
for lag in lag_times:
# Construct MSM
msm = MarkovStateModel(lag_time=lag, n_timescales=5)
msm.fit(data)
msm_objs.append(msm)
ax = plot_implied_timescales(msm_objs)
assert isinstance(ax, SubplotBase)
def test_mfpt_match():
assignments = np.random.randint(10, size=(10, 2000))
msm = MarkovStateModel(lag_time=1)
msm.fit(assignments)
# these two do different things
mfpts0 = np.vstack([tpt.mfpts(msm, i) for i in range(10)]).T
mfpts1 = tpt.mfpts(msm)
npt.assert_array_almost_equal(mfpts0, mfpts1)
def at_lagtime(lt, clustered_trajs):
msm = MarkovStateModel(lag_time=lt, n_timescales=20, verbose=False)
msm.fit(clustered_trajs)
ret = {
'lag_time': lt,
'percent_retained': msm.percent_retained_,
}
for i in range(msm.n_timescales):
ret['timescale_{}'.format(i)] = msm.timescales_[i]
return ret
def at_lagtime(lt):
msm = MarkovStateModel(lag_time=lt, n_timescales=10, verbose=False)
msm.fit(list(ktrajs.values()))
ret = {
'lag_time': lt,
'percent_retained': msm.percent_retained_,
}
for i in range(msm.n_timescales):
ret['timescale_{}'.format(i)] = msm.timescales_[i]
return ret
def test_score_1():
# test that GMRQ is equal to the sum of the first n eigenvalues,
# when testing and training on the same dataset.
sequence = [0, 0, 0, 1, 1, 1, 2, 2, 2, 1, 1, 1,
0, 0, 0, 1, 2, 2, 2, 1, 1, 1, 0, 0]
for n in [0, 1, 2]:
model = MarkovStateModel(verbose=False, n_timescales=n)
model.fit([sequence])
assert_approx_equal(model.score([sequence]), model.eigenvalues_.sum())
assert_approx_equal(model.score([sequence]), model.score_)
def test_fit_1():
# call fit, compare to MSM
sequence = [0, 0, 0, 1, 1, 1, 0, 0, 2, 2, 0, 1, 1, 1, 2, 2, 2, 2, 2]
model = ContinuousTimeMSM(verbose=False)
model.fit([sequence])
msm = MarkovStateModel(verbose=False)
msm.fit([sequence])
# they shouldn't be equal in general, but for this input they seem to be
np.testing.assert_array_almost_equal(model.transmat_, msm.transmat_)
def test_score_1():
# test that GMRQ is equal to the sum of the first n eigenvalues,
# when testing and training on the same dataset.
sequence = [0, 0, 0, 1, 1, 1, 2, 2, 2, 1, 1, 1,
0, 0, 0, 1, 2, 2, 2, 1, 1, 1, 0, 0]
for n in [0, 1, 2]:
model = MarkovStateModel(verbose=False, n_timescales=n)
model.fit([sequence])
assert_approx_equal(model.score([sequence]), model.eigenvalues_.sum())
assert_approx_equal(model.score([sequence]), model.score_)
def test_mle_eq():
seq = [[0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1]]
mle_mdl = MarkovStateModel(lag_time=1)
b_mdl = BootStrapMarkovStateModel(n_samples=10,
n_procs=2,
msm_args={'lag_time': 1})
mle_mdl.fit(seq)
b_mdl.fit(seq)
#make sure we have good model
eq(mle_mdl.populations_, b_mdl.mle_.populations_)
eq(mle_mdl.timescales_, b_mdl.mle_.timescales_)
def test_fit_1():
# call fit, compare to MSM
sequence = [0, 0, 0, 1, 1, 1, 0, 0, 2, 2, 0, 1, 1, 1, 2, 2, 2, 2, 2]
model = ContinuousTimeMSM(verbose=False)
model.fit([sequence])
msm = MarkovStateModel(verbose=False)
msm.fit([sequence])
# they shouldn't be equal in general, but for this input they seem to be
np.testing.assert_array_almost_equal(model.transmat_, msm.transmat_)
def test_11():
# test sample
model = MarkovStateModel()
model.fit([[0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 2, 2, 0, 0]])
sample = model.sample_discrete(n_steps=1000, random_state=0)
assert isinstance(sample, np.ndarray)
assert len(sample) == 1000
bc = np.bincount(sample)
diff = model.populations_ - (bc / np.sum(bc))
assert np.sum(np.abs(diff)) < 0.1
def test_11():
# test sample
model = MarkovStateModel()
model.fit([[0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 2, 2, 0, 0]])
sample = model.sample_discrete(n_steps=1000, random_state=0)
assert isinstance(sample, np.ndarray)
assert len(sample) == 1000
bc = np.bincount(sample)
diff = model.populations_ - (bc / np.sum(bc))
assert np.sum(np.abs(diff)) < 0.1
def case2_micro_combined():
assignments = np.load('Assignments.npy')
lagtime = 50
msmts = []
msm = MarkovStateModel(lag_time=lagtime)
cv = KFold(len(assignments), n_folds=10)
for fold, (train_index, test_index) in enumerate(cv):
assignments_train = assignments[train_index]
msm.fit(assignments_train)
msmts.append(msm.timescales_)
fn_msmts = os.path.join('Data-combined', "ImpliedTimescales-10fold.npy")
np.save(fn_msmts, msmts)
print "Saved: {}".format(fn_msmts)
def test_mfpt_match():
assignments = np.random.randint(10, size=(10, 2000))
msm = MarkovStateModel(lag_time=1)
msm.fit(assignments)
# these two do different things
mfpts0 = np.vstack([tpt.mfpts(msm, i) for i in xrange(10)]).T
mfpts1 = tpt.mfpts(msm)
# print(mfpts0)
# print(mfpts1)
npt.assert_array_almost_equal(mfpts0, mfpts1)
def implied_times():
i_times = np.zeros((len(lag_times), 20))
for i in range(len(lag_times)):
msm = MarkovStateModel(lag_time=lag_times[i],
n_timescales=20,
reversible_type='transpose',
ergodic_cutoff='off',
prior_counts=0,
sliding_window=True,
verbose=True)
msm.fit(sequences)
i_times[i] = msm.eigenvalues_[1:]
print "lag time, msm eigenvalues:", lag_times[i], msm.eigenvalues_
def test_eigtransform_2():
model = MarkovStateModel(n_timescales=2)
traj = [4, 3, 0, 0, 0, 1, 2, 1, 0, 0, 0, 1, 0, 1, 1, 2, 2, 0, 0]
model.fit([traj])
transformed_0 = model.eigtransform([traj], mode='clip')
# clip off the first two states (not ergodic)
assert transformed_0[0].shape == (len(traj) - 2, model.n_timescales)
transformed_1 = model.eigtransform([traj], mode='fill')
assert transformed_1[0].shape == (len(traj), model.n_timescales)
assert np.all(np.isnan(transformed_1[0][:2, :]))
assert not np.any(np.isnan(transformed_1[0][2:]))
def test_12():
# test eigtransform
model = MarkovStateModel(n_timescales=1)
model.fit([[4, 3, 0, 0, 0, 1, 2, 1, 0, 0, 0, 1, 0, 1, 1, 2, 2, 0, 0]])
assert model.mapping_ == {0: 0, 1: 1, 2: 2}
assert len(model.eigenvalues_) == 2
t = model.eigtransform([[0, 1]], right=True)
assert t[0][0] == model.right_eigenvectors_[0, 1]
assert t[0][1] == model.right_eigenvectors_[1, 1]
s = model.eigtransform([[0, 1]], right=False)
assert s[0][0] == model.left_eigenvectors_[0, 1]
assert s[0][1] == model.left_eigenvectors_[1, 1]
def test_eigtransform_2():
model = MarkovStateModel(n_timescales=2)
traj = [4, 3, 0, 0, 0, 1, 2, 1, 0, 0, 0, 1, 0, 1, 1, 2, 2, 0, 0]
model.fit([traj])
transformed_0 = model.eigtransform([traj], mode='clip')
# clip off the first two states (not ergodic)
assert transformed_0[0].shape == (len(traj) - 2, model.n_timescales)
transformed_1 = model.eigtransform([traj], mode='fill')
assert transformed_1[0].shape == (len(traj), model.n_timescales)
assert np.all(np.isnan(transformed_1[0][:2, :]))
assert not np.any(np.isnan(transformed_1[0][2:]))
def test_12():
# test eigtransform
model = MarkovStateModel(n_timescales=1)
model.fit([[4, 3, 0, 0, 0, 1, 2, 1, 0, 0, 0, 1, 0, 1, 1, 2, 2, 0, 0]])
assert model.mapping_ == {0: 0, 1: 1, 2: 2}
assert len(model.eigenvalues_) == 2
t = model.eigtransform([[0, 1]], right=True)
assert t[0][0] == model.right_eigenvectors_[0, 1]
assert t[0][1] == model.right_eigenvectors_[1, 1]
s = model.eigtransform([[0, 1]], right=False)
assert s[0][0] == model.left_eigenvectors_[0, 1]
assert s[0][1] == model.left_eigenvectors_[1, 1]
def build_msm():
assigns = []
for i in range(64):
assigns.append(np.loadtxt('macro12_assigns_%d.txt' % i, dtype=int))
# 40 ns
msm = MarkovStateModel(lag_time=500,
n_timescales=20,
reversible_type='transpose',
ergodic_cutoff='off',
prior_counts=0,
sliding_window=True,
verbose=True)
msm.fit(assigns)
return msm
def cluster_msm(sequences,n_states, lag_times):
for n in n_states:
states = KMeans(n_clusters=n)
states.fit(sequences)
io.dump(states,str(n)+'n_cl.pkl')
ts=np.zeros(5)
for lag_time in lag_times:
msm = MarkovStateModel(lag_time=lag_time, verbose=False,n_timescales=5)
msm.fit(states.labels_)
ts1=msm.timescales_
ts=np.vstack((ts,ts1))
io.dump(msm,str(n)+'n_'+str(lag_time)+'lt_msm.pkl')
ts=np.delete(ts, (0), axis=0)
io.dump(ts,str(n)+'n_timescales.pkl')
class TestModelUtils:
def setUp(self):
numpy.random.seed(12)
self.msm = MarkovStateModel()
self.msm.fit([numpy.random.randint(5, size=10) for _ in range(20)
] # 20 lists of 10 random integers from 0 to 5
)
def test_retrieveMSM(self):
msm = retrieve_MSM(model)
assert isinstance(msm, MarkovStateModel)
def test_retrieve_clusterer(self):
clusterer = retrieve_clusterer(model)
assert isinstance(clusterer, MiniBatchKMeans)
def test_retrieve_feat(self):
feat = retrieve_feat(model)
assert isinstance(feat, DihedralFeaturizer)
def test_retrieve_scaler(self):
scaler = retrieve_scaler(model)
assert isinstance(scaler, MinMaxScaler)
def test_retrieve_decomposer(self):
decomposer = retrieve_decomposer(model)
assert isinstance(decomposer, tICA)
def test_apply_percentile_search1(self):
counts = apply_percentile_search(
count_array=self.msm.transmat_,
percentile=0.1,
desired_length=10,
search_type='clusterer',
msm=None,
)
assert isinstance(counts, list)
assert len(counts) == 10
def test_apply_percentile_search2(self):
counts = apply_percentile_search(
count_array=self.msm.transmat_,
percentile=0.1,
desired_length=2,
search_type='msm',
msm=self.msm,
)
assert isinstance(counts, list)
assert len(counts) == 2
def test_5():
trjs = DoubleWell(random_state=0).get_cached().trajectories
clusterer = NDGrid(n_bins_per_feature=5)
mle_msm = MarkovStateModel(lag_time=100, verbose=False)
b_msm = BayesianMarkovStateModel(lag_time=100, n_samples=1000, n_chains=8, n_steps=1000, random_state=0)
states = clusterer.fit_transform(trjs)
b_msm.fit(states)
mle_msm.fit(states)
# this is a pretty silly test. it checks that the mean transition
# matrix is not so dissimilar from the MLE transition matrix.
# This shouldn't necessarily be the case anyways -- the likelihood is
# not "symmetric". And the cutoff chosen is just heuristic.
assert np.linalg.norm(b_msm.all_transmats_.mean(axis=0) - mle_msm.transmat_) < 1e-2
def test_9():
# what if the input data contains NaN? They should be ignored
model = MarkovStateModel(ergodic_cutoff=0)
seq = [0, 1, 0, 1, np.nan]
model.fit(seq)
assert model.n_states_ == 2
assert model.mapping_ == {0: 0, 1: 1}
if not PY3:
model = MarkovStateModel()
seq = [0, 1, 0, None, 0, 1]
model.fit(seq)
assert model.n_states_ == 2
assert model.mapping_ == {0: 0, 1: 1}
def test_9():
# what if the input data contains NaN? They should be ignored
model = MarkovStateModel(ergodic_cutoff=0)
seq = [0, 1, 0, 1, np.nan]
model.fit(seq)
assert model.n_states_ == 2
assert model.mapping_ == {0: 0, 1: 1}
if not PY3:
model = MarkovStateModel()
seq = [0, 1, 0, None, 0, 1]
model.fit(seq)
assert model.n_states_ == 2
assert model.mapping_ == {0: 0, 1: 1}
def test_3():
model = MarkovStateModel(reversible_type='mle')
model.fit([[0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 2, 2, 2, 2, 0, 0, 0]])
counts = np.array([[8, 1, 1], [1, 3, 0], [1, 0, 3]])
eq(model.countsmat_, counts)
assert np.sum(model.populations_) == 1.0
model.timescales_
# test pickleable
try:
dump(model, 'test-msm-temp.npy', compress=1)
model2 = load('test-msm-temp.npy')
eq(model2.timescales_, model.timescales_)
finally:
os.unlink('test-msm-temp.npy')
def test_3():
model = MarkovStateModel(reversible_type='mle')
model.fit([[0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 2, 2, 2, 2, 0, 0, 0]])
counts = np.array([[8, 1, 1], [1, 3, 0], [1, 0, 3]])
eq(model.countsmat_, counts)
assert np.sum(model.populations_) == 1.0
model.timescales_
# test pickleable
try:
dump(model, 'test-msm-temp.npy', compress=1)
model2 = load('test-msm-temp.npy')
eq(model2.timescales_, model.timescales_)
finally:
os.unlink('test-msm-temp.npy')
def test_score_ll_1():
model = MarkovStateModel(reversible_type='mle')
sequence = ['a', 'a', 'b', 'b', 'a', 'a', 'b', 'b']
model.fit([sequence])
assert model.mapping_ == {'a': 0, 'b': 1}
score_aa = model.score_ll([['a', 'a']])
assert score_aa == np.log(model.transmat_[0, 0])
score_bb = model.score_ll([['b', 'b']])
assert score_bb == np.log(model.transmat_[1, 1])
score_ab = model.score_ll([['a', 'b']])
assert score_ab == np.log(model.transmat_[0, 1])
score_abb = model.score_ll([['a', 'b', 'b']])
assert score_abb == (np.log(model.transmat_[0, 1]) +
np.log(model.transmat_[1, 1]))
assert model.state_labels_ == ['a', 'b']
assert np.sum(model.populations_) == 1.0
def test_score_ll_1():
model = MarkovStateModel(reversible_type='mle')
sequence = ['a', 'a', 'b', 'b', 'a', 'a', 'b', 'b']
model.fit([sequence])
assert model.mapping_ == {'a': 0, 'b': 1}
score_aa = model.score_ll([['a', 'a']])
assert score_aa == np.log(model.transmat_[0, 0])
score_bb = model.score_ll([['b', 'b']])
assert score_bb == np.log(model.transmat_[1, 1])
score_ab = model.score_ll([['a', 'b']])
assert score_ab == np.log(model.transmat_[0, 1])
score_abb = model.score_ll([['a', 'b', 'b']])
assert score_abb == (np.log(model.transmat_[0, 1]) +
np.log(model.transmat_[1, 1]))
assert model.state_labels_ == ['a', 'b']
assert np.sum(model.populations_) == 1.0
def test_3():
model = MarkovStateModel(reversible_type='mle')
model.fit([[0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 2, 2, 2, 2, 0, 0, 0]])
counts = np.array([[8, 1, 1], [1, 3, 0], [1, 0, 3]])
eq(model.countsmat_, counts)
assert np.sum(model.populations_) == 1.0
model.timescales_
# test pickleable
try:
dir = tempfile.mkdtemp()
fn = os.path.join(dir, 'test-msm-temp.npy')
dump(model, fn, compress=1)
model2 = load(fn)
eq(model2.timescales_, model.timescales_)
finally:
os.unlink(fn)
os.rmdir(dir)
def test_hessian():
grid = NDGrid(n_bins_per_feature=10, min=-np.pi, max=np.pi)
seqs = grid.fit_transform(load_doublewell(random_state=0)['trajectories'])
seqs = [seqs[i] for i in range(10)]
lag_time = 10
model = ContinuousTimeMSM(verbose=True, lag_time=lag_time)
model.fit(seqs)
msm = MarkovStateModel(verbose=False, lag_time=lag_time)
print(model.summarize())
print('MSM timescales\n', msm.fit(seqs).timescales_)
print('Uncertainty K\n', model.uncertainty_K())
print('Uncertainty pi\n', model.uncertainty_pi())