Project Details:
I would like to introduce a small-scale project focused on movie recommendations. The project's website, accessible at https://recogoo.herokuapp.com/, serves as a platform for providing personalized movie suggestions to users. The movie data utilized for this project has been sourced from IMDB.
To facilitate access to the project's data, I have stored it on Google Drive. You can find the dataset at the following link: https://drive.google.com/drive/folders/1Nc2rb4wlkkQFkA4j7s7R7MjZlGnYroWF?usp=sharing. This dataset encompasses six movie recommendations tailored for users.
The project's foundation lies in machine learning techniques, with the primary focus on utilizing the Vectorizer approach. The initial phase involved collecting and preprocessing the data. This included extracting key categories such as actors, genres, movie names, ratings, and movie IDs. To enhance the data quality, I meticulously removed blank spaces and duplicates. The culmination of this phase was the creation of a comprehensive movie.csv file.
For the machine learning aspect, the project utilized the popular Python library, scikit-learn (sklearn), to implement various algorithms. Specifically, the Vectorizer played a crucial role in training the model. The outcome of this training process is reflected in the generation of two .plk files that contain important keys and names.
To provide a user-friendly interface for the project, I employed the streamlit package in Python. The website showcases six movie recommendations, a search bar, a background/view option, and a search button to facilitate user interaction.
For deployment, the project leveraged Heroku (Haruko) as the hosting platform. The project files are organized in a .git format, and the necessary requirements for the project are outlined in the accompanying .txt file.
This project represents a convergence of machine learning, web development, and data management, resulting in a functional and engaging movie recommendation platform. If you have any further inquiries or require additional information, please feel free to ask.