This repo includes a step by step exploratory data analysis and a simple modeling approach to predict energy consumption from the WIDS datathon. I hope it will help you understand a little bit more the data science and machine learning process.
It was developed using Jupyter Notebooks with Python3 and very useful libraries such as Pandas for data processing, Numpy for linear algebra operations, Seaborn and Matplotlib for visualization, and Scikit-learn for model building.
Data
Train and Test data can be found in the Datathon website at Kaggle : https://www.kaggle.com/competitions/widsdatathon2022/data