mapreduce_job1

mapreduce_job1.py

def group_by_user_rating(self, key, line):
    """
    Emit the user_id and group by their ratings (item and rating)

    17  70,3
    35  21,1
    49  19,2
    49  21,1
    49  70,4
    87  19,1
    87  21,2
    98  19,2

    """
    user_id, item_id, rating = line.split('|')
    #yield (item_id, int(rating)), user_id
    #yield item_id, (user_id, int(rating))
    yield  user_id, (item_id, float(rating))
    #yield (user_id, item_id), int(rating)

def count_ratings_users_freq(self, user_id, values):
    """
    For each user, emit a row containing their "postings"
    (item,rating pairs)
    Also emit user rating sum and count for use later steps.

    17    1,3,(70,3)
    35    1,1,(21,1)
    49    3,7,(19,2 21,1 70,4)
    87    2,3,(19,1 21,2)
    98    1,2,(19,2)
    """
    item_count = 0
    item_sum = 0
    final = []
    for item_id, rating in values:
        item_count += 1
        item_sum += rating
        final.append((item_id, rating))

    yield user_id, (item_count, item_sum, final)