Skip to content

Latest commit

 

History

History
53 lines (34 loc) · 2.2 KB

readme.md

File metadata and controls

53 lines (34 loc) · 2.2 KB

Movie Recommendation System

Welcome to the Movie Recommendation System project! This project demonstrates my skills in building a movie recommendation system using data science techniques.

Project Structure

The project repository is organized as follows:

  • Movie recommendation system/
    • tmdb_5000_credits.csv: Dataset containing credit information
    • tmdb_5000_movies.csv: Dataset containing movie details
    • movie.py: Python script implementing the recommendation system
    • Website.html: Home page of the web interface (not connected due to Flask issues)
    • thank_you.html: Thank you page of the web interface (not connected due to Flask issues)

Getting Started

Follow these steps to run the movie recommendation system:

  1. Clone this repository by running: git clone https://github.com/Ayushvishwakarma04/Movie-recommendation-system.git
  2. Navigate into the project directory: cd Movie-recommendation-system
  3. Make sure you have Python installed.
  4. Run the movie.py script using: python movie.py

The recommendation system will analyze the data and provide movie recommendations based on user preferences.

Libraries Used

  • Pandas
  • NumPy
  • scikit-learn

About the Recommendation System

The movie.py script uses data from tmdb_5000_credits.csv and tmdb_5000_movies.csv to create a movie recommendation system. It employs text-based similarity techniques to suggest movies that are similar to the ones users have shown interest in.

Additional Web Pages

I have also created a home page (Website.html) and a thank you page (thank_you.html) for this project. However, I encountered Flask-related issues while trying to connect these pages. I'm actively working to resolve this and will update the project as soon as the issues are resolved.

Future Improvements

  • Explore more advanced recommendation algorithms.
  • Enhance the user interface for a more interactive experience.
  • Implement user personalization for more accurate recommendations.

Contact

Feel free to contact me if you have any questions or feedback: