Estimating a probability distribution nonparametrically with a kernel density estimation
In the previous recipe, we applied a parametric estimation method. We had a statistical model (the exponential distribution) describing our data, and we estimated a single parameter (the rate of the distribution). Nonparametric estimation deals with statistical models that do not belong to a known family of distributions. The parameter space is then infinite-dimensional instead of finite-dimensional (that is, we estimate functions rather than numbers).
Here, we use a Kernel Density Estimation (KDE) to estimate the density of probability of a spatial distribution. We look at the geographical locations of tropical cyclones from 1848 to 2013, based on data provided by the NOAA, the US' National Oceanic and Atmospheric Administration.
Getting ready
You need Cartopy, available at http://scitools.org.uk/cartopy/. You can install it with conda install -c conda-forge cartopy.
How to do it...
Let's import the usual...
