Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support multivariate kNN regression #327

Closed
wants to merge 7 commits into from
Closed

Support multivariate kNN regression #327

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a4c8610
support multivariate kNN regression
mateuszbaran Oct 19, 2020
0b8c3bd
updated target of kNN regressor
mateuszbaran Oct 20, 2020
865a352
changing target of KNNRegressor
mateuszbaran Oct 20, 2020
3062a05
target of kNN regressor again
mateuszbaran Oct 20, 2020
e52ea0a
trying to make the multi-target kNN regressor work with tables
mateuszbaran Oct 21, 2020
a794ade
fixing kNN regressor
mateuszbaran Oct 21, 2020
6f28040
code review fixes
mateuszbaran Oct 22, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 20 additions & 6 deletions src/NearestNeighbors.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,26 +128,40 @@ end
function MMI.predict(m::KNNRegressor, (tree, y, w), X)
Xmatrix = MMI.matrix(X, transpose=true) # NOTE: copies the data
idxs, dists = NN.knn(tree, Xmatrix, m.K)
preds = similar(y, length(idxs))

if typeof(y) <: AbstractVector
ymat = reshape(y, length(y), 1)
preds = similar(ymat, length(idxs), 1)
else # for multi-target prediction
ymat = MMI.matrix(y)
preds = similar(ymat, length(idxs), size(ymat, 2))
end

ablaom marked this conversation as resolved.
Show resolved Hide resolved
w_ = ones(m.K)

for i in eachindex(idxs)
idxs_ = idxs[i]
println(idxs_)
dists_ = dists[i]
values = y[idxs_]
values = [ymat[j,:] for j in idxs_]
if w !== nothing
w_ = w[idxs_]
end
println(preds)
if m.weights == :uniform
preds[i] = sum(values .* w_) / sum(w_)
preds[i,:] .= sum(values .* w_) / sum(w_)
else
preds[i] = sum(values .* w_ .* (1.0 .- dists_ ./ sum(dists_))) / (sum(w_) - 1)
preds[i,:] .= sum(values .* w_ .* (1.0 .- dists_ ./ sum(dists_))) / (sum(w_) - 1)
end
end
return preds
if typeof(x) <: AbstractArray
return preds
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Correct but probably less confusing (and future-proof) to use if typeof(y) <: AbstractVector.

else
return MMI.table(preds, names=Tables.schema(y).names, prototype=y)
end
end


# ====

metadata_pkg.((KNNRegressor, KNNClassifier),
Expand All @@ -161,7 +175,7 @@ metadata_pkg.((KNNRegressor, KNNClassifier),

metadata_model(KNNRegressor,
input = Table(Continuous),
target = Union{AbstractVector{Continuous}, AbstractVector{<:AbstractArray{Continuous}}},
target = Union{AbstractVector{Continuous}, Table{Continuous}},
weights = true,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Table(Continuous) instead of Table{Continuous} https://github.com/alan-turing-institute/ScientificTypes.jl#more-on-the-table-type

descr = KNNRegressorDescription
)
Expand Down
16 changes: 7 additions & 9 deletions test/NearestNeighbors.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,21 +109,19 @@ p2 = predict(knnr, f2, xtest)
@test all(p[ntest+1:2*ntest] .≈ 2.0)
@test all(p[2*ntest+1:end] .≈ -2.0)

y1v = fill( [0.0], n)
y2v = fill( [2.0], n)
y3v = fill([-2.0], n)

yv = vcat(y1v, y2v, y3v)
ymat = vcat(fill( 0.0, n, 2), fill(2.0, n, 2), fill(-2.0, n, 2))
yv = Tables.table(ymat; header = [:a, :b])

fv,_,_ = fit(knnr, 1, x, yv)
f2v,_,_ = fit(knnr, 1, x, yv, w)

pv = predict(knnr, fv, xtest)

@test all(pv[1:ntest] .≈ [[0.0]])
@test all(pv[ntest+1:2*ntest] .≈ [[2.0]])
@test all(pv[2*ntest+1:end] .≈ [[-2.0]])

for col in [:a, :b]
@test all(pv[col][1:ntest] .≈ [0.0])
@test all(pv[col][ntest+1:2*ntest] .≈ [2.0])
@test all(pv[col][2*ntest+1:end] .≈ [-2.0])
end



Expand Down