Compsci 101, Fall 2017,
Recommender

See the howto pages for details on starting this project, code, and the details pages for more details. The pages here describe in broad strokes what this assignment is about.

Get the snarf file that has the data files you need for this assignment or get them here.

Background

Collaborative filtering and content-based filtering are two kinds of recommender systems that provide users with information to help them find and choose anything from books, to movies, to restaurants, to courses based on their own preferences compared to the preferences of others.

In 2009 Netflix awarded one million dollars to a group that had developed a better-recommender system than the Netflix, in-house system. This NY Times Magazine article describes the competition, the winning teams, and how the movie Napolean Dynamite caused problems for the algorithms and ranking/rating systems developed by contest participants.

In this assignment, you'll develop a program to test three different algorithms for recommending items based on the responses made by others. You'll be practicing reading data from files, using Python dictionaries and lists, and sorting data to find good matches.

The assignment comes in two conceptual parts:

• Reading data stored in files and converting the data into a common format

• Using the data (stored in the common format) to make recommendations for either every students/rater or for a particular student as described below.

We're providing three sources of data. Sometimes ratings are stored in a single file, sometimes in more than one file. You'll need to write a separate Python module to deal with each data source, then use what these modules return to develop ratings.

Recommendations of Ratings

This first set of recommendations for a particular CS Professor comes from Netflix a while ago. As you can see, these recommendations are based on two movies seen and then all the data Netflix has on similar movies.

This next set of recommendations is for Prof. Rodger a while back, when she bought some small bags, and you can guess what types of things she buys for her kids.

The types of ratings you will see in all the data files uses ratings from 5 to -5.

Rating	Meaning
5	Really liked it!
3	Liked it!
1	Okay — neither hot nor cold about it
0	Have not rated it
-1	Not bad — but nothing really to say about it
-3	Didn't like it
-5	Hated it!

Requirements:

Expectations: For this assignment you are expected to have well documented code and style. This means you should have a comment for each main block of code to describe in words what the code is doing. You should have your name near the top of each file as a comment. See other expectations for style on the main assignment page.

PLEASE NOTE you will lose points for code that is not well commented!

ITEMS to Write:

1. Module ProcessAllFood.py:
   

   • This function reads in the data file AllFoodRatings.txt that has a small file with just 9 people who have rated a few restaurants. You will create and return a list of the restaurants, named itemlist, and a dictionary of information on the ratings for the restaurants, named dictratings.
   • Function processData( filename )
       that returns itemlist and dictratings.
     

2. Module ProcessAllBooks.py:
   

   • This function reads in the data file AllBooksAuthors.txt that has information about books and their authors, and reads in the data file AllBooksRatings.txt that has information about ratings of those books. This function puts this information into the same format as the restaurant information. In particular, this function returns a list of the books, named itemlist, and a dictionary of information on the ratings for the books, named dictratings.
   • Function processData(booktitles, bookratings )
       that returns itemlist and dictratings.
     

3. Module ProcessAllMovies.py:
   

   • This function reads in the data file AllMoviesRatings.txt that has information about ratings of movies. This function puts this information into the same format as the restaurant and book information. In particular, this function returns a list of the movies, named itemlist, and a dictionary of information on the ratings for the movies, named dictratings.
   • Function processData( filename )
       that returns itemlist and dictratings.
     



4. Module RecommenderForAll.py:
   

   • This module will have three functions that will be used to do recommendations for restaurants, books, and movies.
   • Function average( itemlist, dictratings )
       that returns averageList
   • Function similarities( name, dictratings )
       that returns similarList
   • Function recommended( similarList, itemlist, dictratings, n )
       that returns recommendList

5. Module RecommenderFood.py:
   

   • This is the main program for food recomendations. It will use RecommenderForAll and ProcessAllFood. You need to print out specific information explained here on the howto page for this function.

6. Module RecommenderBooks.py:
   

   • This is the main program for book recomendations. It will use RecommenderForAll and ProcessAllBooks. You need to print out specific information explained here on the howto page for this function.

7. Module RecommenderMovies.py:
   

   • This is the main program for movie recomendations. It will use RecommenderForAll and ProcessAllMovies. You need to print out specific information explained here on the howto page for this function.

What to Submit:

Be sure to submit the following SEVEN files:

1. ProcessAllFood.py

2. ProcessAllMovies.py

3. ProcessAllBooks.py

4. RecommenderForAll.py

5. RecommenderFood.py

6. RecommenderMovies.py

7. RecommenderBooks.py

8. Fill out the REFLECT form on the assignment page.
9. LAST STEP: Check Ambient SUBMIT HISTORY, to double check that all seven files were submitted!

Submit the items to the folder assign8-recommender using eclipse/ambient or the websubmit.