Generating movie recommendations

Now that we built all of the different parts of a recommendation engine, we are ready to generate movie recommendations. We will use all the functionality that we built in the previous recipes to build a movie recommendation engine. Let's see how to build it.

How to do it…

  1. Create a new Python file, and import the following packages:
    import json
import numpy as np

from euclidean_score import euclidean_score
from pearson_score import pearson_score
from find_similar_users import find_similar_users
  2. We will define a function to generate movie recommendations for a given user. The first step is to check whether the user exists in the dataset:
    # Generate recommendations for a given user
def generate_recommendations(dataset, user):
    if user not in dataset:
        raise TypeError('User ' + user + ' not present in the dataset')
  3. Let's compute the Pearson score of this user with all the other users in the dataset:
        total_scores = {}
    similarity_sums = {}

    for u in [x for x in dataset if x != user]:
        similarity_score = pearson_score(dataset, user, u)

        if similarity_score <= 0:
            continue
  4. We need to find the movies that haven't been rated by this user:
            for item in [x for x in dataset[u] if x not in dataset[user] or dataset[user][x] == 0]:
            total_scores.update({item: dataset[u][item] * similarity_score})
            similarity_sums.update({item: similarity_score})
  5. If the user has watched every single movie in the database, then we cannot recommend anything to this user. Let's take care of this condition:
        if len(total_scores) == 0:
        return ['No recommendations possible']
  6. We now have a list of these scores. Let's create a normalized list of movie ranks:
        # Create the normalized list
    movie_ranks = np.array([[total/similarity_sums[item], item] 
            for item, total in total_scores.items()])
  7. We need to sort it in descending order based on the score:
        # Sort in decreasing order based on the first column
    movie_ranks = movie_ranks[np.argsort(movie_ranks[:, 0])[::-1]]
  8. We are finally ready to extract the movie recommendations:
        # Extract the recommended movies
    recommendations = [movie for _, movie in movie_ranks]

    return recommendations
  9. Let's define the main function and load the dataset:
    if __name__=='__main__':
    data_file = 'movie_ratings.json'

    with open(data_file, 'r') as f:
        data = json.loads(f.read())
  10. Let's generate recommendations for Michael Henry:
        user = 'Michael Henry'
    print "
Recommendations for " + user + ":"
    movies = generate_recommendations(data, user) 
    for i, movie in enumerate(movies):
        print str(i+1) + '. ' + movie
  11. The user John Carson has watched all the movies. Therefore, if we try to generate recommendations for him, it should display 0 recommendations. Let's see whether this happens:
        user = 'John Carson' 
    print "
Recommendations for " + user + ":"
    movies = generate_recommendations(data, user) 
    for i, movie in enumerate(movies):
        print str(i+1) + '. ' + movie
  12. If you run this code, you will see the following on your Terminal:
    How to do it…
..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset
3.133.141.6