Why Precipitation Data?

In Southern hemisphere, as everybody knows precipitation is going to embark amidst this COVID-19, answering the question of “How precipitation might affect the disease spread?“ has become significantly vital. And India being the second-most populous country, it is a win-win to perform analytics in this space to prevent the excessive spread of the disease.

Why Mobility data?

In various countries the lockdown is being lifted off steadily due to various reasons like economy, ………,……. . As a result of this mobility of people in different sectors like Grocery & Essentials, Parks, Residentials and Workplaces will keep varying in chronological manner. Finding a correlation between disease spread rate and mobility in various verticals, helps us understand what is that sector that is most affecting the disease spread and thereby giving an opportunity for the government to impose rules against movement in the highly correlated space.

After collecting the data we ventured a prolific analysis using the following technologies,

- Python (Programming Language)

- Jupyter Notebook (Where we coded)

- Plotly 

- Pandas profiling

- Numpy

- Pandas Dataframe

- Docker

Conclusions:

-  Spearman correlation of different metrics has being calculated and observed some correlation between states which have higher COVID-19 confirmed cases and states which have lower COVID-19 cases in the following metrics.

1) Transit metric

2) Temperature metric

- We also observed 14 day moving avg data have better correlation with the metrics,

- We need to study/focus more on transit related phenomenon and temperature related features. 

- Further studies will surely help on predicting when and where COVID-19 spread will occur.

Our results are in the following github link

https://github.com/gaganpreet97/covid_correlation.git

- https://www.covid19india.org/ (Covid spread details)

- https://www.google.com/covid19/mobility/ (Global Mobility information)

- https://www1.ncdc.noaa.gov/ (Weather data)