Debug 05/05/2025 demo (#20)

* Switch to gh runners

* Replace branch to `reduce_install_scope`

* threads -> cores

* Update collector for current dev version

Author: imallona

.github/workflows/benchmark.yml

@@ -49,7 +49,7 @@ jobs:
         shell: bash -l {0}
         run: |
           mamba install -y pip
-          pip install git+https://github.com/omnibenchmark/omnibenchmark.git@dev
+          pip install git+https://github.com/omnibenchmark/omnibenchmark.git@reduce_install_scope
 
       - name: Load benchmark cache
         id: cache-benchmark
@@ -62,7 +62,7 @@ jobs:
         shell: bash -l {0}
         continue-on-error: true
         run: |
-          echo "y" | ob run benchmark -b Clustering.yaml --local --threads 20 --continue-on-error
+          echo "y" | ob run benchmark -b Clustering.yaml --local --cores 3 --continue-on-error
 
   upload-artifact:
     name: Benchmark Artifact

Clustering.yaml

@@ -45,6 +45,7 @@ metric_collectors:
     outputs:
       - id: plotting.html
         path: "{input}/{name}/plotting_report.html"
+
 stages:
   ## clustbench data ##########################################################
 
@@ -139,10 +140,10 @@ stages:
         parameters:
           - values: ["--linkage", "complete"]
           - values: ["--linkage", "ward"]
-          - values: ["--linkage", "average"]
-          - values: ["--linkage", "weighted"]
-          - values: ["--linkage", "median"]
-          - values: ["--linkage", "centroid"]
+          # - values: ["--linkage", "average"]
+          # - values: ["--linkage", "weighted"]
+          # - values: ["--linkage", "median"]
+          # - values: ["--linkage", "centroid"]
       - id: sklearn
         name: "sklearn"
         software_environment: "clustbench"
@@ -154,15 +155,15 @@ stages:
           - values: ["--method", "birch"]
           - values: ["--method", "kmeans"]
           # - values: ["--method", "spectral"] ## too slow
-          - values: ["--method", "gm"]
+          # - values: ["--method", "gm"]
       - id: agglomerative
         name: "agglomerative"
         software_environment: "clustbench"
         repository:
           url: https://github.com/imallona/clustbench_agglomerative
           commit: 5454368
         parameters:
-          - values: ["--linkage", "average"]
+          # - values: ["--linkage", "average"]
           - values: ["--linkage", "complete"]
           - values: ["--linkage", "ward"]
       - id: genieclust
@@ -174,7 +175,7 @@ stages:
         parameters:
           - values: ["--method", "genie", "--gini_threshold", 0.5]
           - values: ["--method", "gic"]
-          - values: ["--method", "ica"]
+          # - values: ["--method", "ica"]
       - id: fcps
         name: "fcps"
         software_environment: "fcps"
@@ -185,15 +186,15 @@ stages:
           # - values: ["--method", "FCPS_AdaptiveDensityPeak"] # not in conda
           - values: ["--method", "FCPS_Minimax"]
           - values: ["--method", "FCPS_MinEnergy"]
-          - values: ["--method", "FCPS_HDBSCAN_2"]
-          - values: ["--method", "FCPS_HDBSCAN_4"]
-          - values: ["--method", "FCPS_HDBSCAN_8"]
-          - values: ["--method", "FCPS_Diana"]
-          - values: ["--method", "FCPS_Fanny"]
-          - values: ["--method", "FCPS_Hardcl"]
-          - values: ["--method", "FCPS_Softcl"]
-          - values: ["--method", "FCPS_Clara"]
-          - values: ["--method", "FCPS_PAM"]
+          # - values: ["--method", "FCPS_HDBSCAN_2"]
+          # - values: ["--method", "FCPS_HDBSCAN_4"]
+          # - values: ["--method", "FCPS_HDBSCAN_8"]
+          # - values: ["--method", "FCPS_Diana"]
+          # - values: ["--method", "FCPS_Fanny"]
+          # - values: ["--method", "FCPS_Hardcl"]
+          # - values: ["--method", "FCPS_Softcl"]
+          # - values: ["--method", "FCPS_Clara"]
+          # - values: ["--method", "FCPS_PAM"]
     inputs:
       - entries:
           - data.matrix
@@ -213,19 +214,19 @@ stages:
         parameters:
           - values: ["--metric", "normalized_clustering_accuracy"]
           - values: ["--metric", "adjusted_fm_score"]
-          - values: ["--metric", "adjusted_mi_score"]
-          - values: ["--metric", "adjusted_rand_score"]
-          - values: ["--metric", "fm_score"]
-          - values: ["--metric", "mi_score"]
-          - values: ["--metric", "normalized_clustering_accuracy"]
-          - values: ["--metric", "normalized_mi_score"]
-          - values: ["--metric", "normalized_pivoted_accuracy"]
-          - values: ["--metric", "pair_sets_index"]
-          - values: ["--metric", "rand_score"]
+          # - values: ["--metric", "adjusted_mi_score"]
+          # - values: ["--metric", "adjusted_rand_score"]
+          # - values: ["--metric", "fm_score"]
+          # - values: ["--metric", "mi_score"]
+          # - values: ["--metric", "normalized_clustering_accuracy"]
+          # - values: ["--metric", "normalized_mi_score"]
+          # - values: ["--metric", "normalized_pivoted_accuracy"]
+          # - values: ["--metric", "pair_sets_index"]
+          # - values: ["--metric", "rand_score"]
     inputs:
       - entries:
           - clustering.predicted_ks_range
           - data.true_labels
     outputs:
       - id: metrics.scores
-        path: "{input}/{stage}/{module}/{params}/{dataset}.scores.gz"
+        path: "{input}/{stage}/{module}/{params}/{dataset}.scores.gz"