You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
LECA - The Liquid Electrolyte Composition Analysis Package
The Liquid Electrolyte Composition Analysis (LECA) package creates
a simplified Jupyter-Notebook [1] based workflow for applying
Scikit-Learn [2] machine learning regression models to predict
liquid electrolyte behavior based on composition.
Requirements
Python 3.7+, Jupyter Notebook 6.4.11+
With the following python libraries:
Scikit-learn 1.3.1+
NumPy 1.22.3+
Matplotlib 3.5.1+
Pandas 1.4.2+
SciPy 1.8.1+
Uncertainties 3.1.7+
MAPIE 0.5.6
HDBSCAN 0.8.28+
Seaborn 0.11.2+
GPyOpt 1.2.6+
Installation
The LECA package can be installed directly from source with:
[9] Brian E. Granger and Fernando Pérez. “Jupyter: Thinking and Storytelling With Code and Data”. In: Computing in Science & Engineering 23.2 (2021), pp. 7–14. doi: 10.1109/MCSE.2021.3059263.
Leland McInnes, John Healy, and Steve Astels. “hdbscan: Hierarchical density based clustering”. In: The Journal of Open Source Software 2.11 (2017), p. 205.
Anand Narayanan Krishnamoorthy et al. “Data-Driven Analysis of High-Throughput Experiments on Liquid Battery Electrolyte Formulations: Unraveling the Impact of Composition on Conductivity**”. In: Chemistry–Methods 2.9 (2022), e202200008. doi: https://doi.org/10.1002/cmtd.202200008.
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grants agreement No 957189 (BIG-MAP) and No 957213 (BATTERY2030+).