GraphChem documentation

GraphChem is an open-source Python package for constructing graph-based machine learning models with a focus on fuel property prediction.

Contents

• Installation
  • Prerequisites
  • Install from PyPI
  • Install from source
  • Platform-specific dependencies
  • Development extras
• Quickstart
  • Load data and encode SMILES
  • Build graphs and a model
  • Next steps
• Tutorials and examples
  • Property prediction
  • Comparison experiments
  • Extras
• Bundled datasets
  • Common fields
  • Cetane number (CN)
  • Lower heating value (LHV)
  • Motor octane number (MON)
  • Research octane number (RON)
  • Yield sooting index (YSI)
• Reproducibility
  • Notes
• API reference
  • Package version
  • graphchem.data
  • graphchem.datasets
  • graphchem.nn
  • graphchem.preprocessing
• API stability policy
  • Frozen public surface
  • Signature contracts
  • Behavioral contracts
  • Versioning
  • Oracle parity as a release gate
  • Runtime prerequisites

Indices and tables

• Index

• Module Index

• Search Page