# Nigeria-COVID-19-Data-Analysis-Using-Python
Data Scientist Microdegree Capstone Project- Ustacky
This project is a detailed analysis of datasets correlated to Covid 19 in Nigeria.
Here i was able to collect data, clean, process,and analyse it to get insights on the Outbreak of the Covid 19 and its effects in Nigeria.
This major steps can be Compunded in just 3
# 1) Data Collection.
First step was clearly to fork and clone the data sets from Ustacky github as advised. I did web scrapping on the Ncdc site which involved using the pandas read .html(url) function to extract data from the site.
Budget data set,covid 19 external data set,Real gdp was also extracted using pandas read .csv format.
#Budget data set contained prior and revised budget of Nigeria segmented in states.
#Covid 19 external data set contains population density,overall vunerability index and many more.
#Real gpd contains quartely(Q1-Q4) GDP of nigeria from 2014 to 2020
I also collected data for John Hopkins Repository which contained daily confirmed,recovered and death cases across 275 countries of the world. i used pandas read .html(url) format to extract the data.
A total of 7 datasets was considered and used for analysis in this project.
# 2) Data Cleaning and Preparation.
All data set was check for or explored for basic information using basic functions like df.head() to preview dataset, df.info() to see information on the dataset, df.isnull() to check for empty or null columns and rows and df.duplicated() to check for duplicate values
Particularly on the data we extracted from Ncdc website we had quite alot of duplicated values which sumed up the rows to be 54 instead of 37. I used the df.duplicates() to drop the duplicated row across all colums.
I also renamed the column headers or name on the Ncdc dataset using df.rename()
i was also able to extract daily recovered,confirmed,death cases from John Hopkins Repository for only Nigeria.
# Data Analysis
From Ncdc dataset, a total vis …