pyMAISE: Michigan Artificial Intelligence Standard Environment

pyMAISE is an artificial intelligence (AI) and machine learning (ML) benchmarking library for nuclear reactor applications. It offers to streamline the building, tuning, and comparison of various ML models for user-provided data sets. Additionally, pyMAISE offers benchmarked data sets with example Jupyter Notebooks. Current ML algorithm support includes

• linear regression,

• lasso regression,

• decision tree regression,

• support vector regression,

• random forest regression,

• k-nearest neighbors regression,

• sequential dense neural networks.

These models are built using scikit-learn and Keras. For more information such as installation, examples, and use, refer to the sections below.

Contents

• Installation
  • Prerequisites
  • Pip
  • From Source
• User Guide
  • pyMAISE Initialization
  • Pre-processing
  • Model Initialization
  • Hyper-parameter Tuning
  • Post-processing
• Dev Guide
  • Installation and Setup
  • Branching
  • Committing
  • Pushing
  • General Workflow
• Machine Learning Models
  • Linear Regression
  • Lasso Regression
  • Support Vector Regression
  • Decision Tree Regression
  • Random Forest Regression
  • K-Nearest Neighbors Regression
  • Sequential Dense Neural networks
  • Model Dictionary Templates
• Example Jupyter Notebooks
  • MIT Reactor
  • Reactor Physics
  • Fuel Performance
  • Heat Conduction
  • BWR Micro Core
  • HTGR Micro-Core Quadrant Power
  • NEACRP C1 Rod Ejection Accident
• Apache License