import re, math, collections, itertools import nltk, nltk.classify.util, nltk.metrics from nltk.classify import NaiveBayesClassifier from nltk.metrics import BigramAssocMeasures from nltk.probability import FreqDist, ConditionalFreqDist from read_from_twitter import collated_twitter_data from config import SEARCH_OLA_TERMS from preprocess import preprocess_tweet from filter_words import get_feature_list tweet = collated_twitter_data(since='',until='',search_terms=SEARCH_OLA_TERMS) preprocessed_tweets = preprocess_tweet(tweet) filtered_tweet = get_feature_list(preprocessed_tweets) print filtered_tweet
date_array = dict() date_keys_others = [] #stores all dates data was present for other tweetting about us date_keys_olacabs = [] #stors all the dates data was present for our tweeting #for i in range(1,31): # date_array[str(i)+"_posititve"] = 0.0 # date_array[str(i)+"_negative"] = 0.0 # date_array[str(i)+"_count"] = 0 # date_array[str(i)+"_count_of_olacabs"] = 0 # date_array[i]["negative"] = 0.0 #csv priting #print "Day of This Month ,Sentiment Positive Value, Sentiment Negative Value,Positive(True Or False)" for page in range (1,5): tweets_from_others = collated_twitter_data(search_terms=["#olacabs","@olacabs","#ola cabs"],result_page=page,count_of_tweets=100) for tweet in tweets_from_others: result = sentiment(tweet["text"]) date_of_data = tweet["timestamp"] #print tweet["timestamp"],",",result[0] , ",", result[1],",", positive(tweet["text"],0.1) date_array[str(date_of_data)+"_posititve"] = date_array.get(str(date_of_data)+"_posititve",0) + result[0] date_array[str(date_of_data)+"_negative"] = date_array.get(str(date_of_data)+"_negative",0) + result[1] date_array[str(date_of_data)+"_count"] = date_array.get(str(date_of_data)+"_count",0)+ 1 date_keys_others.append(str(date_of_data)) for page in range (1,10): all_tweets_from_olacabs = get_all_olacabs_tweet(page,count=100) for tweet in all_tweets_from_olacabs: date_of_data = tweet["timestamp"] date_array[str(date_of_data)+"_count_of_olacabs"] = date_array.get((str(date_of_data)+"_count_of_olacabs"),0) + 1 date_keys_olacabs.append(str(date_of_data))
