def big():
from BiCluster import DupbestBC, BiCluster
samples = np.random.choice(['A','T','C','G', None], (1, 4, 6))
Gs = map( Graph, samples)
bcs = []
grammar = {}
totalBits = sum(map(lambda x : x._G.order(), Gs))
Gs[0].vis()
for i in range(50):
print "alpha:%s\n"%(sum(map(lambda x : x._G.order(), Gs))/float(totalBits))
tables, symbols, ecms, cols = prepare(Gs)
bc = DupbestBC(tables, symbols, ecms, cols)
if not bc:
print "no more rules!"
break
#import pdb; pdb.set_trace()
print bc
bcs.append(bc)
new = T((-1, 'NT%s'%i))
bc._nt = new
r = rule.fromBC(bc)
print r
grammar[r._lhs] = r
for G in Gs:
G.reduction(r)
tables, symbols, ecms, cols = prepare(Gs)
for ind, _bc in enumerate(bcs):
bc_new_c = BiCluster().update(_bc, tables, ecms, col=bc._nt)
bc_new_r = BiCluster().update(_bc, tables, ecms, row=bc._nt)
#print "bcG: %s"%bc_new.logGain()
best = None
if bc_new_c :
bc_new = bc_new_c
best = bc_new_c.logGain()
if bc_new_r and bc_new_r.logGain() > best:
bc_new = bc_new_r
best = bc_new_r.logGain()
if best - bc.logGain() > 2.0:
print "Attach"
print bc_new
r = rule.fromBC(bc_new)
print r
grammar[r._lhs] = r
for G in Gs:
G.reduction(r)
bcs[ind] = bc_new
Gs[0].vis(file='big_%s.png'%str(new), rule = r)
for g in grammar.values():
print g
def learning(samples, alpha=0.05, beta=5, cut=30, gamma=2.0, N=50):
from BiCluster import DupbestBC, BiCluster
Gs = map( Graph, samples)
bcs = []
grammar = {}
totalBits = sum(map(lambda x : x._G.order(), Gs))
#Gs[0].vis()
for i in range(N):
print "Compression:%s\n"%(sum(map(lambda x : x._G.order(), Gs))/float(totalBits))
tables, symbols, ecms, cols = prepare(Gs)
bc = DupbestBC(tables, symbols, ecms, cols, alpha=alpha, beta=beta, cut=cut)
if not bc:
print "no more rules!"
break
#import pdb; pdb.set_trace()
print bc
bcs.append(bc)
new = T((-1, 'NT%s'%i))
bc._nt = new
r = rule.fromBC(bc)
grammar[r._lhs] = r
for G in Gs:
G.reduction(r)
tables, symbols, ecms, cols = prepare(Gs)
for ind, _bc in enumerate(bcs):
bc_new_c = BiCluster().update(_bc, tables, ecms, col=bc._nt)
bc_new_r = BiCluster().update(_bc, tables, ecms, row=bc._nt)
best = None
if bc_new_c :
bc_new = bc_new_c
best = bc_new_c.logGain()
if bc_new_r and bc_new_r.logGain() > best:
bc_new = bc_new_r
best = bc_new_r.logGain()
if best - bc.logGain() > gamma:
r = rule.fromBC(bc_new)
grammar[r._lhs] = r
for G in Gs:
G.reduction(r)
bcs[ind] = bc_new
#Gs[0].vis(file='big_%s.png'%str(new), rule = r)
return Gs, grammar, bcs