Analysis using SQL: A Look Behind COVID-19 India Vaccinations

Analysis of Covid Vaccinations using SQL Server

Dataset

The data for this project is taken from Kaggle. This is part 2 of the 2-part analysis of Covid Data. To view the first part, click Part1.
The table used for this analysis contains data from the beginning of the Pandemic till 24th June 2021.

The project contains an in-depth analysis of Covid Vaccinations, implemented using Excel & SQL and visualized using Tableau. SQL analysis is implemented on Microsoft SQL Server.

Cleaning the Data:

In the dataset, half of the dates are in ‘Date’ format and others are in ‘Varchar’ format. This had to be changed to proper date format, which has been done using Excel. The edited data can be downloaded from here.

Here also some columns has been dropped, which were not related to Vaccine information, and used existing feature columns to create new features like perDay Total Vaccinated, perDay Total Doses cases, to get the per day Vaccine information from the Rolling Sum vaccine data. For a detailed understanding of the alterations performed on the dataset, look at this DDL file.

Creating New Features

Output:

Let’s begin the Analysis!!

Here, we analyse data, first in terms of total vaccinations with respect to India and individual states, and finally — with respect to per day Vaccination data of each state.

1. TopVaccinated States
2. Proportion of Covishield, Covaxin, Sputnik administered State-Wise

Output: Covishield was administered in largest quantities for all the states, followed by Covaxin. Among the states, Delhi used the highest proportion of Covaxin(30%) among all, to vaccinate its population.

3. Vaccination proportion among different Age groups

Output: Proportion of Old-age people vaccinated is less in India as well as among different states, which can also be due to major Indian population being from other categories.

Vaccination among various age-groups

4. Percent of First Dose recpients who are also done with their 2nd Dose State-Wise

Output: In India, 21.21% of people vaccinated have completed their both Covid doses, and Delhi(31.43%) has the highest percent of complete dosed popluation out of those vaccinated.

Complete Doses

Visual representation of state-wise Vaccinated population

5. Percent Doses wasted State-Wise

Output: Acc to given Data, maximum Dose wastage occurred in Chattisgarh(57.94%) in the month of May followed by Telangana(49.33%).

Wastage of Doses (State-Wise)

Summary

Following conclusions can be derived from above data analysis:

1. Uttar Pradesh(2,39,18,186) administered most number of vaccinations in India, while maximum dose wastage has been made in Delhi(23.91%).
2. Delhi(31.43%) also has the highest percent of fully dosed popluation out of those vaccinated.
3. In India, among those vaccinated, 53.86% are Males and 46.12% are Females. Almost same ratio has been maintained by all states, except in Andhra Pradesh where 54.03% vaccinated are females & 45.95% Males.
4. Covishield has been administered to approx 80% of vaccinated population in the country, next being Covaxin.

COVID Vaccinations Dashboard

For a detailed understanding of the project, look at the GitHub repository. Additionally, one can also access the dashboard from Tableau link.

If you have feedback, suggestions, or questions about this post, feel free to comment on GitHub or to add to it, or reach out to me on LinkedIn.