Graph Developer's Guide for Property Graph Getting Started with Oracle Property Graphs Using the Machine Learning Library (PgxML) for Graphs Using the Unsupervised GraphWise Algorithm Loading a Graph 8.3.1 Loading a Graph The following describes the steps for loading a graph: Create a Session and an Analyst. JShell Java Python cd /opt/oracle/graph/ ./bin/opg4j // starting the shell will create an implicit session and analyst opg4j> import oracle.pgx.config.mllib.ActivationFunction opg4j> import oracle.pgx.config.mllib.WeightInitScheme opg4j> PgxSession session = Pgx.createSession("my-session") opg4j> Analyst analyst = session.createAnalyst() import oracle.pgx.api.*; import oracle.pgx.api.mllib.UnsupervisedGraphWiseModel; import oracle.pgx.api.frames.*; import oracle.pgx.config.mllib.ActivationFunction; import oracle.pgx.config.mllib.GraphWiseConvLayerConfig; import oracle.pgx.config.mllib.UnsupervisedGraphWiseModelConfig; import oracle.pgx.config.mllib.WeightInitScheme; PgxSession session = Pgx.createSession("my-session"); Analyst analyst = session.createAnalyst(); session = pypgx.get_session() analyst = session.analyst Load the graph. JShell Java Python opg4j> var graph = session.readGraphWithProperties("<path/to/graph_config.json>") PgxGraph graph = session.readGraphWithProperties("<path/to/graph_config.json>"); graph = session.read_graph_with_properties("<path/to/graph_config.json>") You do not need to use a test graph or test vertices, since the model is trained to be unsupervised. Parent topic: Using the Unsupervised GraphWise Algorithm