Improve Node Embeddings

conda-environment.yml

@@ -15,8 +15,6 @@ dependencies:
   - pandas=2.2.3
   - pip=25.0.1
   - setuptools=80.9.0 # opentsne uses sklearn.base uses joblib uses distutils missing in Python >= 12 (TODO use native openTSNE?) 
-  - typing-extensions=4.15.0 # Also needed for opentsne and Python >= 3.12
-  - opentsne=1.0.4 # to visualize node embeddings in 2D (t-SNE dimensionality reduction)
   - wordcloud=1.9.4
   - monotonic=1.6
   - plotly=6.5.0

cypher/Node_Embeddings/Node_Embeddings_0b_Prepare_Degree.cypher

@@ -0,0 +1,28 @@
+// Node Embeddings 0b: Prepare: Calculate Degree Property.
+
+CALL gds.degree.mutate(
+ $dependencies_projection + '-cleaned', {
+   orientation: 'UNDIRECTED'
+  ,relationshipWeightProperty: CASE $dependencies_projection_weight_property WHEN '' THEN null ELSE $dependencies_projection_weight_property END
+  ,mutateProperty: 'degreeForNodeEmbeddings'
+})
+ YIELD nodePropertiesWritten
+      ,preProcessingMillis
+      ,computeMillis
+      ,mutateMillis
+      ,postProcessingMillis
+      ,centralityDistribution
+RETURN nodePropertiesWritten
+      ,preProcessingMillis
+      ,computeMillis
+      ,mutateMillis
+      ,postProcessingMillis
+      ,centralityDistribution.min
+      ,centralityDistribution.mean
+      ,centralityDistribution.max
+      ,centralityDistribution.p50
+      ,centralityDistribution.p75
+      ,centralityDistribution.p90
+      ,centralityDistribution.p95
+      ,centralityDistribution.p99
+      ,centralityDistribution.p999

cypher/Node_Embeddings/Node_Embeddings_0c_Drop_Model.cypher

@@ -0,0 +1,21 @@
+// Node Embeddings 0b: Prepare: Calculate Degree Property.
+
+CALL gds.model.drop($dependencies_projection + '-graphSAGE', false)
+YIELD modelName,
+      modelType,
+      modelInfo,
+      creationTime,
+      trainConfig,
+      graphSchema,
+      loaded,
+      stored,
+      published
+RETURN modelName,
+       modelType,
+       modelInfo,
+       creationTime,
+       trainConfig,
+       graphSchema,
+       loaded,
+       stored,
+       published

cypher/Node_Embeddings/Node_Embeddings_4b_GraphSAGE_Train.cypher

@@ -0,0 +1,27 @@
+// Node Embeddings 4c using GraphSAGE (Graph Neural Networks): Train. Requires: "Node_Embeddings_0b_Prepare_Degree.cypher".
+
+CALL gds.beta.graphSage.train(
+ $dependencies_projection + '-cleaned', {
+      modelName: $dependencies_projection + '-graphSAGE'
+     ,featureProperties: ['degreeForNodeEmbeddings']
+     ,embeddingDimension: toInteger($dependencies_projection_embedding_dimension)
+     ,relationshipWeightProperty: CASE $dependencies_projection_weight_property WHEN '' THEN null ELSE $dependencies_projection_weight_property END
+     ,batchSize: 64
+     ,activationFunction: 'relu'
+     ,sampleSizes: [25, 20, 20, 10]
+     //,aggregator: 'pool'
+     //,epochs: 10
+     //,penaltyL2: 0.0000001
+     //,tolerance: 0.0001
+     //,learningRate: 0.1
+     //,searchDepth: 5
+     ,randomSeed: 47
+  }
+)
+YIELD modelInfo AS info, trainMillis
+RETURN
+  info.modelName           AS modelName,
+  info.metrics.didConverge AS didConverge,
+  info.metrics.ranEpochs   AS ranEpochs,
+  info.metrics.epochLosses AS epochLosses,
+  trainMillis              AS trainingTimeMilliseconds

cypher/Node_Embeddings/Node_Embeddings_4d_GraphSAGE_Stream.cypher

@@ -0,0 +1,22 @@
+// Node Embeddings 4d using GraphSAGE: Stream. Requires "Add_file_name and_extension.cypher".
+
+CALL gds.beta.graphSage.stream(
+ $dependencies_projection + '-cleaned', {
+      modelName: $dependencies_projection + '-graphSAGE'
+  }
+)
+YIELD nodeId, embedding
+ WITH gds.util.asNode(nodeId) AS codeUnit
+     ,embedding
+OPTIONAL MATCH (artifact:Java:Artifact)-[:CONTAINS]->(codeUnit)
+   WITH *, artifact.name AS artifactName
+OPTIONAL MATCH (projectRoot:Directory)<-[:HAS_ROOT]-(proj:TS:Project)-[:CONTAINS]->(codeUnit)
+   WITH *, last(split(projectRoot.absoluteFileName, '/')) AS projectName   
+ RETURN DISTINCT 
+        coalesce(codeUnit.fqn, codeUnit.globalFqn, codeUnit.fileName, codeUnit.signature, codeUnit.name) AS codeUnitName
+       ,codeUnit.name                               AS shortCodeUnitName
+       ,elementId(codeUnit)                         AS nodeElementId
+       ,coalesce(artifactName, projectName)         AS projectName
+       ,coalesce(codeUnit.communityLeidenId, 0)     AS communityId
+       ,coalesce(codeUnit.centralityPageRank, 0.01) AS centrality
+       ,embedding