def classify_tweets(request): consumer_key="Wb4W1n264iHhcrqcXt54bA" consumer_secret="2NFs7pO610XKQUOs5hPAz8wCEO4uxmP3111HPhsmgc" access_token="36641014-28RR3YAp6MxFxJ706gsp5a7bRy0sYDsjLCwixs2iM" access_token_secret="qOGQg84VvurJKX9qSF3Zgl973BxF6ryt7Yruoxtw" auth = tweepy.OAuthHandler(consumer_key, consumer_secret) auth.set_access_token(access_token, access_token_secret) api = tweepy.API(auth) query = request.POST.get('query') result=api.search(query) tweets=[] classification=[] for tweet in result: try: tweets.append(str(tweet.text)) except: pass posScore=0 negScore=0 for tweet in tweets: tokens=tweet.split() data_preprocess.remove_noise_words(tokens) data_preprocess.remove_names(tokens) data_preprocess.remove_links(tokens) tweet_counts=[] token_counts=[] category_counts=defaultdict(lambda:defaultdict(int)) p=tweet_category_count.objects.get(id=1) tweet_counts.append(p.positive_count) tweet_counts.append(p.negative_count) p=token_category_count.objects.get(id=1) token_counts.append(p.positive_count) token_counts.append(p.negative_count) for token in tokens: try: p=pos_tokens.objects.get(ptoken=token) category_counts[token]['pos']=p.pcount except: category_counts[token]['pos']=0 for token in tokens: try: p=neg_tokens.objects.get(ntoken=token) category_counts[token]['neg']=p.ncount except: category_counts[token]['neg']=0 classifier=NaiveBayesClassifier() result=classifier.classify(tokens,category_counts,tweet_counts,token_counts) if(result=='pos'): posScore+=1 else: negScore+=1 classification.append(result) return render_to_response("index.html",{'tweets':tweets,'pos_neg':classification,'posScore':posScore,'negScore':negScore})
======= >>>>>>> 89aa7e23b0b2789d0986b7c01aff694715d5590b for index in request.POST: (ind,a)=index.split(':') if request.POST.get(index,''): if(request.POST[index]=='pos'): out_file=open("positive.txt",'a') <<<<<<< HEAD m.update(current_tweets[int(a)-1]) p=data_set(tweet=current_tweets[int(a)-1],tweet_hash=m.hexdigest(),pos_neg='pos',movie_name=current_tweets[0]) p.save() else: m.update(current_tweets[int(a)-1]) out_file=open("negative.txt",'a') p=data_set(tweet=current_tweets[int(a)-1],tweet_hash=m.hexdigest(),pos_neg='neg',movie_name=current_tweets[0]) p.save() tokens=current_tweets[int(a)-1].split() data_preprocess.remove_noise_words(tokens) data_preprocess.remove_names(tokens) data_preprocess.remove_links(tokens) ======= else: out_file=open("negative.txt",'a') tokens=current_tweets[int(a)-1].split() >>>>>>> 89aa7e23b0b2789d0986b7c01aff694715d5590b for token in tokens: out_file.write(token+'\n') return render_to_response("tweetsSaved.html")
def save_tweets(request): #unpickle the list of recent tweets retrieved with open('current_tweets.txt','rb') as file_id: current_tweets=pickle.load(file_id) tokens=[] """Examine every Post variable one by one and write the positive and negative marked tweets into corresponding files after breaking the tweets into tokens""" m = hashlib.md5() for index in request.POST: (ind,a)=index.split(':') if request.POST.get(index,''): if(request.POST[index]=='pos'): out_file=open("positive.txt",'a') m.update(current_tweets[int(a)-1]) p=data_set(tweet=current_tweets[int(a)-1],tweet_hash=m.hexdigest(),pos_neg='pos',movie_name=current_tweets[0]) p.save() #Update the number of positive tweets seen so far try: p=tweet_category_count.objects.get(id=1) p.positive_count=p.positive_count+1 p.save() except: p=tweet_category_count(id=1,positive_count=1,negative_count=0) p.save() else: out_file=open("negative.txt",'a') m.update(current_tweets[int(a)-1]) p=data_set(tweet=current_tweets[int(a)-1],tweet_hash=m.hexdigest(),pos_neg='neg',movie_name=current_tweets[0]) p.save() #Update the number of negative tweets seen so far try: p=tweet_category_count.objects.get(id=1) p.negative_count=p.negative_count+1 p.save() except: p=tweet_category_count(id=1,positive_count=0,negative_count=1) p.save() tokens=current_tweets[int(a)-1].split() #Removing noise words,names (@) and hyperlinks from the tweets data_preprocess.remove_noise_words(tokens) data_preprocess.remove_names(tokens) data_preprocess.remove_links(tokens) #Removing the name of movie from the token list movieName = current_tweets[0].split() tokens = set(tokens)-set(movieName) for token in tokens: out_file.write(token+'\n') if(request.POST[index]=='pos'): try: q=token_category_count.objects.get(id=1) q.positive_count=q.positive_count+1 q.save() except: p=token_category_count(id=1,positive_count=1,negative_count=0) p.save() try: q=pos_tokens.objects.get(ptoken=token) #Adding 1 to the count of positive tokens q.pcount = q.pcount + 1 q.save() except: r = pos_tokens(ptoken=token,pcount=1) r.save() else: try: q=token_category_count.objects.get(id=1) q.negative_count=q.negative_count+1 q.save() except: p=token_category_count(id=1,positive_count=0,negative_count=1) p.save() try: q=neg_tokens.objects.get(ntoken=token) #Adding 1 to the count of negative tokens q.ncount = q.ncount + 1 q.save() except: r = neg_tokens(ntoken=token,ncount=1) r.save() return render_to_response("tweetsSaved.html")