Title: Machine Learning for Predicting Faradic Efficiency of ZIF-8 Towards Carbon Monoxide

This project involved the collection and analysis of 88 data points sourced from 10 research articles, with a primary focus on predicting the performance of electrocatalysts for carbon dioxide reduction. A thorough exploratory data analysis (EDA) was conducted to uncover key patterns and insights within the dataset. Following the EDA, machine learning models were developed and optimized to enhance prediction accuracy and reliability. To ensure seamless reproducibility and consistent deployment, a Docker environment was set up, providing a robust framework for experimentation and production. Additionally, a user-friendly Flask-based application was developed, enabling easy access and interaction with the predictive models, allowing users to effortlessly leverage the framework for real-time performance predictions.

Key Concepts Explored: Python programming, machine learning, and MLOps

Libraries Used: Pandas, NumPy, Matplotlib, Seaborn, and scikit-learn