Metadata-Version: 2.4
Name: thermoML
Version: 0.1.0
Summary: Physics-informed ML for thermal fluid property prediction
Home-page: https://github.com/AI4ChemS/thermoML
Author: Mahyar Rajabi-Kochi
Author-email: mahyar.rajabi@mail.utoronto.ca
License: MIT
Keywords: python,chemistry-ml,thermodynamics-informed-ml,machine-learning,thermal-fluids
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: Programming Language :: Python :: 3.8
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/x-rst
License-File: LICENSE
Requires-Dist: pandas>=1.3
Requires-Dist: numpy>=1.21
Requires-Dist: pubchempy>=1.0
Requires-Dist: requests>=2.25
Requires-Dist: rdkit>=2022.3.5
Requires-Dist: mordred>=1.2.0
Requires-Dist: scikit-learn>=1.0
Requires-Dist: xgboost>=1.6
Requires-Dist: tensorflow==2.12.0
Requires-Dist: optuna>=3.0
Requires-Dist: openpyxl
Requires-Dist: matplotlib
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary


ThermoML is a Python package for predicting thermophysical properties of pure fluids using chemistry- and temperature-aware machine learning models. This tool integrates physics-informed modeling with machine learning techniques to accurately predict thermophyiscal properties across temperature ranges. The package includes pre-trained models, data preprocessing utilities, and simple interfaces for inference and evaluation.

Key Features:
1. Predict property of interest (such as dynamic viscosity) from SMILES and temperature
2. Flexible equation integration based on the property of interest (e.g., Arrhenius-based scaling for viscosity)
3. Easy-to-use for batch predictions
4. Includes curated datasets and example notebooks

Whether you're working on thermal fluid research, chemical engineering, or data-driven materials science, ThermoML provides a fast and extensible way to estimate temperature-dependent fluid properties.
