sahascodes / music-artist-recommendation-system

Music Artist Recommendation System

A recommendation system for music artists based on TF-IDF vectorization.

Overview

This is a simple Flask web application that provides music recommendations based on artist names. It uses a recommendation algorithm implemented in the recommend.py module to suggest similar artists.

File structure

├── Data cleaning and testing file.ipynb
├── README.md
├── app.py
├── recommend.py
├── requirements.txt
└── templates
    ├── index.html
    └── tempx.html

• Data cleaning and testing file.ipynb: Jupyter Notebook file for data cleaning and testing.
• README.md: Project documentation file.
• app.py: Main Flask application file.
• recommend.py: Module containing the recommendation algorithm.
• requirements.txt: File specifying the project dependencies.
• templates: Folder containing HTML templates for the web application.
• index.html: HTML file for user input.
• tempx.html: HTML file for displaying the recommendation output.

Installation

1. Clone repository:

   git clone https://github.com/sahasCodes/Music-Artist-Recommendation-System

2. Install the required dependencies:

   pip install requirements.txt

3. Make sure you have the necessary data files:
   • artists.csv: Artist data CSV file.
   • similarityscores.h5: HDF5 file containing a similarity matrix.

Usage

1. Run the Flask application:

   python app.py

2. Open a web browser and navigate to http://localhost:5000/.
3. Enter an artist's name in the provided input box and click on the submit button.
4. The app will display a list of recommended artists based on the provided input.

Data

• artist.csv: A .csv file consists of over 1.4 Million musical artists present in MusicBrainz database -- their names, tags, and popularity (listeners/scrobbles), based on data scraped from last.fm.
• similarityscore.h5: HDF5 file containing a similarity matrix generated by Data cleaing and testing file.ipynb