Merge pull request #49 from aclai-lab/lumen-refactoring

Added support for SolePostHoc and SoleXplorer

what's changed:

- porting from Cirrus to GitHub CI workflow
- Lumen implementation
- clean unused packages and deps
- external packages "DecisiontreeExt" and "XgboostExt" implemented and working
- minor

Author: PasoStudio73

.cirrus.yml

@@ -0,0 +1,7 @@
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"

.github/dependabot.yml

@@ -4,6 +4,22 @@ on:
     types:
       - created
   workflow_dispatch:
+    inputs:
+      lookback:
+        default: "3"
+permissions:
+  actions: read
+  checks: read
+  contents: write
+  deployments: read
+  issues: read
+  discussions: read
+  packages: read
+  pages: read
+  pull-requests: read
+  repository-projects: read
+  security-events: read
+  statuses: read
 jobs:
   TagBot:
     if: github.event_name == 'workflow_dispatch' || github.actor == 'JuliaTagBot'

.github/workflows/TagBot.yml

@@ -1,20 +1,47 @@
-name: Upload coverage reports to Codecov
-on: [push, pull_request]
+name: CI
+on:
+  push:
+    branches:
+      - lumen-refactoring
+    tags: ['*']
+  pull_request:
+  workflow_dispatch:
+concurrency:
+  # Skip intermediate builds: always.
+  # Cancel intermediate builds: only if it is a pull request build.
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ startsWith(github.ref, 'refs/pull/') }}
 jobs:
-  run:
-    runs-on: ubuntu-latest
+  test:
+    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }}
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 60
+    permissions: # needed to allow julia-actions/cache to proactively delete old caches that it has created
+      actions: write
+      contents: read
+    strategy:
+      fail-fast: false
+      matrix:
+        version:
+          - '1'
+          - 'lts'
+          - 'pre'
+        os:
+          - ubuntu-latest
+        arch:
+          - x64
     steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-      - name: Set up Julia 1.9.0
-        uses: julia-actions/setup-julia@v1
+      - uses: actions/checkout@v4
+      - uses: julia-actions/setup-julia@v2
         with:
-          version: "1.9.0"
+          version: ${{ matrix.version }}
+          arch: ${{ matrix.arch }}
+      - uses: julia-actions/cache@v2
       - uses: julia-actions/julia-buildpkg@v1
       - uses: julia-actions/julia-runtest@v1
       - uses: julia-actions/julia-processcoverage@v1
       - uses: codecov/codecov-action@v5
         with:
+          files: lcov.info
           token: ${{ secrets.CODECOV_TOKEN }}
-          slug: aclai-lab/SoleModels.jl
-
+          fail_ci_if_error: false

.github/workflows/ci.yml

@@ -2,33 +2,22 @@ name = "SoleModels"
 uuid = "4249d9c7-3290-4ddd-961c-e1d3ec2467f8"
 license = "MIT"
 authors = ["Michele GHIOTTI", "Giovanni PAGLIARINI", "Edoardo PONSANESI", "Eduard I. STAN"]
-version = "0.10.0"
+version = "0.10.1"
 
 [deps]
 AbstractTrees = "1520ce14-60c1-5f80-bbc7-55ef81b5835c"
-CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
 CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
-DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
 FillArrays = "1a297f60-69ca-5386-bcde-b61e274b549b"
 FunctionWrappers = "069b7b12-0de2-55c6-9aab-29f3d0a68a2e"
-Graphs = "86223c79-3864-5bf0-83f7-82e725a168b6"
-HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
 IterTools = "c8e1da08-722c-5040-9ed9-7db0dc04731e"
 Lazy = "50d2b5c4-7a5e-59d5-8109-a42b560f39c0"
-LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
-Logging = "56ddb016-857b-54e1-b83d-db4d58db5568"
 PrettyTables = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
-ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
 Reexport = "189a3867-3050-52da-a836-e630ba90ab69"
-Revise = "295af30f-e4ad-537b-8983-00126c2a3abe"
 SoleBase = "4475fa32-7023-44a0-aa70-4813b230e492"
 SoleData = "123f1ae1-6307-4526-ab5b-aab3a92a2b8c"
 SoleLogics = "b002da8f-3cb3-4d91-bbe3-2953433912b5"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
-Suppressor = "fd094767-a336-5f1f-9728-57cf17d0bbfb"
-Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 ThreadSafeDicts = "4239201d-c60e-5e0a-9702-85d713665ba7"
-ZipFile = "a5390f91-8eb1-5f08-bee0-b1d1ffed6cea"
 
 [weakdeps]
 DecisionTree = "7806a523-6efd-50cb-b5f6-3fa6f1930dbb"
@@ -40,53 +29,48 @@ XGBoostExt = "XGBoost"
 
 [compat]
 AbstractTrees = "0.4"
-BenchmarkTools = "1"
-CSV = "0.10"
 CategoricalArrays = "0.10"
-DataFrames = "1"
-DataStructures = "0.18"
-DecisionTree = "0.12"
 FillArrays = "1"
 FunctionWrappers = "1"
-Graphs = "1.8"
-HTTP = "1.9"
 IterTools = "1"
-Lazy = "0.15.1"
-MLJ = "0.19 - 0.20"
-MLJBase = "1.6 - 1.7"
-MLJDecisionTreeInterface = "0.4"
-MLJModelInterface = "1.8"
+Lazy = "0.15"
 PrettyTables = "2.2"
-ProgressMeter = "1"
-Random = "1"
 Reexport = "1"
-Revise = "3"
 SoleBase = "0.13"
-SoleData = "0.15, 0.16"
+SoleData = "0.16"
 SoleLogics = "0.13"
 StatsBase = "0.30 - 0.34"
-Suppressor = "0.2"
-Tables = "1"
 ThreadSafeDicts = "0.1"
-XGBoost = "2"
-ZipFile = "0.10"
 julia = "1"
 
 [extras]
-BenchmarkTools = "6e4b80f9-dd63-53aa-95a3-0cdb28fa8baf"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
+DecisionTree = "7806a523-6efd-50cb-b5f6-3fa6f1930dbb"
+Distributed = "8ba89e20-285c-5b6f-9357-94700520ee1b"
 InteractiveUtils = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
 MLJ = "add582a8-e3ab-11e8-2d5e-e98b27df1bc7"
-MLJBase = "a7f614a8-145f-11e9-1d2a-a57a1082229d"
 MLJDecisionTreeInterface = "c6f25543-311c-4c74-83dc-3ea6d1015661"
 MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
 MLJXGBoostInterface = "54119dfa-1dab-4055-a167-80440f4f7a91"
 Markdown = "d6f4376e-aef5-505a-96c1-9c027394607a"
 MultiData = "8cc5100c-b3d1-4f82-90cb-0ea93d317aba"
-PlutoUI = "7f904dfe-b85e-4ff6-b463-dae2292396a8"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
-SoleData = "123f1ae1-6307-4526-ab5b-aab3a92a2b8c"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+XGBoost = "009559a3-9522-5dbb-924b-0b6ed2b22bb9"
 
 [targets]
-test = ["Test", "DataFrames", "Random", "MLJ", "MLJXGBoostInterface", "MultiData", "Markdown", "InteractiveUtils", "BenchmarkTools", "MLJBase", "XGBoost", "DecisionTree", "MLJDecisionTreeInterface", "SoleData"]
+test = [
+    "DataFrames",
+    "DecisionTree",
+    "Distributed",
+    "InteractiveUtils",
+    "MLJ",
+    "MLJDecisionTreeInterface",
+    "MLJModelInterface",
+    "MLJXGBoostInterface",
+    "Markdown",
+    "MultiData",
+    "Random",
+    "Test",
+    "XGBoost"
+]

Project.toml

@@ -51,6 +51,6 @@ Test:
     # Distribution of covered examples for consequent
     # Distribution of examples on which the rule was built
     ✔ Testing parser error @done(24-05-31 11:12)
-
+    ☐ Add test for rule-extraction.jl 
 Questions:
-    ✔ Readmetrics for CN2 statistics @done(24-05-31 11:12)
+    ✔ Readmetrics for CN2 statistics @done(24-05-31 11:12)

TODO.md

@@ -9,7 +9,7 @@ import DecisionTree as DT
 function get_condition(featid, featval, featurenames)
     test_operator = (<)
     # @show fieldnames(typeof(tree))
-    feature = !isnothing(featurenames) ? VariableValue(featurenames[featid]) : VariableValue(featid)
+    feature = isnothing(featurenames) ? VariableValue(featid) : VariableValue(featid, featurenames[featid])
     return ScalarCondition(feature, test_operator, featval)
 end
 
@@ -106,9 +106,16 @@ function SoleModels.solemodel(
     return m
 end
 
-function SoleModels.solemodel(tree::DT.InfoNode; keep_condensed = false, featurenames = true, classlabels = tree.info.classlabels, kwargs...)
+function SoleModels.solemodel(
+    tree::DT.InfoNode{T,orig_O};
+    keep_condensed=false,
+    featurenames=true,
+    # classlabels=tree.info.classlabels,
+    kwargs...
+) where {T,orig_O}
     # @show fieldnames(typeof(tree))
     featurenames = featurenames == true ? tree.info.featurenames : featurenames
+    classlabels = haskey(tree.info, :classlabels) ? tree.info.classlabels : nothing
 
     root, info = begin
         if keep_condensed