def NER_HINDINBC(): reader = TaggedCorpusReader('/python27/POS_9/', r'.*\.pos') f1 = reader.fileids() print "The Files of Corpus are:", f1 sents = reader.tagged_sents() sentn = reader.sents() #words=sentn.split() ls = len(sents) #lw=len(words) print "Length of Corpus Is:", ls #print "The Words are:",lw size1 = int(ls * 0.3) test_sents = sents[:size1] train_sents = sents[size1:] nbc_tagger = ClassifierBasedPOSTagger(train=train_sents) test = nbc_tagger.evaluate(test_sents) print "The Test Result is:", test #THE GIVEN INPUT given_sent = "नीतीश कुमार द्वारा भाजपा के साथ हाथ मिलाने से वहां का पूरा राजनीतिक परिदृश्य ही बदल गया है मगर शरद यादव इससे खुश नहीं हैं".decode( 'utf-8') gsw = given_sent.split() tag_gs = nbc_tagger.tag(gsw) print "GIVEN SENT TAG:", tag_gs ftag_gs = " ".join(list(itertools.chain(*tag_gs))) print "And its flattened Version is:", ftag_gs
def nbc_tagger(): news_text = brown.tagged_sents(categories='news') train_sents = news_text[:3230] test_sents = news_text[3230:4600] nbc_tagger = ClassifierBasedPOSTagger(train=train_sents) test = nbc_tagger.evaluate(test_sents) print "The Test Results Is:", test sent3 = "Narendra Modi won Lok Sabha election with massive majority after long years" sent_w = sent3.lower().split() print sent_w tag = nbc_tagger.tag(sent_w) print "The Tag Is:", tag
def parse(): tagger_classes=([nltk.UnigramTagger, nltk.BigramTagger]) trained_sents, tagged_sents = trainer("WSJ_02-21.pos-chunk","WSJ_23.pos") #tagger = nltk.UnigramTagger(trained_sents) print len(trained_sents) tagger = ClassifierBasedPOSTagger(train=trained_sents[:10000], classifier_builder=lambda train_feats: MaxentClassifier.train(train_feats, trace = 0,max_iter=10)) f = open("WSJ_23.chunk",'w') #print sents for sents in tagged_sents: (words,tags)=sents[0],sents[1] chunks = tagger.tag(tags) #print words, chunks wtc = zip(words, chunks) for tup in wtc: f.write("%s\t%s\n" %(tup[0],tup[1][1])) f.write("\n")
def parse(): tagger_classes = ([nltk.UnigramTagger, nltk.BigramTagger]) trained_sents, tagged_sents = trainer("WSJ_02-21.pos-chunk", "WSJ_23.pos") #tagger = nltk.UnigramTagger(trained_sents) print len(trained_sents) tagger = ClassifierBasedPOSTagger( train=trained_sents[:10000], classifier_builder=lambda train_feats: MaxentClassifier.train( train_feats, trace=0, max_iter=10)) f = open("WSJ_23.chunk", 'w') #print sents for sents in tagged_sents: (words, tags) = sents[0], sents[1] chunks = tagger.tag(tags) #print words, chunks wtc = zip(words, chunks) for tup in wtc: f.write("%s\t%s\n" % (tup[0], tup[1][1])) f.write("\n")
def get_chunks(text_string): # tokenization print('Tokenising text...') sentences = sent_tokenize(text_string) tokenized_sentences = [] for s in sentences: tokenized_sentences.append(word_tokenize(s)) # PoS tagging train_sents = treebank.tagged_sents() print('Training PoS tagger...') tagger = ClassifierBasedPOSTagger(train=train_sents) tagged_sentences = [] print('Tagging sentences...') for s in tokenized_sentences: tagged_sentences.append(tagger.tag(s)) # chunking print('Getting trained chunk classifier...') chunk_classifier = get_trained_classifier() chunked_sentences = [] print('Chunking sentences...') for s in tagged_sentences: chunked_sentences.append(chunk_classifier.parse(s)) return chunked_sentences
default = DefaultTagger('NN') train_sents = treebank.tagged_sents()[:3000] test_sents = treebank.tagged_sents()[3000:] tagger = ClassifierBasedPOSTagger(train=train_sents,backoff=default, cutoff_prob = 0.3 ) #tagger.evaluate(test_sents) #applying the tagger rtag = tagger.tag(r) print(rtag) #extracting all the noun phrases from raw string nlist = [] for word,tag in rtag: if (tag == 'NN'): value = "%s" % word nlist.append(value) if (tag == 'NNP'):
##### from nltk.tag.sequential import ClassifierBasedPOSTagger print("started classified") class_tagger = None try: with open('test_pickles/class.pickle', 'rb') as fa: class_tagger = pickle.load(fa) except FileNotFoundError as a: # training data print("dumping class") class_tagger = ClassifierBasedPOSTagger(train=train) with open('test_pickles/class.pickle', 'wb') as fb: pickle.dump(class_tagger, fb) #print(class_tagger.evaluate(test)) print(class_tagger.tag(tokenized_words)) #### # # 4 TnT # #### print("started tnt") from nltk.tag import tnt tnt_tagger = None try: with open('test_pickles/tnt.pickle', 'rb') as fa: tnt_tagger = pickle.load(fa) except FileNotFoundError as a: # training data print("dumping tnt")
from nltk.tag.sequential import ClassifierBasedPOSTagger default = DefaultTagger('NN') train_sents = treebank.tagged_sents()[:3000] test_sents = treebank.tagged_sents()[3000:] tagger = ClassifierBasedPOSTagger(train=train_sents,backoff=default, cutoff_prob = 0.3 ) #implementing it on the url names ntag = tagger.tag(ntoken) #extracting all the noun phrases from URL string nlist = [] for word,tag in ntag: if (tag == 'NN'): value = "%s" % word nlist.append(value) if (tag == 'NNP'): value = "%s" % word
#punctuation = re.compile(r'[-.?,":;()`~!@#$%^*()_=+{}]') #tword = [punctuation.sub("", word) for word in token] #print(tword) #without punctuation #removing all the MS smart quotes #smart_quotes = re.compile(r'[\x80-\x9f]') #words = [smart_quotes.sub("", i) for i in tword] #print(words) #without the smart quotes titletag = tagger.tag(ttoken) #tagging the list print(titletag) #extracting all the noun phrases from title string nlist = [] for word, tag in titletag: if (tag == 'NN'): value = "%s" % word nlist.append(value) if (tag == 'NNP'):
default = DefaultTagger('NN') train_sents = treebank.tagged_sents()[:3000] test_sents = treebank.tagged_sents()[3000:] tagger = ClassifierBasedPOSTagger(train=train_sents,backoff=default, cutoff_prob = 0.3 ) #tagger.evaluate(test_sents) #applying the tagger htag = tagger.tag(hd_tokens) print(htag) #extracting all the noun phrases from raw string nlist = [] for word,tag in htag: if (tag == 'NN'): value = "%s" % word nlist.append(value) if (tag == 'NNP'):
#tword = [punctuation.sub("", word) for word in token] #print(tword) #without punctuation #removing all the MS smart quotes #smart_quotes = re.compile(r'[\x80-\x9f]') #words = [smart_quotes.sub("", i) for i in tword] #print(words) #without the smart quotes titletag = tagger.tag(ttoken) #tagging the list print(titletag) #extracting all the noun phrases from title string nlist = [] for word,tag in titletag: if (tag == 'NN'): value = "%s" % word nlist.append(value) if (tag == 'NNP'):
from nltk.tag.sequential import ClassifierBasedPOSTagger default = DefaultTagger('NN') train_sents = treebank.tagged_sents()[:3000] test_sents = treebank.tagged_sents()[3000:] tagger = ClassifierBasedPOSTagger(train=train_sents, backoff=default, cutoff_prob=0.3) #applying the tagger rawtag = tagger.tag(clean) print rawtag #extracting all the noun phrases from raw string nlist = [] for word, tag in rawtag: if (tag == 'NN'): value = "%s" % word nlist.append(value) if (tag == 'NNP'):
#%% # combined tagger with a list of taggers and use a backoff tagger 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) # evaluating the new combined tagger with backoff taggers print(ct.evaluate(test_data)) print(ct.tag(nltk.word_tokenize(sentence))) #%% ## Training using Supervised classification algorithm from nltk.classify import NaiveBayesClassifier, MaxentClassifier from nltk.tag.sequential import ClassifierBasedPOSTagger nbt = ClassifierBasedPOSTagger(train=train_data, classifier_builder=NaiveBayesClassifier.train) # evaluate tagger on test data and sample sentences print(nbt.evaluate(test_data)) print(nbt.tag(nltk.word_tokenize(sentence)))
class TrainingSetAnalyzer(): ''' This class handles the setting of the training set data and provides support for features exctraction given a text''' def __init__(self, limit=300, debug=True): '''Instance the TrainingSetAnalyzer Keyword arguments: @param: limit size of the tweets which need to be analyzed (300) @param: debug flag for development process ''' self.__debug = debug self.__limit = limit self.__speller = SpellChecker() self.__splitter = Splitter("rtw") self.__replacer = RegexpReplacer() self.__ngramHandler = NgramHandler() train_sents = treebank.tagged_sents()[:3000] self.__tagger = ClassifierBasedPOSTagger(train=train_sents) def __analyzeSingleTweet(self, tweet): ''' Helper function to get unigrams, emoticons, ngrams given a text Keyword arguments: @param: tweet the tweet to be analyzed ''' chunks = self.__splitter.split(u'' + tweet) raw_feature_list_neg = [] emot_list = [] ngrams = [] for subTweet in chunks: try: preprocessed_tweet = self.__replacer.preprocess(subTweet) acr_expanded, tmp_emot_list = self.__replacer \ .acr_emot_exctractor(preprocessed_tweet) emot_list += tmp_emot_list enanched_txt = self.__speller.check_and_replace(acr_expanded) tagged_sent = self.__tagger.tag(enanched_txt) raw_feature_list_neg += self.__replacer \ .filter_raw_feature_list( acr_expanded) ngrams += self.__ngramHandler.exctract_ngrams(tagged_sent) except Exception as e: print "Sorry, something goes wrong: %s txt: %s" \ % (str(e), tweet) return raw_feature_list_neg, emot_list, ngrams def analyze(self): ''' Analyzes a set of tweets ''' print "Found %i elments for training" % self.__limit n = 0 while n < 20: qs = get_tweets_for_analyzing(skip=n) for tweet in qs: raw_feature_list_neg, emot, ngrams = self.__analyzeSingleTweet( tweet.text) if not self.__debug: print "saving...." tweet.set_features(raw_feature_list_neg, emot, ngrams) n += 1 return def extract_features_for_classification(self, text): ''' Helper function to exctract features given a text Keyword arguments: @param: text the text whose the features will be exctracted ''' raw_feature_list_neg, emot_list, ngrams = self.__analyzeSingleTweet( text) return raw_feature_list_neg, emot_list, ngrams, dict([ (word, True) for word in raw_feature_list_neg + emot_list + ngrams ]) def purge_useless_features(self): '''Helper function to prune less frequent unigram features''' tweets = get_tweets_for_pruning() print "Pruning process for %i tweets" % tweets.count() mrt = tweets.map_reduce(mapfunc_filter, reducefunc, "cn") mrt = filter(lambda status: status.value > PURGE_TRESHOLD, mrt) purged_qs = [item.key for item in mrt] for tweet in tweets: try: tweet.features.filtered_unigram = [ item for item in purged_qs if item in tweet.features.raw_feature_list_neg ] tweet.save() except Exception, e: print e print "Done!"
default = DefaultTagger("NN") train_sents = treebank.tagged_sents()[:3000] test_sents = treebank.tagged_sents()[3000:] tagger = ClassifierBasedPOSTagger(train=train_sents, backoff=default, cutoff_prob=0.3) # tagger.evaluate(test_sents) # applying the tagger htag = tagger.tag(hd_tokens) print(htag) # extracting all the noun phrases from raw string nlist = [] for word, tag in htag: if tag == "NN": value = "%s" % word nlist.append(value) if tag == "NNP":
from nltk.tag import DefaultTagger from nltk.tag.sequential import ClassifierBasedPOSTagger default = DefaultTagger('NN') train_sents = treebank.tagged_sents()[:3000] test_sents = treebank.tagged_sents()[3000:] tagger = ClassifierBasedPOSTagger(train=train_sents,backoff=default, cutoff_prob = 0.3 ) #applying the tagger rawtag = tagger.tag(clean) print rawtag #extracting all the noun phrases from raw string nlist = [] for word,tag in rawtag: if (tag == 'NN'): value = "%s" % word nlist.append(value) if (tag == 'NNP'):
def combined_tagger(training_data, taggers, backoff=None): for tagger in taggers: backoff = tagger(training_data, backoff=backoff) return backoff ct = combined_tagger(training_data=train_data, taggers=[UnigramTagger, BigramTagger, TrigramTagger], backoff=rt) # Evaluate the chained tagger with backoff. (Great accuracy! 90.91%) print(ct.evaluate(test_data)) print("\n4-Chained tags:") print(ct.tag(tokens)) # 5. TAGGER TRAINED BY SUPERVISED CLASSIFICATION ALTGORITHM (Naive Bayes Classifier) # The feature_detector function forms the core of the training process. It generates features of the training data, # such as word, previous word, tag, previous tag, case etc. nbt = ClassifierBasedPOSTagger(train=train_data, classifier_builder=NaiveBayesClassifier.train) # Evaluate tagger on test data and sample sentence. (Awesome accuracy! 93.07%) print(nbt.evaluate(test_data)) print("\n5-Naive Bayes Classifier-based tags:") print(nbt.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) print ct.tag(tokens) from nltk.classify import NaiveBayesClassifier, MaxentClassifier from nltk.tag.sequential import ClassifierBasedPOSTagger nbt = ClassifierBasedPOSTagger(train=train_data, classifier_builder=NaiveBayesClassifier.train) print nbt.evaluate(test_data) print nbt.tag(tokens) # try this out for fun! met = ClassifierBasedPOSTagger(train=train_data, classifier_builder=MaxentClassifier.train) print met.evaluate(test_data) print met.tag(tokens)
from nltk.tag.sequential import ClassifierBasedPOSTagger default = DefaultTagger('NN') train_sents = treebank.tagged_sents()[:3000] test_sents = treebank.tagged_sents()[3000:] tagger = ClassifierBasedPOSTagger(train=train_sents, backoff=default, cutoff_prob=0.3) #implementing it on the url names ntag = tagger.tag(ntoken) #extracting all the noun phrases from URL string nlist = [] for word, tag in ntag: if (tag == 'NN'): value = "%s" % word nlist.append(value) if (tag == 'NNP'): value = "%s" % word nlist.append(value)