Repository files navigation

This repository contains all the project files and necessary details about applications required to run the project on your local machine as well as host it as a Django Application on your Server/Domain.

Do you like it? ❤️ Follow me onTwitter,GitHub, &LinkedIn to say Hi 👋

In this section, we try to understand through video demo to play around the project and what all can be achieved through it.

1. Movie Recommendation System Hosted Application Demo

2. Running MRS on local System

3. Sample Screenshots

   1. Home Screen

      

   2. Navigation Screen

      

   3. Search with Auto Suggestion

      

   4. Recommended Movies

      

Please be slightly patient while I create and upload the demo video. Follow and star this project to get latest notifications and update. 🙌

To build this project without any errors/issues, the following requirements needs to be satisfied

1. Create a Virtual Environment using python>=3.8 (Tested on 3.9.16)

2. Install the dependencies from the requirements text file from the repository.

For complete guide to training your model and inference using the trained model, refer to "Movie Recommendation System Python Notebook".

Here is a detailed blog explaining about complete approach and directory structure essential to understand Django integration.

Here is a detailed blog explaining about complete approach and essential details to deploy not just this application but also any other web-application you like to built.

I am assuming you have completedsection 2 in the above reference for creating your environment. Let's start by activating it.

/path/to/env/bin/activate

Once done, you should go to project root directory and run the following command

python manage.py runserver

It will take a moment and then show the following output on the terminal.

You can now open your browser and hit the server IPhttp://localhost:8000 provided to run the demo on your local system.

By default, this project will run on Demo model. If you wish to change model, you can train and download the model of your choice using the python notebook to get better or faster recommendations. Once trained, you can integrate by modifying these 2 lines of code insiderecommender/views.py

Line5 :movies_data=pd.read_parquet("static/<dataset_name>.parquet")Line73:model=pa.parquet.read_table('static/<model_name>.parquet').to_pandas()

Note that you have to place dataset and model into thestatic directory.

This code implements a movie recommendation system based on user input. The system provides a simple web interface built on HTML, CSS, and JavaScript libraries.

Inputs: The user can search for movies by providing a partial or complete movie name.

Outputs: The system provides movie recommendations based on user input.

Dependencies:

• static/recommender/ -- contains the following CSS files:cursor.css,page.css, andnavbar.css
• static/logo.png -- the logo of the application
• static/production ID_4779866.mp4 -- a background video for the web page
• @tabler/icons@latest/iconfont/tabler-icons.min.css
• normalize/5.0.0/normalize.min.css
• jquery-ui.css
• font-awesome.min.css
• bootstrap.min.css
• jquery.min.js
• jquery-ui.js

Usage:

1. Open the HTML file in a web browser.
2. Type the name of a movie in the search bar, and the system will provide the movie recommendation.

Note: Only the top 2.5K movies based on IMBD are present in this system's database.

Working onversion 2 of movie recommendation system on new repository which can process 1 million movies within similar memory footprints, better recommendations, and diverse selections, with added features like recommendation bucket and mutual sharing. Stay tuned and do not forget to start the repository to reach out to open-source community.