Python tag.UnigramTagger類代碼示例

def pos_tag(pos_type, tokenized_sent):
	if pos_type == 'unigram':
		brown_train = pickle.load(open('res/brown_train.pkl', 'rb'))
		unigram_tagger = UnigramTagger(brown_train)
		return unigram_tagger.tag(tokenized_sent)
	elif pos_type == 'max_pos':
		return nltk.pos_tag(tokenized_sent)		

 def tag_unigrams_by_topic(self, dict_of_sentences_by_topic):
     tagged_unigrams_by_topic = {}
     train_sents = mac_morpho.tagged_sents()[:5000]
     tagger = UnigramTagger(train_sents)
     for k, v in dict_of_sentences_by_topic.items():
         tagged_unigrams_by_topic[k] = tagger.batch_tag(dict_of_sentences_by_topic[k])
     return tagged_unigrams_by_topic

 def trainUniTnT(self):
     """train unigram and tnt seperatly without DefaultTagger"""
     self.split_into_folds()
     for k in range(1, (self.folds + 1)):
         train_sents = sum(self.foldlist[: (self.folds - 1)], [])
         tnt_tagger = tnt.TnT(N=100)
         tnt_tagger.train(train_sents)
         print(str(k) + " fold: tnt evaluated")
         unigram = UnigramTagger(train_sents)
         print(str(k) + " fold: unigram evaluated")
         to_tag = [untag(i) for i in self.foldlist[self.folds - 1]]
         self.tnt_tagged += tnt_tagger.tag_sents(to_tag)
         self.uni_tagged += unigram.tag_sents(to_tag)
         self.org_tagged += self.foldlist[self.folds - 1]
         self.foldlist = [self.foldlist[self.folds - 1]] + self.foldlist[: (self.folds - 1)]
     self.tnt = tnt_tagger
     self.unigram = unigram
     self.tnt_avg_acc = accuracy(sum(self.org_tagged, []), sum(self.tnt_tagged, []))
     self.uni_avg_acc = accuracy(sum(self.org_tagged, []), sum(self.uni_tagged, []))
     print("Accuracy of concatenated tnt-tagged sentences: ", self.tnt_avg_acc)
     print("Accuracy of concatenated unigram-tagged sentences: ", self.uni_avg_acc)
     (self.tnt_tagprecision, self.tnt_tagrecall) = self.tagprecision_recall(
         tnt_tagger, self.tnt_tagged, self.org_tagged
     )
     (self.unigram_tagprecision, self.unigram_tagrecall) = self.tagprecision_recall(
         unigram, self.uni_tagged, self.org_tagged
     )
     # delete following values so that trainRegexp has the inicial values
     self.org_tagged = []
     self.foldlist = []
     for i in range(1, self.folds + 1):
         self.foldlist.append(self.create_fold(i))

	def tag_words(self, words, sents):
		train_sents = treebank.tagged_sents()
		tagger = UnigramTagger(train_sents)
		test_sents = tagger.tag(sents[0])
		# test_sents = treebank.tagged_sents()[3000:]
		# print treebank.tagged_sents()[1:]
		# print "accuracy: " + str(self._tagger.evaluate(test_sents))
		# print self._tagger.tag(words)
		# print test_sents
		print tagger.evaluate(test_sents)

def baseline(tagged_sentences):
    from nltk.tag import UnigramTagger
    from nltk.tag import DefaultTagger
    from collections import Counter

    # lowercase everything
    # remove all instances of non-universal tags for propper comparison with
    # the other methods
    new_tagged_sentences = []
    for sent in tagged_sentences:
        sent = [(x[0].lower(), x[1]) for x in sent]
        sent = [x for x in sent if x[1] in _UNI]
        new_tagged_sentences.append(sent)
    tagged_sentences = new_tagged_sentences

    # size of corpus
    corpus_size = sum([len(sent) for sent in tagged_sentences])
    print('Corpus size: {} docs'.format(len(tagged_sentences)))
    print('Corpus size: {} tokens'.format(corpus_size))
    
    # train/test split
    test_pct = 0.3
    test_len = int(len(tagged_sentences) * test_pct)
    test_idx = len(tagged_sentences) - test_len
    train_set = tagged_sentences[:test_idx]
    test_set = tagged_sentences[test_idx:]
    print('Train set: {} docs'.format(len(train_set)))
    print('Test set: {} docs'.format(len(test_set)))

    # calculate test set size in tokens
    test_size = sum([len(sent) for sent in test_set])
    print('Test set: {} tokens'.format(test_size))

    # calculate most comman tag in the train set
    # this should be 'NOUN'
    tag_dist = []
    for sent in train_set:
        tag_dist += [x[1] for x in sent]
    counts = Counter()
    counts.update(tag_dist)
    most_common = counts.most_common(1)[0][0]
    print('Most common tag: {}'.format(most_common))

    # Create model
    backoff = DefaultTagger(most_common)
    tagger = UnigramTagger(train=train_set, backoff=backoff, cutoff=5)

    # Evaluate
    acc = tagger.evaluate(test_set)
    print('Baseline: {}'.format(acc))

def getUnigramTaggerAccuracy(trainingSet, testingSet):
    # trains and returns the accuracy of the UnigramTagger

    # get untagged sentences and gold POS tags
    testingUntaggedSentences = [[taggedWord[0] for taggedWord in sentence] for sentence in testingSet]
    testingGoldPOSTags = [[taggedWord[1] for taggedWord in sentence] for sentence in testingSet]

    # train tagger
    unigramTagger = UnigramTagger(trainingSet)

    # test tagger and get predicted POS tags
    unigramTaggedSentences = unigramTagger.tag_sents(testingUntaggedSentences)
    unigramTaggedSentencesPOSTags = [[taggedWord[1] for taggedWord in sentence] for sentence in unigramTaggedSentences]

    # calculate and return accuracy
    return calculateAccuracy(testingGoldPOSTags, unigramTaggedSentencesPOSTags)

def tag_penn(words):
    """
    Tokenizes text by using a Penn Treebank tagged sentence and word tokenizer.

    Parameters
    ----------
    words: A list of strings.

    Returns
    -------
    A list of tuples of (str, str)
    """

    pt_tagger = UnigramTagger(treebank.tagged_sents())
    tags = pt_tagger.tag(words)

    return tags

def contextual_rules(wikicorpus_dir, context_file):
    sentences = wikicorpus(wikicorpus_dir, words=1000000)

    ANONYMOUS = "anonymous"
    for s in sentences:
        for i, (w, tag) in enumerate(s):
            if tag == "NP": # NP = proper noun in Parole tagset.
                s[i] = (ANONYMOUS, "NP")

    ctx = fntbl37()

    tagger = UnigramTagger(sentences)
    tagger = BrillTaggerTrainer(tagger, ctx, trace=0)
    tagger = tagger.train(sentences, max_rules=100)

    #print tagger.evaluate(wikicorpus(10000, start=1))

    with open(context_file, "w") as f:
        for rule in tagger.rules():
            f.write("%s\n" % rule)

def make_pos_model(model_type):
    now = time.time()

    reader = TaggedCorpusReader('.', 'greek_training_set.pos')
    train_sents = reader.tagged_sents()
    if model_type == 'unigram':
        tagger = UnigramTagger(train_sents)
        file = 'unigram.pickle'
    elif model_type == 'bigram':
        tagger = BigramTagger(train_sents)
        file = 'bigram.pickle'
    elif model_type == 'trigram':
        tagger = TrigramTagger(train_sents)
        file = 'trigram.pickle'
    elif model_type == 'backoff':
        tagger1 = UnigramTagger(train_sents)
        tagger2 = BigramTagger(train_sents, backoff=tagger1)
        tagger = TrigramTagger(train_sents, backoff=tagger2)
        file = '123grambackoff.pickle'
    elif model_type == 'tnt':
        tagger = tnt.TnT()
        tagger.train(train_sents)
        file = 'tnt.pickle'
    else:
        print('Invalid model_type.')

    _dir = os.path.expanduser('~/greek_models_cltk/taggers/pos')
    path = os.path.join(_dir, file)
    with open(path, 'wb') as f:
        pickle.dump(tagger, f)

    print('Completed training {0} model in {1} seconds to {2}.'.format(model_type, time.time() - now, path))

def tag_linked(words, default_tag='INFO'):
    """
    Tokenizes text by using a Penn Treebank tagged sentence and word tokenizers.
    Uses DefaultTagger to assign "default_tag" to any element missed by Penn Treebank tagger.

    Parameters
    ----------
    words: A list of strings.

    Returns
    -------
    A list of tuples of (str, str)
    :param default_tag:
    """

    default_tagger = DefaultTagger(default_tag)
    pt_tagger = UnigramTagger(treebank.tagged_sents())

    pt_tagger._taggers = [pt_tagger, default_tagger]

    tags = pt_tagger.tag(words)

    return tags

class PyTenseShift(object):

    """Initialization of PyTenseShift objects.
    
    The important part when you use the PlPyTenseShift is that
    we allow you to implmenent your own Tagger to optimize your
    results in translating from present to past tense. So, you need
    to implement the taggerinterface and change the second line of
    this code
    """
    def __init__(self, corpus, isPl):
        if isPl:
            self.tagger = FirstTagger(corpus)
        else:
            dtag = DefaultTagger("NN")
            self.__utag = UnigramTagger(corpus.tagged_sents(), backoff = dtag)

    """ Tokenize the input sentence into words.
    This kind of representation is better to evaluate.
    
    """
    def _tokenize(self, tense, isPl):
        if isPl:
            return self.tagger.tag(tense)
        else:
            return self.__utag.tag(tokenize(tense))

    def getPastTense(self, tense):
        """Translates sentence given in present tense into past tense 
        
        Args:
            sentence (str): Sentence to translate
        Returns:
            str. Sentence in past tense
        """
        raise NotImplementedError("abstract method")

from nltk.corpus import brown
from nltk.tag import UnigramTagger
import cPickle as pickle

INPUT_FILE = "/dfs/scratch0/googlengrams/2012-eng-fic/info/commonnonstop-1900-2000-8-6.pkl"

def write_word_list(filename, word_list):
    out_fp = open(filename, "w")
    print >> out_fp, "\n".join(word_list)

if __name__ == '__main__':
    in_fp = open(INPUT_FILE, "rb") 
    words = pickle.load(in_fp)
    tagger = UnigramTagger(brown.tagged_sents())
    good_words = []
    for word in words:
        tag = tagger.tag([word])[0][1]
        if tag == None:
            continue
        if "NP" in tag:
            continue
        good_words.append(word)
    write_word_list("brown.txt", good_words)

import nltk
from nltk.tag import UnigramTagger
from nltk.corpus import treebank
training= treebank.tagged_sents()[:7000]
unitagger=UnigramTagger(training)
print(treebank.sents()[0])
print(unitagger.tag(treebank.sents()[0]))

import nltk
from nltk.tag import UnigramTagger
from nltk.tag import DefaultTagger
from nltk.corpus import treebank
testing = treebank.tagged_sents()[2000:]
training= treebank.tagged_sents()[:7000]
tag1=DefaultTagger('NN')
tag2=UnigramTagger(training,backoff=tag1)
print(tag2.evaluate(testing))

import nltk
import json

from nltk.corpus import brown
from nltk.tag import UnigramTagger
tagger = UnigramTagger(brown.tagged_sents(tagset='universal'))
sent = ['Mitchell', 'decried', 'the', 'high', 'rate', 'of', 'unemployment']
for word, tag in tagger.tag(sent):
	if tag == "VERB":
		print(word, '->', tag)


verbs_tagged = open("../assets/inputText/verbs_tagged_questions.txt", 'w+')
with open("../assets/inputText/all_questions.txt", 'r') as all_lines:
	for line in all_lines:
		splitLine = line.split(' ')
		for word, tag in tagger.tag(splitLine):
			if tag == "VERB":
				verbs_tagged.write(word + "\n")
				#verbs_tagged.write(word + " \"" + line[:-1] + "\"\n")