EXPLORATORY ANALYSIS OF COVID_19 CASES AND VACCINATION IN NIGERIA

 Introduction:

This is a project on the Covid_19 cases and Vaccination as at April 24th, 2022 among the 36 States in Nigeria including the FCT. 

Data was pulled out from the NCDC website for the project. Data was clean enough except for some columns which were cleaned out that didn't serve the purpose such as clinics, testing centers, etc. 

All reports from labs across the states are sent to NCDC for computation and publishing

Columns and rows with null values were cleaned while there were no duplicate values in the cell.

The columns were formatted from text to numbers so python will be able to read the columns with figures as strings instead of objects. Computation cannot be carried out on columns with object data type

Analysis and visualization were carried out using python libraries such as pandas, matplotlib, Plotly, and seaborn.

Python was chosen for the analysis due to the structure of the data, which has a large number of columns, computations and analysis are carried out easily with python when dealing with a file with a large number of rows and columns


Objective:

A. The objective was to perform a descriptive analysis of the cases of Covid_19 with the data broken into States Confirmed Cases, Active Cases, Recoveries  Death, and Testing to measure the following:



1. Descriptive Statistics: Count, Mean, SD, MIN,MAX,25%,50%and 75%

2. Visualization: Data was analyzed leading to the following Visualizations:

  • pivot table showing the comparison of the sections of the data with the state as index

  • a barplot showing the Top Ten States by death

  • a barplot showing the Top 10  States with active cases



B.The Vaccination data was broken down into States, Population, Total Vaccinated Population, First Dose (Partially Vaccinated), and Second Dose (Fully Vaccinated) which was used to carry out the descriptive analysis. Below are the Visualizations.

  •  Top Ten states by vaccination

  • A comparison of the Covid_19 cases to the vaccination using a pivot table



  • A comparison of the Perc Vaccinated and Death recorded in each state using a bar plot





C. Determination of a correlation or causation between Covid-19 Cases and Vaccination in Nigeria.

RESULTS.

These are the results of the analysis:

  • Los State has the highest Confirmed Cases, Deaths, Testing, and active cases and is among the Top 5 states with recovery rates. The mortality rate is low compared to states with lower confirmed cases.
  • Kogi State recorded the least amount of Confirmed Cases of 5 and a significantly high mortality rate.
  • Anambra State recorded the least mortality rate followed by Plateau State.
  • Plateau State however recorded a high percentage of confirmed cases against testing
  • Benue  recorded a higher percentage of active cases against the confirmed cases
  • FCT leads with the highest percentage of the vaccinated population followed by Lagos and Ogun States.
  • There is a correlation between Covid_19 cases and vaccination as seen in the results explained above however there isn't a Causation between Vaccination and Confirmed covid_19 cases as some states among the states with the highest cases didn't record a commensurate number of vaccination.

  • The Jupyter notebook file can be viewed here  COVID_19 project
Kindly post any recommendations you may have in the comment section.

Thank you for reading

Comments

Post a Comment

Popular posts from this blog

  BUILDING AN EXCEL DASHBOARD      DESCRIPTION This is a Descriptive Analysis of the Data on the World's population from 2010 to 2020.   The main information provided are Various Metrics (Series by which data is classified), Country, and Region. More on the Series is available below The Dashboard visualizes the data of the World Population by metrics such as: 1. Infant Mortality for both sexes per (1000 Live births). 2. Life Expectancy for both sexes(years) 3. Life Expectancy at birth female (years) 4. Life Expectancy at birth for males (years) 5. Maternal Mortality ratio (deaths per 100,000 population) 6. Population annual rate of increase(percent) 7. Total fertility rate (children per woman ) It also displays a time series from 2010 to 2022 at a five-year interval. The various charts on the dashboard were created to interact with each other by the use of the slicers DATA  The data was sourced from data.un.org.  Columns with information not usefu...
Read more
 TABLEAU FUNDAMENTALS....DATACAMP Learning a BI tool is of great importance for anybody pursuing a career in Data Analysis, Business Intelligence, and Business Analysis. While there are countless BI tools, one might be stuck in between learning as many as possible. It is important, however, to know the basic of the widely used BI tool such as Tableau, Power bi, IBM Cognos, Qlik, Alteryx, etc. I believe however that it would be beneficial for one to master one of the above-mentioned. I started out using Power Bi, Alteryx, and Tableau but decided to stick to Tableau. The reason is that I found Tableau the most challenging and I feel if I can master it, the rest would be a bit easy to master.  Thanks to Datacamp and Youtube I took courses and tutorials to sharpen my knowledge and bridge the GAP between what I already and how to use up do date Tableau Built-in Functions. From courses such as  1. Introduction to Tableau 2. Analyzing Data in Tableau 3. Creating Dashboards in Ta...
Read more