TextTune is a Python-based application designed to merge, process, and analyze text data. It leverages Streamlit for a user-friendly interface, allowing users to interact with the data and visualization tools seamlessly. When interacting with the interface, the user is able to receive song recommendations as well as artist recommendations along with the cover posters from the spotify API.
- Data Processing: Ability to read and merge data from multiple CSV files.
- Text Analysis: Utilizes Natural Language Processing (NLP) techniques for text analysis.
- Streamlit Interface: A dynamic and responsive web app interface for easy data interaction.
- Custom CSS Styling: Enhanced visual appeal and user experience with custom CSS styles.
The dataset used in this project is the Spotify Million Song Dataset, which was downloaded from Kaggle. It includes a comprehensive collection of song data that is essential for our analysis and recommendations.
You can access and download the dataset here for reference or to replicate the analysis.
To get started with TextTune, you'll need to set up your Python environment and install necessary libraries like Streamlit, Pandas, and NLTK.
- Clone the repository: Download the project files from our GitHub repository to your local machine.
- Install Dependencies: Run
pip install -r requirements.txtto install required Python packages. - You must run the model training in jupyter notebook first.
- Make sure to replace YOUR_SPOTIFY_CLIENT_ID and YOUR_SPOTIFY_SECRET_KEY with your own.
- Launch the Streamlit App: Execute
streamlit run app.pyin your terminal to start the web application. - Access the Web Interface: Open the provided local URL in your web browser to interact with the application.
Check out this demo video for a quick overview:
- Methila Deb
- Alina Alizai
- Project Link