logging.info('\n\n----------------------')
logging.info('SIZE,iset,%d', len(iset))
logging.info('SIZE,dlat,%d', len(dlat))
clunumlist = [1000, 500, 250, 100, 50, 30, 25, 20, 18, 16, 14, 12, 10, 8, 6]
for seqnum in range(1, 3):
for num_clu in clunumlist:
logging.info('\n\n----------------------')
logging.info('NUM_CLUSTER,%d', num_clu)
logging.info('----------------------')
logging.info('Clustering Lattice:')
keylist, clulist, centroid, variance, G = lat.cluster_harch(
dlat, CMr, Dr, theta=.5, num_k=num_clu, dL=None, verbose=False)
logging.info('Scoring Lattice:')
well, tran = lat.score_clusters(clulist, Dr, centroid, variance, G,
sigma, DE_LABEL)
TBIN10 = sorted(set(DE_LABEL))
for k in TBIN10:
logging.info('SCORE,%d,W,%d,%d,%s,%.5f', seqnum, support, num_clu,
k, well[k])
for k in TBIN10:
logging.info('SCORE,%d,T,%d,%d,%s,%.5f', seqnum, support, num_clu,
k, tran[k])
# keylist, clulist, centroid, variance, G = lat.cluster_harch(dlat, CMr, Dr, theta=.5, num_k=num_clu, dL=dL, verbose=True)
# well, tran = lat.score_clusters(clulist, Dr, centroid, variance, G, sigma, DE_LABEL)
# FOR BASE VALUES
base = defaultdict(int)
for i in L:
CM = DS<cutoff
CMr, Dr = CM[:,Kr], DS[:,Kr]
CMm, Dm = CM[:,Km], DS[:,Km]
delabel = np.load(home+'/work/results/DE_label_full.npy')
DW = []
for i in range(42):
for a,b in TS.TimeScape.windows(home+'/work/timescape/desh_%02d_transitions.log'%i):
DW.append((a+i*100000, b+i*100000))
dL = [delabel[a:b] for a,b in DW]
DE_LABEL = [LABEL10(i,.9) for i in dL]
SPT = [i[0] for i in db.runquery('select distinct support from latt order by support')]
NC = [i[0] for i in db.runquery('select distinct numclu from latt order by numclu')]
mf, lf = {}, {}
dl, ik = {}, {}
key, clu, cent, var, Gm = {}, {}, {}, {}, {}
s=support
mf[s], lf[s] = lat.maxminer(CMr, s)
dl[s], ik[s] = lat.derived_lattice(mf[s], Dr, CMr)
pickle.dump(dl[s], open(home + '/work/latt_intrinsics/dlat2_%d.p' % support, 'wb'))
for num_clu in NC:
key[s], clu[s], cent[s], var[s], Gm[s] = lat.cluster_harch(dl[s], CMr, Dr, theta=.5, num_k=num_clu, dL=None, verbose=False)
w, t = lat.score_clusters(clu[s], Dr, cent[s], var[s], Gm[s], sigma, DE_LABEL)
for k in TBIN10:
logging.info('SCORE,W,%d,%d,%s,%.5f', support, num_clu, k, w[k])
for k in TBIN10:
logging.info('SCORE,T,%d,%d,%s,%.5f', support, num_clu, k, t[k])
for m, k in enumerate(KrD):
idx = Kr[m]
alld = hist(DS[:,idx])
kdistr[k]['All'] = alld/np.sum(alld)
for st, c in enumerate(C):
d = hist(cluD[st][:,idx])
kdistr[k]['%d'%st] = d/np.sum(d)
pickle.dump(kdistr, open('kdistr', 'wb'))
for k in KrD:
P.show_distr(kdistr[k], xscale=(4,10), showlegend=True, states={str(i):i for i in range(5)},\
xlabel='Distance (in Angstroms)', ylabel='Frequency', fname='distr_'+k, latex=True)
# TO Score Clusters based on total PDF:
well, tran = lat.score_clusters(clulist, Dr, centroid, variance, G, sigma, DE_LABEL)
# TBIN10 = sorted(set(DE_LABEL))
for k in TBIN10: logging.info('SCORE,%d,W,%d,%d,%s,%.5f', seqnum, support, num_clu, k, well[k])
for k in TBIN10: logging.info('SCORE,%d,T,%d,%d,%s,%.5f', seqnum, support, num_clu, k, tran[k])
for k,v in kdistr['q']: print(k, v)
elms = (n, k, len(v), state, stperc, bc) if incldist else (n, k, len(v), state, stperc)
clusterlist.append(elms)
# print('%2d.'%n, '%-15s'%k, '%4d '%len(v), 'State: %d (%4.1f%%)' % (state, stperc))
n += 1
for i in sorted(clusterlist, key =lambda x : x[2], reverse=True):
i[0]
for i in db.runquery('select distinct support from latt order by support')
]
NC = [
i[0]
for i in db.runquery('select distinct numclu from latt order by numclu')
]
mf, lf = {}, {}
dl, ik = {}, {}
key, clu, cent, var, Gm = {}, {}, {}, {}, {}
s = support
mf[s], lf[s] = lat.maxminer(CMr, s)
dl[s], ik[s] = lat.derived_lattice(mf[s], Dr, CMr)
pickle.dump(dl[s],
open(home + '/work/latt_intrinsics/dlat2_%d.p' % support, 'wb'))
for num_clu in NC:
key[s], clu[s], cent[s], var[s], Gm[s] = lat.cluster_harch(dl[s],
CMr,
Dr,
theta=.5,
num_k=num_clu,
dL=None,
verbose=False)
w, t = lat.score_clusters(clu[s], Dr, cent[s], var[s], Gm[s], sigma,
DE_LABEL)
for k in TBIN10:
logging.info('SCORE,W,%d,%d,%s,%.5f', support, num_clu, k, w[k])
for k in TBIN10:
logging.info('SCORE,T,%d,%d,%s,%.5f', support, num_clu, k, t[k])
