Unofficial Implementation of "Machine Learning Strategy for Accelerated Design of Polymer Dielectrics"

Overview

This repository provides Jupyter Notebooks as an unofficial implementation of the strategy discussed in the paper titled "Machine Learning Strategy for Accelerated Design of Polymer Dielectrics". Dive into the notebooks for an interactive exploration of polymer design powered by machine learning.

Notebooks Structure:

1. Polymer Fingerprinting I: This notebook implements a Kernel Ridge Regression usig Sci-Kit learn library following the polymer fingerprinting I discussed in the paper.
2. Polymer Fingerprinting II: This notebook implements a Kernel Ridge Regression usig Sci-Kit learn library following the polymer fingerprinting II discussed in the paper.
3. Polymer Fingerprinting III: This notebook implements a Kernel Ridge Regression usig Sci-Kit learn library following the polymer fingerprinting III discussed in the paper.

Getting Started:

Prerequisites:

• Jupyter Notebook or Jupyter Lab
• Required Python libraries:

  pip install -r requirements.txt

Running the Notebooks:

1. Clone the repository:

   git clone https://github.com/shadzzz90/Machine-Learning-for-Accelerated-Polymer-Design-Ploymer-

2. Navigate to the repository and start Jupyter:

   cd path/to/repo
   jupyter notebook

3. Open the desired notebook from the Jupyter interface in your browser.

Citation:

Though this is an unofficial implementation, please credit the original authors when using or referencing this work:

@article{Kanakkithodi2016,
  title={Machine Learning Strategy for Accelerated Design of Polymer Dielectrics},
  author={Arun Mannodi-Kanakkithodi, Ghanshyam Pilania, Tran Doan Huan, Turab Lookman & Rampi Ramprasad },
  journal={Scientific Reports},
  year={2016}
}

---

Engage, explore, and enhance the world of polymer dielectrics with machine learning through these notebooks.