Merge pull request #21 from JuliaAI/dev

For a 0.1.2 release

Author: ablaom

Project.toml

@@ -1,7 +1,7 @@
 name = "MLJParticleSwarmOptimization"
 uuid = "17a086e9-ed03-4f30-ab88-8b63f0f6126c"
 authors = ["Long Nguyen <[email protected]> and contributors"]
-version = "0.1.1"
+version = "0.1.2"
 
 [deps]
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
@@ -12,6 +12,6 @@ Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 
 [compat]
 Distributions = "0.25"
-MLJBase = "0.18"
-MLJTuning = "0.6.11"
+MLJBase = "0.18, 0.19, 0.20"
+MLJTuning = "0.6, 0.7"
 julia = "1.4"

test/parameters.jl

@@ -92,11 +92,10 @@
         ranges = [r1, (r2, Uniform), (r3, d3), r4]
         state = PSO.initialize(rng, ranges, n)
         PSO.retrieve!(rng, state)
-        @test state.parameters == (
-            ["a", "a", "c"],
-            [553, 250, 375],
-            [3.9372495283243105, 3.6569395920512977, 3.6354556967115146],
-            [-0.8067647f0, 0.4209916f0, 0.6736019f0]
-        )
+        params =  state.parameters
+        @test params[1] == ["a", "a", "c"]
+        @test params[2] ≈  [553, 250, 375]
+        @test params[3] ≈  [3.9372495283243105, 3.6569395920512977, 3.6354556967115146]
+        @test params[4] ≈ [-0.8067647f0, 0.4209916f0, 0.6736019f0]
     end
-end
+end

test/strategies/adaptive.jl

@@ -75,7 +75,10 @@ end
     @test c2 ≥ 1.8 # increase social
 end
 
-for acceleration in (CPU1(), CPUProcesses(), CPUThreads())
+const losses = []
+const modes = [CPU1(), CPUProcesses(), CPUThreads()]
+
+for acceleration in modes
     @testset "EvoTree Tuning with AdaptiveParticleSwarm and $(typeof(acceleration))" begin
         rng = StableRNG(123)
         features = rand(rng, 10_000) .* 5 .- 2
@@ -115,9 +118,14 @@ for acceleration in (CPU1(), CPUProcesses(), CPUThreads())
         fit!(mach, verbosity=0)
         rep = report(mach)
         best_loss = rep.best_history_entry.measurement[1]
+        push!(losses, best_loss)
+
+        # There is no reason to expect PSO to be better than
+        # RandomSearch, but they should give similar results, say within 10%:
 
-        # Compare with random search result with the same settings
-        @test best_loss < baseline_best_loss ||
-              isapprox(best_loss, baseline_best_loss; atol=1e-3)
+        @test abs(best_loss/baseline_best_loss - 1) < 0.1
     end
-end
+end
+
+println("Adaptive PSO losses (see Issue #14):")
+(; modes=modes, losses=losses) |> MLJBase.pretty