def run(): c = Counter() for fn in friends_ids_files(): with open(fn) as f: c.update(k.strip() for k in f.readlines()) top_ids = [str(f_id) for f_id, f_count in c.most_common() if f_count >= MIN_FRIEND_OCCURENCES] # now merge top_ids with congress_twitter_ids() cong_ids = [str(cid) for cid in congress_twitter_ids()] all_ids = list(set(top_ids + cong_ids)) with open(TOP_FRIENDS_IDS_PATH, 'w') as o: o.write("\n".join(all_ids))
def run(): c = csv.writer(open(COMPILED_TOP_FRIENDSHIPS_PATH, "w")) c.writerow(["user_screen_name", "friend_id"]) all_top_ids = set([k.strip() for k in open(TOP_FRIENDS_IDS_PATH).readlines()]) for fn in friends_ids_files(): # get the user screen_name from the filename (icky) user_screen_name = splitext(basename(fn))[0] with open(fn) as f: _ids = set([k.strip() for k in f.readlines()]) # filter ids for ids that are in all_top_ids top_friends_ids = all_top_ids.intersection(_ids) for t_id in top_friends_ids: c.writerow([user_screen_name, t_id])