def load_PCA_Subspace(catalog):
# HCube leaf size of 500 points
settings = systemsettings()
vectfile = settings.PCA_VECTOR_FILE
logging.info("Loading PCA Vectors from %s", vectfile)
pc_vect = np.load(vectfile)
max_pc = pc_vect.shape[1]
num_pc = min(settings.PCA_NUMPC, max_pc)
pc = pc_vect[:num_pc]
logging.info("Storing PCA Vectors to key: %s", 'pcaVectors')
catalog.storeNPArray(pc, 'pcaVectors')
logging.info("Loading Pre-Calculated PCA projections from Historical BPTI Trajectory")
pre_calc_deshaw = np.load('data/pca_applied.npy')
# Extract only nec'y PC's
pts = pre_calc_deshaw.T[:num_pc].T
pipe = catalog.pipeline()
for si in pts:
pipe.rpush('subspace:pca', bytes(si))
pipe.execute()
logging.debug("PCA Subspace stored in Catalog")
logging.info('Creating KD Tree')
kd = KDTree(500, maxdepth=8, data=pts)
logging.info('Encoding KD Tree')
packaged = kd.encode()
encoded = json.dumps(packaged)
logging.info('Storing in catalog')
catalog.delete('hcube:pca')
catalog.set('hcube:pca', encoded)
logging.info('PCA Complete')
def calcDEShaw_PCA(catalog, force=False):
numPC = 3
numpts = catalog.llen('subspace:pca')
if numpts == 0 or force:
catalog.delete('subspace:pca')
logging.debug("Projecting DEshaw PCA Vectors (assuming PC's are pre-calc'd")
pcavect = catalog.loadNPArray('pcaVectors')
logging.debug("Loaded PCA Vectors: %s, %s", str(pcavect.shape), str(pcavect.dtype))
src = np.load(DESHAW_PTS_FILE)
logging.debug("Loaded source points: %s, %s", str(src.shape), str(src.dtype))
pcalist = np.zeros(shape=(len(src), numPC))
start = dt.datetime.now()
pdbfile, dcdfile = deshaw.getHistoricalTrajectory(0)
traj = md.load(dcdfile, top=pdbfile, frame=0)
filt = traj.top.select_atom_indices(selection='heavy')
pipe = catalog.pipeline()
for i, conform in enumerate(src):
if i % 10000 == 0:
logging.debug("Projecting: %d", i)
heavy = np.array([conform[k] for k in filt])
np.copyto(pcalist[i], np.array([np.dot(heavy.reshape(pc.shape),pc) for pc in pcavect[:numPC]]))
raw_index = i * DESHAW_SAMPLE_FACTOR
pipe.rpush('xid:reference', '(-1, %d)' % raw_index)
end = dt.datetime.now()
logging.debug("Projection time = %d", (end-start).seconds)
rIdx = []
for si in pcalist:
rIdx.append(pipe.rpush('subspace:pca', bytes(si)))
pipe.execute()
logging.debug("R_Index Created (pca)")
else:
logging.info('PCA Already created. Retrieving existing lower dim pts')
X = catalog.lrange('subspace:pca', 0, -1)
pcalist = np.array([np.fromstring(si) for si in X])
# HCube leaf size of 500 points
logging.info('Creating KD Tree')
kd = KDTree(500, data=pcalist)
logging.info('Encoding KD Tree')
encoded = json.dumps(kd.encode())
logging.info('Storing in catalog')
catalog.delete('hcube:pca')
catalog.set('hcube:pca', encoded)
logging.info('PCA Complete')
