Sample of joining together yelp review & business data

join.py

import json


def main():
    businesses_by_id = {}
    with open('yelp_academic_dataset_business.json') as business_file:
        # for every line in this file (every business)
            # load the json in from that line into an object (json.loads)
            #
            # save the object to the businesses_by_id dict by its `business_id`

    with open('yelp_academic_dataset_review.json') as review_file:
        # for every line in this file (every review)
            # load the json in from that line into an object (json.loads)
            #
            # look up the business from businesses_by_id by using the `business_id` in the review object you just loaded
            #
            # do whatever other processing you want to do now that you've got the business

if __name__ == '__main__':
    main()