def runSentanal(train, test): sentanal = SentimentAnalyzer() all_words_neg = sentanal.all_words([mark_negation(doc) for doc in train]) unigramFeats = sentanal.unigram_word_feats(all_words_neg, min_freq=4) sentanal.add_feat_extractor(extract_unigram_feats, unigrams=unigramFeats, handle_negation=True) # bigramFeats = sentanal. # sentanal.add_feat_extractor(extract_bigram_feats, bigrams=bigramFeats) trainList = sentanal.apply_features(train) testList = sentanal.apply_features(test) trainer = NaiveBayesClassifier.train classifier = sentanal.train(trainer, trainList) classifier.show_most_informative_features() # creates array for storing values values = [] # display results for key, value in sorted(sentanal.evaluate(testList).items()): print('{0}: {1}'.format(key, value)) values.append(value) # write results to csv with open(OUTPUT_CSV, mode='a') as csvFile: writer = csv.writer(csvFile, delimiter=',') writer.writerow(values)
def createClassifier(ignoreTweets=False): neg_ids = movie_reviews.fileids('neg') pos_ids = movie_reviews.fileids('pos') neg_sents = [(extractWords(movie_reviews.words(fileids=[f])), 'neg') for f in neg_ids] pos_sents = [(extractWords(movie_reviews.words(fileids=[f])), 'pos') for f in pos_ids] #if you dont want to process all tweets, just call : (neg_pols, pos_pols) = getSentPolarities() (neg_tweets, pos_tweets) = getTweets(ignoreTweets) neg_sents = neg_sents + neg_tweets + neg_pols pos_sents = pos_sents + pos_tweets + pos_pols trainsizeneg = int(0.75 * len(neg_sents)) trainsizepos = int(0.75 * len(pos_sents)) all_train = neg_sents[:trainsizeneg] + pos_sents[:trainsizepos] all_test = neg_sents[trainsizeneg:] + pos_sents[trainsizepos:] # train size = 1500, test size = 500 s_analyzer = SentimentAnalyzer() classifier = NaiveBayesClassifier.train(all_train) print accuracy(classifier, all_test) #classifier.show_most_informative_features() return classifier
def train(): subj_docs = [ (sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances] ] obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]] train_subj_docs = subj_docs[:80] test_subj_docs = subj_docs[80:100] train_obj_docs = obj_docs[:80] test_obj_docs = obj_docs[80:100] training_docs = train_subj_docs + train_obj_docs testing_docs = test_subj_docs + test_obj_docs sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words( [mark_negation(doc) for doc in training_docs]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) training_set = sentim_analyzer.apply_features(training_docs) test_set = sentim_analyzer.apply_features(testing_docs) trainer = NaiveBayesClassifier.train classifier = sentim_analyzer.train(trainer, training_set) for key, value in sorted(sentim_analyzer.evaluate(test_set).items()): print('{0}: {1}'.format(key, value))
def sentiment_classifier(df): df = df.copy() # prepping data df = df[['txgot_binary', 'Convo_1']].dropna() text_process_col = pre.process_corpus(np.asarray(df['Convo_1']), []) txgot_col = np.asarray(df['txgot_binary']) # turns into list of tuples (convo, label) docs = list(zip(text_process_col, txgot_col)) shuffle(docs) training_docs = docs[:int(len(docs) * 2 / 3)] test_docs = docs[int(len(docs) * 2 / 3):] # sentiment analyzer sentim_analyzer = SentimentAnalyzer() # simple unigram word features, handling negation all_words_neg = sentim_analyzer.all_words( [mark_negation(doc) for doc in training_docs]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) # train classifier training_set = sentim_analyzer.apply_features(training_docs) test_set = sentim_analyzer.apply_features(test_docs) trainer = NaiveBayesClassifier.train classifier = sentim_analyzer.train(trainer, training_set) # show results for key, value in sentim_analyzer.evaluate(test_set).items(): print('{}: {}'.format(key, value))
def load_data(self, classifier=None): # source: http://www.nltk.org/book/ch06.html, http://www.nltk.org/howto/sentiment.html print "Loading training data...", sys.stdout.flush() training_docs, testing_docs = self.load_web_reviews() # documents = [(word_tokenize(movie_reviews.raw(fileid)), category) # for category in movie_reviews.categories() # for fileid in movie_reviews.fileids(category)] # random.shuffle(documents) # cutoff = int(len(documents) * 0.1) # training_docs, testing_docs = documents[cutoff:], documents[:cutoff] print "Done!" print "Extracting unigram features and applying to training data...", sys.stdout.flush() sentim_analyzer = SentimentAnalyzer(classifier=classifier) all_words = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words)#, top_n=5000) # print len(unigrams) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats, handle_negation=True) training_set = sentim_analyzer.apply_features(training_docs) testing_set = sentim_analyzer.apply_features(testing_docs) print "Done!" return sentim_analyzer, training_set, testing_set
def train(): positive_tweets = read_tweets('/root/295/new/positive.txt', 'positive') negative_tweets = read_tweets('/root/295/new/negative.txt', 'negative') print len(positive_tweets) print len(negative_tweets) #pos_train = positive_tweets[:2000] #neg_train = negative_tweets[:2000] #pos_test = positive_tweets[2001:3000] #neg_test = negative_tweets[2001:3000] pos_train = positive_tweets[:len(positive_tweets)*80/100] neg_train = negative_tweets[:len(negative_tweets)*80/100] pos_test = positive_tweets[len(positive_tweets)*80/100+1:] neg_test = negative_tweets[len(positive_tweets)*80/100+1:] training_data = pos_train + neg_train test_data = pos_test + neg_test sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_data]) #print all_words_neg unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) #print unigram_feats print len(unigram_feats) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) training_set = sentim_analyzer.apply_features(training_data) test_set = sentim_analyzer.apply_features(test_data) print test_set trainer = NaiveBayesClassifier.train classifier = sentim_analyzer.train(trainer, training_set) for key,value in sorted(sentim_analyzer.evaluate(test_set).items()): print('{0}: {1}'.format(key, value)) print sentim_analyzer.classify(tokenize_sentance('I hate driving car at night')) return sentim_analyzer
def nb_cv(cleaned_df): # Get Features training_set = get_nb_features(cleaned_df) # Get 10-Fold. Important: Shuffle=True cv = KFold(n_splits=10, random_state=0, shuffle=True) # Model sentiment_analyzer = SentimentAnalyzer() trainer = NaiveBayesClassifier.train # Store Result Accuracy = [] # For each fold, train model, evaluate for train_index, test_index in cv.split(training_set): classifier = sentiment_analyzer.train( trainer, np.array(training_set)[train_index].tolist()) truth_list = np.array(training_set)[test_index].tolist() performance = sentiment_analyzer.evaluate(truth_list, classifier) Accuracy.append(performance['Accuracy']) '''## Can add all other measures here. Sample Result as below: {'Accuracy': 0.525, 'Precision [negative]': 0.28337874659400547, 'Recall [negative]': 0.7272727272727273, 'F-measure [negative]': 0.407843137254902, 'Precision [neutral]': 0.5011933174224343, 'Recall [neutral]': 0.30837004405286345, 'F-measure [neutral]': 0.38181818181818183, 'Precision [positive]': 0.7461629279811098, 'Recall [positive]': 0.611810261374637, 'F-measure [positive]': 0.672340425531915} ''' return np.mean(np.asarray(Accuracy))
def __init__(self): #document represented by a tuple (sentence,labelt) n_instances = 100 subj_docs = [(sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances]] obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]] #split subj and objinstances to keep a balanced uniform class distribution in both train and test sets. train_subj_docs = subj_docs[:80] test_subj_docs = subj_docs[80:100] train_obj_docs = obj_docs[:80] test_obj_docs = obj_docs[80:100] training_docs = train_subj_docs+train_obj_docs testing_docs = test_subj_docs+test_obj_docs #train classifier sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs]) #use simple unigram word features, handling negation unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) #apply features to obtain a feature_value representations of our datasets training_set = sentim_analyzer.apply_features(training_docs) test_set = sentim_analyzer.apply_features(testing_docs) self.trainer = NaiveBayesClassifier.train self.classifier = sentim_analyzer.train(self.trainer, training_set) for key,value in sorted(sentim_analyzer.evaluate(test_set).items()): print('{0}: {1}'.format(key, value)) self.sid = SentimentIntensityAnalyzer()
def trainSubjectivity(): # Subjective vs. objective sentence classifier. Borrows from NLTK Documentation. # Plan on using it in larger machine learning sentiment model as pre-processing # Must differentiate between objective and subjective subjDocs = [(sent, 'subj') for sent in subjectivity.sents(categories='subj')] objDocs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')] nSubj = len(subjDocs) nObj = len(objDocs) # 90% Training, 10% Test subjTrain = int(.9 * nSubj) objTrain = int(.9 * nObj) trainSubj = subjDocs[:subjTrain] testSubj = subjDocs[subjTrain:nSubj] trainObj = objDocs[:objTrain] testObj = objDocs[objTrain:nObj] trainDocs = trainSubj + trainObj testDocs = testSubj + testObj # Create sentiment class, mark negation, create features (unigram) sentiment = SentimentAnalyzer() markNegation = sentiment.all_words([mark_negation(doc) for doc in trainDocs]) unigramFeats = sentiment.unigram_word_feats(markNegation, min_freq=4) sentiment.add_feat_extractor(extract_unigram_feats, unigrams=unigramFeats) training = sentiment.apply_features(trainDocs) testing = sentiment.apply_features(testDocs) # Train classifier trainer = NaiveBayesClassifier.train subjectivityClassifier = sentiment.train(trainer, training) joblib.dump(subjectivityClassifier, 'subjectivity.pkl') for key, value in sorted(sentiment.evaluate(testing).items()): print('{0}: {1}'.format(key, value)) '''
def demo_subjectivity(trainer, save_analyzer=False, n_instances=None, output=None): """ Train and test a classifier on instances of the Subjective Dataset by Pang and Lee. The dataset is made of 5000 subjective and 5000 objective sentences. All tokens (words and punctuation marks) are separated by a whitespace, so we use the basic WhitespaceTokenizer to parse the data. :param trainer: `train` method of a classifier. :param save_analyzer: if `True`, store the SentimentAnalyzer in a pickle file. :param n_instances: the number of total sentences that have to be used for training and testing. Sentences will be equally split between positive and negative. :param output: the output file where results have to be reported. """ from nltk.sentiment import SentimentAnalyzer from nltk.corpus import subjectivity if n_instances is not None: n_instances = int(n_instances/2) subj_docs = [(sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances]] obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]] # We separately split subjective and objective instances to keep a balanced # uniform class distribution in both train and test sets. train_subj_docs, test_subj_docs = split_train_test(subj_docs) train_obj_docs, test_obj_docs = split_train_test(obj_docs) training_docs = train_subj_docs+train_obj_docs testing_docs = test_subj_docs+test_obj_docs sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs]) # Add simple unigram word features handling negation unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) # Apply features to obtain a feature-value representation of our datasets training_set = sentim_analyzer.apply_features(training_docs) test_set = sentim_analyzer.apply_features(testing_docs) classifier = sentim_analyzer.train(trainer, training_set) try: classifier.show_most_informative_features() except AttributeError: print('Your classifier does not provide a show_most_informative_features() method.') results = sentim_analyzer.evaluate(test_set) if save_analyzer == True: save_file(sentim_analyzer, 'sa_subjectivity.pickle') if output: extr = [f.__name__ for f in sentim_analyzer.feat_extractors] output_markdown(output, Dataset='subjectivity', Classifier=type(classifier).__name__, Tokenizer='WhitespaceTokenizer', Feats=extr, Instances=n_instances, Results=results) return sentim_analyzer
def addfeatures(cleaned_tokens_list): sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words( [mark_negation(token_list) for token_list in cleaned_tokens_list]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)
def GetSampleTrainDataForNLTK(self, trainSet): sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words( [mark_negation(doc) for doc in trainSet]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) sampleTrainData = sentim_analyzer.apply_features(trainSet) return sampleTrainData
def main(): x, y = load_datasets(["../datasets/sentiment_uci/yelp_labelled.txt"]) stopwords = set() with open('../stopwords.txt', 'r') as f: for w in f: stopwords.add(w.strip()) tok = TweetTokenizer() x = [remove_stopwords(tok.tokenize(s.lower()), stopwords) for s in x] x = np.array(x) accumulate = dict() folds = 10 for train_idx, test_idx in StratifiedKFold(y=y, n_folds=folds, shuffle=True): train_x, train_y = x[train_idx], y[train_idx] test_x, test_y = x[test_idx], y[test_idx] # train_x = [remove_stopwords(tok.tokenize(s), stopwords) for s in train_x] # test_x = [remove_stopwords(tok.tokenize(s), stopwords) for s in test_x] train_docs = [(sent, label) for sent, label in zip(train_x, train_y)] test_docs = [(sent, label) for sent, label in zip(test_x, test_y)] cls = SentimentAnalyzer() # train words_with_neg = cls.all_words([mark_negation(a) for a in train_x]) unigram_feats = cls.unigram_word_feats(words_with_neg) # bigram_feats = cls.bigram_collocation_feats(train_x) cls.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats, handle_negation=True) # cls.add_feat_extractor(extract_bigram_feats, bigrams=bigram_feats) training_set = cls.apply_features(train_docs, labeled=True) cls.train(MaxentClassifier.train, training_set, max_iter=10, trace=0) # test & evaluate test_set = cls.apply_features(test_docs) for key, value in sorted(cls.evaluate(test_set).items()): print('\t{0}: {1}'.format(key, value)) accumulate.setdefault(key, 0.0) accumulate[key] += value if value is not None else 0.0 print("Averages") for key, value in sorted(accumulate.items()): print('\tAverage {0}: {1}'.format(key, value / folds))
def train_lr(training_set): sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_set]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) training_set = sentim_analyzer.apply_features(training_set) trainer = logreg.train classifier = sentim_analyzer.train(trainer, training_set) return [sentim_analyzer,classifier]
def demo_movie_reviews(trainer, n_instances=None, output=None): """ Train classifier on all instances of the Movie Reviews dataset. The corpus has been preprocessed using the default sentence tokenizer and WordPunctTokenizer. Features are composed of: - most frequent unigrams :param trainer: `train` method of a classifier. :param n_instances: the number of total reviews that have to be used for training and testing. Reviews will be equally split between positive and negative. :param output: the output file where results have to be reported. """ from nltk.corpus import movie_reviews from nltk.sentiment import SentimentAnalyzer if n_instances is not None: n_instances = int(n_instances/2) pos_docs = [(list(movie_reviews.words(pos_id)), 'pos') for pos_id in movie_reviews.fileids('pos')[:n_instances]] neg_docs = [(list(movie_reviews.words(neg_id)), 'neg') for neg_id in movie_reviews.fileids('neg')[:n_instances]] # We separately split positive and negative instances to keep a balanced # uniform class distribution in both train and test sets. train_pos_docs, test_pos_docs = split_train_test(pos_docs) train_neg_docs, test_neg_docs = split_train_test(neg_docs) training_docs = train_pos_docs+train_neg_docs testing_docs = test_pos_docs+test_neg_docs sentim_analyzer = SentimentAnalyzer() all_words = sentim_analyzer.all_words(training_docs) # Add simple unigram word features unigram_feats = sentim_analyzer.unigram_word_feats(all_words, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) # Apply features to obtain a feature-value representation of our datasets training_set = sentim_analyzer.apply_features(training_docs) test_set = sentim_analyzer.apply_features(testing_docs) classifier = sentim_analyzer.train(trainer, training_set) try: classifier.show_most_informative_features() except AttributeError: print('Your classifier does not provide a show_most_informative_features() method.') results = sentim_analyzer.evaluate(test_set) if output: extr = [f.__name__ for f in sentim_analyzer.feat_extractors] output_markdown(output, Dataset='Movie_reviews', Classifier=type(classifier).__name__, Tokenizer='WordPunctTokenizer', Feats=extr, Results=results, Instances=n_instances)
def train(self): training_docs = list() for index, row in self.training_data.iterrows(): row['text'] = self.clean_tweet(row['text']) row['text'] = row['text'].translate(self.translate_table) tokens = self.tokenizer.tokenize(row['text']) training_docs.append((tokens, row['sentiment'].lower())) sentim_analyzer = SentimentAnalyzer() training_set = nltk.classify.apply_features(self.extract_features, training_docs) self.classifier = nltk.NaiveBayesClassifier.train(training_set)
def sentiment_analysis(data): from nltk.classify import NaiveBayesClassifier from nltk.corpus import subjectivity from nltk.sentiment import SentimentAnalyzer from nltk.sentiment.util import * n_instances = 100 subj_docs = [ (sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances] ] obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]] train_subj_docs = subj_docs[:80] test_subj_docs = subj_docs[80:100] train_obj_docs = obj_docs[:80] test_obj_docs = obj_docs[80:100] training_docs = train_subj_docs + train_obj_docs testing_docs = test_subj_docs + test_obj_docs sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words( [mark_negation(doc) for doc in training_docs]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) training_set = sentim_analyzer.apply_features(training_docs) test_set = sentim_analyzer.apply_features(testing_docs) trainer = NaiveBayesClassifier.train classifier = sentim_analyzer.train(trainer, training_set) for key, value in sorted(sentim_analyzer.evaluate(test_set).items()): print('{0}: {1}'.format(key, value)) from nltk.sentiment.vader import SentimentIntensityAnalyzer from nltk import tokenize sid = SentimentIntensityAnalyzer() for line in data: ss = sid.polarity_scores(line['line_text']) line['compound'] = ss['compound'] line['neg'] = ss['neg'] line['pos'] = ss['pos'] line['neu'] = ss['neu']
def train_sentiment(): instances = 8000 subj = [(sent, 'subj') for sent in subjectivity.sents(categories='subj')[:instances]] obj = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:instances]] train_subj = subj train_obj = obj train_set = train_subj + train_obj sentiment = SentimentAnalyzer() all_neg = sentiment.all_words([mark_negation(doc) for doc in train_set]) uni_g = sentiment.unigram_word_feats(all_neg, min_freq=4) sentiment.add_feat_extractor(extract_unigram_feats, unigrams=uni_g) trained_set = sentiment.apply_features(train_set) nb = NaiveBayesClassifier.train classifier = sentiment.train(nb, trained_set) return classifier
def runClassifier(classifierKey, emailsInSentenceForm, unigram_features): #Create a sentiment analyzer to analyze the text documents. This analyzer #provides an abstraction for managing a classifier, and feature extractor. #It also provides convinence data metrics on classifier performance. sentim_analyzer = SentimentAnalyzer() #Create a feature extractor based on the unigram word features created. #The unigram feature extractor is found in the sentiment utils package. sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_features) print("Current classifier: " + classifierKey) #Load the classifier. classifier = loadModel(classifierKey) #Set up sentiment counts for the emails. posVote = 0 negVote = 0 classifierResultsDict = [] #int(emailsInSentenceForm.shape[0]/3.0) for emailIndex in range(0, int(emailsInSentenceForm.shape[0])): if (emailIndex % 100 == 0): print(classifierKey + " On email: " + str(emailIndex)) #Write the results to a file. f = open("./" + classifierKey + "Results.pkl", "w") pickle.dump(classifierResultsDict, f) f.close() #Get the list of sentences for the email. email = emailsInSentenceForm.iloc[emailIndex, :][0] featurizedSentenceList = sentim_analyzer.apply_features(email) for sent in featurizedSentenceList: label = classifier.classify(sent[0]) if label == "pos": posVote += 1 else: negVote += 1 #Take the maximum vote for the class label. Use 1 and -1 to faciliitate the later correlation calculations. if posVote >= negVote: classifierResultsDict.append(1) else: classifierResultsDict.append(-1) #Reset pos and neg votes to 0. posVote = 0 negVote = 0 #Write the results to a file. f = open("./" + classifierKey + "Results.pkl", "w") pickle.dump(classifierResultsDict, f) f.close()
def get_best_classifier_from_debates(): """ The best classifier for debates turned out to be Freq Dist, Logitic :return: the trained classifier using the entire corpus """ neg_docs, pos_docs = sentimentAnalysisDocumentBased.get_political_debates() train_docs = neg_docs + pos_docs # Set up the Sentiment Analyzer analyzer = SentimentAnalyzer() analyzer.add_feat_extractor( sentimentAnalysisDocumentBased.extract_freq_dist) train_feat = list(analyzer.apply_features(train_docs, labeled=True)) classifier = SklearnClassifier(LogisticRegression()).train(train_feat) return analyzer, classifier
def run_sa_mov(train, test): a = SentimentAnalyzer() tr = NaiveBayesClassifier.train all_words = mov_analyzer.all_words(train) # Add simple unigram word features unigram_feats = a.unigram_word_feats(all_words, min_freq=4) a.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) # Apply features to obtain a feature-value representation of our datasets tr_set = a.apply_features(train) test_set = a.apply_features(test) #Training clf = a.train(tr, tr_set) res = a.evaluate(test_set) print(res)
def get_best_classifer_from_movies(): """ The best classifier for movies turned out to be Bigram, Linear SVM :return: the trained classifier using the entire corpus """ neg_docs, pos_docs = sentimentAnalysisDocumentBased.get_movie_corpus() train_docs = neg_docs + pos_docs # Set up the Sentiment Analyzer analyzer = SentimentAnalyzer() analyzer.add_feat_extractor( sentimentAnalysisDocumentBased.extract_sig_bigram_feats) train_feat = list(analyzer.apply_features(train_docs, labeled=True)) classifier = SklearnClassifier(LinearSVC()).train(train_feat) return analyzer, classifier
def NB(df_train, df_dev): # Feature extraction # n=1200 df_train['clean_text'] = df_train['clean_text'].apply( lambda x: stem_stop(x)) df_dev['clean_text'] = df_dev['clean_text'].apply(lambda x: stem_stop(x)) df_pos_train = df_train[df_train['tweet_sentiment'] == 'positive'] # df_pos_train= df_pos_train.sample(n=n, random_state=1) pos_tweets = df_pos_train['clean_text'].tolist() df_neg_train = df_train[df_train['tweet_sentiment'] == 'negative'] # df_neg_train= df_neg_train.sample(n=n, random_state=1) neg_tweets = df_neg_train['clean_text'].tolist() df_neutral_train = df_train[df_train['tweet_sentiment'] == 'neutral'] # df_neutral_train= df_neutral_train.sample(n=n, random_state=1) neutral_tweets = df_neutral_train['clean_text'].tolist() positive_featuresets = [(features(tweet), 'positive') for tweet in pos_tweets] negative_featuresets = [(features(tweet), 'negative') for tweet in neg_tweets] neutral_featuresets = [(features(tweet), 'neutral') for tweet in neutral_tweets] training_features = positive_featuresets + negative_featuresets + neutral_featuresets ngram_vectorizer = CountVectorizer(analyzer='word', binary=True, lowercase=False, ngram_range=(1, 2)) # train the model sentiment_analyzer = SentimentAnalyzer() trainer = NaiveBayesClassifier.train classifier = sentiment_analyzer.train(trainer, training_features) truth_list = list(df_dev[['clean_text', 'tweet_sentiment']].itertuples(index=False, name=None)) # test the model for i, (text, expected) in enumerate(truth_list): text_feats = features(text) truth_list[i] = (text_feats, expected) re = sentiment_analyzer.evaluate(truth_list, classifier) print(re) return classifier
def sentimentAnalysis(self, number): ids = self.getHandleIds(number) rows = self.query(date=True, text=True, is_from_me=True, condition='handle_id in (' + ','.join(ids) + ')') sent_analyzer = SentimentAnalyzer() res = {"Me": {}, number: {}} plt.title("Sentiment Analysis") plt.ylabel("Sentiment") plt.xlabel("Date") plt.legend() plt.savefig("results/sentiment") plt.show()
def subjectivity_classifier(): from nltk.classify import NaiveBayesClassifier from nltk.corpus import subjectivity from nltk.sentiment import SentimentAnalyzer from nltk.sentiment.util import * """ Initializes and trains categorical subjectivity analyzer """ N_INSTANCES = 100 subj_docs = [ (sent, 'subj') for sent in subjectivity.sents(categories='subj')[:N_INSTANCES] ] obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:N_INSTANCES]] train_subj_docs = subj_docs[:80] test_subj_docs = subj_docs[80:] train_obj_docs = obj_docs[:80] test_obj_docs = obj_docs[80:] training_docs = train_subj_docs + train_obj_docs testing_docs = test_subj_docs + test_obj_docs sent_analyzer = SentimentAnalyzer() all_words_neg = sent_analyzer.all_words( [mark_negation(doc) for doc in training_docs]) unigram_feats = sent_analyzer.unigram_word_feats(all_words_neg, min_freq=4) print(f"unigram feats: {len(unigram_feats)}") sent_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) training_set = sent_analyzer.apply_features(training_docs) test_set = sent_analyzer.apply_features(testing_docs) trainer = NaiveBayesClassifier.train classifier = sent_analyzer.train(trainer, training_set) for k, v in sorted(sent_analyzer.evaluate(test_set).items()): print(f"{k}: {v}") return sent_analyzer
def __init__(self, n_instances=500): self.n_instances = n_instances self.subj_classifier = None self.sentim_analyzer = None try: BASE_DIR = os.path.dirname( os.path.dirname(os.path.abspath(__file__))) with open(os.path.join(BASE_DIR, 'main\my_classifier.pickle'), 'rb') as f: sentim_analyzer = pickle.load(f) self.sentim_analyzer = sentim_analyzer except IOError: with open('plot.tok.gt9.5000') as obj_sents: obj_sents = obj_sents.read() with open('quote.tok.gt9.5000') as subj_sents: subj_sents = subj_sents.read() self.obj_sents = obj_sents self.sentim_analyzer = SentimentAnalyzer() self.train_diploma(subj_sents, obj_sents)
def getNonEmptyEmailBodysTokenized(): db = sql.connect("./data/database.sqlite") cursor = db.cursor() #Used to mark all words that come between negations. sentiment_analyzer = SentimentAnalyzer() #Load the pre-trained sentence tokenizer. sent_detector = nltk.data.load('tokenizers/punkt/english.pickle') #Get the keys for the pandas data frame. cursor.execute('''PRAGMA table_info('Emails');''') columnNames = [] for row in cursor: columnNames.append(row[1]) #Retrieve all email data. cursor.execute( '''SELECT ExtractedBodyText FROM Emails WHERE (ExtractedBodyText != '');''' ) dataDict = {'ExtractedBodyText': []} for row in cursor: #Extract each column value and add it to the dictionary. tokenizedToSentences = sent_detector.tokenize(row[0].strip()) tokenizedToWordsList = [] for sentence in tokenizedToSentences: #Split sentences into words. tokenizedWords = word_tokenize(sentence) #Add negation tag to each word that has been negated, from the sentiment utils package. tokenizedWordsWithNeg = mark_negation(tokenizedWords) #Re-encode each word tokenizedWordsWithNeg = [ string.encode('ascii', 'ignore').decode('ascii') for string in tokenizedWordsWithNeg ] #Add newly tokenized word to list. tokenizedToWordsList.append(tokenizedWordsWithNeg) #Add list of tokenized sentences to dataDict. dataDict['ExtractedBodyText'].append(tokenizedToWordsList) #Return pandas data frame with all data. data = pd.DataFrame(dataDict) db.close() return data
def get_nltk_NB(NEG_DATA, POS_DATA, num_train): train_neg, test_neg = get_nltk_train_test(NEG_DATA, 'neg', num_train) train_pos, test_pos = get_nltk_train_test(POS_DATA, 'pos', num_train) training_docs = train_neg + train_pos testing_docs = test_neg + test_pos sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) training_set = sentim_analyzer.apply_features(training_docs) test_set = sentim_analyzer.apply_features(testing_docs) trainer = NaiveBayesClassifier.train classifier = sentim_analyzer.train(trainer, training_set) #results = [] for key,value in sorted(sentim_analyzer.evaluate(test_set).items()): print('{0}: {1}'.format(key,value))
def analyze_sentiment(paragraph): n_instances = 100 subj_docs = [ (sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances] ] obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]] train_subj_docs = subj_docs[:80] test_subj_docs = subj_docs[80:100] train_obj_docs = obj_docs[:80] test_obj_docs = obj_docs[80:100] training_docs = train_subj_docs + train_obj_docs testing_docs = test_subj_docs + test_obj_docs sentim_analyzer = SentimentAnalyzer() all_words_neg = sentim_analyzer.all_words( [mark_negation(doc) for doc in training_docs]) unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4) sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) training_set = sentim_analyzer.apply_features(training_docs) test_set = sentim_analyzer.apply_features(testing_docs) trainer = NaiveBayesClassifier.train classifier = sentim_analyzer.train(trainer, training_set) sid = SentimentIntensityAnalyzer() total_sum = 0 count = 0.0 sentences = sent_tokenize(paragraph) for sentence in sentences: total_sum += sid.polarity_scores(sentence)["compound"] count += 1 return total_sum * 10 / count
def run_sa_twitt(train, test): a = SentimentAnalyzer() tr = NaiveBayesClassifier.train all_words = [word for word in a.all_words(train)] # Add simple unigram word features unigram_feats = a.unigram_word_feats(all_words, top_n=1000) a.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats) # Add bigram collocation features bigram_collocs_feats = a.bigram_collocation_feats( [tweet[0] for tweet in train_twitt], top_n=100, min_freq=12) a.add_feat_extractor(extract_bigram_feats, bigrams=bigram_collocs_feats) tr_set = a.apply_features(train) test_set = a.apply_features(test) #Training clf = a.train(tr, tr_set) res = a.evaluate(test_set) print(res)