def baseline(self, id_bo):
self.baseline_predicates = []
#TODO syntax and word based predicates
if id_bo in self.pairs:
value = self.pairs[id_bo].get_value()
lemmas_text = self.pairs[id_bo].get_feature_text('lemmas')
lemmas_hypo = self.pairs[id_bo].get_feature_hypo('lemmas')
metric = SetMetrics(text = lemmas_text, hypo = lemmas_hypo)
isec = metric.get_isec()
bo = '>overlap\n%s %s'%(id_bo, isec)
self.baseline_predicates.append(bo)
return self.baseline_predicates
def baseline(self, id_bo):
self.baseline_predicates = []
#TODO syntax and word based predicates
if id_bo in self.pairs:
value = self.pairs[id_bo].get_value()
lemmas_text = self.pairs[id_bo].get_feature_text('lemmas')
lemmas_hypo = self.pairs[id_bo].get_feature_hypo('lemmas')
metric = SetMetrics(text = lemmas_text, hypo = lemmas_hypo)
isec = metric.get_isec()
bo = 'Overlap(%s, %s)'%(id_bo, isec)
self.baseline_predicates.append(bo)
return self.baseline_predicates
def backoff(self, id_bo):
self.backoff_predicates = []
#TODO syntax and word based predicates
#TODO backoff with cosine metric instead of intersection
if id_bo in self.pairs:
value = self.pairs[id_bo].get_value()
lemmas_text = self.pairs[id_bo].get_feature_text('lemmas')
lemmas_hypo = self.pairs[id_bo].get_feature_hypo('lemmas')
metric = SetMetrics(text = lemmas_text, hypo = lemmas_hypo)
isec = metric.get_isec()
bo = '>overlap\n%s %s'%(id_bo, isec)
self.backoff_predicates.append(bo)
return self.backoff_predicates
def backoff(self, id_bo):
self.backoff_predicates = []
#TODO syntax and word based predicates
#TODO backoff with cosine metric instead of intersection
if id_bo in self.pairs:
value = self.pairs[id_bo].get_value()
lemmas_text = self.pairs[id_bo].get_feature_text('lemmas')
lemmas_hypo = self.pairs[id_bo].get_feature_hypo('lemmas')
metric = SetMetrics(text=lemmas_text, hypo=lemmas_hypo)
isec = metric.get_isec()
bo = '>overlap\n%s %s' % (id_bo, isec)
self.backoff_predicates.append(bo)
return self.backoff_predicates
def loadData(file_data, subset):
with open(file_data, 'r') as pf1:
tmp_pairs = pickle.load(pf1)
metric = SetMetrics()
X = []
Y = []
for pair in tmp_pairs:
id = pair.get_id()
if id in subset:
value = pair.get_value()
lemmas_text = pair.get_feature_text('lemmas')
lemmas_hypo = pair.get_feature_hypo('lemmas')
metric.set_text(lemmas_text)
metric.set_hypo(lemmas_hypo)
isec = metric.get_isec()
X.append([isec])
if value == 'TRUE':
Y.append(1)
else:
Y.append(0)
return (X, Y)
def load_file(file):
isec_t = []
values = {}
#C = 1.0
with open(file, 'r') as pf1:
tmp_pairs = pickle.load(pf1)
metric = SetMetrics()
X = []
Y = []
for pair in tmp_pairs:
id = pair.get_id()
value = pair.get_value()
lemmas_text = pair.get_feature_text('lemmas')
lemmas_hypo = pair.get_feature_hypo('lemmas')
metric.set_text(lemmas_text)
metric.set_hypo(lemmas_hypo)
isec = metric.get_isec()
isec_t.append(isec)
if isec in values:
values[isec] += 1
else:
values[isec] = 1
X.append([isec])
if value == 'TRUE':
Y.append(1)
else:
Y.append(0)
#svc = svm.SVC(kernel='linear', C=C).fit(X, Y)
#clf = svm.SVC(kernel='linear')
#clf.fit(X, Y)
# get the separating hyperplane
#print 'Weights asigned to the features: ', clf.coef_
#print 'Constants in decision function: ', clf.intercept_
#print 'number of support vector for each class: ', clf.n_support_
return (isec_t, values, X, Y)
def baseline(self, id_bo):
self.baseline_predicates = []
#TODO syntax and word based predicates
if id_bo in self.pairs:
value = self.pairs[id_bo].get_value()
pos_text = self.pairs[id_bo].get_feature_text('pos')
pos_hypo = self.pairs[id_bo].get_feature_hypo('pos')
pos_text.extend(pos_hypo)
for word, pos in pos_text:
lemma_predicate = '>token_back_lemma\n%s "%s"'%(id_bo, self.clean_str(word))
pos_predicate = '>toke_back_pos\n%s "%s"'%(id_bo, self.clean_str(pos))
self.baseline_predicates.append(lemma_predicate)
self.baseline_predicates.append(pos_predicate)
lemmas_text = self.pairs[id_bo].get_feature_text('lemmas')
lemmas_hypo = self.pairs[id_bo].get_feature_hypo('lemmas')
metric = SetMetrics(text = lemmas_text, hypo = lemmas_hypo)
isec = metric.get_isec()
bo = '>overlap\n%s %s'%(id_bo, isec)
self.baseline_predicates.append(bo)
return self.baseline_predicates
def baseline(self, id_bo):
self.baseline_predicates = []
#TODO syntax and word based predicates
if id_bo in self.pairs:
value = self.pairs[id_bo].get_value()
pos_text = self.pairs[id_bo].get_feature_text('pos')
pos_hypo = self.pairs[id_bo].get_feature_hypo('pos')
pos_text.extend(pos_hypo)
for word, pos in pos_text:
lemma_predicate = 'TokenBack(%s, "%s")'%(id_bo, self.clean_str(word))
pos_predicate = 'TokenBack(%s, "%s")'%(id_bo, self.clean_str(pos))
self.baseline_predicates.append(lemma_predicate)
self.baseline_predicates.append(pos_predicate)
lemmas_text = self.pairs[id_bo].get_feature_text('lemmas')
lemmas_hypo = self.pairs[id_bo].get_feature_hypo('lemmas')
metric = SetMetrics(text = lemmas_text, hypo = lemmas_hypo)
isec = metric.get_isec()
bo = 'Overlap(%s, %s)'%(id_bo, isec)
self.baseline_predicates.append(bo)
return self.baseline_predicates
def loadData(file_data, subset):
with open(file_data, 'r') as pf1:
tmp_pairs = pickle.load(pf1)
metric = SetMetrics()
X = []
Y = []
for pair in tmp_pairs:
id = pair.get_id()
if id in subset:
value = pair.get_value()
lemmas_text = pair.get_feature_text('lemmas')
lemmas_hypo = pair.get_feature_hypo('lemmas')
metric.set_text(lemmas_text)
metric.set_hypo(lemmas_hypo)
isec = metric.get_isec()
X.append([isec])
if value == 'TRUE':
Y.append(1)
else:
Y.append(0)
return (X, Y)