def make_gec_instances(raw_file, pos_file, correct_file=None): global nf, vf, df, pf, prof instances = FgExampleMemoryStore() raw_lines = [[BOS] + rl.strip().split() + [EOS] for rl in codecs.open(raw_file, 'r', 'utf8').readlines()] pos_lines = [[BOS] + pl.strip().split() + [EOS] for pl in codecs.open(pos_file, 'r', 'utf8').readlines()] if correct_file is not None: correct_lines = [[BOS] + cl.strip().split() + [EOS] for cl in codecs.open(correct_file, 'r', 'utf8').readlines()] pass else: correct_lines = [None] * len(raw_lines) pass for line_idx in range(len(raw_lines)): factor_graph = FactorGraph() vc = VarConfig() prev_hc = None for w_idx, (w,p,c) in enumerate(zip(raw_lines[line_idx], pos_lines[line_idx], correct_lines[line_idx])): candidates = generate_correction_candidates(p,w) print w, p, c print 'can', candidates, c hc = Var(Var.VarType.PREDICTED, len(candidates), "TAG_" + str(w_idx) , candidates) vc.put(hc, c) if prev_hc: t_varset = VarSet(hc) t_varset.add(prev_hc) t_factor = CRFFactor(t_varset, [prev_hc, hc], "BIGRAM") factor_graph.addFactor(t_factor) else: pass prev_hc = hc pass instances.add(LabeledFgExample(factor_graph, vc)) return instances
def make_instances(txt_file, tag_list, obs_list):
instances = FgExampleMemoryStore()
text_train = [t.strip() for t in open(txt_file).read().split('###/###') if t.strip() != '']
for x in range(len(text_train)):
factor_graph = FactorGraph()
vc = VarConfig()
prev_hc = None
for i, line in enumerate(text_train[x].split('\n')):
hidden_state = line.split('/')[1].strip()
observed_state = line.split('/')[0].strip()
# print 'h', hidden_state, 'o', observed_state
# make variables with their configurations
#r = random.randint(0, len(tag_list))
#s = set(tag_list[:r])
#s.add(hidden_state)
#s = list(s)
s = tag_list
hc = Var(Var.VarType.PREDICTED, len(s), "TAG_" + str(i), s)
vc.put(hc, hidden_state)
# o = Var(Var.VarType.PREDICTED , len(obs_list), "OBS_" + str(i), obs_list)
# vc.put(o, observed_state)
# make transition factor
if prev_hc:
t_varset = VarSet(hc)
t_varset.add(prev_hc)
t_factor = CRFFactor(t_varset, [prev_hc, hc], 'TAG-TAG')
factor_graph.addFactor(t_factor)
else:
pass
prev_hc = hc
# make emission factor
e_varset = VarSet(hc)
# e_varset.add(o)
# e_factor = CRFFactor(e_varset, [hc, o], 'TAG-OBS')
e_factor = ObservedFactor(e_varset, [hc], 'TAG-OBS', observed_state)
factor_graph.addFactor(e_factor)
# make clamp factor
# c_factor = Clamper(o, obs_list.index(observed_state))
# factor_graph.addFactor(c_factor)
instances.add(LabeledFgExample(factor_graph, vc))
return instances
def make_gec_instances(raw_file, pos_file, aspect_file):
global cl
instances = FgExampleMemoryStore()
#raw_lines = [[BOS] + rl.strip().split() + [EOS] for rl in codecs.open(raw_file, 'r', 'utf8').readlines()]
#pos_lines = [[BOS] + pl.strip().split() + [EOS] for pl in codecs.open(pos_file, 'r', 'utf8').readlines()]
with codecs.open(aspect_file, 'r', 'utf8') as aspect_f, codecs.open(
raw_file, 'r',
'utf8') as raw_f, codecs.open(pos_file, 'r', 'utf8') as pos_f:
for raw_line, pos_line, aspect_line in zip(raw_f, pos_f, aspect_f):
rl = [BOS] + raw_line.strip().split() + [EOS]
pl = [BOS] + pos_line.strip().split() + [EOS]
al = [BOS] + aspect_line.strip().split() + [EOS]
sys.stderr.write('.')
factor_graph = FactorGraph()
vc = VarConfig()
prev_hc = None
for w_idx, (w, p, a) in enumerate(zip(rl, pl, al)):
#w does not contain aspet
candidates = get_candidates(cl, w, p)
if len(candidates) == 1:
sys.stderr.write('no cans:' + w + ' ' + p + '\n')
else:
pass
hc = Var(Var.VarType.PREDICTED, len(candidates),
"TAG_" + str(w_idx), candidates)
vc.put(hc, w + '|||' + a)
assert w + '|||' + a in candidates
if prev_hc:
t_varset = VarSet(hc)
t_varset.add(prev_hc)
t_factor = CRFFactor(t_varset, [prev_hc, hc], "BIGRAM")
factor_graph.addFactor(t_factor)
else:
pass
prev_hc = hc
pass
instances.add(LabeledFgExample(factor_graph, vc))
return instances
def get(self, i):
global tag2id, id2tag, obs2id, id2obs, obs_list
#pdb.set_trace()
ti = self.training_instances[i]
tag_subset = self.en_vocab
factor_graph = FactorGraph()
vc = VarConfig()
curr_g = {}
curr_s = {}
past_g_sent = {}
curr_rg = {}
curr_s_order = []
for crg in ti.current_revealed_guesses:
curr_rg[tuple(crg.id)] = crg
for psg in ti.past_guesses_for_current_sent:
past_g_sent[tuple(psg.id)] = psg
for cg in ti.current_guesses:
curr_g[tuple(cg.id)] = cg
for cs in ti.current_sent:
curr_s[tuple(cs.id)] = cs
curr_s_order.append((int(cs.position), cs))
curr_s_order.sort()
var_map = {}
fac_map = {}
#pdb.set_trace()
# fac_map_summary = {}
for cso_id0, cso0 in curr_s_order:
c, hs = self.get_hs(cso0, curr_rg, curr_g)
print c, hs
hc_var = Var(Var.VarType.PREDICTED, len(tag_subset),
'TAG_' + str(cso_id0), tag_subset)
var_map[cso_id0] = (hc_var, hs, c)
if not c:
try:
vc.put(hc_var, hs)
except:
print hs
print 'vc is broken...'
pdb.set_trace()
assert cso0.id not in curr_rg
e_factor = ObservedEFactor(VarSet(hc_var), hc_var,
cso0.l2_word)
fid = (cso_id0, 'er')
fac_map[fid] = fac_map.get(fid, []) + [e_factor]
# fac_map_summary[fid] = fac_map_summary.get(fid, []) + [cso0.l2_word + '->emission->' + str(cso_id0)]
else:
pass
for cso_id1, cso1 in curr_s_order:
for cso_id2, cso2 in curr_s_order:
if cso_id1 != cso_id2 and cso_id1 - cso_id2 == 1:
(v1_hc, v1_hs, v1_c) = var_map[cso_id1]
(v2_hc, v2_hs, v2_c) = var_map[cso_id2]
if not v1_c and not v2_c: # both vars are not revealed
fid = tuple(sorted([(cso_id1, 'h'), (cso_id2, 'h')]))
# there can be only 1 TT factor between 2 unobserved vars
if fid not in fac_map:
print fid, 'both are hidden'
t_varset = VarSet(v1_hc)
t_varset.add(v2_hc)
t_factor = TTFactor(t_varset,
var1=v1_hc,
var1pos=cso_id1,
var2=v2_hc,
var2pos=cso_id2)
fac_map[fid] = fac_map.get(fid, []) + [t_factor]
# fac_map_summary[fid] = fac_map_summary.get(fid, []) + [
# str(cso_id1) + '->trans->' + str(cso_id2)]
elif not v1_c and v2_c: # var 2 is reveled i.e. observed
fid = tuple(sorted([(cso_id1, 'h'), (cso_id2, 'r')]))
if fid not in fac_map:
print cso_id1, ' is hidden', cso_id2, 'is reveled'
t_factor = ObservedTFactor(VarSet(v1_hc),
var1=v1_hc,
var1pos=cso_id1,
var2=None,
var2pos=None,
observed_state=v2_hs)
# there can be multiple factors connected to a v1_hc
fac_map[fid] = fac_map.get(fid, []) + [t_factor]
# fac_map_summary[fid] = fac_map_summary.get(fid, []) + [
# v2_hs + '->trans->' + str(cso_id1)]
elif v1_c and not v2_c: # var 1 is reveled i.e. observed
fid = tuple(sorted([(cso_id1, 'r'), (cso_id2, 'h')]))
if fid not in fac_map:
print cso_id2, 'is hidden', cso_id1, 'is reveled'
t_factor = ObservedTFactor(VarSet(v2_hc),
var1=None,
var1pos=None,
var2=v2_hc,
var2pos=cso_id2,
observed_state=v1_hs)
fac_map[fid] = fac_map.get(fid, []) + [t_factor]
# fac_map_summary[fid] = fac_map_summary.get(fid, []) + [v1_hs + '->trans->' + str(cso_id2)]
else:
# this means both v1_hc and v2_hc are reveled, so we dont do anything..
pass
for fid, factors in fac_map.items():
for _factor in factors:
try:
factor_graph.addFactor(_factor)
except:
print 'something broken when adding factor to factor_graph'
pdb.set_trace()
sys.stderr.write('.')
return LabeledFgExample(factor_graph, vc)