Add relative strong component size as feature to anomaly detection exploration

Author: JohT

domains/anomaly-detection/explore/AnomalyDetectionIsolationForestExploration.ipynb

@@ -36,7 +36,8 @@
     "| `Normalized Cluster Distance`    | Geometric          | Relative to cluster radius                  | Adds context to position                    |\n",
     "| `1.0 - HDBSCAN membership probability` | Cluster Confidence | How confidently HDBSCAN clustered this node, 1-x inverted | High score = likely anomaly                   |\n",
     "| `Average Cluster Radius`          | Cluster Context    | How tight or spread out the cluster is         | Highly spread clusters may be a less meaningful one   |\n",
-    "| `Abstractness` (Robert C. Martin) | Design / OO Metric | Ratio of abstract types (interfaces, abstract classes) to total types | Indicates architectural intent; supports Dependency Inversion Principle and stability balance |\n"
+    "| `Abstractness` (Robert C. Martin) | Design / OO Metric | Ratio of abstract types (interfaces, abstract classes) to total types | Indicates architectural intent; supports Dependency Inversion Principle and stability balance |\n",
+    "| `Relative Strong Component Size (vs WCC Median)` | Structural / Graph Topology | Size of the node’s strongly connected component normalized by the median SCC size within its weakly connected component | Highlights unusually large cyclic dependency groups relative to local context; high values often indicate architectural tangles or stability issues |\n"
    ]
   },
   {
@@ -210,6 +211,8 @@
     "             ,coalesce(codeUnit.outgoingDependencies, 0) AS outgoingDependencies\n",
     "             ,coalesce(codeUnit.fqn, codeUnit.globalFqn, codeUnit.fileName, codeUnit.signature, codeUnit.name) AS codeUnitName\n",
     "             ,coalesce(artifactName, projectName, \"\")    AS projectName\n",
+    "        OPTIONAL MATCH (codeUnit)-[:IN_STRONGLY_CONNECTED_COMPONENT]->(stronglyConnectedComponent:StronglyConnectedComponent)\n",
+    "        OPTIONAL MATCH (codeUnit)-[:IN_WEAKLY_CONNECTED_COMPONENT]->(weaklyConnectedComponent:WeaklyConnectedComponent)\n",
     "       RETURN DISTINCT \n",
     "              codeUnitName\n",
     "             ,codeUnit.name                                                 AS shortCodeUnitName\n",
@@ -232,6 +235,7 @@
     "             ,codeUnit.clusteringHDBSCANSize                                AS clusterSize\n",
     "             ,codeUnit.clusteringHDBSCANLabel                               AS clusterLabel\n",
     "             ,codeUnit.clusteringHDBSCANMedoid                              AS clusterMedoid\n",
+    "             ,coalesce(stronglyConnectedComponent.size / weaklyConnectedComponent.stronglyConnectedComponentSizePercentile50, 1.0) AS stronglyConnectedComponentSizeRatio\n",
     "             ,codeUnit.embeddingsFastRandomProjectionTunedForClusteringVisualizationX          AS embeddingVisualizationX\n",
     "             ,codeUnit.embeddingsFastRandomProjectionTunedForClusteringVisualizationY          AS embeddingVisualizationY\n",
     "        \"\"\"\n",

domains/anomaly-detection/tunedAnomalyDetectionExplained.py

@@ -255,6 +255,8 @@ def query_data(input_parameters: Parameters = Parameters.example()) -> pd.DataFr
              ,coalesce(codeUnit.outgoingDependencies, 0) AS outgoingDependencies
              ,coalesce(codeUnit.fqn, codeUnit.globalFqn, codeUnit.fileName, codeUnit.signature, codeUnit.name) AS codeUnitName
              ,coalesce(artifactName, projectName, "")    AS projectName
+     OPTIONAL MATCH (codeUnit)-[:IN_STRONGLY_CONNECTED_COMPONENT]->(stronglyConnectedComponent:StronglyConnectedComponent)
+     OPTIONAL MATCH (codeUnit)-[:IN_WEAKLY_CONNECTED_COMPONENT]->(weaklyConnectedComponent:WeaklyConnectedComponent)
        RETURN DISTINCT 
               codeUnitName
              ,codeUnit.name                                                 AS shortCodeUnitName
@@ -277,6 +279,7 @@ def query_data(input_parameters: Parameters = Parameters.example()) -> pd.DataFr
              ,codeUnit.clusteringHDBSCANSize                                AS clusterSize
              ,codeUnit.clusteringHDBSCANLabel                               AS clusterLabel
              ,codeUnit.clusteringHDBSCANMedoid                              AS clusterMedoid
+             ,coalesce(stronglyConnectedComponent.size / weaklyConnectedComponent.stronglyConnectedComponentSizePercentile50, 1.0) AS stronglyConnectedComponentSizeRatio
              ,codeUnit.embeddingsFastRandomProjectionTunedForClusteringVisualizationX          AS embeddingVisualizationX
              ,codeUnit.embeddingsFastRandomProjectionTunedForClusteringVisualizationY          AS embeddingVisualizationY
         """
@@ -500,6 +503,7 @@ def objective(trial) -> float:
     study.enqueue_trial({'isolation_max_samples': 0.42726366840740576, 'isolation_n_estimators': 141, 'proxy_n_estimators': 190, 'proxy_max_depth': 5})
     study.enqueue_trial({'isolation_max_samples': 0.40638732079782663, 'isolation_n_estimators': 108, 'proxy_n_estimators': 191, 'proxy_max_depth': 9})
 
+    study.enqueue_trial({'isolation_max_samples': 0.10105966483207725, 'isolation_n_estimators': 271, 'proxy_n_estimators': 237, 'proxy_max_depth': 9})
     study.enqueue_trial({'isolation_max_samples': 0.10010443935999927, 'isolation_n_estimators': 350, 'proxy_n_estimators': 344, 'proxy_max_depth': 8})
     study.enqueue_trial({'isolation_max_samples': 0.10015063610944819, 'isolation_n_estimators': 329, 'proxy_n_estimators': 314, 'proxy_max_depth': 8})