Art Gower

I agree with Fei. Associated Legendre polynomials, and [spherical harmonics](https://en.wikipedia.org/wiki/Spherical_harmonics), are core to so many branches of physics. They involve many connections to other special functions and complicated identities. It...

Agreed we leave `FrequencySimulationResult` alone. For now I've just made ```julia result = run(particles, source, x, ω) ``` as a call to ```julia sim = FrequencySimulation(particles, source) result = run(sim,...

And yes, for discoverability, we should have `run`, or `FrequencySimulation` output the basis order and other needed info. I also think that an adaptive basis order for every particle is...

Thanks Pan, great I'll test out the multiple independent variable capabilities. Afraid I can't help develop much at the moment as am new to nonparametric regression.

Any tips how to adjust the bias/variance trade off for `localconstant(x,y)`? Also guessing that passing `localconstant(x,y; eval=newx)`, will predict the labels for newx right? Also ran into this: ``` julia>n=50...

Thanks @alok, seems like a sensible suggestion. Certainly if we were to add other shapes, or more flexibility in shapes, it seem like relying on Meshes.jl would be good. At...

Much of the inner machinery has now been made more abstract, making it easier to add a new kind of wave, including vectorial waves. Below is a list of functions...

Have a look at the first function in plots.jl. plot(SimulationResult) works, but plot(SimulationResult, linetype=:contour) and plot(SimulationResult, linetype=:field) do not...

I think having a plot, like surface, that takes any x is awesome. But really it needs to be a 2D plot, for quality and to show particles/sources. Compare the...

Here is my suggestion. I know you don't love keywords! But for me this the most useful and intuitive option: - `plot(simres; kws..)` shows line plots, where kws can include...