Skip to main content

Covid19 Prediction based on Symptoms

·
Table of Contents

GitHub
#

avaneesh2001/Covid_Dection_by_Symptoms

ML: Classification using logistic regression and KNN on the iconic titanic daaset

Jupyter Notebook
1
0

About Covid 19
#

From WHO website

Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. Most people infected with the virus will experience mild to moderate respiratory illness and recover without requiring special treatment. However, some will become seriously ill and require medical attention. Older people and those with underlying medical conditions like cardiovascular disease, diabetes, chronic respiratory disease, or cancer are more likely to develop serious illness. Anyone can get sick with COVID-19 and become seriously ill or die at any age.

Covid Detection model
#

I have created an ML model which can predict if a person has covid or not using symptoms they have. It is a supervised Classification model (Random forest model) developed using python. The model has a 96.7% Accuracy.

Dataset
#

The data for developing model was taken from Here

This dataset was cleaned and Classification performed using python in a jupyter notebook. The cleaned data set can be found in data folder and is saved as data.csv. You can also find it by clicking here

Classification model
#

Classification was done using logistic regression and Random forest and the following confusion matrix was obtained.

Confusion matrix

The Accuracy, Precision and recall along with F1 score were better for the random forest model and so I went with it.

R Avaneesh
Author
R Avaneesh