Added plots for the README

Author: theogf

README.md

@@ -8,12 +8,35 @@ KernelFunctions.jl provide a flexible and complete framework for kernel function
 
 The aim is to make the API as model-agnostic as possible while still being user-friendly.
 
+## Examples
+
+```julia
+  X = reshape(collect(range(-3.0,3.0,length=100)),:,1)
+  # Set simple scaling of the data
+  k₁ = SqExponentialKernel(1.0)
+  K₁ = kernelmatrix(k,X,obsdim=1)
+
+  # Set a function transformation on the data
+  k₂ = MaternKernel(FunctionTransform(x->sin.(x)))
+  K₂ = kernelmatrix(k,X,obsdim=1)
+
+  # Set a matrix premultiplication on the data
+  k₃ = PolynomialKernel(LowRankTransform(randn(4,1)),0.0,2.0)
+  K₃ = kernelmatrix(k,X,obsdim=1)
+
+  # Add and sum kernels
+  k₄ = 0.5*SqExponentialKernel()*LinearKernel(0.5) + 0.4*k₂
+  K₄ = kernelmatrix(k,X,obsdim=1)
+
+  heatmap([K₁,K₂,K₃,K₄],yflip=false,colorbar=false)
+```
+<p align=center>
+  <img src="docs/src/assets/heatmap_combination.png" width=400px>
+</p>
+
 ## Objectives (by priority)
-- ARD Kernels
-- AD Compatible (Zygote, ForwardDiff, ReverseDiff)
-- Kernel sum and product
+- AD Compatibility (Zygote, ForwardDiff)
 - Toeplitz Matrices
 - BLAS backend
 
-
-Directly inspired by the [MLKernels](https://github.com/trthatcher/MLKernels.jl) package
+Directly inspired by the [MLKernels](https://github.com/trthatcher/MLKernels.jl) package.

docs/.gitignore

@@ -1,5 +1,4 @@
 build/
 site/
-src/assets/*.png
 
 #Temp to avoid to many changes

docs/create_kernel_plots.jl

@@ -10,6 +10,33 @@ x₀ = 0.0; l=0.1
 n_grid = 101
 fill(x₀,n_grid,1)
 xrange = reshape(collect(range(-3,3,length=n_grid)),:,1)
+
+k = SqExponentialKernel(1.0)
+K1 = kernelmatrix(k,xrange,obsdim=1)
+p = heatmap(K1,yflip=true,colorbar=false,framestyle=:none,background_color=RGBA(0.0,0.0,0.0,0.0))
+savefig(joinpath(@__DIR__,"src","assets","heatmap_sqexp.png"))
+
+
+k = Matern32Kernel(FunctionTransform(x->(sin.(x)).^2))
+K2 = kernelmatrix(k,xrange,obsdim=1)
+p = heatmap(K2,yflip=true,colorbar=false,framestyle=:none,background_color=RGBA(0.0,0.0,0.0,0.0))
+savefig(joinpath(@__DIR__,"src","assets","heatmap_matern.png"))
+
+
+k = PolynomialKernel(LowRankTransform(randn(3,1)),2.0,0.0)
+K3 = kernelmatrix(k,xrange,obsdim=1)
+p = heatmap(K3,yflip=true,colorbar=false,framestyle=:none,background_color=RGBA(0.0,0.0,0.0,0.0))
+savefig(joinpath(@__DIR__,"src","assets","heatmap_poly.png"))
+
+k = 0.5*SqExponentialKernel()*LinearKernel(0.5) + 0.4*Matern32Kernel(FunctionTransform(x->sin.(x)))
+K4 = kernelmatrix(k,xrange,obsdim=1)
+p = heatmap(K4,yflip=true,colorbar=false,framestyle=:none,background_color=RGBA(0.0,0.0,0.0,0.0))
+savefig(joinpath(@__DIR__,"src","assets","heatmap_prodsum.png"))
+
+plot(heatmap.([K1,K2,K3,K4],yflip=true,colorbar=false)...,layout=(2,2))
+savefig(joinpath(@__DIR__,"src","assets","heatmap_combination.png"))
+
+
 for k in [SqExponentialKernel,ExponentialKernel]
     K = kernelmatrix(k(),xrange,obsdim=1)
     v = rand(MvNormal(K+1e-7I))

docs/src/assets/heatmap_combination.png

@@ -25,7 +25,8 @@ Base.:+(k1::Kernel,k2::Kernel) = KernelSum([k1,k2],weights=[1.0,1.0])
 Base.:+(k1::KernelSum,k2::KernelSum) = KernelSum(vcat(k1.kernels,k2.kernels),weights=vcat(k1.weights,k2.weights))
 Base.:+(k::Kernel,ks::KernelSum) = KernelSum(vcat(k,ks.kernels),weights=vcat(1.0,ks.weights))
 Base.:+(ks::KernelSum,k::Kernel) = KernelSum(vcat(ks.kernels,k),weights=vcat(ks.weights,1.0))
-Base.:*(w::Real,k::Kernel) = KernelSum([k],[w]) #TODO add tests
+Base.:*(w::Real,k::Kernel) = KernelSum([k],weights=[w]) #TODO add tests
+Base.:*(w::Real,k::KernelSum) = KernelSum(k.kernels,weights=w*k.weights) #TODO add tests
 
 
 Base.length(k::KernelSum) = length(k.kernels)

docs/src/assets/heatmap_matern.png

@@ -87,7 +87,7 @@ function kernelmatrix(
         obsdim=defaultobs
     )
     if !check_dims(X,Y,feature_dim(obsdim),obsdim)
-        throw(DimensionMismatch("X ($(size(X))) and Y ($(size(Y))) do not have the same number of features on the dimension obsdim : $(feature_dim(obsdim))"))
+        throw(DimensionMismatch("X $(size(X)) and Y $(size(Y)) do not have the same number of features on the dimension : $(feature_dim(obsdim))"))
     end
     _kernelmatrix(κ,X,Y,obsdim)
 end