Covid-19 Data Analysis Using Tableau
Tableau is a fast-growing data visualization and data intelligence software used worldwide to drive better data-driven decisions. Dynamic software manipulates updated data as and when it is introduced into Tableau. A simplistic description of Tableau is a pivot table on steroids. But Tableau is so much more than Excel and other software available in the market for analyzing data.
Today Tableau is at the forefront of data analysis with millions of users globally. Apart from its advanced features, interactive dashboards have the facility to import data from different data systems like Python and R.
The Covid-19 epidemic has devastated the whole world and resulted in many deaths. It transcended national borders and attacked citizens of all countries without discrimination.
Many countries maintained a daily tracker of Covid-19 patient statistics to take appropriate action regarding lockdowns, curfew, treatment plans, ensuring availability of medical and health care facilities, availability of oxygen, vaccine production, emission, etc. Tableau software has been handy for all the data at a global level and facilitated decision-making by the governments of the respective countries.
Tableau helped government health organizations and companies in data analysis during the Covid-19 epidemic. Given below is the use of a Tableau to track the progress of the Covid-19 epidemic in the U.S.
Tableau workday data file was used.
The Tableau workday data file was used with Tableau Prep Builder and data from John Hopkins to represent a dynamic data representation. The above is a static view of the Tableau Dynamic Prep Builder. A survey of work from home employees, which was administered on the Salesforce platform, is represented below:
Filters were used to enable analysis by employee’s region, quota responsibility, and previous work experience from home.
Tableau launched the Datahub to make sense of the Covid-19 data.
In India, Covid-19 data was analyzed using Tableau. The analysis of the data focused on the following key data points:
- The timeline of the spread in the country
- The primary reasons for the spread and the various government responses to it.
- Analysis of research and development.
- The number of Covid-19 tests carried out and analysis of the same.
Timelines were plotted, charting the return of tourists from Wuhan and the return of tourists from Italy. The various events which led to the congregation of people were all charted.
Most of the reasons for the spread were the various religious congregations in the country belonging to different faiths. This led to the peaking of the Covid-19 cases, as shown in the above chart.
Government responses can be classified as under:-
- Thermal screening of patients returning from abroad. This was gradually extended to the various airports in India.
- By Mid-March, containment measures were introduced to prevent spread through contact.
- By 22nd March, lockdown measures were introduced in 22 states, followed by inter-state movement restrictions. The gradual nationwide lockdown was also introduced. The data graphs in Tableau show rapidly increasing numbers of Covid-19 patients resulting in further extensions of the lockdown.
- Research and treatment: India fared better compared to the rest of the world, as shown in the Tableau graph below:
- Many government facilities such as the DRDO and ISRO started producing protective equipment, PPE suits, and ventilators to fight against Covid-19. Gradually other Public and private sector enterprises were also drawn into the production of equipment to protect against the Covid-19 epidemic.
- Testing: Covid-19 testing was gradually extended to cover significant population proportions. All pneumonia cases were included in the ambit of testing.
The testing ambit was gradually widened to include broader testing in all the hotspot areas. The graph below shows the confirmed cases contrasted against the number of deaths in India.
Some of the important takeaways from the above exercise were:
- Data from Tableau graphs and data visualization models were used for public decisions.
- The data visualization models were used to communicate the immense scale of the tragedy in a way that mere numbers could not.
- The summary statistics mask inequalities between regions, states, and groups of people.
- The data collection itself was a very complex exercise.
- One measure from the data charts or visualization exercises does not tell the complete story. Many measures had to be taken together to tell the complete story of the progress of the Covid-19 epidemic.
- Rapid developments of Covid-19 charts happened at the expense of accessibility. The Tableau statistics and graphs were not accessible to those working on the ground.
Visit Imarticus Learning to learn more. Contact us through chat support, or drive to our training centers in Mumbai, Thane, Pune, Chennai, Bengaluru, Delhi, and Gurgaon.