Icon

Nashville_​meetup_​demo_​batch_​mode

Neo4j graph embeddings for ML (batch mode)

The workflow describes a simple use case how Neo4j Graph Data Science and Knime algorithms can be used together.

Populating graph Graph cleaning Feature engineering and labeling Analysis The workflow describes a simple use case how Neo4j GraphData Science and Knime algorithms can be used together.Data used in the example is based on a Nashville MeetupNetwork data set from Kaggle:https://www.kaggle.com/stkbailey/nashville-meetup Connect tothe databaseCleaining existing data(optional)Fill inmissing valuesCreate edgesCreate indexon GroupCreate indexon MemberCreate memory graphRemove existing memory graph(optional)Train/Test70/30Trainbased on embeddingsPredictEstimatepredictionsColorby labelClassifybased on embeddingsEmbeddingsSAGEPageRankBetweennesscentralityEigenVectorcentralityEstimatepredictionsPlot by labelExtractingfeaturesDimensionalityreductionEmbeddingsas propertiesUnwindembeddingsmeta-groups.csvmeta-members.csvmember-to-group-edges.csvSelect features for kNNTrain/Test70/30Node 20995Node 20996Delete model(optional)Neo4j Connection Neo4j Writer Missing Value Neo4j Writer Neo4j Writer Neo4j Writer Neo4j Writer Neo4j Reader Partitioning Random ForestLearner Random ForestPredictor Scorer Color Manager K Nearest Neighbor Neo4j Writer Neo4j Writer Neo4j Writer Neo4j Writer Scorer 3D ScatterPlot (Plotly) Neo4j Reader t-SNE (L. Jonsson) Neo4j Writer Split CollectionColumn Labeling members CSV Reader CSV Reader CSV Reader Column Filter Partitioning Neo4j Writer Neo4j Writer Neo4j Writer Model scoring Populating graph Graph cleaning Feature engineering and labeling Analysis The workflow describes a simple use case how Neo4j GraphData Science and Knime algorithms can be used together.Data used in the example is based on a Nashville MeetupNetwork data set from Kaggle:https://www.kaggle.com/stkbailey/nashville-meetup Connect tothe databaseCleaining existing data(optional)Fill inmissing valuesCreate edgesCreate indexon GroupCreate indexon MemberCreate memory graphRemove existing memory graph(optional)Train/Test70/30Trainbased on embeddingsPredictEstimatepredictionsColorby labelClassifybased on embeddingsEmbeddingsSAGEPageRankBetweennesscentralityEigenVectorcentralityEstimatepredictionsPlot by labelExtractingfeaturesDimensionalityreductionEmbeddingsas propertiesUnwindembeddingsmeta-groups.csvmeta-members.csvmember-to-group-edges.csvSelect features for kNNTrain/Test70/30Node 20995Node 20996Delete model(optional)Neo4j Connection Neo4j Writer Missing Value Neo4j Writer Neo4j Writer Neo4j Writer Neo4j Writer Neo4j Reader Partitioning Random ForestLearner Random ForestPredictor Scorer Color Manager K Nearest Neighbor Neo4j Writer Neo4j Writer Neo4j Writer Neo4j Writer Scorer 3D ScatterPlot (Plotly) Neo4j Reader t-SNE (L. Jonsson) Neo4j Writer Split CollectionColumn Labeling members CSV Reader CSV Reader CSV Reader Column Filter Partitioning Neo4j Writer Neo4j Writer Neo4j Writer Model scoring

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: artem
Created at: 2021-11-26
On NodePit since: 2022-07-27
Last update: 2024-04-27
Created with KNIME version: v4.6.1
Tags: Neo4jGraphEmbeddingsNetwork analysisRedfield

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!