txx = np.concatenate(tica_trajs)
#_ = msme.plot_histogram(txx)
clusterer = MiniBatchKMeans(n_clusters=int(args.clusters),
random_state=42)
clustered_trajs = tica_trajs.fit_transform_with(clusterer,
'kmeans/',
fmt='dir-npy')
#plt.figure()
#plt.hexbin(txx[:,0], txx[:,1], bins='log', mincnt=1, cmap='viridis')
#plt.scatter(clusterer.cluster_centers_[:,0], clusterer.cluster_centers_[:,1], s=100, c='w')
#plt.savefig('microstate_clusters.png')
# We can construct an MSM from the labeled trajectories
msm = MarkovStateModel(lag_time=int(args.lag), n_timescales=20)
msm.fit(clustered_trajs)
assignments = clusterer.partial_transform(txx)
assignments = msm.partial_transform(assignments)
#msme.plot_free_energy(txx, obs=(0, 1), n_samples=10000,
# pi=msm.populations_[assignments],
# xlabel='tIC 1', ylabel='tIC 2')
#plt.figure()
#plt.scatter(clusterer.cluster_centers_[msm.state_labels_, 0],
# clusterer.cluster_centers_[msm.state_labels_, 1],
# s=1e4 * msm.populations_, # size by population
# c=msm.left_eigenvectors_[:, 1], # color by eigenvector
# cmap="coolwarm",
# zorder=3)
#plt.colorbar(label='First dynamical eigenvector')
#plt.tight_layout()
#plt.savefig('free_energy_plot.png')
"""Cluster tICA results
{{header}}
Meta
----
depends:
- ttrajs
- meta.pandas.pickl
"""
from msmbuilder.io import load_trajs, save_trajs, save_generic
from msmbuilder.cluster import MiniBatchKMeans
## Load
meta, ttrajs = load_trajs('ttrajs')
## Fit
dim = 5
kmeans = MiniBatchKMeans(n_clusters=500)
kmeans.fit([traj[:, :dim] for traj in ttrajs.values()])
## Transform
ktrajs = {}
for k, v in ttrajs.items():
ktrajs[k] = kmeans.partial_transform(v[:, :dim])
## Save
print(kmeans.summarize())
save_trajs(ktrajs, 'ktrajs', meta)
save_generic(kmeans, 'kmeans.pickl')
