Python project advanced: Movie Recommendation System using Collaborative Filtering

Sharing is caring!

Python project advanced: Movie Recommendation System using Collaborative Filtering: here’s an advanced Python project with code. This project involves building a recommendation system using collaborative filtering.

Steps of the Python project advanced

1. Load the data into a Pandas dataframe:

import pandas as pd

ratings_data = pd.read_csv('ratings.csv')
movies_data = pd.read_csv('movies.csv')

2. Merge the two dataframes:

movie_ratings = pd.merge(ratings_data, movies_data, on='movieId')

3. Group the movie ratings by user ID:

user_ratings = movie_ratings.groupby(['userId', 'title'])['rating'].max().unstack()

4. Fill in missing ratings with 0:

user_ratings = user_ratings.fillna(0)

5. Calculate the user similarity matrix using cosine similarity:

from sklearn.metrics.pairwise import cosine_similarity

user_similarity = cosine_similarity(user_ratings)

6. Define a function to get similar users:

def get_similar_users(user_id, user_similarity_matrix, num_users=5):
    user_similarity = user_similarity_matrix[user_id]
    similar_users = user_similarity.argsort()[:-num_users-1:-1]
    return similar_users

7. Define a function to recommend movies:

def recommend_movies(user_id, user_similarity_matrix, user_ratings, num_recommendations=5):
    similar_users = get_similar_users(user_id, user_similarity_matrix)
    recommendations = []
    for user in similar_users:
        movies = user_ratings.iloc[user]
        movies_not_watched = movies[movies == 0].index
        for movie in movies_not_watched:
            if movie in recommendations:
                continue
            rating = user_ratings.iloc[user][movie]
            if rating > 3:
                recommendations.append(movie)
            if len(recommendations) == num_recommendations:
                break
        if len(recommendations) == num_recommendations:
            break
    return recommendations

8. Test the recommendation system:

user_id = 1
recommendations = recommend_movies(user_id, user_similarity, user_ratings)
print(recommendations)