In this three-part series for Chemistry Department researchers we will setup and use data science tools for handling small to large numbers of DFT calculations and building multi-variate linear regression (MLR) models. Design of experiment (DoE) concepts and tools will be presented by Lauren Ehehalt (Weix Group) to help researchers plan efficient experiments and maximize experimental data. During this hands-on practical introduction, Spencer Heins will help you setup your personal computer with Anaconda, Python 3.8.8, Jupyter notebooks, and JMP Pro while learning tips for a successful workflow.
Part 1-Computer Setup:
• SMILES-to-.log workflow on Chemistry clusters
• Jupyter notebook for data collection and processing DFT calculations
• Jupyter notebook for building multi-variate linear regression (MLR) models
• JMP Pro software for statistical analysis and design of experiment (DoE)