Code Monkey home page Code Monkey logo

ncfrey / pumml Goto Github PK

View Code? Open in Web Editor NEW
34.0 5.0 13.0 10.47 MB

Positive and Unlabeled Materials Machine Learning (pumml) is a code that uses semi-supervised machine learning to classify materials from only positive and unlabeled examples.

Home Page: https://pumml.readthedocs.io/

License: MIT License

Jupyter Notebook 27.39% Python 72.61%
machine-learning positive-unlabeled-learning density-functional-theory materials-science materials-informatics materials-design materials-discoveries physics chemistry

pumml's Introduction

Hi there, I'm Nathan ๐Ÿ‘‹

I'm a Machine Learning Scientist and Group Leader at Prescient Design โ€ข Genentech, where I develop and apply ML methods for molecular discovery and design. Previously, I was a Postdoc at MIT with the Lincoln Lab Supercomputing and AI groups, working with Profs Gomez-Bombarelli and Coley on ML for materials and molecule design. I have a PhD in Materials Science & Engineering from the University of Pennsylvania. I was a National Defense Science & Engineering Graduate Fellow in the Shenoy Group and an affiliate scientist at Berkeley Lab with the Materials Project.

pumml's People

Contributors

dependabot[bot] avatar ncfrey avatar vishnuharshith avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

pumml's Issues

Add library of pre-trained models

Pre-train PU learning models on different subsets of Materials Project database and 2D material databases.

Models should then be available to predict synthesizability of new materials. Training data for models should be available on figshare.

Automate pre-processing and featurization

Add helper functions to automate pre-processing.

Given a data frame of pymatgen Structures and PU labels, there should be functions to clean up the data frame if needed, featurize the materials, and save to file for PU learning.

MatProj support

To-do:

  • Address comments on #13, primarily how pre-featurized data is downloaded and accessed
  • Add unit tests for pupredict.py
  • Add example notebooks for pupredict.py

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.