Machine Learning Automation Pipeline

RESOURCE

Abstract

Machine Learning Automation Pipeline (MLAP) is a package to perform machine learning (ML) analysis in a step by step manner, starting with data extraction until analysis and prediction. The scripts provide the users option to chose an action such as "Extract", "Prep", and "Train" and numerous cases can be launched with just a single command. The inputs for each case are provided using a JSON file. The simulation results of several cases can be assessed using an automated process and analyzed for various metrics pertinent to ML analysis.
Developers:
Jha, Pankaj [1]
  1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Release Date:
2024-09-18
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Version:
1.0
Licenses:
MIT License
Sponsoring Org.:
Code ID:
157408
Site Accession Number:
LLNL-CODE-2001016
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Jha, Pankaj. Machine Learning Automation Pipeline. Computer Software. https://github.com/LLNL/MLAP. USDOE National Nuclear Security Administration (NNSA). 18 Sep. 2024. Web. doi:10.11578/dc.20250630.1.
Jha, Pankaj. (2024, September 18). Machine Learning Automation Pipeline. [Computer software]. https://github.com/LLNL/MLAP. https://doi.org/10.11578/dc.20250630.1.
Jha, Pankaj. "Machine Learning Automation Pipeline." Computer software. September 18, 2024. https://github.com/LLNL/MLAP. https://doi.org/10.11578/dc.20250630.1.
@misc{ doecode_157408,
title = {Machine Learning Automation Pipeline},
author = {Jha, Pankaj},
abstractNote = {Machine Learning Automation Pipeline (MLAP) is a package to perform machine learning (ML) analysis in a step by step manner, starting with data extraction until analysis and prediction. The scripts provide the users option to chose an action such as "Extract", "Prep", and "Train" and numerous cases can be launched with just a single command. The inputs for each case are provided using a JSON file. The simulation results of several cases can be assessed using an automated process and analyzed for various metrics pertinent to ML analysis.},
doi = {10.11578/dc.20250630.1},
url = {https://doi.org/10.11578/dc.20250630.1},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20250630.1}},
year = {2024},
month = {sep}
}