def test_score_3():
import warnings
warnings.simplefilter('ignore')
from msmbuilder.example_datasets.muller import MULLER_PARAMETERS as PARAMS
cluster = NDGrid(n_bins_per_feature=6,
min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
ds = MullerPotential(random_state=0).get()['trajectories']
assignments = cluster.fit_transform(ds)
train_indices = [9, 4, 3, 6, 2]
test_indices = [8, 0, 5, 7, 1]
model = ContinuousTimeMSM(lag_time=3,
n_timescales=1,
sliding_window=False,
ergodic_cutoff=1)
train_data = [assignments[i] for i in train_indices]
test_data = [assignments[i] for i in test_indices]
model.fit(train_data)
train = model.score_
test = model.score(test_data)
print(train, test)
def test_doublewell():
trjs = load_doublewell(random_state=0)['trajectories']
for n_states in [10, 50]:
clusterer = NDGrid(n_bins_per_feature=n_states)
assignments = clusterer.fit_transform(trjs)
for sliding_window in [True, False]:
model = ContinuousTimeMSM(lag_time=100, sliding_window=sliding_window)
model.fit(assignments)
assert model.optimizer_state_.success
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_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_doublewell():
trjs = load_doublewell(random_state=0)['trajectories']
for n_states in [10, 50]:
clusterer = NDGrid(n_bins_per_feature=n_states)
assignments = clusterer.fit_transform(trjs)
for sliding_window in [True, False]:
model = ContinuousTimeMSM(lag_time=100,
sliding_window=sliding_window)
model.fit(assignments)
assert model.optimizer_state_.success
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())
def test_dump():
# gh-713
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])
d = tempfile.mkdtemp()
try:
utils.dump(model, '{}/cmodel'.format(d))
m2 = utils.load('{}/cmodel'.format(d))
np.testing.assert_array_almost_equal(model.transmat_, m2.transmat_)
finally:
shutil.rmtree(d)
def test_hessian_3():
grid = NDGrid(n_bins_per_feature=4, 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=False, 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 eigs\n', model.uncertainty_eigenvalues())
def test_hessian_3():
grid = NDGrid(n_bins_per_feature=4, min=-np.pi, max=np.pi)
trajs = DoubleWell(random_state=0).get_cached().trajectories
seqs = grid.fit_transform(trajs)
seqs = [seqs[i] for i in range(10)]
lag_time = 10
model = ContinuousTimeMSM(verbose=False, 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 eigs\n', model.uncertainty_eigenvalues())
def test_fit_2():
grid = NDGrid(n_bins_per_feature=5, min=-np.pi, max=np.pi)
seqs = grid.fit_transform(load_doublewell(random_state=0)['trajectories'])
model = ContinuousTimeMSM(verbose=False, lag_time=10)
model.fit(seqs)
t1 = np.sort(model.timescales_)
t2 = -1 / np.sort(np.log(np.linalg.eigvals(model.transmat_))[1:])
model = MarkovStateModel(verbose=False, lag_time=10)
model.fit(seqs)
t3 = np.sort(model.timescales_)
np.testing.assert_array_almost_equal(t1, t2)
# timescales should be similar to MSM (withing 50%)
assert abs(t1[-1] - t3[-1]) / t1[-1] < 0.50
def test_guess():
ds = MullerPotential(random_state=0).get_cached().trajectories
cluster = NDGrid(n_bins_per_feature=5,
min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
assignments = cluster.fit_transform(ds)
model1 = ContinuousTimeMSM(guess='log')
model1.fit(assignments)
model2 = ContinuousTimeMSM(guess='pseudo')
model2.fit(assignments)
diff = model1.loglikelihoods_[-1] - model2.loglikelihoods_[-1]
assert np.abs(diff) < 1e-3
assert np.max(np.abs(model1.ratemat_ - model2.ratemat_)) < 1e-1
def test_score_2():
ds = MullerPotential(random_state=0).get_cached().trajectories
cluster = NDGrid(n_bins_per_feature=6,
min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
assignments = cluster.fit_transform(ds)
test_indices = [5, 0, 4, 1, 2]
train_indices = [3, 6, 7, 8, 9]
model = ContinuousTimeMSM(lag_time=3, n_timescales=1)
model.fit([assignments[i] for i in train_indices])
test = model.score([assignments[i] for i in test_indices])
train = model.score_
print('train', train, 'test', test)
assert 1 <= test < 2
assert 1 <= train < 2
def test_fit_2():
grid = NDGrid(n_bins_per_feature=5, min=-np.pi, max=np.pi)
seqs = grid.fit_transform(load_doublewell(random_state=0)['trajectories'])
model = ContinuousTimeMSM(verbose=True, lag_time=10)
model.fit(seqs)
t1 = np.sort(model.timescales_)
t2 = -1/np.sort(np.log(np.linalg.eigvals(model.transmat_))[1:])
model = MarkovStateModel(verbose=False, lag_time=10)
model.fit(seqs)
t3 = np.sort(model.timescales_)
np.testing.assert_array_almost_equal(t1, t2)
# timescales should be similar to MSM (withing 50%)
assert abs(t1[-1] - t3[-1]) / t1[-1] < 0.50
def test_score_2():
from msmbuilder.example_datasets.muller import MULLER_PARAMETERS as PARAMS
ds = MullerPotential(random_state=0).get()['trajectories']
cluster = NDGrid(n_bins_per_feature=6,
min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
assignments = cluster.fit_transform(ds)
test_indices = [5, 0, 4, 1, 2]
train_indices = [3, 6, 7, 8, 9]
model = ContinuousTimeMSM(lag_time=3, n_timescales=1)
model.fit([assignments[i] for i in train_indices])
test = model.score([assignments[i] for i in test_indices])
train = model.score_
print('train', train, 'test', test)
assert 1 <= test < 2
assert 1 <= train < 2
def test_score_2():
from msmbuilder.example_datasets.muller import MULLER_PARAMETERS as PARAMS
ds = MullerPotential(random_state=0).get()['trajectories']
cluster = NDGrid(n_bins_per_feature=6,
min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
assignments = cluster.fit_transform(ds)
test_indices = [5, 0, 4, 1, 2]
train_indices = [3, 6, 7, 8, 9]
model = ContinuousTimeMSM(lag_time=3, n_timescales=1)
model.fit([assignments[i] for i in train_indices])
test = model.score([assignments[i] for i in test_indices])
train = model.score_
print('train', train, 'test', test)
assert 1 <= test < 2
assert 1 <= train < 2
def test_guess():
from msmbuilder.example_datasets.muller import MULLER_PARAMETERS as PARAMS
cluster = NDGrid(n_bins_per_feature=5,
min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
ds = MullerPotential(random_state=0).get()['trajectories']
assignments = cluster.fit_transform(ds)
model1 = ContinuousTimeMSM(guess='log')
model1.fit(assignments)
model2 = ContinuousTimeMSM(guess='pseudo')
model2.fit(assignments)
assert np.abs(model1.loglikelihoods_[-1] - model2.loglikelihoods_[-1]) < 1e-3
assert np.max(np.abs(model1.ratemat_ - model2.ratemat_)) < 1e-1
def test_guess():
from msmbuilder.example_datasets.muller import MULLER_PARAMETERS as PARAMS
cluster = NDGrid(n_bins_per_feature=5,
min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
ds = MullerPotential(random_state=0).get()['trajectories']
assignments = cluster.fit_transform(ds)
model1 = ContinuousTimeMSM(guess='log')
model1.fit(assignments)
model2 = ContinuousTimeMSM(guess='pseudo')
model2.fit(assignments)
diff = model1.loglikelihoods_[-1] - model2.loglikelihoods_[-1]
assert np.abs(diff) < 1e-3
assert np.max(np.abs(model1.ratemat_ - model2.ratemat_)) < 1e-1
def test_score_3():
ds = MullerPotential(random_state=0).get_cached().trajectories
cluster = NDGrid(n_bins_per_feature=6,
min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
assignments = cluster.fit_transform(ds)
train_indices = [9, 4, 3, 6, 2]
test_indices = [8, 0, 5, 7, 1]
model = ContinuousTimeMSM(lag_time=3, n_timescales=1, sliding_window=False,
ergodic_cutoff=1)
train_data = [assignments[i] for i in train_indices]
test_data = [assignments[i] for i in test_indices]
model.fit(train_data)
train = model.score_
test = model.score(test_data)
print(train, test)
lag_times=list(range(1, 100,2))
n_timescales=10
msm_timescales = implied_timescales(kmeanslabel, lag_times, n_timescales=n_timescales, msm=MarkovStateModel(verbose=False))
#for i in range(n_timescales):
# plt.plot(lag_times, msm_timescales[:, i], 'o-')
#plt.title('Discrete-time MSM Relaxation Timescales')
#plt.xlabel('lag time')
#plt.ylabel('Relaxation Time')
#plt.semilogy()
#plt.show()
cont_time_msm = ContinuousTimeMSM(lag_time=10, n_timescales=None)
time_model=cont_time_msm.fit(kmeanslabel)
print (time_model.ratemat_)
P=time_model.transmat_
M = msm.markov_model(P)
NetworkPlot.plot_network(P)
#mplt.plot_markov_model(M);
MLMSM_good = msm.estimate_markov_model(kmeanslabel, 4)
ck_good_msm=MLMSM_good.cktest(4)
fig, axes = mplt.plot_cktest(ck_good_msm)
fig.savefig('my_file.png', dpi=300)
