def main():
"""
Select frames from the supplied xyz file (fxyz) using one of the following algorithms:
1. random: random selection
2. fps: farthest point sampling selection. Need to supply a kernel matrix or descriptor matrix using -fmat
4. CUR decomposition
Parameters
----------
fxyz: Path to xyz file.
fmat: Path to the design matrix or name of the tags in ase xyz file
prefix: Filename prefix, default is ASAP
nkeep: The number of representative samples to select
algorithm: 'the algorithm for selecting frames ([random], [fps], [cur])')
fmat: Location of descriptor or kernel matrix file. Needed if you select [fps] or [cur].
"""
fxyz = os.path.join(os.path.split(__file__)[0], 'small_molecules-SOAP.xyz')
fmat = ['SOAP-n4-l3-c1.9-g0.23']
nkeep = 10
prefix = "test-frame-select"
# read the xyz file
asapxyz = ASAPXYZ(fxyz)
# for both algo we read in the descriptor matrix
desc, _ = asapxyz.get_descriptors(fmat)
print("shape of the descriptor matrix: ", np.shape(desc),
"number of descriptors: ", np.shape(desc[0]))
for algorithm in ['random', 'cur', 'fps']:
sparsifier = Sparsifier(algorithm)
sbs = sparsifier.sparsify(desc, nkeep)
# save
selection = np.zeros(asapxyz.get_num_frames(), dtype=int)
for i in sbs:
selection[i] = 1
np.savetxt(prefix + "-" + algorithm + "-n-" + str(nkeep) + '.index',
selection,
fmt='%d')
asapxyz.write(prefix + "-" + algorithm + "-n-" + str(nkeep), sbs)
def select(ctx, fxyz, design_matrix, algorithm, nkeep, prefix, savexyz,
savetxt):
"""
Select a subset of frames using sparsification algorithms
"""
if not fxyz and not design_matrix[0]:
return
if prefix is None: prefix = "ASAP-select-" + algorithm + "-n-" + str(nkeep)
ctx.obj['asapxyz'], ctx.obj['design_matrix'], _ = read_xyz_n_dm(
fxyz, design_matrix, False, False, False)
from asaplib.compressor import Sparsifier
sparsifier = Sparsifier(algorithm)
sbs = sparsifier.sparsify(ctx.obj['design_matrix'], nkeep)
# save
if savetxt:
selection = np.zeros(asapxyz.get_num_frames(), dtype=int)
for i in sbs:
selection[i] = 1
np.savetxt(prefix + '.index', selection, fmt='%d')
if savexyz: ctx.obj['asapxyz'].write(prefix, sbs)
# fmat = ['SOAP-n4-l3-c1.9-g0.23']
fmat = ['*']
nkeep = args.number #50
prefix = "test-frame-select"
# read the xyz file
asapxyz = ASAPXYZ(fxyz)
# for both algo we read in the descriptor matrix
desc, _ = asapxyz.get_descriptors(fmat)
print("shape of the descriptor matrix: ", np.shape(desc), "number of descriptors: ", np.shape(desc[0]))
algorithm = args.method#'fps' # 3 options: 'random', 'cur', 'fps'
#algorithm = 'random' # 3 options: 'random', 'cur', 'fps'
sparsifier = Sparsifier(algorithm)
sbs = sparsifier.sparsify(desc, nkeep)
sbs.sort()
if args.stride is None:
pass
else:
sbs = sbs*args.stride
np.savetxt(prefix + "-" + algorithm + "-n-" + str(nkeep) + '.index', sbs, fmt='%d')
# save
#selection = np.zeros(asapxyz.get_num_frames(), dtype=int)
#for i in sbs:
# selection[i] = 1
#np.savetxt(prefix + "-" + algorithm + "-n-" + str(nkeep) + '.index', selection, fmt='%d')
#asapxyz.write(prefix + "-" + algorithm + "-n-" + str(nkeep), sbs)