Human Factors

The emergence and spread of infectious diseases, like COVID-19, are on the rise. Can you identify patterns between population density and COVID-19 cases and identify factors that could help predict hotspots of disease spread?

Implications due to Human Factor

Summary

Implication due to Human FactorLogistic model is used to predict Dead and Not dead and how the human factor brought changes in the rate by staying home and isolating themselves.The Death rate is calulated before and after the lockdown.Consideration while cleaning the data set:If deaths occured for particular day the death rate is 1.If death doesn't occured for particular day the not_dead rate is 0.Variables :Dead = 1Not_dead = 0 USA GDP we are considering USA Gross Domestic Product from 2018 Jan to 2020 Jan on quarterly basis.In finding we cab observed that GDP from 2018 Jan to 2019 was constant same wi

How We Addressed This Challenge

Our project shows the growth of covid 19 over time and how changes in human activities that help to flatten the cure.

How We Developed This Project

We first shortlisted the data set as per our needs

We selected data set that caters our need of developing the model that we thought of.

We cleaned the data set using various data cleaning techniques 

And build the model using keeping the dead as the dependent variable.

Project Demo

Our logistic model show the changes in death rate before and after lockdown.

while the decision tree shows how the covid 19 grew over time.

Tableau dashboard further shows hotspots for covid 19.

Data & Resources

We used Covid-19 Data set from kaggle

You can find the dataset from the below link.

https://github.com/NEU-20/Hackathon.git

We used R to build decission tree, logistic model and time series model.

We used Tableau to build dasboard showing heat maps for Covid 19 spread

Tags
#covid-19#logisticmodel#R#Tableau#Human factor
Global Judging
This project was submitted for consideration during the Space Apps Global Judging process.