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.
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.
-
Train two models: one based on logistic regression and one based on support vector machines.
-
Compare their performances on the test data.
Performance of the machine learning algorithms used in this project:
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