Large tests added

Author: agudys

.github/workflows/large.yml

@@ -0,0 +1,76 @@
+name: Large data CI
+
+on:
+  workflow_dispatch:
+
+jobs:
+
+ ########################################################################################
+  checkout:
+    name: Checkout
+    runs-on: [self-hosted, clusty, x64_linux, large]
+    
+    steps:
+    - name: clean
+      run: rm -rf ${{ github.workspace }}/*
+    - uses: actions/checkout@v4
+      with:
+        submodules: recursive
+    - name: Get tags
+      run: | 
+        cd ./libs/igraph
+        git fetch --prune --unshallow
+        echo exit code $?
+        git tag --list
+      continue-on-error: true
+
+ ########################################################################################
+  make:
+    name: Make
+    needs: checkout
+    strategy:
+      matrix:
+        compiler: [14]
+    runs-on: [self-hosted, clusty, x64_linux, large]
+    
+    steps:
+    - name: make
+      run: gmake -j32 CXX=g++-${{matrix.compiler}} CC=gcc-${{matrix.compiler}} PLATFORM=avx2 LEIDEN=true STATIC_LINK=true
+    - name: print info
+      run: ./bin/clusty --help 
+
+ ########################################################################################
+  clustering:
+    name: clustering
+    needs: make
+    strategy:
+      fail-fast: false
+      matrix:
+        dataset: [ICTV, IMGVR, IMGVR_HQ]
+        algo_name: [single, complete, set-cover, uclust, cd-hit, leiden_07, leiden_10]
+        include:
+        - {dataset: ICTV, variant_name: full, args: '--numeric-ids --similarity --distance-col tani --min tani 0.95'}
+        - {dataset: IMGVR, variant_name: fraction_02, args: '--numeric-ids --similarity --distance-col ani --min ani 0.95 --min qcov 0.85'}
+        - {dataset: IMGVR_HQ, variant_name: full, args: '--numeric-ids --similarity --distance-col ani --min ani 0.95 --min qcov 0.85'}
+        - {algo_name: single, algo_cmd: single}
+        - {algo_name: complete, algo_cmd: complete}
+        - {algo_name: set-cover, algo_cmd: set-cover}
+        - {algo_name: uclust, algo_cmd: uclust}
+        - {algo_name: cd-hit, algo_cmd: cd-hit}
+        - {algo_name: leiden_07, algo_cmd: 'leiden --leiden-resolution 0.7'}
+        - {algo_name: leiden_10, algo_cmd: 'leiden --leiden-resolution 1.0'}
+     
+    env:
+      INPUT_DIR: ../../../../clusty/input
+      TEMP_DIR: ../../../../clusty/temp
+      REF_DIR: ../../../../clusty/ref
+       
+    runs-on: [self-hosted, clusty, x64_linux, large] 
+
+    steps:
+    - name: cluster
+      run: /usr/bin/time -v ./bin/clusty ${INPUT_DIR}/${{ matrix.dataset }}.${{ matrix.variant_name }}.ani.tsv --objects-file ${INPUT_DIR}/${{ matrix.dataset }}.${{ matrix.variant_name }}.ani.ids.tsv ${TEMP_DIR}/${{ matrix.dataset }}.${{ matrix.variant_name }}.${{ matrix.algo_name }}.clusty --algo ${{ matrix.algo_cmd }} ${{ matrix.args }}
+    - name: compare
+      run: cmp ${TEMP_DIR}/${{ matrix.dataset }}.${{ matrix.variant_name }}.${{ matrix.algo_name }}.clusty ${REF_DIR}/${{ matrix.dataset }}.${{ matrix.variant_name }}.${{ matrix.algo_name }}.clusty
+    - name: python compare
+      run: python3 ./test/cmp.py ${TEMP_DIR}/${{ matrix.dataset }}.${{ matrix.variant_name }}.${{ matrix.algo_name }}.clusty ${REF_DIR}/${{ matrix.dataset }}.${{ matrix.variant_name }}.${{ matrix.algo_name }}.clusty