17.2.5 Supported Property Types for Supervised GraphWise Model

The model supports two types of properties for both vertices and edges:

• continuous properties (boolean, double, float, integer, long)
• categorical properties (string)

For categorical properties, two categorical configurations are possible:

• one-hot-encoding: Each category is mapped to a vector, that is concatenated to other features (default)
• embedding table: Each category is mapped to an embedding that is concatenated to other features and is trained along with the model

• JShell
• Java
• Python

opg4j> import oracle.pgx.config.mllib.inputconfig.CategoricalPropertyConfig;
opg4j> var prop1config = analyst.categoricalPropertyConfigBuilder("vertex_str_feature_1").
    oneHotEncoding().
    setMaxVocabularySize(100).
    build()
opg4j> var prop2config = analyst.categoricalPropertyConfigBuilder("vertex_str_feature_2").
    embeddingTable().
    setShared(false). // set whether to share the vocabulary or not when several vertex types have a property with the same name
    setEmbeddingDimension(32).
    setOutOfVocabularyProbability(0.001). // probability to set the word embedding to the out-of-vocabulary embedding
    build()
opg4j> var model = analyst.supervisedGraphWiseModelBuilder().
    setVertexInputPropertyNames(
        "vertex_int_feature_1", // continuous feature
        "vertex_str_feature_1", // string feature using one-hot-encoding
        "vertex_str_feature_2", // string feature using embedding table
        "vertex_str_feature_3" // string feature using one-hot-encoding (default)
    ).
    setVertexTargetPropertyName("label").
    setVertexInputPropertyConfigs(prop1config, prop2config).
    build()

import oracle.pgx.config.mllib.inputconfig.CategoricalPropertyConfig;
import oracle.pgx.config.mllib.inputconfig.InputPropertyConfig;

InputPropertyConfig prop1config = analyst.categoricalPropertyConfigBuilder("vertex_str_feature_1")
    .oneHotEncoding()
    .setMaxVocabularySize(100)
    .build();
InputPropertyConfig prop2config = analyst.categoricalPropertyConfigBuilder("vertex_str_feature_2")
    .embeddingTable()
    .setShared(false) // set whether to share the vocabulary or not when several vertex types have a property with the same name
    .setEmbeddingDimension(32)
    .setOutOfVocabularyProbability(0.001) // probability to set the word embedding to the out-of-vocabulary embedding
    .build();
SupervisedGraphWiseModelBuilder model = analyst.supervisedGraphWiseModelBuilder()
    .setVertexInputPropertyNames(
        "vertex_int_feature_1", // continuous feature
        "vertex_str_feature_1", // string feature using one-hot-encoding
        "vertex_str_feature_2", // string feature using embedding table
        "vertex_str_feature_3" // string feature using one-hot-encoding (default)
    )
    .setVertexInputPropertyConfigs(prop1config, prop2config)
    .setVertexTargetPropertyName("label")
    .build();

vertex_input_property_configs = [
    analyst.one_hot_encoding_categorical_property_config(
        property_name="vertex_str_feature_1",
        max_vocabulary_size=100,
    ),
    analyst.learned_embedding_categorical_property_config(
        property_name="vertex_str_feature_2",
        embedding_dim=4,
        shared=False, // set whether to share the vocabulary or not when several  types have a property with the same name
        oov_probability=0.001 // probability to set the word embedding to the out-of-vocabulary embedding
    )
]

model_params = dict(
    vertex_input_property_names=[
        "vertex_int_feature_1", // continuous feature
        "vertex_str_feature_1", // string feature using one-hot-encoding
        "vertex_str_feature_2", // string feature using embedding table
        "vertex_str_feature_3", // string feature using one-hot-encoding (default)
    ],
    vertex_input_property_configs=vertex_input_property_configs,
    vertex_target_property_name="label"
)

model = analyst.supervised_graphwise_builder(**model_params)