#list religious sources sources['5'] = ['news_va_en', 'Buddhism_Now', 'HinduismToday', 'Pearlsofprophet', 'YourJudaism', 'HuffPostRelig', 'RNS'] #list entertainment sources sources['6'] = ['MTV', 'Rock Music', 'TheGRAMMYs', 'TheAcademy', 'bbcentertain', 'EntMagazine', 'EW', 'mashentertain', 'CBSShowbiz'] #job and careers sources sources['7'] = ['GuardianCareers', 'CareerBuilder', 'LinkedIn', 'indeed', 'TweetMyJobs', 'USNewsCareers', 'UCSBcareer', 'BI_Careers'] #weather sources sources['8'] = ['weatherchannel', 'bbcweather','wunderground', 'weathernetwork', 'capitalweather', 'CNNweather'] #random/other sources sources['9'] = ['Seldomaniac', 'Callamasta', 'jwharris', 'don_brown', 'lou1derful', 'ChrisPawelski'] api = API(sources) api.gettweets() api.cleantweets() api.tokenizetweets() api.writetofile() top = api.gettop() api.getfeatures() print top print api.train()