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 missing values in find_intersections #202

Draft
wants to merge 4 commits into
base: master
Choose a base branch
from
+35 −11
Draft

Support missing values in find_intersections #202

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7588195
empty interval array edge case
haberdashPI Oct 6, 2022
9fc9a3d
fix typo
haberdashPI Oct 6, 2022
c7d534a
review revisions
haberdashPI Oct 11, 2022
7dc3d37
wip: initial implementation sketch
haberdashPI Oct 11, 2022
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
40 changes: 29 additions & 11 deletions src/interval_sets.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,13 +161,19 @@ unbunch_by_fn(_) = identity
function unbunch(
intervals::Union{
AbstractVector{<:AbstractInterval},
Base.Iterators.Enumerate{<:Union{AbstractIntervals, AbstractVector{<:AbstractInterval}}}
Base.Iterators.Enumerate{<:Union{AbstractIntervals,
AbstractVector{<:Union{Missing, AbstractInterval}}}}
},
tracking::EndpointTracking;
lt=isless,
)
by = unbunch_by_fn(intervals)
filtered = Iterators.filter(!isempty ∘ by, intervals)
filtered = Iterators.filter(intervals) do x
let interval = by(x)
ismissing(interval) && return false
return isempty(interval)
end
end
isempty(filtered) && return endpoint_type(tracking)[]
result = mapreduce(x -> unbunch(x, tracking), vcat, filtered)
return sort!(result; lt, by)
Expand All @@ -176,11 +182,12 @@ end
unbunch_by_fn(::Base.Iterators.Enumerate) = last
function unbunch((i, interval)::Tuple, tracking; lt=isless)
eltype = Tuple{Int, endpoint_type(tracking)}
ismissing(interval) && return missing
return eltype[(i, LeftEndpoint(interval)), (i, RightEndpoint(interval))]
end

function unbunch(a::Union{AbstractVector{<:AbstractInterval}, AbstractIntervals},
b::Union{AbstractVector{<:AbstractInterval}, AbstractIntervals}; kwargs...)
function unbunch(a::Union{AbstractVector{<:Union{Missing, AbstractInterval}}, AbstractIntervals},
b::Union{AbstractVector{<:Union{Missing, AbstractInterval}}, AbstractIntervals}; kwargs...)
tracking = endpoint_tracking(a, b)
a_ = unbunch(a, tracking; kwargs...)
b_ = unbunch(b, tracking; kwargs...)
Expand Down Expand Up @@ -469,16 +476,27 @@ function intersection_isless_fn(::TrackEachEndpoint)
end

"""
find_intersections(
x::AbstractVector{<:AbstractInterval},
y::AbstractVector{<:AbstractInterval}
)
find_intersections(x, y; missings=:error)

Returns a `Vector{Vector{Int}}` where the value at index `i` gives the indices to all
intervals in `y` that intersect with `x[i]`.
intervals in `y` that intersect with `x[i]`. Calls collect on the arguments if they
aren't already arrays.

When `missings` == `:error` (the default), `find_intersections` will throw an error
if any values are missing in `x` or `y`. If set to `:skip`, missing values will
be skipped, thus behaving the same way as an interval that does not overlap with any
other interval.
"""
find_intersections(x, y) = find_intersections(vcat(x), vcat(y))
function find_intersections(x::AbstractVector{<:AbstractInterval}, y::AbstractVector{<:AbstractInterval})
find_intersections(x, y; kwargs...) = find_intersections_(collect(x), collect(y); kwargs...)
function find_intersections_(
x::AbstractVector{<:Union{Missing, AbstractInterval}},
y::AbstractVector{<:Union{Missing, AbstractInterval}};
missings=:error
)
(isempty(x) || isempty(y)) && return Vector{Int}[]
if missings ∈ (:error, :skip)
throw(ArgumentError("`missings` should be set to `:error` or `:skip`"))
end
tracking = endpoint_tracking(x, y)
lt = intersection_isless_fn(tracking)
x_endpoints = unbunch(enumerate(x), tracking; lt)
Expand Down
6 changes: 6 additions & 0 deletions test/sets.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,12 @@ end
@test !issubset(11, IntervalSet([1..3, 5..10]))
@test issubset(2, IntervalSet([1.0 .. 3.0, 5.0 .. 10.0]))

@test isempty(find_intersections([], []))
@test_throws ArgumentError find_intersections([1], [2])
@test isempty(find_intersections(Interval[], Interval[]))
@test isempty(find_intersections([1..3], Interval[]))
@test isempty(find_intersections(Interval[], [1..3]))

function testsets(a, b)
@test area(a ∪ b) ≤ area(myunion(a)) + area(myunion(b))
@test area(setdiff(a, b)) ≤ area(myunion(a))
Expand Down