Data Wrangling

Data set is organized by combining 7 different data sets obtained from United States Environment Protection Agency. Data Wrangling is done through splitting columns and rows, filtering the data set, aggregating and by performing basic statistic operations.

Data Visualization

Above graph represents the percentage of unhealthy days of each state over the past 7 years.
The following insights can be drawn from the above graph:

The above heat map shows the percentage of good days by state over the past 7 years.This visualization is helpful to quickly look at the distribution of percentage of good days over the years of each state.




The above maps show the percentage of unhealthy days over the past 7 years. Hovering over the states gives extra information regarding percentage of good days,moderate days and unhealthy for sensitive groups.




Insights from above visualizations

This visualization shows how the Unhealthy days and Unhealthy days for sensitive groups are distributed over the years.










These visualizations show the top cities with unhealthy days for sensitive groups,unhealth days,and very unhealthy days of 2020. This data can be used to take appropriate measures to regulate the air quality in the respective cities.