Skip to content

Reduce allocations #266

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

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Reduce allocations #266

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
28 changes: 16 additions & 12 deletions src/modelframe.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,22 +53,26 @@ end
_missing_omit(x::AbstractVector{T}) where T = copyto!(similar(x, nonmissingtype(T)), x)
Copy link
Member

Choose a reason for hiding this comment

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

If I recall, the fact that this makes a copy even if T doesn't allow Missing was intentional to ensure that every column gets copied and downstream users of this function can mutate the result without worrying about affecting the original data. If we don't care about that, we can do

Suggested change
_missing_omit(x::AbstractVector{T}) where T = copyto!(similar(x, nonmissingtype(T)), x)
_missing_omit(x::AbstractVector{T}) where {T>:Missing} = copyto!(similar(x, nonmissingtype(T)), x)
_missing_omit(x::AbstractVector{T}) where {T} = x

without needing any other changes.

_missing_omit(x::AbstractVector, rows) = _missing_omit(view(x, rows))

function missing_omit(d::T) where T<:ColumnTable
function _maybe_missing_omit(d::T) where T<:ColumnTable
nonmissings = trues(length(first(d)))
for col in d
_nonmissing!(nonmissings, col)
end
d_nonmissing = if all(nonmissings)
map(_missing_omit, d)
if any(eltype(col) >: Missing for col in d)
for col in d
_nonmissing!(nonmissings, col)
end
d_nonmissing = if all(nonmissings)
map(_missing_omit, d)
else
rows = findall(nonmissings)
map(Base.Fix2(_missing_omit, rows), d)
end
return d_nonmissing, nonmissings
else
rows = findall(nonmissings)
map(Base.Fix2(_missing_omit, rows), d)
return d, nonmissings
end
d_nonmissing, nonmissings
end

missing_omit(data::T, formula::AbstractTerm) where T<:ColumnTable =
missing_omit(NamedTuple{tuple(termvars(formula)...)}(data))
_maybe_missing_omit(data::T, formula::AbstractTerm) where T<:ColumnTable =
_maybe_missing_omit(NamedTuple{tuple(termvars(formula)...)}(data))

function ModelFrame(f::FormulaTerm, data::ColumnTable;
model::Type{M}=StatisticalModel, contrasts=Dict{Symbol,Any}()) where M
Expand All @@ -78,7 +82,7 @@ function ModelFrame(f::FormulaTerm, data::ColumnTable;
throw(ArgumentError(msg))
end

data, _ = missing_omit(data, f)
data, _ = _maybe_missing_omit(data, f)

sch = schema(f, data, contrasts)
f = apply_schema(f, sch, M)
Expand Down
2 changes: 1 addition & 1 deletion src/statsmodel.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,7 +174,7 @@ function StatsBase.predict(mm::TableRegressionModel, data; kwargs...)
throw(ArgumentError("expected data in a Table, got $(typeof(data))"))

f = mm.mf.f
cols, nonmissings = missing_omit(columntable(data), f.rhs)
cols, nonmissings = _maybe_missing_omit(columntable(data), f.rhs)
new_x = modelcols(f.rhs, cols)
y_pred = predict(mm.model, reshape(new_x, size(new_x, 1), :);
kwargs...)
Expand Down