Hi ! I m using the link prediction model for predicting links. I would like to get 2k links only for one node using TopN method. I give the id of the node as follows.
WITH "CALL gds.alpha.ml.pipeline.linkPrediction.predict.stream('POI', {
modelName: 'mylinkpredict_with_embedding',
relationshipTypes: ['RELATION'],
topN: 20000,
threshold: 0.00001,
concurrency: 1
}) YIELD node1, node2, probability
MATCH (n), (m) WHERE id(n) = 4461 AND id(m) = node2 RETURN n.nodeid AS node1, m.nodeid AS node2, probability " AS query
CALL apoc.export.csv.query(query, "result.csv", {}) YIELD file RETURN file;
My concern is that I am not able to see the predicted links as function of distance. I use l2 link combiner and give only latitude as feature.
