- Click here to view the full Tableau presentation.
- Click here to view my Jupyter Notebook on GitHub and more
| Context | Objectives | Key Analysis |
|---|---|---|
| From World Health Organization – On 31 December 2019, WHO was alerted to several Cases of Pneumonia in Wuhan City, China. The virus did not match any other virus. It raised concern because when a virus is new, we do not know how it affects people. Coronavirus disease (COVID-19) is an infectious disease. These virus cases in the U.S. are stacking up higher and higher. Understanding this virus is crucial to stop its spread. In this case study, we will be exploring ways to prevent the further spread of this virus by using vaccines. | As a Data Analyst, my task is to find which states need urgent vaccinations and medical services. Vaccinations of COVID-19 in the U.S. will begin on Dec.14, 2020. This case study will identify the vulnerable Age Groups and top 10 States for vaccinations. The Key analyses are the following: | - 1.Explore the change in Confirmed and Death Cases of COVID-19 by States.- 2. Explore the time series of Confirmed and Deaths Cases of COVID-19 by months.- 3. Does Gender play a role in Death Cases of COVID-19? - 4. Which age groups are the vulnerable populations in COVID-19 Cases? - 5. What are the top 10 states with the highest number of vulnerable populations? - 6. Understand the relationship between Confirmed Cases and Deaths Cases by State.- 7. What further strategies should be used to stop spreading the COVID-19 cases? |
Process
| Data preparation | Analyzing data | Visualization of the data |
|---|---|---|
| Searched for the right Data | Supervised machines learning: Regression analysis | Mapping the data |
| Cleaned the Data (merging, grouping, aggregating, etc.) | Unsupervised Machine Learning: Clustering analysis | Line charts, Bar charts, Pies Charts, etc. |
| Create new variables to glean insights | Time-series Analysis | Creating a Data Dashboard |
Results
Starting January and ending September, both Confirmed and death cases increased. The average number of death cases increased by each month. However, the number of Confirmed cases reached 7000k, and death cases exceed 200k.
Gender impacts Death Cases of COVID-19. Male populations have higher Death Cases compare to females. However, this comparison changes by each age group.
Males and females above 65 years-old are at high risk of COVID-19 Deaths. And they are considered vulnerable populations. However, Female over 85 years old and Male between 75-84 years has comparatively higher death rates than other age groups.
The top 10 states with a higher number of vulnerable populations are New Jersey, New York, Massachusetts, Pennsylvania, California, Florida, Illinois, Texas, Connecticut, and Michigan.
As the total Confirmed Cases of COVID-19 increased, Death cases increased as well. However, it differs in each state.
Recommendation
My recommendation is to start the vaccinations with the top 10 states identified.
Priorities the vulnerable populations in the top 10 states identified and all other states.
| Challenges | Solutions |
|---|---|
| I had a hard time merging Large data in Jupyter Notebook. The KERNAL of Jupyter slowed down dramatically and would not save my work. | I updated Anaconda and Python libraries through Terminal. This process helped me better understand Terminal usage. |
| TOOLS USED |
|---|
| Importing libraries (Python) |
| Importing, exporting, and Combining datasets (Python) |
| Data Consistency Checks (Python) |
| Descriptive Analysis (Python) |
| Data wrangling and Merging (Python) |
| Deriving New Variables (Python) |
| Grouping Data and Aggregating Variables (Python) |
| Sourcing Open Data (Python) |
| Exploring Relationships (Python) |
| Geographical Visualizations (Python / Tableau) |
| Supervised Machine Learning: Regression (Python) |
| Unsupervised Machine Learning: Clustering (Python) |
| Sourcing and Analyzing Time Series Data (Python/ Tableau) |
| Creating Data Dashboards (Tableau) |
Want to see something else added? Open an issue.