Overview
Description of the Data:This dataset provides a comprehensive, multi-city view of daily air quality metrics and corresponding respiratory-related hospital admissions. Designed for environmental modeling, public health analysis, and machine learning applications, it enables robust exploration of the relationship between urban air pollution and health outcomes.
- Cities Covered: Delhi, Beijing, Mexico City, Los Angeles, London, Tokyo, Cairo, São Paulo
- Metrics Included: AQI, PM2.5, PM10, NO₂, O₃, temperature, humidity, population density,
hospital capacity, and daily respiratory hospital admissions
Perform the following tasks on the given dataset:- After performing usual housekeeping tasks read this data from your working directory
- Discuss various ways to measure missingness in the data using R, use one of the appropriate methods to detect the rate of missingness, provide solutions and perform them on this data to make this data complete for analysis purpose.
- Discuss various ways to identify outliers in the data, also discuss ways to treat the outlier values in the dataset. Use those methods to identify outliers in the given data set and if you detect any outlier value treat the outlier with the mentioned ways.
- Create a new variable of percentage of hospital admission due to the respiratory issues caused by the poor air quality with the hospital capacity.
- subset data for each city and save it in your working directory with the name of city.
- Read data for each city created in step 5 and convert long format data into wide format.
- Combine all the data into one file and write down a function that will help calculate five values summaries (min, max, mean, median, SD) for all the continuous variables present in the data. Use this function to calculate 5 values summary for each continuous variable and report your results in the form of a table (generated by your function) and also report it in your RMarkdown report.
- Which city has the greatest number of cases reported?
- Compare the temperatures of rural, suburban and urban areas
- Do you think urban areas have higher PM 2.5 and PM 10 as compared with suburban and rural areas? If so show it with a bar chart for each city.
- Is there any correlation between the aqi,PM 2.5, PM 10, no2, O3, temperature and humidity in our dataset, show it using a correlation heatmap.
- Develop and R Shiny flexdashboard to report your statistical results.
- Construct a table that shows average with standard deviation of each of the following variables for each of the city: aqi, PM 2.5, PM 10, no2, O3, temperature and humidity.
- Construct an interactive scatter plot representing the relationship between the variables aqi,PM 2.5, PM 10, no2, O3, temperature and humidity.