{"id":21228835,"url":"https://github.com/anras5/songs-classifier","last_synced_at":"2026-04-10T07:39:05.521Z","repository":{"id":245147310,"uuid":"799267653","full_name":"anras5/songs-classifier","owner":"anras5","description":"Classify songs' genres with Machine Learning","archived":false,"fork":false,"pushed_at":"2024-06-05T21:49:20.000Z","size":13736,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-21T17:49:54.969Z","etag":null,"topics":["data-science","docker","machine-learning","mlflow","pandas","python","scikit-learn","seaborn","streamlit","tpot"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anras5.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-11T16:14:09.000Z","updated_at":"2024-06-21T18:51:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"0aa55720-f1a9-41bf-b1b9-5c560ca89680","html_url":"https://github.com/anras5/songs-classifier","commit_stats":null,"previous_names":["anras5/songs-classifier"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anras5%2Fsongs-classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anras5%2Fsongs-classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anras5%2Fsongs-classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anras5%2Fsongs-classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anras5","download_url":"https://codeload.github.com/anras5/songs-classifier/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243672377,"owners_count":20328762,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["data-science","docker","machine-learning","mlflow","pandas","python","scikit-learn","seaborn","streamlit","tpot"],"created_at":"2024-11-20T23:22:28.199Z","updated_at":"2026-04-10T07:39:00.498Z","avatar_url":"https://github.com/anras5.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Songs Classifier\n\n**Songs Classifier** is a project that consists of two parts.\n- In `Data analysis` you can find Jupyter notebook with data analysis of the dataset and a lot of insights into how the data looks like and how the machine learning models were trained.\n- In `Classifier App` you can find an app that uses `Streamlit`, `mlflow` and `spotipy` to allow users to classify songs from Spotify with trained Gradient Boosting Tree. Everything is running in containers.\n\n# How to run?\n## Data analysis\n\n```shell\ncd data-analysis\ndocker compose up\n```\n\nThe jupyter lab is available at `localhost:8888`.\n\n## Classifier App\n\nCreate a `.env` file inside the `classifier-app/frontend` directory with the same structure as `.env.example`. Get your own\nSpotify credentials from [Spotify Developers Website](https://developer.spotify.com/dashboard).\n\n```shell\ncd classifier-app\ndocker compose up\n```\n\nFrontend app is available at `localhost:8080` and backend app (model) is available at `localhost:5000`.\n\n### Develop backend (if you want to change the model)\n\n```shell\ncd classifier-app/backend\ndocker build -f develop.dockerfile -t mlflow-develop-image .\ndocker run -it -v \"${PWD}:/app\" -p 5000:5000 --rm mlflow-develop-image /bin/bash\n```\n\nChange the `${PWD}` to `$(pwd)` if you are on Linux. If you have already built the image in the past skip the second\ncommand.\n\n**Run the training**\n\n```shell\npython3 src/train.py --file_path=/app/data/dataset_cleaned.csv\n```\n\nScript prints out `runid` at the end.\n\n**Serve the model**\n\n```shell\nmlflow models serve --model-uri runs:/\u003crunid\u003e/GradBoostClassifier --no-conda -p 5000 -h 0.0.0.0\n```\n\n# How does the app look like?\n\n![image](https://github.com/anras5/songs-classifier/assets/91278796/a227135e-1172-49f3-85dd-d59ac0a19a32)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanras5%2Fsongs-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanras5%2Fsongs-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanras5%2Fsongs-classifier/lists"}