def test_dim_and_var_cutoff(full_rank_time_series, dim, var_cutoff, partial_fit):
# basically dim should be ignored here since var_cutoff takes precedence if it is None
est = VAMP(lagtime=1, dim=dim, var_cutoff=var_cutoff)
if partial_fit:
for chunk in timeshifted_split(full_rank_time_series, lagtime=1, chunksize=15):
est.partial_fit(chunk)
est2 = VAMP(lagtime=1, dim=dim, var_cutoff=var_cutoff).fit(full_rank_time_series)
np.testing.assert_array_almost_equal(est.fetch_model().operator,
est2.fetch_model().operator, decimal=4) # can fail on M$ with higher acc.
else:
est.fit(full_rank_time_series)
projection = est.transform(full_rank_time_series)
np.testing.assert_equal(projection.shape[0], full_rank_time_series.shape[0])
if var_cutoff is not None:
if var_cutoff == 1.:
# data is internally mean-free
np.testing.assert_equal(projection.shape[1], full_rank_time_series.shape[1] - 1)
else:
np.testing.assert_array_less(projection.shape[1], full_rank_time_series.shape[1])
else:
if dim is None:
# data is internally mean-free
np.testing.assert_equal(projection.shape[1], full_rank_time_series.shape[1] - 1)
else:
np.testing.assert_equal(projection.shape[1], dim)
def setUpClass(cls):
N_steps = 10000
N_traj = 20
lag = 1
T = np.linalg.matrix_power(np.array([[0.7, 0.2, 0.1], [0.1, 0.8, 0.1], [0.1, 0.1, 0.8]]), lag)
dtrajs = [generate(T, N_steps) for _ in range(N_traj)]
p0 = np.zeros(3)
p1 = np.zeros(3)
trajs = []
for dtraj in dtrajs:
traj = np.zeros((N_steps, T.shape[0]))
traj[np.arange(len(dtraj)), dtraj] = 1.0
trajs.append(traj)
p0 += traj[:-lag, :].sum(axis=0)
p1 += traj[lag:, :].sum(axis=0)
estimator = VAMP(scaling=None, var_cutoff=1.0)
cov = VAMP.covariance_estimator(lagtime=lag).fit(trajs).fetch_model()
vamp = estimator.fit(cov).fetch_model()
msm = estimate_markov_model(dtrajs, lag=lag, reversible=False)
cls.trajs = trajs
cls.dtrajs = dtrajs
cls.trajs_timeshifted = list(timeshifted_split(cls.trajs, lagtime=lag, chunksize=5000))
cls.lag = lag
cls.msm = msm
cls.vamp = vamp
cls.estimator = estimator
cls.p0 = p0 / p0.sum()
cls.p1 = p1 / p1.sum()
cls.atol = np.finfo(np.float32).eps * 1000.0
np.linspace(np.min(feature_trajectory[:, 1]),
np.max(feature_trajectory[:, 1]), 4))
ax.scatter(*feature_trajectory.T, marker='.')
ax.quiver(x, y, dxy[0], dxy[1])
ax.set_title(title)
ax.set_aspect('equal')
ax.set_xlabel('x')
ax.set_ylabel('y')
data = ellipsoids(seed=17)
discrete_trajectory = data.discrete_trajectory(n_steps=1000)
feature_trajectory = data.map_discrete_to_observations(discrete_trajectory)
vamp = VAMP(dim=1, lagtime=1)
vamp = vamp.fit(feature_trajectory).fetch_model()
vamp_projection = vamp.transform(feature_trajectory)
dxy_vamp = vamp.singular_vectors_left[:, 0] # dominant vamp component
tica = TICA(dim=1, lagtime=1)
tica = tica.fit(feature_trajectory).fetch_model()
tica_projection = tica.transform(feature_trajectory)
dxy_tica = tica.singular_vectors_left[:, 0] # dominant tica component
pca = PCA(n_components=1)
pca.fit(feature_trajectory)
pca_projection = pca.transform(feature_trajectory)
dxy_pca = pca.components_[0] # dominant pca component
f = plt.figure(constrained_layout=False, figsize=(14, 14))
gs = f.add_gridspec(nrows=2, ncols=3)