Skip to content

Predict mortality among confirmed CoVID-19 patients in South Korea using logistic regression and support vector machines.

Notifications You must be signed in to change notification settings

nilijing/Predicting-Covid-Mortality-with-Machine-Learning

Repository files navigation

Predicting-Covid-Mortality-with-Machine-Learning

The aim of the final project is to predict mortality among confirmed CoVID-19 patients in South Korea using logistic regression and support vector machines. We explained the models and visualized classifiers. We also made tables that summarizes our classification errors for both of models.

Data Source

Download the Covid-19 dataset from the URL: https://www.kaggle.com/kimjihoo/coronavirusdataset

The dataset is online and publicly available with a free Kaggle account.This dataset was released by Korea Centers for Disease Control and Prevention, and it contains information the Covid-19 cases in South Korea. Use 80% of data as the training data and 20% of data as the test data.

Prerequisites

  • Train two models: one based on logistic regression and one based on support vector machines.

  • Compare their performances on the test data.

Results

Performance of the machine learning algorithms used in this project:

Reference

There's a similar approach to the following paper:

Predicting CoVID-19 community mortality risk using machine learning and development of an online prognostic tool, 2020 by Das et al.

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7528809/pdf/peerj-08-10083.pdf

About

Predict mortality among confirmed CoVID-19 patients in South Korea using logistic regression and support vector machines.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages