def value_for_text(self, t, rp=default_rp, ignore_pos=False):
_and = rp.pos_tagger().tagset.AND
occurrences = [
count_occurrences(sent, _and, ignore_pos)
for sent in rp.tagged_sentences(t)
]
return sum(occurrences) / (len(rp.all_words(t)) / 1000) \
if len(rp.all_words(t)) else 0
def test():
logic_operators = default_rp.pos_tagger().tagset.LOGIC_OPERATORS
print(count_occurrences([('O', 'ART'), ('gato', 'N'), ('correu', 'V'),
('e', 'KC'), ('sumiu', 'V'), ('.', 'PU')],
logic_operators[0]))
print(count_occurrences([('Ele', 'PROPESS'), ('entra', 'V'), (',', 'PU'),
('contanto', 'KS'), ('que', 'KS'),
('saia', 'V'), ('.', 'PU')],
logic_operators[12]))
print(count_occurrences_for_all([('Ele', 'PROPESS'), ('entra', 'V'),
(',', 'PU'), ('contanto', 'KS'),
('que', 'KS'), ('saia', 'V'), ('e', 'KC'),
('feche', 'V'), ('a', 'ART'),
('porta', 'N'), ('.', 'PU')],
logic_operators))
lo = LogicOperators()
t = base.Text(base_path + '/corpora/folha/folha0.txt')
results = lo.values_for_text(t)
print(results)
def test():
logic_operators = default_rp.pos_tagger().tagset.LOGIC_OPERATORS
print(
count_occurrences([('O', 'ART'), ('gato', 'N'), ('correu', 'V'),
('e', 'KC'), ('sumiu', 'V'), ('.', 'PU')],
logic_operators[0]))
print(
count_occurrences([('Ele', 'PROPESS'), ('entra', 'V'), (',', 'PU'),
('contanto', 'KS'), ('que', 'KS'), ('saia', 'V'),
('.', 'PU')], logic_operators[12]))
print(
count_occurrences_for_all([('Ele', 'PROPESS'), ('entra', 'V'),
(',', 'PU'), ('contanto', 'KS'),
('que', 'KS'), ('saia', 'V'), ('e', 'KC'),
('feche', 'V'), ('a', 'ART'),
('porta', 'N'), ('.', 'PU')],
logic_operators))
lo = LogicOperators()
t = base.Text(base_path + '/corpora/folha/folha0.txt')
results = lo.values_for_text(t)
print(results)
def value_for_text(self, t, rp=default_rp, ignore_pos=False):
_and = rp.pos_tagger().tagset.AND
occurrences = [count_occurrences(sent, _and, ignore_pos)
for sent in rp.tagged_sentences(t)]
return sum(occurrences) / (len(rp.all_words(t)) / 1000) \
if len(rp.all_words(t)) else 0