kknani24/FLIX-HUB-An-Advanced-Movie-Recommendation-System-Leveraging-Netflix-Data

FLIX-HUB is a movie recommendation system utilizing the Netflix dataset. It features comprehensive data preprocessing and analysis, generating personalized movie and TV show suggestions based on TF-IDF vectorization and cosine similarity. The project includes interactive visualizations for insights into content trends and distributions.

FLIX-HUB: An Advanced Movie Recommendation System Leveraging Netflix Data

Table of Contents

• Recommendation System (FLIX-HUB)
  • Table of Contents
  • Project Overview
  • Features
  • Installation
  • Usage
  • Data Preprocessing
  • Exploratory Data Analysis
  • Feature Engineering
  • Recommendation System
  • Results
  • Contributing
  • License

Project Overview

This project performs a comprehensive analysis of Netflix data and implements a content-based recommendation system called FLIX-HUB. It includes data preprocessing, exploratory data analysis, advanced feature engineering, and a movie/TV show recommendation engine.

Features

• Data cleaning and preprocessing
• Exploratory data analysis with interactive visualizations
• Text processing and feature engineering
• Content-based recommendation system
• Support for both movies and TV shows

Installation

To run this project, you need to have Python installed on your system. Then, follow these steps:

1. Clone the repository:

   git clone https://github.com/yourusername/Recommendation-System .git
   

2. Navigate to the project directory:

   cd movie-recommendation-system.ipynb
   

3. Install the required packages:

   pip install -r requirements.txt
   

Usage

To use the FLIX-HUB recommendation system:

1. Run the Jupyter notebook or Python script.
2. Use the FlixHub class to get recommendations:

flix_hub = FlixHub(final_data, cosine_sim)
movies, tv_shows = flix_hub.recommendation('Movie Title', total_result=10, threshold=0.5)

print('Similar Movie(s) list:')
for movie in movies:
    print(movie)

print('\nSimilar TV_show(s) list:')
for tv_show in tv_shows:
    print(tv_show)

Data Preprocessing

The data preprocessing steps include:

• Loading the Netflix dataset
• Handling missing values
• Cleaning text data (titles, descriptions, etc.)
• Creating a bag of words representation

Exploratory Data Analysis

The EDA process includes various visualizations:

• Distribution of content types (movies vs. TV shows)
• Number of movies released each year
• Top countries producing Netflix content
• Movie ratings distribution
• Word clouds for titles, descriptions, and genres

Feature Engineering

Advanced feature engineering techniques are applied:

• Text cleaning and normalization
• TF-IDF vectorization
• Cosine similarity calculation

Recommendation System

The FLIX-HUB recommendation system uses:

• Content-based filtering
• Cosine similarity for finding similar content
• Separate recommendations for movies and TV shows

Results

The project provides insights into Netflix's content library and offers personalized recommendations based on user input. Some key findings include:

• Distribution of movies vs. TV shows
• Trends in content production over the years
• Popular genres and themes

Contributing

Contributions to this project are welcome. Please fork the repository and submit a pull request with your changes.

License

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