# Basic usage / workflow
ds = dataset("**/*.dcd")

dihed = ds.derive('dihed', fmt='dir-npy')
dihed += DihedralFeaturizer().fit_transform(ds)

tica = dihed.derive('tica', fmt='hdf5')
tica += tICA().fit_transform(dihed)

clusters = tica.derive('clusters', fmt='hdf5')
clusters += KMeans().fit_transform(tica)

msm = MSM().fit(clusters)
dump(msm, 'msm.pickl')