{"id":16343583,"url":"https://github.com/costrouc/mse-machinelearning-notebooks","last_synced_at":"2025-03-23T00:32:37.219Z","repository":{"id":47572035,"uuid":"137913951","full_name":"costrouc/mse-machinelearning-notebooks","owner":"costrouc","description":"Machine Learning Introduction for a Material Scientist","archived":false,"fork":false,"pushed_at":"2021-08-23T19:46:53.000Z","size":848,"stargazers_count":20,"open_issues_count":6,"forks_count":6,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-03-18T15:54:28.967Z","etag":null,"topics":["binder-ready","machine-learning","materials-science","python"],"latest_commit_sha":null,"homepage":"http://mybinder.org/v2/gh/costrouc/mse-machinelearning-notebooks/master?urlpath=lab/tree/notebooks/Overview.ipynb","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/costrouc.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}},"created_at":"2018-06-19T15:56:06.000Z","updated_at":"2024-02-26T12:06:14.000Z","dependencies_parsed_at":"2022-08-23T21:41:18.352Z","dependency_job_id":null,"html_url":"https://github.com/costrouc/mse-machinelearning-notebooks","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/costrouc%2Fmse-machinelearning-notebooks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/costrouc%2Fmse-machinelearning-notebooks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/costrouc%2Fmse-machinelearning-notebooks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/costrouc%2Fmse-machinelearning-notebooks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/costrouc","download_url":"https://codeload.github.com/costrouc/mse-machinelearning-notebooks/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245040235,"owners_count":20551297,"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":["binder-ready","machine-learning","materials-science","python"],"created_at":"2024-10-11T00:25:01.993Z","updated_at":"2025-03-23T00:32:36.338Z","avatar_url":"https://github.com/costrouc.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Binder](https://mybinder.org/badge.svg)](http://mybinder.org/v2/gh/costrouc/mse-machinelearning-notebooks/master?urlpath=lab/tree/notebooks/Overview.ipynb)\n\n[![pipeline status](https://gitlab.com/costrouc/mse-machinelearning-notebooks/badges/master/pipeline.svg)](https://gitlab.com/costrouc/mse-machinelearning-notebooks/commits/master)\n\n# Machine Learning with a focus on Material Science\n\nA presentation given and written by Christopher Ostrouchov all\ncontributions are welcome. We will be using the materials project and\nit's available data to \"predict\" material properties through machine\nlearning. Many of the examples may be trivial but the focus is on\nintroducing the workflow that is typical in machine learning.\n\n# Introduction to Python and Packages\n\nThe goal of this set of notebooks is to introduce you to the most\nimportant concepts of machine learning. While there are many many\nalgorithms for fitting your data the methodology of gathering,\nsanitizing, investigating, and evaluating the goodness of fit is\nmostly the same. I hope to show you the process along with showing\nsome methods from each branch of machine learning. Python has evolved\ninto a great solution for easily performning these steps and along\nwith R are great choices. My favorite description of Python is that it\nis the 2nd best language for every problem. Also it is probably the\nbest glue language out there.\n\nPython is a language that while it comes with \"batteries included\"\nmost of the functionality is provided through packages. I myself may\nconsider myself an \"expert\" the standard library (packages that are\nincluded by default with python) but there are always new packages to\nlearn. The packages that we will be using:\n\n - [jupyter notebooks](https://jupyter.org/) for [literate\n   programming](https://en.wikipedia.org/wiki/Literate_programming)\n\n - [requests](http://docs.python-requests.org/en/master/) for\n   gathering the materials project data\n\n - [pandas](https://pandas.pydata.org/) for storing data, sanitizing,\n   and investigating the data. A supercharged excell spreadsheet.\n\n - [matplotlib](https://matplotlib.org/users/pyplot_tutorial.html)\n   visualizing data\n\n - [numpy](http://www.numpy.org/) used underneath the covers for\n   pandas and basis of linear algebra in python\n\n - [scikit-learn](http://scikit-learn.org/) most popular machine\n   learning library. Does not perform neural network\n   calculations. Overview of available algorithms (does not cover all)\n   [link](http://scikit-learn.org/stable/tutorial/machine_learning_map/index.html)\n   \n - [pymatgen](https://github.com/materialsproject/pymatgen/) a package\n   by the Materials Project for working with material science\n   structures and analysis of calculations.\n\nThese packages have many many features but learning these core\nlibraries will be more than enough for getting started.\n\nResources that we will be using that are not python specific are:\n\n - [mybinder](https://mybinder.org/) which is a way to make a custom\n   programming environment available for free hosted on google\n   cloud. Note that resources are limited about 1 CPU and 8 GiB RAM\n   per instance. It is awesome you should use it too.\n\n - [materialsproject](https://materialsproject.org/) based at Lawrence\n   Berkely National Lab using the NERSC resources they provide data\n   from their VASP similations available using a [RESTfull\n   API](https://www.quora.com/What-is-a-REST-API).\n\n# Getting Started\n\nTo get started we will lanch the introduction notebook with binderhub.\n\n[![Binder](https://mybinder.org/badge.svg)](http://mybinder.org/v2/gh/costrouc/mse-machinelearning-notebooks/master?urlpath=lab/tree/notebooks/Overview.ipynb)\n\n# Contributing\n\nAll contributions, bug reports, bug fixes, documentation improvements,\nenhancements and ideas are welcome! These should be submitted at the\n[Gitlab repository](https://gitlab.com/costrouc/\nmse-machinelearning-notebooks). Github is only used for visibility.\n\nContributors:\n - [Chris Ostrouchov](https://gitlab.com/costrouc) (maintainer)\n\n# License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcostrouc%2Fmse-machinelearning-notebooks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcostrouc%2Fmse-machinelearning-notebooks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcostrouc%2Fmse-machinelearning-notebooks/lists"}