This repository contains a movie recommendation system built using data from TMDb (The Movie Database). The system is designed to analyze and provide recommendations based on various features and user preferences. The system utilizes a dataset consisting of 5000 movies from TMDb. The data includes movie titles, genres, ratings, cast, crew, and more, allowing for comprehensive analysis and recommendation generation.
The following Python libraries are used in this project:
Pandas: Data manipulation and analysis
NumPy: Mathematical functions on large, multi-dimensional arrays
Scikit-learn: Machine learning library for building recommendation models
Matplotlib: Data visualization
pickle : Serializing and deserializing Python objects
streamlit : To create web applications
ast : Abstract syntax trees
nltk : Natural Language ToolKit