Skip to content

A Movie Recommendation System along with Data Analysis and Data Visualization and Revenue Prediction Model

License

Notifications You must be signed in to change notification settings

RohanHBTU/MovieRecommendationSystem

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Movie Recommendation System

Contributors Forks Issues Pull Request

Contents

  1. Description
  2. Project structure
  3. Datasets
  4. Project Overview
  5. Project roadmap
  6. Getting started
  7. Contributing
  8. Authors
  9. License
  10. Acknowledgments

Description

Who does not love Movies? The DataSet was scraped from https://www.kaggle.com/datasets/tmdb/tmdb-movie-metadata and includes all the major Movies and the information relevent to it.

Point System

  • Easy Tag issues will fetch you 100 Points.
  • Medium Tag issues will fetch you 200 Points.
  • Hard Tag issues will fetch you 300 Points.

Project structure

  ├── datasets/         Dataset of Movies.
  ├── notebooks/        Contains the jupyter notebook file of Movies.

Datasets

  • movies.csv is the dataset for Data Cleaning and Preprocessing and Recommendation Systems Section of the notebook
  • tmdb_5000_credits.csv and tmdb_5000_movies.csv are the datasets for the notebook Data Visualization and Revenue Prediction Sections of the Notebook

Project Overview

  • https://colab.research.google.com/github/Mangalam0512/Movie-Recomendation/blob/main/Notebook/MovieRecommendation.ipynb link of the colab Notebook

Project roadmap

The project currently does the following things.

  • Cleans the Dataset tmdb_5000_movies.csv and tmdb_5000_credits.csv
  • Cosine Similarity Algorithm is used on that data to predict movie
  • Data Visualization on Movies and their profit percent.

See below for our future steps.

  • Find other possible algorithms for Recommendtion System
  • Make Revenue Prediction on movies whose Status!=released.
  • Make more Productive Visualizations.
  • Clean movies.csv and make Recommendation System based on that data.

Getting started

Prerequisites

Software Needed

  1. A web browser.

    OR
    
  2. Anaconda software.

Knowledge Needed

  • Very basic understanding of git and github:

    1. What are repositories (local - remote - upstream), issues, pull requests
    2. How to clone a repository, how to fork a repository, how to set upstreams
    3. Adding, committing, pulling, pushing changes to remote repositories
  • For EDA and Visualisation

    1. Basic syntax and working of python.(This is a must)
    2. Basic knowledge of pandas library. Reading this blog might help.
    3. Basic knowledge of matplotlib library. Reading this blog might help.
    4. Basic knowledge of seaborn library. Reading this blog might help.
    5. Basic knowledge of scikit learn library. Reading this blog might help.

    However the code is well explained, so anyone knowing the basics of Python can get a idea of what's happenning and contribute to this.

Installing

There are two ways of running the code.

  1. Running the code on web browser.(Google Colab) [Recommended]

    • Head on to Google colab
    • Then click on Upload Notebook Tab.
    • Upload the notebook that you got from this repo. Colab-1
    • Connect with the runtime. Colab-2
    • Upload your dataset. Colab-3
    • Then Click on Run All. Colab-4
    • Start Editing.
  2. You can also run the code locally in your computer by installing Anaconda.

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated. Contributing is also a great way to learn more about social coding on Github, new technologies and and their ecosystems and how to make constructive, helpful bug reports, feature requests and the noblest of all contributions: a good, clean pull request.

Guidelines

  • Before starting to work on any issue or feature, open an issue explaining the changes you want to make and wait for any of the project maintainers to assign it to you.
  • Use better commit messages that explain the changes you make. View the example below:
    • Bad commit message: updated readme
    • Good commit message: updated contributors list in readme
  • You should not, in any case, use resources or code snippets from sources that do not allow their public use.

Steps to follow for Pull Request

  • For solving an issue/adding a feature, write the code after the original code finishes and do not forget to add the issue name and number as a heading in the notebook.
  • Before Submitting the PR, make sure to have a link of colab notebook of the feature/issue solved so that we can check easily. This even applies to those who are doing on anaconda.

Authors

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

About

A Movie Recommendation System along with Data Analysis and Data Visualization and Revenue Prediction Model

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%