def _do_lumping(self):
"""Do the MVCA lumping.
"""
model = LandmarkAgglomerative(linkage='ward',
n_clusters=self.n_macrostates,
metric=self.metric,
n_landmarks=self.n_landmarks,
landmark_strategy=self.landmark_strategy,
random_state=self.random_state)
model.fit([self.transmat_])
if self.fit_only:
microstate_mapping_ = model.landmark_labels_
else:
microstate_mapping_ = model.transform([self.transmat_])[0]
self.microstate_mapping_ = microstate_mapping_
def _do_lumping(self):
"""Do the MVCA lumping.
"""
model = LandmarkAgglomerative(linkage='ward',
n_clusters=self.n_macrostates,
metric=self.metric,
n_landmarks=self.n_landmarks,
landmark_strategy=self.landmark_strategy,
random_state=self.random_state)
model.fit([self.transmat_])
if self.fit_only:
microstate_mapping_ = model.landmark_labels_
else:
microstate_mapping_ = model.transform([self.transmat_])[0]
self.microstate_mapping_ = microstate_mapping_
i, row = irow
traj = md.load(row['traj_fn'], top=tops[row['top_fn']])
return i, traj
traj_dict = dict(map(traj_load, meta.iterrows()))
trajs = [traj for traj in traj_dict.values()]
# cluster
print('Attempting to cluster')
num_clusters = 20
cluster = LandmarkAgglomerative(n_clusters=num_clusters,
n_landmarks=int(totframes / 100),
linkage='ward',
metric='rmsd')
cluster.fit(trajs)
#
# print('Fitting cluster labels')
# ctraj = {}
# for k, v in traj_dict.items():
# v = cluster.partial_predict(v)
# diff = nframes-v.shape[0]
# v = np.append(v, np.zeros(diff)-1)
# ctraj[k] = v
# Convert to DF for plotting and sampling.
# df = to_dataframe(ctraj, nframes, dt=1)
print('Fitting cluster labels for MSM')
ctraj = {}
ctraj_path = 'ctraj-200'
if isdir(ctraj_path):
meta, all_ctrajs_dict = load_trajs(ctraj_path)
else:
def traj_load(irow):
i, row = irow
traj = md.load(row['traj_fn'], top=tops[row['top_fn']])
return i, traj
traj_dict = dict(map(traj_load, meta.iterrows()))
all_trajs = [traj for traj in traj_dict.values()]
cluster = LandmarkAgglomerative(n_clusters=200, n_landmarks=int(totframes /200), linkage='ward', metric='rmsd')
cluster.fit(all_trajs)
# TODO will this work?
args = [(k,v,cluster) for k, v in traj_dict.items()]
with Pool() as pool:
all_ctrajs_dict = dict(pool.imap_unordered(clust, args))
save_generic(cluster, 'cluster-200')
save_trajs(all_ctrajs_dict, 'ctraj-200', meta)
long_ctrajs = [np.squeeze(traj) for traj in all_ctrajs_dict.values() if traj.shape[0] > 1000]
all_ctrajs = [np.squeeze(traj) for traj in all_ctrajs_dict.values()]
lags = np.concatenate((np.arange(200, 1000, 200),np.arange(1000, 5000, 500)))
all_msms = []
