Add topological sort max distance from source for strongly connected components as anomaly detection feature

Author: JohT

domains/anomaly-detection/anomalyDetectionCsv.sh

@@ -80,6 +80,11 @@ anomaly_detection_features() {
     execute_cypher_queries_until_results "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-WeaklyConnectedComponents-Exists.cypher" \
                                          "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-WeaklyConnectedComponents-Write.cypher" "${@}"
     execute_cypher "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-WeaklyConnectedComponents-CreateNode.cypher" "${@}"
+    # Determines topological sort max distance from source for strongly connected components if not already done
+    execute_cypher_queries_until_results "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-TopologicalSortComponents-Exists.cypher" \
+                                         "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-TopologicalSortComponents-Projection.cypher" "${@}"
+    execute_cypher_queries_until_results "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-TopologicalSortComponents-Exists.cypher" \
+                                         "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-TopologicalSortComponents-Write.cypher" "${@}"
 }
 
 # Run queries to find anomalies in the graph.

domains/anomaly-detection/anomalyDetectionPython.sh

@@ -127,6 +127,11 @@ anomaly_detection_features() {
     execute_cypher_queries_until_results "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-WeaklyConnectedComponents-Exists.cypher" \
                                          "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-WeaklyConnectedComponents-Write.cypher" "${@}"
     execute_cypher "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-WeaklyConnectedComponents-CreateNode.cypher" "${@}"
+    # Determines topological sort max distance from source for strongly connected components if not already done
+    execute_cypher_queries_until_results "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-TopologicalSortComponents-Exists.cypher" \
+                                         "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-TopologicalSortComponents-Projection.cypher" "${@}"
+    execute_cypher_queries_until_results "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-TopologicalSortComponents-Exists.cypher" \
+                                         "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-TopologicalSortComponents-Write.cypher" "${@}"
 }
 
 # Execute the Python scripts for anomaly detection.

domains/anomaly-detection/features/AnomalyDetectionFeature-TopologicalSortComponents-Exists.cypher

@@ -0,0 +1,9 @@
+// Return the first node with a "topologicalSortMaxDistanceFromSource" if it exists
+
+   MATCH (component:StronglyConnectedComponent)
+   WHERE $projection_node_label + 'Members' IN labels(component)
+     AND component.topologicalSortMaxDistanceFromSource       IS NOT NULL
+  RETURN component.name                                       AS shortCodeUnitName
+        ,elementId(component)                                 AS nodeElementId
+        ,component.topologicalSortMaxDistanceFromSource       AS topologicalSortMaxDistanceFromSource
+   LIMIT 1

domains/anomaly-detection/features/AnomalyDetectionFeature-TopologicalSortComponents-Projection.cypher

@@ -0,0 +1,10 @@
+// Creates a projection of the strongly connected components graph for the given member type. Requires: "AnomalyDetectionFeature-StronglyConnectedComponents-CreateDependency.cypher"
+
+   MATCH (sourceComponent:StronglyConnectedComponent)
+OPTIONAL MATCH (sourceComponent)-[:DEPENDS_ON]->(targetComponent:StronglyConnectedComponent)
+   WHERE $projection_node_label + 'Members' IN labels(sourceComponent)
+     AND $projection_node_label + 'Members' IN labels(targetComponent)
+    WITH gds.graph.project($projection_name + '-components', sourceComponent, targetComponent) AS graph
+  RETURN graph.graphName         AS graphName
+        ,graph.nodeCount         AS nodeCount
+        ,graph.relationshipCount AS relationshipCount

domains/anomaly-detection/features/AnomalyDetectionFeature-TopologicalSortComponents-Write.cypher

@@ -0,0 +1,14 @@
+// Topological Sort to write the property "topologicalSortMaxDistanceFromSource" (e.g. build order) for strongly connected components into the graph. Requires "AnomalyDetectionFeature-TopologicalSortComponents-Projection".
+// Needs graph-data-science plugin version >= 2.5.0
+
+CALL gds.dag.topologicalSort.stream(
+ $projection_name + '-components', {
+    computeMaxDistanceFromSource: true
+}) YIELD nodeId, maxDistanceFromSource
+   WITH nodeId
+       ,gds.util.asNode(nodeId)           AS component
+       ,toInteger(maxDistanceFromSource)  AS maxDistanceFromSource
+    SET component.topologicalSortMaxDistanceFromSource = maxDistanceFromSource
+   WITH maxDistanceFromSource, count(*) AS occurrences
+ RETURN maxDistanceFromSource, occurrences
+ ORDER BY maxDistanceFromSource