https://github.com/excerebrose/playlist-generator-using-network-analysis
Repository for STN Project - Generating playlist using network analysis and custom pagerank
https://github.com/excerebrose/playlist-generator-using-network-analysis
community-detection music-similarity network-analysis pagerank playlist-generator python3
Last synced: 7 months ago
JSON representation
Repository for STN Project - Generating playlist using network analysis and custom pagerank
- Host: GitHub
- URL: https://github.com/excerebrose/playlist-generator-using-network-analysis
- Owner: excerebrose
- Created: 2017-12-12T18:34:35.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2017-12-12T18:35:48.000Z (almost 8 years ago)
- Last Synced: 2025-01-28T05:27:13.899Z (8 months ago)
- Topics: community-detection, music-similarity, network-analysis, pagerank, playlist-generator, python3
- Language: Python
- Size: 380 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Instructions to Install and Setup
Download the [database](http://labrosa.ee.columbia.edu/millionsong/sites/default/files/lastfm/lastfm_similars.db)
Download the [track metadata](http://labrosa.ee.columbia.edu/millionsong/sites/default/files/AdditionalFiles/unique_tracks.txt)
Put them in the root level of the project
Create a conda environment to install all packages with:
``` conda create --name myenv --file conda-requirements.txt ```
Then activate the conda environment:
``` source activate myenv ```
To install Python-Louvain:
``` cd ./python-louvain-0.9 ```
``` python setup.py install ```
To Run the program:
```python script.py ```
Note to initially preprocess the db and create graph / communities it takes about 10-15 mins, be patient please.
After that the prompt runs in an infinite loop, *ctrl + c* to quit.
Each songs need to be given in the following format:
*Artist - Song;Artist2 - Song2;Artist3 - Song3*
Be careful of the spaces please.