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 lexical(tokens): print "\n" print "Step 2: Lexical Analysis\n" print "Essentially refers to dictionary and obtains the properties of the word" print "Part-Of-Speech tagging" print "The tagset is:\n" tag = DefaultTagger('NN') tagg = UnigramTagger(train_sent, backoff=tag) tagger = BigramTagger(train_sent, backoff=tagg) tagtokens = tagger.tag(tokens) for token, tag in tagtokens: print token + "->" + tag print "\n" print "The acurracy of the trained pos tagger is:" print tagger.evaluate(test_sents) return tagtokens
unigramTagger = UnigramTagger(training, cutoff=2) # same as tagger.train(training) print('Uniigram tagger accuracy:') print(unigramTagger.evaluate(testing)) #----------------------------------------------------- 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)
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
# print "Data is splitted!" # 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])),
print("------------Trigram Tagger------------") print(trigramTagger.tag(sent)) print("------------Brill Tagger------------") print(brillTagger.tag(sent)) print("------------Accuracy: Unigram Tagger Trained------------") unigramTagger = UnigramTagger(brown_train_sents) print(unigramTagger.evaluate(brown_test_sents)) print("------------Accuracy: Unigram Tagger Trained with cutoff = 3------------") unigramTagger = UnigramTagger(brown_train_sents, cutoff = 3) print(unigramTagger.evaluate(brown_test_sents)) print("------------Accuracy: Bigram Tagger Trained------------") print(bigramTagger.evaluate(brown_test_sents)) print("------------Accuracy: Trigram Tagger Trained------------") print(trigramTagger.evaluate(brown_test_sents)) print("------------Accuracy: Unigram Tagger with backoff enabled. Backoff Chain: UnigramTagger -> DefaultTagger------------") unigramTagger = UnigramTagger(brown_train_sents, backoff=defaultTagger) print(unigramTagger.evaluate(brown_test_sents)) print("------------Accuracy: Tagger with backoff enabled. Backoff Chain: TrigramTagger -> BigramTagger -> UnigramTagger -> DefaultTagger------------") print(initialTagger.evaluate(brown_test_sents)) print("------------Accuracy: Brill Tagger------------") print(brillTagger.evaluate(brown_test_sents)) print(brillTagger.rules())
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))
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)
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)
print(rt.evaluate(test_data)) 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) #testing perfomence of unigram tagger print(ut.evaluate(test_data)) print(ut.tag(tokens)) #testing perfomence of bigram tagger print(bt.evaluate(test_data)) print(bt.tag(tokens)) #testing perfomence of trigram tagger 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 ct = combined_tagger(train_data=train_data, taggers=[UnigramTagger, BigramTagger, TrigramTagger],
from nltk.tag import UnigramTagger from nltk.tag import TrigramTagger from nltk.tag import BigramTagger from nltk.tag import DefaultTagger # 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) # unigram_tagger = UnigramTagger(train_data, backoff=regexp_tagger) print(unigram_tagger.evaluate(test_data)) # 0.8361407355726104 bigram_tagger = BigramTagger(train_data, backoff=unigram_tagger) print(bigram_tagger.evaluate(test_data)) # 0.8452108043456593 trigram_tagger = TrigramTagger(train_data, backoff=bigram_tagger) print(trigram_tagger.evaluate(test_data)) # 0.843317053722715 # 命名实体识别 # NER tagger from nltk import ne_chunk from nltk import word_tokenize sent = "Mark is studying at Stanford University in California" print(ne_chunk(nltk.pos_tag(word_tokenize(sent)), binary=False)) print(ne_chunk(nltk.pos_tag(word_tokenize(sent)), binary=True))
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 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 ### #######################
import nltk from nltk.tag import BigramTagger from nltk.corpus import treebank training_1 = treebank.tagged_sents()[:7000] bigramtagger = BigramTagger(training_1) print(treebank.sents()[0]) print(bigramtagger.tag(treebank.sents()[0])) testing_1 = treebank.tagged_sents()[2000:] print(bigramtagger.evaluate(testing_1))
def indivBigram(bambara, backoff): bigram= BigramTagger(bambara.train_sents, backoff=backoff) print("Bigram accuracy: ",bigram.evaluate(bambara.test_sents)) return bigram
>>>default_tagger = nltk.DefaultTagger('NN') >>>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
accuracy = ugb_tagger.evaluate(test_sents) print(f"Accuracy of backoff: {accuracy}\n") # 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
X_test = tagged_sentences[int(len(tagged_sentences) * 0.8):] ''' Question 2 - Performance of 0.13, 0.9 and 0.91 ''' # using only the default - NN - 0.1308 default_tagger = nltk.DefaultTagger('NN') print(default_tagger.evaluate(tagged_sentences)) # Unigrams - 0.902 unigram_tagger = UnigramTagger(X_train) print(unigram_tagger.evaluate(X_test)) # Bigrams with backoff of unigrams - 0.911 bigram_tagger = BigramTagger(X_train, backoff=unigram_tagger) print(bigram_tagger.evaluate(X_test)) ''' Question 3 Performace of 0.77 and 0.79 ''' treebank_tagged_sents = nltk.corpus.treebank.tagged_sents(tagset='universal') print(default_tagger.evaluate(treebank_tagged_sents)) print(unigram_tagger.evaluate(treebank_tagged_sents)) # 0.77 print(bigram_tagger.evaluate(treebank_tagged_sents)) # 0.79 ''' Question 4-5 - F1 of 0.972 for brown dataset. Better performance ''' # modified code def word2features(sent, i): word = sent[i][0]
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)) # Note that the best accuracy is provided by the 1-Gram tagger, as it isn't always the case that the same bigrams # and trigrams observed in the training data will be present in the same way in the testing data (e.g. pairs of words # do not always appear paired in the same way)
print(default_tagger.evaluate(brown_tagged_sents)) # 0.13089484257215028 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
import nltk from nltk.tag import BigramTagger from nltk.corpus import treebank training_1= treebank.tagged_sents()[:7000] bigramtagger=BigramTagger(training_1) print(treebank.sents()[0]) print(bigramtagger.tag(treebank.sents()[0])) testing_1 = treebank.tagged_sents()[2000:] print(bigramtagger.evaluate(testing_1))
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 ct = combined_tagger(train_data=train_data, taggers=[UnigramTagger, BigramTagger, TrigramTagger], backoff=rt) print ct.evaluate(test_data)
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