Module dstats.kerneldensity
This module contains a small but growing library for performing kernel density estimation.
Author
David Simcha
Functions
Name  Description 

scottBandwidth(data)

Uses Scott's Rule to select the bandwidth of the Gaussian kernel density estimator. This is 1.06 * min(stdev(data), interquartileRange(data) / 1.34) N ^^ 0.2. R must be a forward range of numeric types. 
Classes
Name  Description 

KernelDensity

Construct an Ndimensional kernel density estimator. This is done using the textbook definition of kernel density estimation, since the binning and convolving method used in the 1D case would rapidly become unfeasible w.r.t. memory usage as dimensionality increased. 
KernelDensity1D

Estimates densities in the 1dimensional case. The 1D case is special enough to be treated as a special case, since it's very common and enables some significant optimizations that are otherwise not feasible. 