17.2.2 Building a Minimal GraphWise Model

You can build a GraphWise model using the minimal configuration and default hyper-parameters as described in the following code. You can create a model with one of the following options:

• only vertex properties
• only edge properties
• both vertex and edge properties

• JShell
• Java
• Python

opg4j> var model = analyst.supervisedGraphWiseModelBuilder().
                setVertexInputPropertyNames("features").
                setVertexTargetPropertyName("label").
                setEdgeInputPropertyNames("cost").  
                build()

SupervisedGraphWiseModel model = analyst.supervisedGraphWiseModelBuilder()
    .setVertexInputPropertyNames("features")
    .setVertexTargetPropertyName("labels")
    .setEdgeInputPropertyNames("cost")  
    .build();

params = dict(vertex_target_property_name="label",
              edge_input_property_names=["cost"],
              vertex_input_property_names=["features"])

model = analyst.supervised_graphwise_builder(**params)

Note:

Even though only one vertex and one edge property is specified in the preceding example, you can specify a list of vertex or edge properties.