explore_tifu.py

import json

# Read entire file
posts = []
i = 1
j = 0
with open('tifu_all_tokenized_and_filtered.json', 'r') as fp:
    for line in fp:
        print("{} / 79,949".format(i))
        i += 1
        try:
            x = json.loads(line)['tldr']
            x = json.loads(line)['tldr_tokenized']
            j += 1
            y = i
        except KeyError:
            pass
        posts.append(json.loads(line))

        #print('=================')
        # print(posts[-1]['selftext'].encode('utf-8'))
        print('=================')
        print(posts[-1]['selftext_without_tldr'].encode('utf-8'))
        #print('=================')
        #print(posts[-1]['title'].encode('utf-8'))
        print('=================')
        print(posts[-1]['trimmed_title'].encode('utf-8'))
        try:
            print(posts[-1]['tldr'].encode('utf-8'))
        except:
            pass
        #print('=================')
        #print(posts[-1]['id'])
        input()