Count up ratings given for each movie

All you need is to change one thing in the mapper we dont care about

ratings now, we care about movie IDs!

Start with this and make sure you can do it.

You can use nano to just edit the existing RatingsBreakdown.py script

from mrjob.job import MRJob from mrjob.step import MRStep

class MostPopularMovie(MRJob): def steps(self): return [ MRStep(mapper=self.mapper_get_ratings, reducer=self.reducer_count_ratings), MRStep(reducer = self.reducer_find_max) ]

def mapper_get_ratings(self, _, line): (userID, movieID, rating, timestamp) = line.split('\t') yield movieID, 1

def reducer_count_ratings(self, key, values): yield None, (sum(values), key)

def reducer_find_max(self, key, values): yield max(values)

if __name__ == '__main__': MostPopularMovie.run()

from mrjob.job import MRJob from mrjob.step import MRStep

class RatingsBreakdown(MRJob): def steps(self): return [ MRStep(mapper=self.mapper_get_ratings, reducer=self.reducer_count_ratings) ]

def mapper_get_ratings(self, _, line): (userID, movieID, rating, timestamp) = line.split('\t') yield rating, 1

def reducer_count_ratings(self, key, values): yield key, sum(values)

if __name__ == '__main__': RatingsBreakdown.run()

from mrjob.job import MRJob from mrjob.step import MRStep

class RatingsBreakdown(MRJob): def steps(self): return [ MRStep(mapper=self.mapper_get_ratings, reducer=self.reducer_count_ratings), MRStep(reducer=self.reducer_sorted_output) ]

def mapper_get_ratings(self, _, line): (userID, movieID, rating, timestamp) = line.split('\t') yield movieID, 1

def reducer_count_ratings(self, key, values): yield str(sum(values)).zfill(5), key

def reducer_sorted_output(self, count, movies): for movie in movies: yield movie, count

if __name__ == '__main__': RatingsBreakdown.run()