This repository contains the code and data for my group submission to the WiDS Datathon 2023. The challenge is to develop a machine learning model to predict extreme weather events.
The dataset contains weather data from 1981 to 2022. The target variable is the occurrence of an extreme weather event. We used a variety of machine learning algorithms to train my model, including XGBoost, Random Forest, and LightGBM. I also used feature engineering to improve the performance of my model.
Our best model achieved an accuracy of 85% on the test set. This repository is still under development, but I plan to add more information and documentation in the future.
* data/: contains the dataset used for the challenge.
* models/: contains the code for the machine learning models.
* notebooks/: contains the Jupyter notebooks used to develop and evaluate the models.
* README.md this file, which provides an overview of the repository.
To get started, you can clone the repository and install the dependencies using the following commands:
git clone https://github.com/[your-username]/widsdatathon2023.git
cd widsdatathon2023
pip install -r requirements.txt
Once the dependencies are installed, you can run the Jupyter notebooks to develop and evaluate the models.
I hope this helps!