Movie Recommender System 🎬

A content-based movie recommendation system that suggests similar movies based on your selection. The system uses natural language processing and machine learning techniques to analyze movie features and provide personalized recommendations.

🌟 Features

• Interactive web interface built with Streamlit
• Movie recommendations based on content similarity
• Movie poster display for visual reference
• User-friendly dropdown selection
• Real-time movie poster fetching using TMDB API

🛠️ Technologies Used

• Python 3.x
• Streamlit
• Pandas
• scikit-learn
• NLTK
• TMDB API
• Pickle (for model serialization)

📊 Dataset

The project uses the TMDB 5000 Movie Dataset from Kaggle, which includes:

• TMDB 5000 Movie Dataset
  • tmdb_5000_movies.csv: Contains movie metadata
  • tmdb_5000_credits.csv: Contains movie credits and cast information

🚀 Setup and Installation

1. Clone the repository
2. Install required packages:

   pip install -r requirements.txt

3. Set up TMDB API key:
   • Create a .env file in the root directory
   • Add your TMDB API key: TMDB_API_KEY=your_api_key_here

🎯 How It Works

1. Data Preprocessing:

   • Merges movies and credits data
   • Extracts relevant features (genres, cast, crew, keywords)
   • Processes text data using natural language processing techniques

2. Feature Engineering:

   • Converts text data to vectors
   • Calculates similarity scores between movies
   • Creates a recommendation model

3. Recommendation Process:

   • Takes a movie input from user
   • Finds similar movies using cosine similarity
   • Fetches movie posters from TMDB API
   • Displays top 5 recommendations with posters

🏃‍♂️ Running the Application

Run the Streamlit app:

streamlit run app.py

📝 Project Structure

• main.ipynb: Contains the data preprocessing and model creation code
• app.py: Streamlit web application code
• movies.pkl: Serialized movie data
• vectorsSim.pkl: Serialized similarity vectors
• requirements.txt: Project dependencies

🤝 Contributing

Feel free to fork this repository and submit pull requests. You can also open issues for bugs or feature requests.

📄 License

This project is open source and available under the MIT License.