Explore personalized music recommendations with this ML-powered system. Utilizing Spotify data, TF-IDF vectorization, and cosine similarity, discover your next favorite song effortlessly! Table of Contents Dataset Download Libraries Used How to Install and Run the Project How to Use the Project Results Dataset Download Download the dataset from Kaggle: Spotify Million Song Dataset. Libraries Used pandas - Used for data manipulation and analysis. nltk - Provides natural language processing tools for text data. scikit-learn - Implements machine learning algorithms for TF-IDF vectorization and cosine similarity. streamlit - Utilized for creating an interactive web application. spotipy - Used to interact with the Spotify API for song information. How to Install and Run the Project Clone the repository:
git clone https://github.com/srujanboda/Music-Recommendation-System.git Navigate to the project directory:
cd music-recommendation-system Install the required dependencies:
pip install -r requirements.txt Run the recommendation model script:
python recommendation_model.ipynb Run the web hosting script:
streamlit run app.py
How to Use the Project Open the web application by navigating to http://localhost:8501 in your web browser.
Select a song from the dropdown menu.
Click the "Show Recommendation" button to view recommended songs.
The recommended songs along with their album covers will be displayed.