Last active
September 6, 2018 09:50
-
-
Save fjavieralba/3969016 to your computer and use it in GitHub Desktop.
Python class for tagging text with dictionaries
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class DictionaryTagger(object): | |
def __init__(self, dictionary_paths): | |
files = [open(path, 'r') for path in dictionary_paths] | |
dictionaries = [yaml.load(dict_file) for dict_file in files] | |
map(lambda x: x.close(), files) | |
self.dictionary = {} | |
self.max_key_size = 0 | |
for curr_dict in dictionaries: | |
for key in curr_dict: | |
if key in self.dictionary: | |
self.dictionary[key].extend(curr_dict[key]) | |
else: | |
self.dictionary[key] = curr_dict[key] | |
self.max_key_size = max(self.max_key_size, len(key)) | |
def tag(self, postagged_sentences): | |
return [self.tag_sentence(sentence) for sentence in postagged_sentences] | |
def tag_sentence(self, sentence, tag_with_lemmas=False): | |
""" | |
the result is only one tagging of all the possible ones. | |
The resulting tagging is determined by these two priority rules: | |
- longest matches have higher priority | |
- search is made from left to right | |
""" | |
tag_sentence = [] | |
N = len(sentence) | |
if self.max_key_size == 0: | |
self.max_key_size = N | |
i = 0 | |
while (i < N): | |
j = min(i + self.max_key_size, N) #avoid overflow | |
tagged = False | |
while (j > i): | |
expression_form = ' '.join([word[0] for word in sentence[i:j]]).lower() | |
expression_lemma = ' '.join([word[1] for word in sentence[i:j]]).lower() | |
if tag_with_lemmas: | |
literal = expression_lemma | |
else: | |
literal = expression_form | |
if literal in self.dictionary: | |
#self.logger.debug("found: %s" % literal) | |
is_single_token = j - i == 1 | |
original_position = i | |
i = j | |
taggings = [tag for tag in self.dictionary[literal]] | |
tagged_expression = (expression_form, expression_lemma, taggings) | |
if is_single_token: #if the tagged literal is a single token, conserve its previous taggings: | |
original_token_tagging = sentence[original_position][2] | |
tagged_expression[2].extend(original_token_tagging) | |
tag_sentence.append(tagged_expression) | |
tagged = True | |
else: | |
j = j - 1 | |
if not tagged: | |
tag_sentence.append(sentence[i]) | |
i += 1 | |
return tag_sentence |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dicttagger = DictionaryTagger([ 'dicts/positive.yml', 'dicts/negative.yml', 'dicts/inc.yml', 'dicts/dec.yml']) | |
dict_tagged_sentences = dicttagger.tag(pos_tagged_sentences) | |
pprint(dict_tagged_sentences) | |
[[('What', 'What', ['WP']), | |
('can', 'can', ['MD']), | |
('I', 'I', ['PRP']), | |
('say', 'say', ['VB']), | |
('about', 'about', ['IN']), | |
('this', 'this', ['DT']), | |
('place', 'place', ['NN']), | |
('.', '.', ['.'])], | |
[('The', 'The', ['DT']), | |
('staff', 'staff', ['NN']), | |
('of', 'of', ['IN']), | |
('the', 'the', ['DT']), | |
('restaurant', 'restaurant', ['NN']), | |
('is', 'is', ['VBZ']), | |
('nice', 'nice', ['positive', 'JJ']), | |
('and', 'and', ['CC']), | |
('eggplant', 'eggplant', ['NN']), | |
('is', 'is', ['VBZ']), | |
('not', 'not', ['RB']), | |
('bad', 'bad', ['negative', 'JJ']), | |
('.', '.', ['.'])], | |
[('apart', 'apart', ['NN']), | |
('from', 'from', ['IN']), | |
('that', 'that', ['DT']), | |
(',', ',', [',']), | |
('very', 'very', ['inc', 'RB']), | |
('uninspired', 'uninspired', ['negative', 'VBN']), | |
('food', 'food', ['NN']), | |
(',', ',', [',']), | |
('lack', 'lack', ['NN']), | |
('of', 'of', ['IN']), | |
('atmosphere', 'atmosphere', ['NN']), | |
('and', 'and', ['CC']), | |
('too', 'too', ['inc', 'RB']), | |
('expensive', 'expensive', ['negative', 'JJ']), | |
('.', '.', ['.'])], | |
[('I', 'I', ['PRP']), | |
('am', 'am', ['VBP']), | |
('a', 'a', ['DT']), | |
('staunch', 'staunch', ['NN']), | |
('vegetarian', 'vegetarian', ['NN']), | |
('and', 'and', ['CC']), | |
('was', 'was', ['VBD']), | |
('sorely', 'sorely', ['inc', 'RB']), | |
('dissapointed', 'dissapointed', ['negative', 'VBN']), | |
('with', 'with', ['IN']), | |
('the', 'the', ['DT']), | |
('veggie', 'veggie', ['NN']), | |
('options', 'options', ['NNS']), | |
('on', 'on', ['IN']), | |
('the', 'the', ['DT']), | |
('menu', 'menu', ['NN']), | |
('.', '.', ['.'])], | |
[('Will', 'Will', ['NNP']), | |
('be', 'be', ['VB']), | |
('the', 'the', ['DT']), | |
('last', 'last', ['JJ']), | |
('time', 'time', ['NN']), | |
('I', 'I', ['PRP']), | |
('visit', 'visit', ['VBP']), | |
(',', ',', [',']), | |
('I', 'I', ['PRP']), | |
('recommend others to avoid', 'recommend others to avoid', ['negative']), | |
('.', '.', ['.'])]] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dicttagger = DictionaryTagger([ 'dicts/positive.yml', 'dicts/negative.yml', 'dicts/inc.yml', 'dicts/dec.yml', 'dicts/inv.yml']) | |
dict_tagged_sentences = dicttagger.tag(pos_tagged_sentences) | |
pprint(dict_tagged_sentences) | |
[[('What', 'What', ['WP']), | |
('can', 'can', ['MD']), | |
('I', 'I', ['PRP']), | |
('say', 'say', ['VB']), | |
('about', 'about', ['IN']), | |
('this', 'this', ['DT']), | |
('place', 'place', ['NN']), | |
('.', '.', ['.'])], | |
[('The', 'The', ['DT']), | |
('staff', 'staff', ['NN']), | |
('of', 'of', ['IN']), | |
('the', 'the', ['DT']), | |
('restaurant', 'restaurant', ['NN']), | |
('is', 'is', ['VBZ']), | |
('nice', 'nice', ['positive', 'JJ']), | |
('and', 'and', ['CC']), | |
('eggplant', 'eggplant', ['NN']), | |
('is', 'is', ['VBZ']), | |
('not', 'not', ['inv', 'RB']), | |
('bad', 'bad', ['negative', 'JJ']), | |
('.', '.', ['.'])], | |
[('apart', 'apart', ['NN']), | |
('from', 'from', ['IN']), | |
('that', 'that', ['DT']), | |
(',', ',', [',']), | |
('very', 'very', ['inc', 'RB']), | |
('uninspired', 'uninspired', ['negative', 'VBN']), | |
('food', 'food', ['NN']), | |
(',', ',', [',']), | |
('lack of', 'lack of', ['inv']), | |
('atmosphere', 'atmosphere', ['NN']), | |
('and', 'and', ['CC']), | |
('too', 'too', ['inc', 'RB']), | |
('expensive', 'expensive', ['negative', 'JJ']), | |
('.', '.', ['.'])], | |
[('I', 'I', ['PRP']), | |
('am', 'am', ['VBP']), | |
('a', 'a', ['DT']), | |
('staunch', 'staunch', ['NN']), | |
('vegetarian', 'vegetarian', ['NN']), | |
('and', 'and', ['CC']), | |
('was', 'was', ['VBD']), | |
('sorely', 'sorely', ['inc', 'RB']), | |
('dissapointed', 'dissapointed', ['negative', 'VBN']), | |
('with', 'with', ['IN']), | |
('the', 'the', ['DT']), | |
('veggie', 'veggie', ['NN']), | |
('options', 'options', ['NNS']), | |
('on', 'on', ['IN']), | |
('the', 'the', ['DT']), | |
('menu', 'menu', ['NN']), | |
('.', '.', ['.'])], | |
[('Will', 'Will', ['NNP']), | |
('be', 'be', ['VB']), | |
('the', 'the', ['DT']), | |
('last', 'last', ['JJ']), | |
('time', 'time', ['NN']), | |
('I', 'I', ['PRP']), | |
('visit', 'visit', ['VBP']), | |
(',', ',', [',']), | |
('I', 'I', ['PRP']), | |
('recommend others to avoid', 'recommend others to avoid', ['negative']), | |
('.', '.', ['.'])]] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dicttagger = DictionaryTagger([ 'dicts/positive.yml', 'dicts/negative.yml']) | |
dict_tagged_sentences = dicttagger.tag(pos_tagged_sentences) | |
pprint(dict_tagged_sentences) | |
[[('What', 'What', ['WP']), | |
('can', 'can', ['MD']), | |
('I', 'I', ['PRP']), | |
('say', 'say', ['VB']), | |
('about', 'about', ['IN']), | |
('this', 'this', ['DT']), | |
('place', 'place', ['NN']), | |
('.', '.', ['.'])], | |
[('The', 'The', ['DT']), | |
('staff', 'staff', ['NN']), | |
('of', 'of', ['IN']), | |
('the', 'the', ['DT']), | |
('restaurant', 'restaurant', ['NN']), | |
('is', 'is', ['VBZ']), | |
('nice', 'nice', ['positive', 'JJ']), | |
('and', 'and', ['CC']), | |
('eggplant', 'eggplant', ['NN']), | |
('is', 'is', ['VBZ']), | |
('not', 'not', ['RB']), | |
('bad', 'bad', ['negative', 'JJ']), | |
('.', '.', ['.'])], | |
[('apart', 'apart', ['NN']), | |
('from', 'from', ['IN']), | |
('that', 'that', ['DT']), | |
(',', ',', [',']), | |
('very', 'very', ['RB']), | |
('uninspired', 'uninspired', ['negative', 'VBN']), | |
('food', 'food', ['NN']), | |
(',', ',', [',']), | |
('lack', 'lack', ['NN']), | |
('of', 'of', ['IN']), | |
('atmosphere', 'atmosphere', ['NN']), | |
('and', 'and', ['CC']), | |
('too', 'too', ['RB']), | |
('expensive', 'expensive', ['negative', 'JJ']), | |
('.', '.', ['.'])], | |
[('I', 'I', ['PRP']), | |
('am', 'am', ['VBP']), | |
('a', 'a', ['DT']), | |
('staunch', 'staunch', ['NN']), | |
('vegetarian', 'vegetarian', ['NN']), | |
('and', 'and', ['CC']), | |
('was', 'was', ['VBD']), | |
('sorely', 'sorely', ['RB']), | |
('dissapointed', 'dissapointed', ['negative', 'VBN']), | |
('with', 'with', ['IN']), | |
('the', 'the', ['DT']), | |
('veggie', 'veggie', ['NN']), | |
('options', 'options', ['NNS']), | |
('on', 'on', ['IN']), | |
('the', 'the', ['DT']), | |
('menu', 'menu', ['NN']), | |
('.', '.', ['.'])], | |
[('Will', 'Will', ['NNP']), | |
('be', 'be', ['VB']), | |
('the', 'the', ['DT']), | |
('last', 'last', ['JJ']), | |
('time', 'time', ['NN']), | |
('I', 'I', ['PRP']), | |
('visit', 'visit', ['VBP']), | |
(',', ',', [',']), | |
('I', 'I', ['PRP']), | |
('recommend others to avoid', 'recommend others to avoid', ['negative']), | |
('.', '.', ['.'])]] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment