{"id":20512032,"url":"https://github.com/wardlt/ward-npj-2016-examples","last_synced_at":"2025-09-02T08:43:43.272Z","repository":{"id":91621882,"uuid":"109404769","full_name":"WardLT/ward-npj-2016-examples","owner":"WardLT","description":"Scripts for replicating a paper on predicting the properties of materials with machine learning","archived":false,"fork":false,"pushed_at":"2017-11-03T14:28:41.000Z","size":30004,"stargazers_count":3,"open_issues_count":0,"forks_count":4,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-04-13T22:47:46.775Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/WardLT.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":"2017-11-03T14:24:59.000Z","updated_at":"2023-04-15T08:00:50.000Z","dependencies_parsed_at":null,"dependency_job_id":"db9aaa2c-4690-43e4-a98f-c0466896db0c","html_url":"https://github.com/WardLT/ward-npj-2016-examples","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/WardLT/ward-npj-2016-examples","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fward-npj-2016-examples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fward-npj-2016-examples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fward-npj-2016-examples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fward-npj-2016-examples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/WardLT","download_url":"https://codeload.github.com/WardLT/ward-npj-2016-examples/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fward-npj-2016-examples/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273257755,"owners_count":25073531,"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","status":"online","status_checked_at":"2025-09-02T02:00:09.530Z","response_time":77,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-11-15T20:39:26.967Z","updated_at":"2025-09-02T08:43:43.226Z","avatar_url":"https://github.com/WardLT.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Predicting Properties of Inorganic Materials with Machine Learning\n\nThis repository contains software and scripts necessary to replicate most calculations from a 2016 paper by [Ward *et al*](https://www.nature.com/articles/npjcompumats201628): \"A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials.\" \nThe scripts are all contained within Jupyter notebooks alongside explainations for the calculations. \n\n## Contents\n\nThere are several important directories in this repository:\n\n    `datasets`: Datasets for the band gap energy predictions and glass forming ability models\n    `magpie`: The Materials-Agnostic Platform for Informatics and Exploration (Magpie), its required libraries, and documentation. See [bitbucket.org](https://bitbucket.org/wolverton/magpie)\n    `predicting-band-gap-energies`: Scripts for creating models for band gap energies of crystalline compounds\n    `modeling-metallic-glasses`: Scripts for predicting the glass-forming ability of metallic alloys\n    \nThe latter two directories contain Jupyter notebooks that replicate the key tables and figures from this paper.\n\n## Running\n\nThese notebooks are designed to be run via Docker. \nDocker is a tool for creating very lightweight virtual machines, which - in our case - makes it possible to run these notebooks in the same software environment.\n\nTo launch the notebooks, first install docker on your computer and then call either `./docker.bs` if you are running Mac or Linux, or double-click `docker.bat` if you are running Windows. \nThis will create a Docker container with the correct environment, assign it in an appropriate amount of RAM (though you might want to adjust it, if your computer has \u003c6GB of RAM), and allow it to access the appropriate files.\n\nOnce the docker container is launched, you can connect to the Jupyter environment via a web browser (see the URL listed by the Docker container). \nThen, you can either run each notebook on its own, or run `./run-all.bs inplace` in the `/home/joyvan/data` directory via the command line to execute all notebooks in the proper order.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwardlt%2Fward-npj-2016-examples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwardlt%2Fward-npj-2016-examples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwardlt%2Fward-npj-2016-examples/lists"}