def post(self):
io = StringIO(self.get_argument('matrix'))
w = sio.mmread(io)
msm = MarkovStateModel()
msm.transmat_, msm.populations_ = _transmat_mle_prinz(w)
msm.n_states_ = msm.populations_.shape[0]
if bool(int(self.get_argument('mode'))):
self.write(make_json_paths(msm, self)) # TP
else:
self.write(make_json_graph(msm, self)) # MSM
def test_hubscore():
#Make an actual hub!
tprob = np.array([[0.8, 0.0, 0.2, 0.0, 0.0], [0.0, 0.8, 0.2, 0.0, 0.0],
[0.1, 0.1, 0.6, 0.1, 0.1], [0.0, 0.0, 0.2, 0.8, 0.0],
[0.0, 0.0, 0.2, 0.0, 0.8]])
msm = MarkovStateModel(lag_time=1)
msm.transmat_ = tprob
msm.n_states_ = 5
score = tpt.hub_scores(msm, 2)[0]
assert score == 1.0
def test_hubscore():
# Make an actual hub!
tprob = np.array([[0.8, 0.0, 0.2, 0.0, 0.0],
[0.0, 0.8, 0.2, 0.0, 0.0],
[0.1, 0.1, 0.6, 0.1, 0.1],
[0.0, 0.0, 0.2, 0.8, 0.0],
[0.0, 0.0, 0.2, 0.0, 0.8]])
msm = MarkovStateModel(lag_time=1)
msm.transmat_ = tprob
msm.n_states_ = 5
score = tpt.hub_scores(msm, 2)[0]
assert score == 1.0
def test_2():
model = MarkovStateModel(verbose=False)
C = np.array([[4380, 153, 15, 2, 0, 0], [211, 4788, 1, 0, 0, 0],
[169, 1, 4604, 226, 0, 0], [3, 13, 158, 4823, 3, 0],
[0, 0, 0, 4, 4978, 18], [7, 5, 0, 0, 62, 4926]],
dtype=float)
C = C + 1.0 / 6.0
model.n_states_ = C.shape[0]
model.countsmat_ = C
model.transmat_, model.populations_ = model._fit_mle(C)
n_trials = 5000
random = np.random.RandomState(0)
all_timescales = np.zeros((n_trials, model.n_states_ - 1))
all_eigenvalues = np.zeros((n_trials, model.n_states_))
for i in range(n_trials):
T = np.vstack([random.dirichlet(C[i]) for i in range(C.shape[0])])
u = _solve_msm_eigensystem(T, k=6)[0]
all_eigenvalues[i] = u
all_timescales[i] = -1 / np.log(u[1:])
pp.figure(figsize=(12, 8))
for i in range(3):
pp.subplot(2, 3, i + 1)
pp.title('Timescale %d' % i)
kde = scipy.stats.gaussian_kde(all_timescales[:, i])
xx = np.linspace(all_timescales[:, i].min(), all_timescales[:,
i].max())
r = scipy.stats.norm(loc=model.timescales_[i],
scale=model.uncertainty_timescales()[i])
pp.plot(xx, kde.evaluate(xx), c='r', label='Samples')
pp.plot(xx, r.pdf(xx), c='b', label='Analytic')
for i in range(1, 4):
pp.subplot(2, 3, 3 + i)
pp.title('Eigenvalue %d' % i)
kde = scipy.stats.gaussian_kde(all_eigenvalues[:, i])
xx = np.linspace(all_eigenvalues[:, i].min(), all_eigenvalues[:,
i].max())
r = scipy.stats.norm(loc=model.eigenvalues_[i],
scale=model.uncertainty_eigenvalues()[i])
pp.plot(xx, kde.evaluate(xx), c='r', label='Samples')
pp.plot(xx, r.pdf(xx), c='b', label='Analytic')
pp.tight_layout()
pp.legend(loc=4)
pp.savefig('test_msm_uncertainty_plots.png')
def test_2():
model = MarkovStateModel(verbose=False)
C = np.array([
[4380, 153, 15, 2, 0, 0],
[211, 4788, 1, 0, 0, 0],
[169, 1, 4604, 226, 0, 0],
[3, 13, 158, 4823, 3, 0],
[0, 0, 0, 4, 4978, 18],
[7, 5, 0, 0, 62, 4926]], dtype=float)
C = C + 1.0 / 6.0
model.n_states_ = C.shape[0]
model.countsmat_ = C
model.transmat_, model.populations_ = model._fit_mle(C)
n_trials = 5000
random = np.random.RandomState(0)
all_timescales = np.zeros((n_trials, model.n_states_ - 1))
all_eigenvalues = np.zeros((n_trials, model.n_states_))
for i in range(n_trials):
T = np.vstack([random.dirichlet(C[i]) for i in range(C.shape[0])])
u = _solve_msm_eigensystem(T, k=6)[0]
all_eigenvalues[i] = u
all_timescales[i] = -1 / np.log(u[1:])
pp.figure(figsize=(12, 8))
for i in range(3):
pp.subplot(2,3,i+1)
pp.title('Timescale %d' % i)
kde = scipy.stats.gaussian_kde(all_timescales[:, i])
xx = np.linspace(all_timescales[:,i].min(), all_timescales[:,i].max())
r = scipy.stats.norm(loc=model.timescales_[i], scale=model.uncertainty_timescales()[i])
pp.plot(xx, kde.evaluate(xx), c='r', label='Samples')
pp.plot(xx, r.pdf(xx), c='b', label='Analytic')
for i in range(1, 4):
pp.subplot(2,3,3+i)
pp.title('Eigenvalue %d' % i)
kde = scipy.stats.gaussian_kde(all_eigenvalues[:, i])
xx = np.linspace(all_eigenvalues[:,i].min(), all_eigenvalues[:,i].max())
r = scipy.stats.norm(loc=model.eigenvalues_[i], scale=model.uncertainty_eigenvalues()[i])
pp.plot(xx, kde.evaluate(xx), c='r', label='Samples')
pp.plot(xx, r.pdf(xx), c='b', label='Analytic')
pp.tight_layout()
pp.legend(loc=4)
pp.savefig('test_msm_uncertainty_plots.png')
def test_mfpt2():
tprob = np.array([[0.90, 0.10],
[0.22, 0.78]])
pi0 = 1
pi1 = pi0 * tprob[0, 1] / tprob[1, 0]
pops = np.array([pi0, pi1]) / (pi0 + pi1)
msm = MarkovStateModel(lag_time=1)
msm.transmat_ = tprob
msm.n_states_ = 2
msm.populations_ = pops
mfpts = np.vstack([tpt.mfpts(msm, i) for i in range(2)]).T
# since it's a 2x2 the mfpt from 0 -> 1 is the
# same as the escape time of 0
npt.assert_almost_equal(1 / (1 - tprob[0, 0]), mfpts[0, 1])
npt.assert_almost_equal(1 / (1 - tprob[1, 1]), mfpts[1, 0])
def test_countsmat():
model = MarkovStateModel(verbose=False)
C = np.array([[4380, 153, 15, 2, 0, 0], [211, 4788, 1, 0, 0, 0],
[169, 1, 4604, 226, 0, 0], [3, 13, 158, 4823, 3, 0],
[0, 0, 0, 4, 4978, 18], [7, 5, 0, 0, 62, 4926]],
dtype=float)
C = C + (1.0 / 6.0)
model.n_states_ = C.shape[0]
model.countsmat_ = C
model.transmat_, model.populations_ = model._fit_mle(C)
n_trials = 5000
random = np.random.RandomState(0)
all_timescales = np.zeros((n_trials, model.n_states_ - 1))
all_eigenvalues = np.zeros((n_trials, model.n_states_))
for i in range(n_trials):
T = np.vstack([random.dirichlet(C[i]) for i in range(C.shape[0])])
u = _solve_msm_eigensystem(T, k=6)[0]
u = np.real(u) # quiet warning. Don't know if this is legit
all_eigenvalues[i] = u
all_timescales[i] = -1 / np.log(u[1:])
def test_mfpt2():
tprob = np.array([[0.90, 0.10], [0.22, 0.78]])
pi0 = 1
# pi1 T[1, 0] = pi0 T[0, 1]
pi1 = pi0 * tprob[0, 1] / tprob[1, 0]
pops = np.array([pi0, pi1]) / (pi0 + pi1)
msm = MarkovStateModel(lag_time=1)
msm.transmat_ = tprob
msm.n_states_ = 2
msm.populations_ = pops
mfpts = np.vstack([tpt.mfpts(msm, i) for i in xrange(2)]).T
#print(1 / (1 - tprob[0, 0]), mfpts[0, 1])
#print(1 / (1 - tprob[1, 1]), mfpts[1, 0])
# since it's a 2x2 the mfpt from 0 -> 1 is the
# same as the escape time of 0
npt.assert_almost_equal(1 / (1 - tprob[0, 0]), mfpts[0, 1])
npt.assert_almost_equal(1 / (1 - tprob[1, 1]), mfpts[1, 0])
def test_countsmat():
model = MarkovStateModel(verbose=False)
C = np.array([
[4380, 153, 15, 2, 0, 0],
[211, 4788, 1, 0, 0, 0],
[169, 1, 4604, 226, 0, 0],
[3, 13, 158, 4823, 3, 0],
[0, 0, 0, 4, 4978, 18],
[7, 5, 0, 0, 62, 4926]], dtype=float)
C = C + (1.0 / 6.0)
model.n_states_ = C.shape[0]
model.countsmat_ = C
model.transmat_, model.populations_ = model._fit_mle(C)
n_trials = 5000
random = np.random.RandomState(0)
all_timescales = np.zeros((n_trials, model.n_states_ - 1))
all_eigenvalues = np.zeros((n_trials, model.n_states_))
for i in range(n_trials):
T = np.vstack([random.dirichlet(C[i]) for i in range(C.shape[0])])
u = _solve_msm_eigensystem(T, k=6)[0]
u = np.real(u) # quiet warning. Don't know if this is legit
all_eigenvalues[i] = u
all_timescales[i] = -1 / np.log(u[1:])
def calculate_fitness(population_dihedral, diheds, score_global, i, lock):
import pandas as pd
import numpy as np
pop_index = i
new_diheds = []
for i in range(0, len(diheds)):
X = diheds[i]
selected_features = X[:, population_dihedral]
new_diheds.append(selected_features)
from msmbuilder.preprocessing import RobustScaler
scaler = RobustScaler()
scaled_diheds = scaler.fit_transform(new_diheds)
scaled_diheds = new_diheds
from msmbuilder.decomposition import tICA
tica_model = tICA(lag_time=2, n_components=5)
tica_model.fit(scaled_diheds)
tica_trajs = tica_model.transform(scaled_diheds)
from msmbuilder.cluster import MiniBatchKMeans
clusterer = MiniBatchKMeans(n_clusters=200, random_state=42)
clustered_trajs = clusterer.fit_transform(tica_trajs)
from msmbuilder.msm import MarkovStateModel
msm = MarkovStateModel(lag_time=50, n_timescales=5)
#msm.fit_transform(clustered_trajs)
from sklearn.cross_validation import KFold
n_states = [4]
cv = KFold(len(clustered_trajs), n_folds=5)
results = []
for n in n_states:
msm.n_states_ = n
for fold, (train_index, test_index) in enumerate(cv):
train_data = [clustered_trajs[i] for i in train_index]
test_data = [clustered_trajs[i] for i in test_index]
msm.fit(train_data)
train_score = msm.score(train_data)
test_score = msm.score(test_data)
time_score = msm.timescales_[0]
time_test_score = time_score + test_score
print(time_score)
print(test_score)
av_score = time_test_score / 2
results.append({
'train_score': train_score,
'test_score': test_score,
'time_score': time_score,
'av_score': av_score,
'n_states': n,
'fold': fold
})
print(msm.timescales_)
results = pd.DataFrame(results)
avgs = (results.groupby('n_states').aggregate(np.median).drop('fold',
axis=1))
best_nt = avgs['test_score'].idxmax()
best_n = avgs['av_score'].idxmax()
best_score = avgs.loc[best_n, 'av_score']
best_scorent = avgs.loc[best_nt, 'test_score']
print(best_scorent)
lock.acquire()
score_global.update({pop_index: best_scorent})
lock.release()
