Welcome to the TAMU Datathon 2023 GitHub repository for Team: 45.
This repository contains all the resources, code, and data for our team's participation in the TAMU Datathon for 2023. Our project is training an ai model using a dataset to determine the accuracy of a patient surviving given the specifics of their condition.
Debrief
- The dataset given to us is in the form of a csv file, the first row having the titles of the columns, and each subsequent row will containing information for a patient given by the hospital with one row representing one patient.
- Provided with a dataset with inherent flaws, we had to adjust, scrape through, and clean up the data.
- Afterwards, we used recursive feature elimination to find what features contributed most to survival.
- This allowed us to train the Keras Sequential Model to predict data.
- The predictions from this model were submitted to get a score on how accurate it was.
- Bao
- Taylor
- Arul
- code: All our code and scripts for data analysis, modeling, and visualization.
- docs: Any additional documentation or reports/outline of our project.
- resources: Useful resources related to the Datathon including Python documentation, programming library resources, etc.
If you have any questions do not hesitate to reach out!