Exercise: Statistical analysis of raster data using NumPy
In the Chapter 10 folder of the GitHub repo, you will find a set of rasters that represent pollution over New York City. This data covers 10 years of annual average pollution for a variety of pollution types. You will use the Nitrous Oxide files for this section. The files go from 2009 ("aa1_no300m"
) to 2018 ("aa10_no300m"
) and are at a resolution of 300 meters.
You’ll use them to explore the statistical methods available using NumPy, including mean, median, and standard deviation. You’ll also create histograms and charts depicting the reduction in pollution data over the 10-year monitoring period.
The data was downloaded from this dataset: https://catalog.data.gov/dataset/nyccas-air-pollution-rasters.
- To start, create a new cell in your Notebook and make sure you have the filepath for the raster pollution data for 2009. You’ll need to convert the raster...