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 train(self, sentence_list): """Trains the tagger from the tagged sentences provided """ noun_fallback = DefaultTagger('NN') affix_fallback = AffixTagger(sentence_list, backoff=noun_fallback) unigram_fallback = UnigramTagger(sentence_list, backoff=affix_fallback) bigram_fallback = BigramTagger(sentence_list, backoff=unigram_fallback) trigram_fallback = TrigramTagger(sentence_list, backoff=bigram_fallback) templates = [ brill.SymmetricProximateTokensTemplate(brill.ProximateTagsRule, (1, 1)), brill.SymmetricProximateTokensTemplate(brill.ProximateTagsRule, (2, 2)), brill.SymmetricProximateTokensTemplate(brill.ProximateTagsRule, (1, 2)), brill.SymmetricProximateTokensTemplate(brill.ProximateTagsRule, (1, 3)), brill.SymmetricProximateTokensTemplate(brill.ProximateWordsRule, (1, 1)), brill.SymmetricProximateTokensTemplate(brill.ProximateWordsRule, (2, 2)), brill.SymmetricProximateTokensTemplate(brill.ProximateWordsRule, (1, 2)), brill.SymmetricProximateTokensTemplate(brill.ProximateWordsRule, (1, 3)), brill.ProximateTokensTemplate(brill.ProximateTagsRule, (-1, -1), (1, 1)), brill.ProximateTokensTemplate(brill.ProximateWordsRule, (-1, -1), (1, 1)) ] trainer = brill.FastBrillTaggerTrainer(trigram_fallback, templates) self.tagger = trainer.train(sentence_list, max_rules=100, min_score=3)
def train(self): self.re_tagger = nltk.RegexpTagger(self.patterns) self.bi_tagger = BigramTagger(brown.tagged_sents(), backoff=self.re_tagger) self.tri_tagger = TrigramTagger(brown.tagged_sents(), backoff=self.bi_tagger)
def get_pos_tagger(self): from nltk.corpus import brown regexp_tagger = RegexpTagger( [ (r"^-?[0-9]+(\.[0-9]+)?$", "CD"), # cardinal numbers (r"(The|the|A|a|An|an)$", "AT"), # articles (r".*able$", "JJ"), # adjectives (r".*ness$", "NN"), # nouns formed from adjectives (r".*ly$", "RB"), # adverbs (r".*s$", "NNS"), # plural nouns (r".*ing$", "VBG"), # gerunds (r".*ed$", "VBD"), # past tense verbs (r".*", "NN"), # nouns (default) ] ) brown_train = brown.tagged_sents(categories="news") unigram_tagger = UnigramTagger(brown_train, backoff=regexp_tagger) bigram_tagger = BigramTagger(brown_train, backoff=unigram_tagger) trigram_tagger = TrigramTagger(brown_train, backoff=bigram_tagger) # Override particular words main_tagger = RegexpTagger( [(r"(A|a|An|an)$", "ex_quant"), (r"(Every|every|All|all)$", "univ_quant")], backoff=trigram_tagger, ) return main_tagger
def traintest_bigram_trigram_tagger(self): from nltk.tag import DefaultTagger,UnigramTagger, BigramTagger, TrigramTagger from nltk.corpus import treebank test_sents = treebank.tagged_sents()[3000:] train_sents = treebank.tagged_sents()[:3000] print 'trainging bigramTagger' bitagger = BigramTagger(train_sents) print 'evaluation bitagger' print bitagger.evaluate(test_sents) print 'trainging trigram Tagger' tritagger = TrigramTagger(train_sents) print 'evaluation bitagger' print tritagger.evaluate(test_sents) print 'tagging'
def get_pos_tagger(self): from nltk.corpus import brown regexp_tagger = RegexpTagger([ (r'^-?[0-9]+(.[0-9]+)?$', 'CD'), # cardinal numbers (r'(The|the|A|a|An|an)$', 'AT'), # articles (r'.*able$', 'JJ'), # adjectives (r'.*ness$', 'NN'), # nouns formed from adjectives (r'.*ly$', 'RB'), # adverbs (r'.*s$', 'NNS'), # plural nouns (r'.*ing$', 'VBG'), # gerunds (r'.*ed$', 'VBD'), # past tense verbs (r'.*', 'NN'), # nouns (default) ]) brown_train = brown.tagged_sents(categories='news') unigram_tagger = UnigramTagger(brown_train, backoff=regexp_tagger) bigram_tagger = BigramTagger(brown_train, backoff=unigram_tagger) trigram_tagger = TrigramTagger(brown_train, backoff=bigram_tagger) # Override particular words main_tagger = RegexpTagger( [(r'(A|a|An|an)$', 'ex_quant'), (r'(Every|every|All|all)$', 'univ_quant')], backoff=trigram_tagger, ) return main_tagger
def train(self, sentence_list): noun_fallback = DefaultTagger('NN') affix_fallback = AffixTagger(sentence_list, backoff=noun_fallback) unigram_fallback = UnigramTagger(sentence_list, backoff=affix_fallback) bigram_fallback = BigramTagger(sentence_list, backoff=unigram_fallback) self.tagger = TrigramTagger(sentence_list, backoff=bigram_fallback)
def train_tagger(tagger_name): train_sents = treebank.tagged_sents()[:5000] if tagger_name == "TnT" or tagger_name == 'tagger': trained_tagger = tnt.TnT() trained_tagger.train(train_sents) else: tagger1 = DefaultTagger('NN') tagger2 = TrigramTagger(train_sents, backoff=tagger1) tagger3 = BigramTagger(train_sents, backoff=tagger2) trained_tagger = UnigramTagger(train_sents, backoff=tagger3) return trained_tagger
def train_tagger(language, model_type, feature, train_sents): if model_type == 'unigram': tagger = UnigramTagger(train_sents) elif model_type == 'bigram': tagger = BigramTagger(train_sents) elif model_type == 'trigram': tagger = TrigramTagger(train_sents) elif model_type == 'backoff': tagger1 = UnigramTagger(train_sents) tagger2 = BigramTagger(train_sents, backoff=tagger1) tagger = TrigramTagger(train_sents, backoff=tagger2) elif model_type == 'crf': tagger = CRFTagger() tagger.train(train_sents, 'taggers/{0}/{1}/crf.pickle'.format(language, feature)) elif model_type == 'perceptron': tagger = PerceptronTagger(load=False) tagger.train(train_sents) return tagger
def ngram_tagger(tagged_sents): patterns = [(r'''(b|c|d|f|g|h|j|k|l|m|n||p|q|r|s|t|v|w|x|z)e (b|c|d|f|g|h|j|k|l|m|n||p|q|r|s|t|v|w|x|z)''', 'MORA'), (r'.*(a|e|i|o|u|ä|î|ô|ü)(a|e|i|o|u|ä|î|ô|ü)', 'DOPPEL'), (r'.*', 'MORA_HAUPT')] # default regex_tagger = nltk.RegexpTagger(patterns) tagger1 = UnigramTagger(tagged_sents, backoff=regex_tagger) # cutoff = 3, if necessary tagger2 = BigramTagger(tagged_sents, backoff=tagger1) tagger3 = TrigramTagger(tagged_sents, backoff=tagger2) return tagger3
def test_ngram_taggers(self): unitagger = UnigramTagger(self.corpus, backoff=self.default_tagger) bitagger = BigramTagger(self.corpus, backoff=unitagger) tritagger = TrigramTagger(self.corpus, backoff=bitagger) ntagger = NgramTagger(4, self.corpus, backoff=tritagger) encoded = self.encoder.encode(ntagger) decoded = self.decoder.decode(encoded) self.assertEqual(repr(ntagger), repr(decoded)) self.assertEqual(repr(tritagger), repr(decoded.backoff)) self.assertEqual(repr(bitagger), repr(decoded.backoff.backoff)) self.assertEqual(repr(unitagger), repr(decoded.backoff.backoff.backoff)) self.assertEqual(repr(self.default_tagger), repr(decoded.backoff.backoff.backoff.backoff))
class TriGramTagger(object): """ Trigram tagger """ implements(IPOSTagger) def __init__(self): self.tagger = None def train(self, sentence_list): noun_fallback = DefaultTagger('NN') affix_fallback = AffixTagger(sentence_list, backoff=noun_fallback) unigram_fallback = UnigramTagger(sentence_list, backoff=affix_fallback) bigram_fallback = BigramTagger(sentence_list, backoff=unigram_fallback) self.tagger = TrigramTagger(sentence_list, backoff=bigram_fallback) def tag(self, words): if not self.tagger: raise Exception("Trigram Tagger not trained.") return self.tagger.tag(words)
def train_brill_tagger(tagged_sents): # The brill tagger module in NLTK. Template._cleartemplates() templates = brill24() # or fntbl37 # default_tagger = nltk.DefaultTagger('MORA_HAUPT') patterns = [(r'''(b|c|d|f|g|h|j|k|l|m|n||p|q|r|s|t|v|w|x|z)e (b|c|d|f|g|h|j|k|l|m|n||p|q|r|s|t|v|w|x|z)''', 'MORA'), (r'.*(a|e|i|o|u|ä|î|ô|ü)(a|e|i|o|u|ä|î|ô|ü)', 'DOPPEL'), (r'.*', 'MORA_HAUPT')] # default regex_tagger = nltk.RegexpTagger(patterns) tagger1 = UnigramTagger(tagged_sents, backoff=regex_tagger) # cutoff = 3, if necessary tagger2 = BigramTagger(tagged_sents, backoff=tagger1) tagger3 = TrigramTagger(tagged_sents, backoff=tagger2) tagger4 = brill_trainer.BrillTaggerTrainer(tagger3, templates, trace=3) tagger5 = tagger4.train(tagged_sents, max_rules=200) print return tagger5
def train_tagger(): ''' Um exemplo de treinamento de um etiquetador sintático usando um modelo de tri-gramas baseado em probabilidades. Um etiquetador sintático identifica quais a classe de uma palavra Ex.: Isso é um teste = Isso-PROSUB é-V um-ART teste-N Preposição Verbo Artigo Substantivo ''' # Carregando um conjunto de dados em português que possui # sentenças manualmente identificadas data = [ [(w, re.split('[|-]', tag)[0]) for w, tag in sent] for sent in mac_morpho.tagged_sents()] # Classe sintática padrão. N siginifica Nome/substantivo tagger0 = DefaultTagger('N') print('train unigram') tagger1 = UnigramTagger(data, backoff=tagger0) print('training bigram') tagger2 = BigramTagger(data, backoff=tagger1) print('training trigram') return TrigramTagger(data, backoff=tagger2)
from nltk.tag import DefaultTagger, UnigramTagger, BigramTagger, TrigramTagger from nltk.corpus import treebank from tag_util import backoff_tagger train_sents = treebank.tagged_sents()[:3000] test_sents = treebank.tagged_sents()[3000:] bitagger = BigramTagger(train_sents) print(bitagger.evaluate(test_sents)) tritagger = TrigramTagger(train_sents) print(tritagger.evaluate(test_sents)) default_tagger = DefaultTagger('NN') combined_tagger = backoff_tagger(train_sents, [UnigramTagger, BigramTagger, TrigramTagger], backoff=default_tagger) print(combined_tagger.evaluate(test_sents)) # # train # default_tagger = DefaultTagger('NN') # # train_sents = treebank.tagged_sents()[:3000] # tagger = UnigramTagger(train_sents, backoff=default_tagger) # # # test # test_sents = treebank.tagged_sents()[3000:] # print(tagger.evaluate(test_sents)) # # # save to pickle # import pickle # with open('unitagger.pkl', 'wb') as output: # pickle.dump(tagger, output)
# unigrams from nltk.tag import UnigramTagger unigram_tagger = UnigramTagger(train_sents) tagger = UnigramTagger(train_sents, cutoff=3) print(tagger.evaluate(test_sents)) # bigrams from nltk.tag import BigramTagger bigram_tagger = BigramTagger(train_sents) tagger = BigramTagger(train_sents, cutoff=3) print(tagger.evaluate(test_sents)) # trigrams from nltk.tag import TrigramTagger trigram_tagger = TrigramTagger(train_sents) tagger = TrigramTagger(train_sents, cutoff=3) print(tagger.evaluate(test_sents)) # backoff bigram_tagger = BigramTagger(train_sents, backoff=unigram_tagger) def backoff_tagger(train_sents, tagger_classes, backoff=None): for cls in tagger_classes: backoff = cls(train_sents, backoff=backoff) return backoff tagger = backoff_tagger(train_sents, [UnigramTagger, BigramTagger, TrigramTagger],
>>>print default_tagger.evaluate(brown_tagged_sents) # N-gram taggers >>>from nltk.tag import UnigramTagger >>>from nltk.tag import DefaultTagger >>>from nltk.tag import BigramTagger >>>from nltk.tag import TrigramTagger # we are dividing the data into a test and train to evaluate our taggers. >>>train_data= brown_tagged_sents[:int(len(brown_tagged_sents) * 0.9)] >>>test_data= brown_tagged_sents[int(len(brown_tagged_sents) * 0.9):] >>>unigram_tagger = UnigramTagger(train_data,backoff=default_tagger) >>>print unigram_tagger.evaluate(test_data) >>>bigram_tagger= BigramTagger(train_data, backoff=unigram_tagger) >>>print bigram_tagger.evaluate(test_data) >>>trigram_tagger=TrigramTagger(train_data,backoff=bigram_tagger) >>>print trigram_tagger.evaluate(test_data) # Regex tagger >>>from nltk.tag.sequential import RegexpTagger >>>regexp_tagger = RegexpTagger( [( r'^-?[0-9]+(.[0-9]+)?$', 'CD'), # cardinal numbers ( r'(The|the|A|a|An|an)$', 'AT'), # articles ( r'.*able$', 'JJ'), # adjectives ( r'.*ness$', 'NN'), # nouns formed from adj ( r'.*ly$', 'RB'), # adverbs ( r'.*s$', 'NNS'), # plural nouns ( r'.*ing$', 'VBG'), # gerunds (r'.*ed$', 'VBD'), # past tense verbs (r'.*', 'NN') # nouns (default)
(r'.*', 'NN') # nouns (default) ... ] rt = RegexpTagger(patterns) print rt.evaluate(test_data) print rt.tag(tokens) ## N gram taggers from nltk.tag import UnigramTagger from nltk.tag import BigramTagger from nltk.tag import TrigramTagger ut = UnigramTagger(train_data) bt = BigramTagger(train_data) tt = TrigramTagger(train_data) print ut.evaluate(test_data) print ut.tag(tokens) print bt.evaluate(test_data) print bt.tag(tokens) print tt.evaluate(test_data) print tt.tag(tokens) def combined_tagger(train_data, taggers, backoff=None): for tagger in taggers: backoff = tagger(train_data, backoff=backoff) return backoff
# Saving pickle and testing it. with open('pickles/pos-taggers/unigram_backoff_tagger.pickle', 'wb') as file: pickle.dump(ugb_tagger, file) with open('pickles/pos-taggers/unigram_backoff_tagger.pickle', 'rb') as file: pk_tagger = pickle.load(file) accuracy = pk_tagger.evaluate(test_sents) print(f"Accuracy of pickled backoff: {accuracy}\n") # Testing bigram and trigram taggers bg_tagger = BigramTagger(train_sents) accuracy = bg_tagger.evaluate(test_sents) print(f"Accuracy of bigram: {accuracy}\n") tg_tagger = TrigramTagger(train_sents) accuracy = tg_tagger.evaluate(test_sents) print(f"Accuracy of trigram: {accuracy}\n") def make_backoffs(training, tagger_classes, backoff=None): """ Function for training and make chains of backoff tagger """ # Make a tagger using the previous one as a backoff for cls in tagger_classes: backoff = cls(training, backoff=backoff) return backoff # Testing the function with all 4 taggers
one_hot_multi.classes_ # 查看特征名 from nltk.corpus import brown from nltk.tag import UnigramTagger from nltk.tag import BigramTagger from nltk.tag import TrigramTagger # 从布朗语料库中获取文本数据,切分为句子 sentences = brown.tagged_sents(categories='news') # 将4000个句子用作训练,623个句子用作测试 train = sentences[:4000] test = sentences[4000:] # 创建回退标注器 unigram = UnigramTagger(train) bigram = BigramTagger(train, backoff=unigram) trigram = TrigramTagger(train, backoff=bigram) # 查看准确率 trigram.evaluate(test) # TF-IDF import numpy as np from sklearn.feature_extraction.text import TfidfVectorizer # 创建文本 text_data = np.array( ['I love Brazil. Brazil!', 'Sweden is best', 'Germany beats both']) # 创建TF-IDF特征矩阵 tfidf = TfidfVectorizer() feature_matrix = tfidf.fit_transform(text_data) # 查看TF-IDF特征矩阵 feature_matrix feature_matrix.toarray()
import nltk from nltk.tag import BigramTagger, TrigramTagger from nltk.corpus import treebank testing = treebank.tagged_sents()[2000:] training= treebank.tagged_sents()[:7000] bigramtag = BigramTagger(training) print(bigramtag.evaluate(testing)) trigramtag = TrigramTagger(training) print(trigramtag.evaluate(testing))
# Regular expression tagger nn_cd_tagger = RegexpTagger([(r'^-?[0-9]+(.[0-9]+)?$', 'PUNC'), (r'.*', 'NOUN_NOM')]) # Unigram tagger unigram_tagger = UnigramTagger(training_data, backoff=nn_cd_tagger) print "Unigram accuracy: " print unigram_tagger.evaluate(evaulation_data) # Bigram tagger bigram_tagger = BigramTagger(training_data, backoff=unigram_tagger) print "Bigram accuracy: " print bigram_tagger.evaluate(evaulation_data) # Trigram tagger trigram_tagger = TrigramTagger(training_data, backoff=bigram_tagger) print "Trigram accuracy: " print trigram_tagger.evaluate(evaulation_data) # Brill tagger templates templates = [ Template(brill.Pos([1, 1])), Template(brill.Pos([2, 2])), Template(brill.Pos([1, 2])), Template(brill.Pos([1, 3])), Template(brill.Word([1, 1])), Template(brill.Word([2, 2])), Template(brill.Word([1, 2])), Template(brill.Word([1, 3])), Template(brill.Pos([-1, -1]), brill.Pos([1, 1])), Template(brill.Word([-1, -1]), brill.Word([1, 1])),
def cltk_pos_cv(full_training_set, local_dir_rel): print("full_training_set", full_training_set) unigram_accuracies = [] bigram_accuracies = [] trigram_accuracies = [] backoff_accuracies = [] tnt_accuracies = [] with open(full_training_set) as f: training_set_string = f.read() pos_set = training_set_string.split('\n\n') # mk into a list sentence_count = len(pos_set) # 3473 tenth = math.ceil(int(sentence_count) / int(10)) random.seed(0) random.shuffle(pos_set) def chunks(l, n): """Yield successive n-sized chunks from l. http://stackoverflow.com/a/312464 """ for i in range(0, len(l), n): yield l[i:i+n] # a list of 10 lists ten_parts = list(chunks(pos_set, tenth)) # a list of 10 lists with ~347 sentences each #for counter in list(range(10)): for counter, part in list(enumerate(ten_parts)): # map test list to part of given loop test_set = ten_parts[counter] # or: test_set = part # filter out this loop's test index training_set_lists = [x for x in ten_parts if x is not ten_parts[counter]] # next concatenate the list together into 1 file ( http://stackoverflow.com/a/952952 ) training_set = [item for sublist in training_set_lists for item in sublist] # save shuffled tests to file (as NLTK trainers expect) #local_dir_rel = '~/cltk_data/user_data' local_dir = os.path.expanduser(local_dir_rel) if not os.path.isdir(local_dir): os.makedirs(local_dir) test_path = os.path.join(local_dir, 'test.pos') with open(test_path, 'w') as f: f.write('\n\n'.join(test_set)) train_path = os.path.join(local_dir, 'train.pos') with open(train_path, 'w') as f: f.write('\n\n'.join(training_set)) # read POS corpora print("local_dir", local_dir) train_reader = TaggedCorpusReader(local_dir, 'train.pos') train_sents = train_reader.tagged_sents() test_reader = TaggedCorpusReader(local_dir, 'test.pos') test_sents = test_reader.tagged_sents() print('Loop #' + str(counter)) # make unigram tagger unigram_tagger = UnigramTagger(train_sents) # evaluate unigram tagger unigram_accuracy = None unigram_accuracy = unigram_tagger.evaluate(test_sents) unigram_accuracies.append(unigram_accuracy) print('Unigram:', unigram_accuracy) # make bigram tagger bigram_tagger = BigramTagger(train_sents) # evaluate bigram tagger bigram_accuracy = None bigram_accuracy = bigram_tagger.evaluate(test_sents) bigram_accuracies.append(bigram_accuracy) print('Bigram:', bigram_accuracy) # make trigram tagger trigram_tagger = TrigramTagger(train_sents) # evaluate trigram tagger trigram_accuracy = None trigram_accuracy = trigram_tagger.evaluate(test_sents) trigram_accuracies.append(trigram_accuracy) print('Trigram:', trigram_accuracy) # make 1, 2, 3-gram backoff tagger tagger1 = UnigramTagger(train_sents) tagger2 = BigramTagger(train_sents, backoff=tagger1) tagger3 = TrigramTagger(train_sents, backoff=tagger2) # evaluate trigram tagger backoff_accuracy = None backoff_accuracy = tagger3.evaluate(test_sents) backoff_accuracies.append(backoff_accuracy) print('1, 2, 3-gram backoff:', backoff_accuracy) # make tnt tagger tnt_tagger = tnt.TnT() tnt_tagger.train(train_sents) # evaulate tnt tagger tnt_accuracy = None tnt_accuracy = tnt_tagger.evaluate(test_sents) tnt_accuracies.append(tnt_accuracy) print('TnT:', tnt_accuracy) final_accuracies_list = [] mean_accuracy_unigram = mean(unigram_accuracies) standard_deviation_unigram = stdev(unigram_accuracies) uni = {'unigram': {'mean': mean_accuracy_unigram, 'sd': standard_deviation_unigram}} final_accuracies_list.append(uni) mean_accuracy_bigram = mean(bigram_accuracies) standard_deviation_bigram = stdev(bigram_accuracies) bi = {'bigram': {'mean': mean_accuracy_bigram, 'sd': standard_deviation_bigram}} final_accuracies_list.append(bi) mean_accuracy_trigram = mean(trigram_accuracies) standard_deviation_trigram = stdev(trigram_accuracies) tri = {'trigram': {'mean': mean_accuracy_trigram, 'sd': standard_deviation_trigram}} final_accuracies_list.append(tri) mean_accuracy_backoff = mean(backoff_accuracies) standard_deviation_backoff = stdev(backoff_accuracies) back = {'1, 2, 3-gram backoff': {'mean': mean_accuracy_backoff, 'sd': standard_deviation_backoff}} final_accuracies_list.append(back) mean_accuracy_tnt = mean(tnt_accuracies) standard_deviation_tnt = stdev(tnt_accuracies) tnt_score = {'tnt': {'mean': mean_accuracy_tnt, 'sd': standard_deviation_tnt}} final_accuracies_list.append(tnt_score) final_dict = {} for x in final_accuracies_list: final_dict.update(x) return final_dict
from nltk.corpus import wordnet as wn from os.path import isfile, join from os import listdir from pprint import pprint import gensim.downloader as api import re import nltk import os TEST_PATH = '../test/untagged' COMMON_WORDS_PATH = '../resources/1-1000.txt' TRAINING_SENTS = treebank.tagged_sents() UNIGRAM = UnigramTagger(TRAINING_SENTS, backoff=DefaultTagger('NN')) BIGRAM = BigramTagger(TRAINING_SENTS, backoff=UNIGRAM) TRIGRAM = TrigramTagger(TRAINING_SENTS, backoff=BIGRAM) STOPWORDS = set(nltk.corpus.stopwords.words('english')) WORD_VECTORS = api.load("glove-wiki-gigaword-100") TEST_FILES = [f for f in listdir(TEST_PATH) if isfile(join(TEST_PATH, f))] # Manual list of words to be considered "irrelevant" IRRELEVANT_WORDS = ["talk", "seminar", "lecture"] # manually created ontology tree, which is later extended TREE = {"science": {}, "maths": {}, "engineering": {}, "medicine": {}} # code to convert POS tags into the right form for lemmatization # https://stackoverflow.com/questions/25534214/nltk-wordnet-lemmatizer-shouldnt-it-lemmatize-all-inflections-of-a-word POS_TO_WORDNET = { 'JJ': wn.ADJ,
def tagger_default(corpus): default_tagger = DefaultTagger('NOUN') tagger1 = UnigramTagger(corpus, backoff=default_tagger) tagger2 = BigramTagger(corpus, backoff=tagger1) tagger3 = TrigramTagger(corpus, backoff=tagger2) return tagger3
from nltk.tag import TrigramTagger # we are dividing the data into a test and train to evaluate our taggers. train_data = brown_tagged_sents[:int(len(brown_tagged_sents) * 0.9)] test_data = brown_tagged_sents[int(len(brown_tagged_sents) * 0.9):] #Unigram selecciona la clasificación + probable #https://www.nltk.org/api/nltk.tag.html?highlight=postagger#nltk.tag.sequential.UnigramTagger unigram_tagger = UnigramTagger(train_data,backoff=default_tagger) print("Unigram Tagger: {}".format(unigram_tagger.evaluate(test_data))) #Bigram se basa en la palabra actual y la anterior para clasificar #https://www.nltk.org/api/nltk.tag.html?highlight=postagger#nltk.tag.sequential.BigramTagger bigram_tagger = BigramTagger(train_data, backoff=unigram_tagger) print("Bigram Tagger: {}".format(bigram_tagger.evaluate(test_data))) #Trigram se basa en la actual, anterior y anterior a la anterior #https://www.nltk.org/api/nltk.tag.html?highlight=postagger#nltk.tag.sequential.TrigramTagger trigram_tagger = TrigramTagger(train_data,backoff=bigram_tagger) print("Trigram Tagger: {}".format(trigram_tagger.evaluate(test_data))) ''' Aquí lo que se ha hecho ha sido crear 3 "taggeadores" N-Gram con un conjunto de datos de entrenamiento del corpus brown, que ya estaba clasificado. Además, se han podido combinar para que cuando un "taggeador" no sepa que hacer pruebe con su "taggeador" N-1 hasta llegar al por defecto de clasificarlo como NN. ####################### ### Regexp Tagger ### ####################### Otra opción para crear nuestro propio "taggeador" es recurrir a las queridas expresiones regulares con un RegexpTagger
def indivTrigram(bambara,backoff): trigram=TrigramTagger(bambara.train_sents, backoff=backoff) print("Trigram accuracy: ",trigram.evaluate(bambara.test_sents)) return trigram
def baseline_tagger(self): from nltk.corpus import brown from nltk.tag import TrigramTagger print("Number of words in Brown corpus: 1333212") print("Number of unique tags in Brown corpus: 474") f = open("input.txt", "r").read() file_info = stat("input.txt") print("Size of test file: ", file_info.st_size) sents_tokens = word_tokenize(f) print("Number of tags to be tokenized: ", len([j for i in sents_tokens for j in i])) t0 = time() tagger = TrigramTagger(brown.tagged_sents()[:55000]) t1 = time() nltk_train_time = t1 - t0 print("Time taken by NLTK for training: ", nltk_train_time) nltk_tags = [] t0 = time() for sent in sents_tokens: nltk_tags.append(tagger.tag(sent)) t1 = time() nltk_tag_time = t1 - t0 print("Time taken by NLTK to tag text: ", nltk_tag_time) t0 = time() self.tokenize() self.init_tags() self.init_words_tags() self.init_dict() self.calc_Q() self.calc_R() t1 = time() pos_train_time = t1 - t0 print("Time taken by pos_tagger to train: ", pos_train_time) pos_tagger_tags = [] t0 = time() for sent in sents_tokens: pos_tagger_tags.append(self.viterbi(sent)) t1 = time() pos_tag_time = t1 - t0 print("Time taken by pos_tagger to tag: ", pos_tag_time) if nltk_train_time < pos_train_time: print("Training time of NLTK is less than pos_tagger by: ", abs(nltk_train_time - pos_train_time)) else: print("Training time of pos_tagger is less than NLTK by: ", abs(nltk_train_time - pos_train_time)) if nltk_tag_time < pos_tag_time: print("Tagging time of NLTK is less than pos_tagger by: ", abs(nltk_tag_time - pos_tag_time)) else: print("Tagging time of pos_tagger is less than NLTK by: ", abs(nltk_tag_time - pos_tag_time)) nltk_tag_count = defaultdict(int) for i in nltk_tags: for j in i: nltk_tag_count[j[1]] += 1 pos_tag_count = defaultdict(int) for i in pos_tagger_tags: for j in i: pos_tag_count[j[1]] += 1 print("POS tags generated by NLTK: ") for i in nltk_tag_count.items(): print(i) print("POS tags generated by pos_tagger: ") for i in pos_tag_count.items(): print(i) print("Number of unique tags generated by NLTK: ", len([i for i in nltk_tag_count.keys()])) print("Number of unique tags generated by pos_tagger: ", len([i for i in pos_tag_count.keys()])) print("NLTK failed to tag", nltk_tag_count[None], "tokens") print("pos_tagger failed to tag", pos_tag_count[''], "tokens") if nltk_tag_count[None] > pos_tag_count['']: print("pos_tagger tagged", abs(nltk_tag_count[None] - pos_tag_count['']), "more tokens than NLTK") else: print("NLTK tagged", abs(nltk_tag_count[None] - pos_tag_count['']), "more tokens than pos_tagger") tagged_sents = open("input_tagged.txt", "r").read().splitlines() tags = [] for sent in tagged_sents: words = sent.split() for word in words: m = re.search('(.*)_(.*)', word) tags.append(m.group(2)) n_tags = [j[1] for i in nltk_tags for j in i] nltk_count = 0 for x, y in zip(n_tags, tags): if x == y: nltk_count += 1 len_tokens = len([j for i in sents_tokens for j in i]) print("NLTK accurately tagged", nltk_count, "tokens") print("NLTK accuracy score: ", float(nltk_count) / float(len_tokens)) p_tags = [j[1] for i in pos_tagger_tags for j in i] pos_count = 0 for x, y in zip(p_tags, tags): if x == y: pos_count += 1 print("pos_tagger accurately tagged", pos_count, "tokens") print("pos_tagger accuracy score: ", float(pos_count) / float(len_tokens)) if nltk_count > pos_count: print("NLTK accurately tagged", abs(nltk_count - pos_count), "more tokens than pos_tagger") else: print("pos_tagger accurately tagged", abs(nltk_count - pos_count), "more tokens than NLTK")
from nltk.tag import BigramTagger as BigT from nltk.tag import TrigramTagger as TriT biTagger=BigT(train_sents) biTagger.evaluate(test_sents) triTagger=TriT(train_sents) triTagger.evaluate(test_sents)
for page in list(root): l = [] text = page.find('text').text.decode('utf8') language = page.find('language').text.decode('utf8') pos = page.find('pos_tags').text.decode('utf8') splitText = text.split(" ")[1:-1] posText = pos.split(" ")[1:-1] for i in range(len(splitText)): l.append((splitText[i], posText[i])) data.append(l) count = count + 1 shuffle(data) # Divide data into train and test sets eightyPercent = count*0.9 training_set = data[0:int(eightyPercent)] test_set = data[int(eightyPercent):] # Train train_data = training_set tag1 = DefaultTagger('NN') tag2 = UnigramTagger(train_data, backoff = tag1) tag3 = BigramTagger(train_data, backoff = tag2) tag4 = TrigramTagger(train_data, backoff = tag3) # Accuracy # print tag4.tag('open a start up'.encode('utf-8').decode('utf-8').split()) # print tag4.tag('OUT nahi KARDO ISSE BAHUT HOGAYA aaj Salman'.encode('utf-8').decode('utf-8').split()) gold_sentences = test_set print tag4.evaluate(gold_sentences)
brown_tagged_sents2 = [[('The', 'AT'), ('Fulton', 'NP-TL'), ('manner', 'NN')]] print(default_tagger.evaluate(brown_tagged_sents2)) # 0.3333333333333333 train_data = brown_tagged_sents[:int(len(brown_tagged_sents) * 0.9)] test_data = brown_tagged_sents[int(len(brown_tagged_sents) * 0.9):] unigram_tagger = UnigramTagger(train_data, backoff=default_tagger) print(unigram_tagger.evaluate(test_data)) # 0.835841722316356 bigram_tagger = BigramTagger(train_data, backoff=unigram_tagger) print(bigram_tagger.evaluate(test_data)) # 0.8454101465164956 trigram_tagger = TrigramTagger(train_data, backoff=bigram_tagger) print(trigram_tagger.evaluate(test_data)) # 0.8427190272102063 regexp_tagger = RegexpTagger( [( r'^-?[0-9]+(.[0-9]+)?$', 'CD'), # cardinal numbers ( r'(The|the|A|a|An|an)$', 'AT'), # articles ( r'.*able$', 'JJ'), # adjectives ( r'.*ness$', 'NN'), # nouns formed from adj ( r'.*ly$', 'RB'), # adverbs ( r'.*s$', 'NNS'), # plural nouns ( r'.*ing$', 'VBG'), # gerunds (r'.*ed$', 'VBD'), # past tense verbs (r'.*', 'NN') # nouns (default) ])
for file in files: with open(file) as file: print(os.path.basename(file.name)) splitEmail = file.read().split("Abstract:") try: emailDicts.append({'head' : splitEmail[0], 'body' : splitEmail[1]}) except IndexError: print(file.name) pass print(len(emailDicts)) for emailDict in emailDicts: emailDict['body'] = word_tokenize(emailDict.get('body')) train_sents = treebank.tagged_sents()[:3000] unigram_tagger = UnigramTagger(train_sents) bigram_tagger = BigramTagger(train_sents) trigram_tagger = TrigramTagger(train_sents) def backoff_tagger(train_sents, tagger_classes, backoff=None): for cls in tagger_classes: backoff = cls(train_sents, backoff=backoff) return backoff tagger = backoff_tagger(train_sents, [UnigramTagger, BigramTagger, TrigramTagger], backoff=DefaultTagger('NN')) for emailDict in emailDicts: print(tagger.tag(emailDict.get('body')))
brill.Template(brill.Word([1, 2, 3])), brill.Template(brill.Word([-1]), brill.Word([1])), ] trainer = brill_trainer.BrillTaggerTrainer(initial_tagger, templates, deterministic=True) return trainer.train(train_sents, **kwargs) defaultTagger = DefaultTagger('NN') initialTagger = backoff_tagger(brown_train_sents, [UnigramTagger, BigramTagger, TrigramTagger], backoff=defaultTagger) brillTagger = train_brill_tagger(initialTagger, brown_train_sents) tnt_tagger = tnt.TnT(N=100) tnt_tagger.train(brown_train_sents) bigramTagger = BigramTagger(brown_train_sents) trigramTagger = TrigramTagger(brown_train_sents) print("------------Recommended Tagger------------") print(nltk.pos_tag(sent)) print("------------Default Tagger------------") print(defaultTagger.tag(sent)) print("------------Unigram Tagger Overrode------------") unigramTagger = UnigramTagger(model={'Pierre': 'NN'}) print(unigramTagger.tag(sent)) print("------------Unigram Tagger Trained------------") unigramTagger = UnigramTagger(brown_train_sents) print(unigramTagger.tag(sent))
#----------------------------------------------------- print('Bigram tagger accuracy:') from nltk.tag import BigramTagger bigramTagger = BigramTagger(training) print(bigramTagger.evaluate(testing)) #----------------------------------------------------- print('Trigram tagger accuracy:') from nltk.tag import TrigramTagger trigramTagger = TrigramTagger(training) print(trigramTagger.evaluate(testing)) #----------------------------------------------------- #Brill Tagger from nltk.tag import brill, brill_trainer # make sure you've got some train_sents! #brill_tagger = train_brill_tagger(unigramTagger, training) print('Brill tagger accuracy:') #print(brill_tagger.evaluate(testing)) #------------------------------------------------------ # Backoff tagger
# ============================================================================= """ """ 1. run tagger with different corpus size (50% and 100%) """ # backoff tagger tag1_eval = dict() # train with backoff and Brill tic() tag1_tagger = DefaultTagger('NO') tag1_tagger = AffixTagger(train_sents, affix_length=-1, backoff=tag1_tagger) tag1_tagger = AffixTagger(train_sents, affix_length=-2, backoff=tag1_tagger) tag1_tagger = AffixTagger(train_sents, affix_length=-3, backoff=tag1_tagger) tag1_tagger = AffixTagger(train_sents, affix_length=-4, backoff=tag1_tagger) tag1_tagger = AffixTagger(train_sents, affix_length=-5, backoff=tag1_tagger) tag1_tagger = UnigramTagger(train_sents, cutoff=3, backoff=tag1_tagger) tag1_tagger = BigramTagger(train_sents, backoff=tag1_tagger) tag1_tagger = TrigramTagger(train_sents, backoff=tag1_tagger) tag1b_tagger = train_brill_tagger(tag1_tagger, train_sents, True, max_rules=100) tag1_eval['train_time'] = toc() # test tic() tag1_eval['test_accuracy'] = tag1b_tagger.evaluate(val_sents) tag1_eval['test_time'] = toc() # display results display_training_metrics(tag1_eval) """ # ============================================================================= # finalise a classification-based tagger # =============================================================================
] rt = RegexpTagger(regexps=patterns) print(rt.evaluate(test_data)) print(rt.tag(tokens)) # 3. N-GRAM TAGGERS: # Contiguous sequences of n items from a sequence of text or speech. Items can be words, phonemes, # letters, characters or syllabes. Shingles: n-grams where items are just words. # UnigramTagger -> NGramTagger -> ContextTagger -> SequentialBackoffTagger # Train the N-Gram taggers using the training_data (pre-tagged tokens, i.e. labeled observations) ut = UnigramTagger(train=train_data) bt = BigramTagger(train_data) tt = TrigramTagger(train_data) # Test the performance of each N-Gram tagger print("1-Gram Tagger Accuracy: {}".format(ut.evaluate(test_data))) print("2-Gram Tagger Accuracy: {}".format(bt.evaluate(test_data))) print("3-Gram Tagger Accuracy: {}".format(tt.evaluate(test_data))) print("\n1-Gram tags:") print(ut.tag(tokens)) print("\n2-Gram tags:") print(bt.tag(tokens)) print("\n3-Gram tags:") print(tt.tag(tokens))