• finalDS.csv is the dataset we have used in the project. It is a pre-processed dataset of a dataset taken from Kaggle[link: https://www.kaggle.com/rohanrao/air-quality-data-in-india].
• pollutants table.csv is a dataset we have created that is used in the pollutant trends tab.

• We have used R shiny to develop a dashboard to explain our findings and insights. T
• The HOME tab introduces the topic and gives insight into the current affairs related to pollution .
• The MAP DISTRIBUTION tab shows the India map with the states we are analyzing and the AQI for that state, the distribution of various pollutants using bar graph was also presented in the same page.
• In the LINE GRAPH tab one can understand the trends/patterns of how pollutants change in different cities on a weekly basis.
• The POLLUTANT TRENDS tab showsthe correlation between the various pollutants and how they affect the value of AQI using heat map and correlation matrices. This tab also provides some suggestions for the people in those cities to have a better life against pollution.

Air pollution is one of the biggest challenges that our country is facing right now. It’s all the more important in our country where the common man is not quite familiar with the technical terminologies and measuring units (like ppm /ppb / or µg/mg3). Hence the AQI simplifies the understanding of their air quality by decoding the quality in terms of unitless numbers. By knowing which pollutant contributes more, that specific pollutant can be reduced from usage. By knowing the highest polluted city that city can take measures to avoid the air pollution in future.