{"id":23414646,"url":"https://github.com/glemaitre/traces-sklearn","last_synced_at":"2026-03-09T02:31:14.334Z","repository":{"id":266046483,"uuid":"897211555","full_name":"glemaitre/traces-sklearn","owner":"glemaitre","description":"Introduction to scikit-learn for the TRACES program","archived":false,"fork":false,"pushed_at":"2025-03-07T08:05:30.000Z","size":47718,"stargazers_count":1,"open_issues_count":3,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-18T18:49:52.262Z","etag":null,"topics":["data-science","machine-learning"],"latest_commit_sha":null,"homepage":"https://glemaitre.github.io/traces-sklearn/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/glemaitre.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"zenodo":null}},"created_at":"2024-12-02T08:33:37.000Z","updated_at":"2025-03-05T21:59:14.000Z","dependencies_parsed_at":null,"dependency_job_id":"4cc8e46e-6e05-4f81-af38-2780e0aa28e6","html_url":"https://github.com/glemaitre/traces-sklearn","commit_stats":null,"previous_names":["glemaitre/traces-sklearn"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/glemaitre/traces-sklearn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glemaitre%2Ftraces-sklearn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glemaitre%2Ftraces-sklearn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glemaitre%2Ftraces-sklearn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glemaitre%2Ftraces-sklearn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/glemaitre","download_url":"https://codeload.github.com/glemaitre/traces-sklearn/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glemaitre%2Ftraces-sklearn/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30280824,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-09T02:23:26.802Z","status":"ssl_error","status_checked_at":"2026-03-09T02:22:46.175Z","response_time":61,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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","machine-learning"],"created_at":"2024-12-22T20:20:16.560Z","updated_at":"2026-03-09T02:31:14.321Z","avatar_url":"https://github.com/glemaitre.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Introduction to scikit-learn for the TRACES program\n\nThis tutorial introduces how to use scikit-learn to craft predictive models using\nmachine learning.\n\n## Browse online:\n\n[![Launch JupyterBook](./book/images/jupyterbook_badge.svg 'Our JupyterBook\nwebsite')](https://glemaitre.github.io/traces-sklearn) [![Launch\nJupyterLite](./book/images/jupyterlite_badge.svg 'Our JupyterLite\nwebsite')](https://glemaitre.github.io/traces-sklearn/jupyterlite)\n\n## Getting started\n\nThe following dependencies are required for the course:\n\n- `jupyterlab`\n- `jupytext`\n- `notebook`\n- `numpy`\n- `scipy`\n- `scikit-learn`\n- `skrub`\n- `pandas`\n- `pyarrow`\n- `matplotlib`\n- `seaborn`\n\nWe offer several ways to run the course locally. Depending on your favorite package\nmanager, you can use one of the following options:\n\n- JupyterLite: if you want to avoid installing anything on your computer.\n- `pixi`: if you want the latest cutting-edge technology.\n- `conda`: if you want to stick to a more traditional approach.\n- `pip`: if you want to use the standard Python package manager.\n\n### Use JupyterLite\n\nJupyterLite is JupyterLab distribution running in the browser. It uses the Pyodide\nkernel. In short, you can click on the badge below to start the course in your\nbrowser. The lecture notes are located in `content/notebooks`.\n\n[![Launch\nJupyterLite](./book/images/jupyterlite_badge.svg 'Our JupyterLite\nwebsite')](https://glemaitre.github.io/traces-sklearn/jupyterlite)\n\nHere, we describe the pros and cons of this approach.\n\n**Pros**:\n\n- No installation required\n- Fast to start\n- No need to configure Python environment\n\n**Cons**:\n\n- The execution of the first cell is always slow because it requires to potentially\n  download the package and intialize the kernel.\n- You will witness that we need to call `%pip install` to install a couple of packages\n  in addition of the `import` statements in the notebook.\n- We need to use `pyodide-http` to load some datasets when fetching from the internet.\n- We need to make some defensive import when those are optional dependencies of\n  some libraries, e.g. importing `matplotlib` when using `pandas` plot.\n\n### Use `pixi`, `conda` or `pip`\n\n#### Prerequisites\n\nFirst clone the repository:\n\n```bash\ngit clone https://github.com/glemaitre/traces-sklearn.git\n```\n\nAlternatively, download an archive at the\n[following link](https://github.com/glemaitre/traces-sklearn/archive/refs/heads/main.zip).\n\n#### Install the package manager\n\nFor `pixi`, refer to the [official website](https://pixi.sh/latest/#installation) for\ninstallation.\n\nFor `conda`, download and install the latest version of `miniforge` from the [official\nwebsite](https://conda-forge.org/download/).\n\nFor `pip`, it is already installed if you have Python.\n\n#### Install the dependencies\n\nFor `pixi`, you don't need to do anything. It will be automatically installed in the\nnext step.\n\nFor `conda`, you can install the dependencies using the `environment.yml` file:\n\n```bash\nconda env create --file environment.yml\n```\n\nFor `pip`, you can install the dependencies using the `requirements.txt` file:\n\n```bash\npip install -r requirements.txt\n```\n\n#### Launching Jupyter Lab\n\nTo launch Jupyter Lab, run the following command:\n\n```bash\npixi run jupyter lab\n```\n\nThe Python environment and necessary packages will be automatically installed for you.\n\nFor `conda`, you need to activate the environment:\n\n```bash\nconda activate traces-sklearn\n```\n\nThen, for `conda` and `pip`, you can launch Jupyter Lab with:\n\n```bash\njupyter lab\n```\n\n#### Opening lecture notes\n\nThe lecture notes are available in the `python_files` directory. To open the Python\nfile as notebook, you need to right click on the file and select\n`Open with` -\u003e `Notebook`. This is using `jupytext` to interpret those files as\nnotebooks.\n\nAlternatively, you convert those files into notebooks.\n\nWith `pixi`, you can run:\n\n```bash\npixi run -e docs convert-to-notebooks\n```\n\nWith `conda` and `pip`, you can run the `jupytext` command:\n\n```bash\njupytext --to notebook ./content/python_files/*.py\nmkdir -p ./content/notebooks\nmv ./content/python_files/*.ipynb ./content/notebooks\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fglemaitre%2Ftraces-sklearn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fglemaitre%2Ftraces-sklearn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fglemaitre%2Ftraces-sklearn/lists"}