CI for GNNGraphs.jl (#451)

CarloLucibello · web-flow · commit 1823e0daf4ea · 2024-07-24T13:01:56.000+02:00
* CI from GNNGraphs.jl

* cleanup

* fix perturb_edges

* fix spelling

* import

* fix runtest

* fix

* workflow
diff --git a/.github/workflows/tests_GNNGraphs.yml b/.github/workflows/tests_GNNGraphs.yml
@@ -0,0 +1,48 @@
+name: GNNGraphs
+on:
+  pull_request:
+    branches:
+      - master
+  push:
+    branches:
+      - master
+jobs:
+  test:
+    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        version:
+          - '1.10' # Replace this with the minimum Julia version that your package supports.
+          - '1' #  '1' will automatically expand to the latest stable 1.x release of Julia.
+          # - 'pre'
+        os:
+          - ubuntu-latest
+        arch:
+          - x64
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: julia-actions/setup-julia@v2
+        with:
+          version: ${{ matrix.version }}
+          arch: ${{ matrix.arch }}
+      - uses: julia-actions/cache@v2
+      - uses: julia-actions/julia-buildpkg@v1
+      - name: Install Julia dependencies and run tests
+        shell: julia --project=monorepo {0}
+        run: |
+          using Pkg
+          # dev mono repo versions
+          pkg"registry up"
+          Pkg.update()
+          pkg"dev ./GNNGraphs"
+          Pkg.test("GNNGraphs"; coverage=true)
+      - uses: julia-actions/julia-processcoverage@v1
+        with:
+          # directories: ./GNNGraphs/src, ./GNNGraphs/ext
+          directories: ./GNNGraphs/src
+      - uses: codecov/codecov-action@v4
+        with:
+          files: lcov.info
diff --git a/.github/workflows/tests_GraphNeuralNetworks.yml b/.github/workflows/tests_GraphNeuralNetworks.yml
@@ -1,4 +1,4 @@
-name: CI
+name: GNN
 on:
   pull_request:
     branches:
@@ -8,15 +8,15 @@ on:
       - master
 jobs:
   test:
-    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }}
+    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }}
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
       matrix:
         version:
-          # - '1.9' # Replace this with the minimum Julia version that your package supports. E.g. if your package requires Julia 1.5 or higher, change this to '1.5'.
-          - '1' # Leave this line unchanged. '1' will automatically expand to the latest stable 1.x release of Julia.
-          - 'nightly'
+          - '1.10' # Replace this with the minimum Julia version that your package supports.
+          - '1' #  '1' will automatically expand to the latest stable 1.x release of Julia.
+          # - 'pre'
         os:
           - ubuntu-latest
         arch:
diff --git a/GNNGraphs/ext/GNNGraphsSimpleWeightedGraphsExt.jl b/GNNGraphs/ext/GNNGraphsSimpleWeightedGraphsExt.jl
diff --git a/GNNGraphs/src/GNNGraphs.jl b/GNNGraphs/src/GNNGraphs.jl
@@ -12,7 +12,7 @@ import KrylovKit
 using ChainRulesCore
 using LinearAlgebra, Random, Statistics
 import MLUtils
-using MLUtils: getobs, numobs, ones_like, zeros_like, chunk, batch
+using MLUtils: getobs, numobs, ones_like, zeros_like, chunk, batch, rand_like
 import Functors
 using LuxDeviceUtils: get_device, cpu_device, LuxCPUDevice
 
@@ -77,6 +77,7 @@ export add_nodes,
        to_bidirected,
        to_unidirected,
        random_walk_pe,
+       perturb_edges,
        remove_nodes,
        ppr_diffusion,
        drop_nodes,
diff --git a/GNNGraphs/src/query.jl b/GNNGraphs/src/query.jl
@@ -349,7 +349,7 @@ function _degree((s, t)::Tuple, T::Type, dir::Symbol, edge_weight::Nothing, num_
 end
 
 function _degree((s, t)::Tuple, T::Type, dir::Symbol, edge_weight::AbstractVector, num_nodes::Int)
-    degs = fill!(similar(s, T, num_nodes), 0)
+    degs = zeros_like(s, T, num_nodes)
 
     if dir ∈ [:out, :both]
         degs = degs .+ NNlib.scatter(+, edge_weight, s, dstsize = (num_nodes,))
diff --git a/GNNGraphs/src/transform.jl b/GNNGraphs/src/transform.jl
@@ -503,6 +503,74 @@ function add_edges(g::GNNHeteroGraph{<:COO_T},
 end
 
 
+"""
+    perturb_edges([rng], g::GNNGraph, perturb_ratio)
+
+Return a new graph obtained from `g` by adding random edges, based on a specified `perturb_ratio`. 
+The `perturb_ratio` determines the fraction of new edges to add relative to the current number of edges in the graph. 
+These new edges are added without creating self-loops. 
+Optionally, a random `seed` can be provided to ensure reproducible perturbations.
+
+The function returns a new `GNNGraph` instance that shares some of the underlying data with `g` but includes the additional edges. 
+The nodes for the new edges are selected randomly, and no edge data (`edata`) or weights (`w`) are assigned to these new edges.
+
+# Arguments
+
+- `g::GNNGraph`: The graph to be perturbed.
+- `perturb_ratio`: The ratio of the number of new edges to add relative to the current number of edges in the graph. For example, a `perturb_ratio` of 0.1 means that 10% of the current number of edges will be added as new random edges.
+- `rng`: An optionalrandom number generator to ensure reproducible results.
+
+# Examples
+
+```julia
+julia> g = GNNGraph((s, t, w))
+GNNGraph:
+  num_nodes: 4
+  num_edges: 5
+
+julia> perturbed_g = perturb_edges(g, 0.2)
+GNNGraph:
+  num_nodes: 4
+  num_edges: 6
+```
+"""
+perturb_edges(g::GNNGraph{<:COO_T}, perturb_ratio::AbstractFloat) = 
+    perturb_edges(Random.default_rng(), g, perturb_ratio)
+
+function perturb_edges(rng::AbstractRNG, g::GNNGraph{<:COO_T}, perturb_ratio::AbstractFloat)
+    @assert perturb_ratio >= 0 && perturb_ratio <= 1 "perturb_ratio must be between 0 and 1"
+
+    num_current_edges = g.num_edges
+    num_edges_to_add = ceil(Int, num_current_edges * perturb_ratio)
+
+    if num_edges_to_add == 0
+        return g
+    end
+
+    num_nodes = g.num_nodes
+    @assert num_nodes > 1 "Graph must contain at least 2 nodes to add edges"
+
+    snew = ceil.(Int, rand_like(rng, ones(num_nodes), Float32, num_edges_to_add) .* num_nodes)
+    tnew = ceil.(Int, rand_like(rng, ones(num_nodes), Float32, num_edges_to_add) .* num_nodes)
+
+    mask_loops = snew .!= tnew
+    snew = snew[mask_loops]
+    tnew = tnew[mask_loops]
+
+    while length(snew) < num_edges_to_add
+        n = num_edges_to_add - length(snew)
+        snewnew = ceil.(Int, rand_like(rng, ones(num_nodes), Float32, n) .* num_nodes)
+        tnewnew = ceil.(Int, rand_like(rng, ones(num_nodes), Float32, n) .* num_nodes)
+        mask_new_loops = snewnew .!= tnewnew
+        snewnew = snewnew[mask_new_loops]
+        tnewnew = tnewnew[mask_new_loops]
+        snew = [snew; snewnew]
+        tnew = [tnew; tnewnew]
+    end
+
+    return add_edges(g, (snew, tnew, nothing))
+end
+
 
 ### TODO Cannot implement this since GNNGraph is immutable (cannot change num_edges). make it mutable
 # function Graphs.add_edge!(g::GNNGraph{<:COO_T}, snew::T, tnew::T; edata=nothing) where T<:Union{Integer, AbstractVector}
diff --git a/GNNGraphs/test/ext/SimpleWeightedGraphs.jl b/GNNGraphs/test/ext/SimpleWeightedGraphs.jl
diff --git a/GNNGraphs/test/runtests.jl b/GNNGraphs/test/runtests.jl
@@ -36,7 +36,7 @@ tests = [
     "sampling",
     "gnnheterograph",
     "temporalsnapshotsgnngraph",
-    "ext/SimpleWeightedGraphs/SimpleWeightedGraphs"
+    "ext/SimpleWeightedGraphs"
 ]
 
 !CUDA.functional() && @warn("CUDA unavailable, not testing GPU support")
@@ -49,7 +49,6 @@ for graph_type in (:coo, :dense, :sparse)
     # global TEST_GPU = false
 
     @testset "$t" for t in tests
-        t == "GNNGraphs/sampling" && GRAPH_T != :coo && continue
         include("$t.jl")
     end
 end
diff --git a/GNNGraphs/test/sampling.jl b/GNNGraphs/test/sampling.jl
@@ -1,46 +1,48 @@
-@testset "sample_neighbors" begin
-    # replace = false
-    dir = :in
-    nodes = 2:3
-    g = rand_graph(10, 40, bidirected = false, graph_type = GRAPH_T)
-    sg = sample_neighbors(g, nodes; dir)
-    @test sg.num_nodes == 10
-    @test sg.num_edges == sum(degree(g, i; dir) for i in nodes)
-    @test size(sg.edata.EID) == (sg.num_edges,)
-    @test length(union(sg.edata.EID)) == length(sg.edata.EID)
-    adjlist = adjacency_list(g; dir)
-    s, t = edge_index(sg)
-    @test all(t .∈ Ref(nodes))
-    for i in nodes
-        @test sort(neighbors(sg, i; dir)) == sort(neighbors(g, i; dir))
-    end
+if GRAPH_T == :coo
+    @testset "sample_neighbors" begin
+        # replace = false
+        dir = :in
+        nodes = 2:3
+        g = rand_graph(10, 40, bidirected = false, graph_type = GRAPH_T)
+        sg = sample_neighbors(g, nodes; dir)
+        @test sg.num_nodes == 10
+        @test sg.num_edges == sum(degree(g, i; dir) for i in nodes)
+        @test size(sg.edata.EID) == (sg.num_edges,)
+        @test length(union(sg.edata.EID)) == length(sg.edata.EID)
+        adjlist = adjacency_list(g; dir)
+        s, t = edge_index(sg)
+        @test all(t .∈ Ref(nodes))
+        for i in nodes
+            @test sort(neighbors(sg, i; dir)) == sort(neighbors(g, i; dir))
+        end
 
-    # replace = true
-    dir = :out
-    nodes = 2:3
-    K = 2
-    g = rand_graph(10, 40, bidirected = false, graph_type = GRAPH_T)
-    sg = sample_neighbors(g, nodes, K; dir, replace = true)
-    @test sg.num_nodes == 10
-    @test sg.num_edges == sum(K for i in nodes)
-    @test size(sg.edata.EID) == (sg.num_edges,)
-    adjlist = adjacency_list(g; dir)
-    s, t = edge_index(sg)
-    @test all(s .∈ Ref(nodes))
-    for i in nodes
-        @test issubset(neighbors(sg, i; dir), adjlist[i])
-    end
+        # replace = true
+        dir = :out
+        nodes = 2:3
+        K = 2
+        g = rand_graph(10, 40, bidirected = false, graph_type = GRAPH_T)
+        sg = sample_neighbors(g, nodes, K; dir, replace = true)
+        @test sg.num_nodes == 10
+        @test sg.num_edges == sum(K for i in nodes)
+        @test size(sg.edata.EID) == (sg.num_edges,)
+        adjlist = adjacency_list(g; dir)
+        s, t = edge_index(sg)
+        @test all(s .∈ Ref(nodes))
+        for i in nodes
+            @test issubset(neighbors(sg, i; dir), adjlist[i])
+        end
 
-    # dropnodes = true
-    dir = :in
-    nodes = 2:3
-    g = rand_graph(10, 40, bidirected = false, graph_type = GRAPH_T)
-    g = GNNGraph(g, ndata = (x1 = rand(10),), edata = (e1 = rand(40),))
-    sg = sample_neighbors(g, nodes; dir, dropnodes = true)
-    @test sg.num_edges == sum(degree(g, i; dir) for i in nodes)
-    @test size(sg.edata.EID) == (sg.num_edges,)
-    @test size(sg.ndata.NID) == (sg.num_nodes,)
-    @test sg.edata.e1 == g.edata.e1[sg.edata.EID]
-    @test sg.ndata.x1 == g.ndata.x1[sg.ndata.NID]
-    @test length(union(sg.ndata.NID)) == length(sg.ndata.NID)
-end
+        # dropnodes = true
+        dir = :in
+        nodes = 2:3
+        g = rand_graph(10, 40, bidirected = false, graph_type = GRAPH_T)
+        g = GNNGraph(g, ndata = (x1 = rand(10),), edata = (e1 = rand(40),))
+        sg = sample_neighbors(g, nodes; dir, dropnodes = true)
+        @test sg.num_edges == sum(degree(g, i; dir) for i in nodes)
+        @test size(sg.edata.EID) == (sg.num_edges,)
+        @test size(sg.ndata.NID) == (sg.num_nodes,)
+        @test sg.edata.e1 == g.edata.e1[sg.edata.EID]
+        @test sg.ndata.x1 == g.ndata.x1[sg.ndata.NID]
+        @test length(union(sg.ndata.NID)) == length(sg.ndata.NID)
+    end
+end
diff --git a/GNNGraphs/test/transform.jl b/GNNGraphs/test/transform.jl
@@ -181,7 +181,7 @@ end
     s, t = [1, 2, 3, 4, 5], [2, 3, 4, 5, 1]
     g = GNNGraph((s, t))
     rng = MersenneTwister(42)
-    g_per = perturb_edges(g, 0.5, rng=rng)
+    g_per = perturb_edges(rng, g, 0.5)
     @test g_per.num_edges == 8
 end end
 
