Skip to content

The goal of this project is to predict car crash fatality using predictive models. Secured 3rd position in GW Data Science Datathon competition.

Notifications You must be signed in to change notification settings

sheldonsebastian/GW-Data-Science-Datathon

Repository files navigation

README:

Final Report:

https://sheldonsebastian.github.io/GW-Data-Science-Datathon/

Folder Structure:

Path Description
common contains utility functions to clean data, perform evaluation, modelling, etc.
images contains all saved images
input_data contains the input data, cleaned train-test-validation data and feature-target NumPy arrays
model_trainer contains model training and feature importance notebooks
0_preprocessing_eda.ipynb contains cleaning, preprocessing, stratified split and feature-target separator code
1_final_report.ipynb FINAL REPORT

Steps to replicate project:

  1. Download data from here.
  2. Run 0_preprocessing_eda.ipynb to preprocess data and create stratified train-test-holdout splits.
  3. Run all scripts in model_trainer folder to create all the respective models

About

The goal of this project is to predict car crash fatality using predictive models. Secured 3rd position in GW Data Science Datathon competition.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published