def execute(self, num):
dlat = self.lattice.dlat
Ik = self.lattice.Ik
CM = self.lattice._CM()
D = self.lattice.E[:, self.lattice.Kr]
print('DEBUG: ', len(dlat), len(Ik), CM.shape, D.shape)
clusters, score, elmlist = clusterlattice(dlat,
CM,
D,
Ik,
theta=self.theta,
num_k=self.num_cluster)
samplecount = np.zeros(len(clusters), dtype=np.int16)
pdf = score / np.sum(score)
candidates = []
for i in range(num):
while True:
cluster_index = int(np.random.choice(len(pdf), p=pdf))
if samplecount[cluster_index] < len(elmlist[cluster_index]):
break
elm, dist = elmlist[cluster_index][samplecount[cluster_index]]
samplecount[cluster_index] += 1
candidates.append(elm)
return candidates
def execute(self, num):
dlat = self.lattice.dlat
Ik = self.lattice.Ik
CM = self.lattice._CM()
D = self.lattice.E[:, self.lattice.Kr]
print('DEBUG: ', len(dlat), len(Ik), CM.shape, D.shape)
cuboids, score, elmlist = clusterlattice(dlat,
CM,
D,
Ik,
theta=self.theta,
num_k=self.num_cluster)
keylist = list(cuboids.keys())
candlist = [cuboids[k] for k in keylist]
clu_var = {}
for k, v in cuboids.items():
try:
ew, ev = LA.eigh(np.cov(D[sorted(v)].T))
clu_var[k] = 10 * np.sum(ew)
except LA.LinAlgError:
clu_var[k] = 0
clu_size = [len(v) for v in candlist]
clu_cent = [np.mean(D[list(v)], axis=0) for v in candlist]
# clu_elsc = [sorted({i:LA.norm(D[i]-clu_cent[k]) for i in v}.items(), key=lambda x: x[1]) for v in candlist]
clu_totD = [np.sum(D[list(v)]) / len(v) for v in candlist]
clu_basc = [
sorted({i: D[i][toidx(keylist[n])].sum()
for i in v}.items(),
key=lambda x: x[1],
reverse=True) for n, v in enumerate(candlist)
]
# if print_c:
# for i, k in enumerate([x[0] for x in sorted(clu_totD.items(), key=lambda p: p[1], reverse=True)]):
# expt, explr = clu_basc[k][0][0], clu_elsc[k][-1][0]
# print('%3d. %4d %4.2f %6.2f - %5d (%s) vs %5d (%s)' % (i, clu_size[k], clu_var[k], clu_totD[k], expt, rlab(expt), explr, rlab(explr)))
samplecount = np.zeros(len(cuboids), dtype=np.int16)
score = clu_totD
pdf = score / np.sum(score)
candidates = []
for i in range(num):
while True:
cluster_index = int(np.random.choice(len(pdf), p=pdf))
if samplecount[cluster_index] < len(candlist[cluster_index]):
break
# elm = candlist[cluster_index][samplecount[cluster_index]]
elm, _ = clu_basc[cluster_index][samplecount[cluster_index]]
samplecount[cluster_index] += 1
candidates.append(elm)
return candidates
def execute(self, num):
dlat = self.lattice.dlat
Ik = self.lattice.Ik
CM = self.lattice._CM()
D = self.lattice.E[:, self.lattice.Kr]
print("DEBUG: ", len(dlat), len(Ik), CM.shape, D.shape)
cuboids, score, elmlist = clusterlattice(dlat, CM, D, Ik, theta=self.theta, num_k=self.num_cluster)
keylist = list(cuboids.keys())
candlist = [cuboids[k] for k in keylist]
clu_var = {}
for k, v in cuboids.items():
try:
ew, ev = LA.eigh(np.cov(D[sorted(v)].T))
clu_var[k] = 10 * np.sum(ew)
except LA.LinAlgError:
clu_var[k] = 0
clu_size = [len(v) for v in candlist]
clu_cent = [np.mean(D[list(v)], axis=0) for v in candlist]
# clu_elsc = [sorted({i:LA.norm(D[i]-clu_cent[k]) for i in v}.items(), key=lambda x: x[1]) for v in candlist]
clu_totD = [np.sum(D[list(v)]) / len(v) for v in candlist]
clu_basc = [
sorted({i: D[i][toidx(keylist[n])].sum() for i in v}.items(), key=lambda x: x[1], reverse=True)
for n, v in enumerate(candlist)
]
# if print_c:
# for i, k in enumerate([x[0] for x in sorted(clu_totD.items(), key=lambda p: p[1], reverse=True)]):
# expt, explr = clu_basc[k][0][0], clu_elsc[k][-1][0]
# print('%3d. %4d %4.2f %6.2f - %5d (%s) vs %5d (%s)' % (i, clu_size[k], clu_var[k], clu_totD[k], expt, rlab(expt), explr, rlab(explr)))
samplecount = np.zeros(len(cuboids), dtype=np.int16)
score = clu_totD
pdf = score / np.sum(score)
candidates = []
for i in range(num):
while True:
cluster_index = int(np.random.choice(len(pdf), p=pdf))
if samplecount[cluster_index] < len(candlist[cluster_index]):
break
# elm = candlist[cluster_index][samplecount[cluster_index]]
elm, _ = clu_basc[cluster_index][samplecount[cluster_index]]
samplecount[cluster_index] += 1
candidates.append(elm)
return candidates
def execute(self, num):
dlat = self.lattice.dlat
Ik = self.lattice.Ik
CM = self.lattice._CM()
D = self.lattice.E[:, self.lattice.Kr]
print("DEBUG: ", len(dlat), len(Ik), CM.shape, D.shape)
clusters, score, elmlist = clusterlattice(dlat, CM, D, Ik, theta=self.theta, num_k=self.num_cluster)
samplecount = np.zeros(len(clusters), dtype=np.int16)
pdf = score / np.sum(score)
candidates = []
for i in range(num):
while True:
cluster_index = int(np.random.choice(len(pdf), p=pdf))
if samplecount[cluster_index] < len(elmlist[cluster_index]):
break
elm, dist = elmlist[cluster_index][samplecount[cluster_index]]
samplecount[cluster_index] += 1
candidates.append(elm)
return candidates
len(dlat)
logging.info('\n\n----------------------')
logging.info('SIZE,iset,%d', len(iset))
logging.info('SIZE,dlat,%d', len(dlat))
logging.info('Clustering Lattice:')
SKIPCLU = False
if SKIPCLU:
clu = pickle.load(open('clu.p', 'rb'))
score = pickle.load(open('score.p', 'rb'))
elmlist = pickle.load(open('elmlist.p', 'rb'))
else:
clu, score, elmlist = lat.clusterlattice(dlat,
CMr,
Dm,
iset,
num_k=num_clu)
cluk = list(clu.keys())
clulist = [clu[k] for k in cluk]
variance = np.zeros(len(cluk))
for n, k in enumerate(cluk):
if len(clulist[n]) == 1:
continue
cov = np.cov(DS[clulist[n]][:, Km].T)
ew, _ = LA.eigh(cov)
variance[n] = np.sum(ew)
variance2 = np.zeros(len(cluk))
iset = pickle.load(open(home + '/work/latt_intrinsics/iset_%d.p' % support, 'rb')); len(iset)
dlat = pickle.load(open(home + '/work/latt_intrinsics/dlat_%d.p' % support, 'rb')); len(dlat)
logging.info('\n\n----------------------')
logging.info('SIZE,iset,%d', len(iset))
logging.info('SIZE,dlat,%d', len(dlat))
logging.info('Clustering Lattice:')
SKIPCLU = False
if SKIPCLU:
clu = pickle.load(open('clu.p', 'rb'))
score = pickle.load(open('score.p', 'rb'))
elmlist = pickle.load(open('elmlist.p', 'rb'))
else:
clu, score, elmlist = lat.clusterlattice(dlat, CMr, Dm, iset, num_k=num_clu)
cluk = list(clu.keys())
clulist = [clu[k] for k in cluk]
variance = np.zeros(len(cluk))
for n, k in enumerate(cluk):
if len(clulist[n]) == 1:
continue
cov = np.cov(DS[clulist[n]][:,Km].T)
ew,_ = LA.eigh(cov)
variance[n] = np.sum(ew)
variance2 = np.zeros(len(cluk))
for n, k in enumerate(cluk):
if len(clulist[n]) == 1:
