oracle.pgx.api.mllib

Class SupervisedEdgeWiseModel

java.lang.Object

oracle.pgx.api.mllib.Model<ModelType>

oracle.pgx.api.mllib.EdgeWiseModel<SupervisedEdgeWiseModelConfig,oracle.pgx.api.internal.mllib.SupervisedEdgeWiseModelMetadata,SupervisedEdgeWiseModel>

oracle.pgx.api.mllib.SupervisedEdgeWiseModel

All Implemented Interfaces:

java.lang.AutoCloseable

public class SupervisedEdgeWiseModel
extends EdgeWiseModel<SupervisedEdgeWiseModelConfig,oracle.pgx.api.internal.mllib.SupervisedEdgeWiseModelMetadata,SupervisedEdgeWiseModel>

A variant of GraphSAGE working on edges. See SupervisedEdgeWiseModelBuilder for documentation of the hyperparameters.

Since:

23.1

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	SupervisedEdgeWiseModel.SupervisedEdgeWiseInferenceType

Field Summary

Fields

Modifier and Type	Field and Description
static java.lang.String	ALGORITHM_NAME

Constructor Summary

Constructors

Constructor and Description
SupervisedEdgeWiseModel(PgxSession session, oracle.pgx.api.internal.Core core, java.util.function.Supplier<java.lang.String> keystorePathSupplier, java.util.function.Supplier<char[]> keystorePasswordSupplier, java.util.function.BiFunction<PgxSession,oracle.pgx.api.internal.Graph,PgxGraph> graphConstructor, oracle.pgx.api.internal.mllib.ModelMetadata modelMetadata)
SupervisedEdgeWiseModel(PgxSession session, oracle.pgx.api.internal.Core core, java.util.function.Supplier<java.lang.String> keystorePathSupplier, java.util.function.Supplier<char[]> keystorePasswordSupplier, java.util.function.BiFunction<PgxSession,oracle.pgx.api.internal.Graph,PgxGraph> graphConstructor, oracle.pgx.api.internal.mllib.SupervisedEdgeWiseModelMetadata modelMetadata) This constructor should never be used to get a model.

Method Summary

Modifier and Type	Method and Description
PgxFrame	evaluate(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Blocking version of evaluateAsync(PgxGraph, Iterable).
PgxFrame	evaluate(PgxGraph graph, java.lang.Iterable<PgxEdge> edges, float threshold) Blocking version of evaluateAsync(PgxGraph, Iterable, float).
PgxFuture<PgxFrame>	evaluateAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Evaluates performance statistics for the specified edges.
PgxFuture<PgxFrame>	evaluateAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges, float threshold) Evaluates performance statistics for the specified vertices.
PgxFrame	evaluateLabels(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Blocking version of evaluateLabelsAsync(PgxGraph, Iterable).
PgxFrame	evaluateLabels(PgxGraph graph, java.lang.Iterable<PgxEdge> edges, float threshold) Blocking version of evaluateLabelsAsync(PgxGraph, Iterable, float).
PgxFuture<PgxFrame>	evaluateLabelsAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Evaluates (macro averaged) classification performance statistics for the specified edges.
PgxFuture<PgxFrame>	evaluateLabelsAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges, float threshold) Evaluates (macro averaged) classification performance statistics for the specified vertices.
PgxFuture<java.lang.Double>	fitAsync(PgxGraph graph) Trains the EdgeWise model on the input graph.
java.util.Map<?,java.lang.Float>	getClassWeights() Gets the class weights
java.lang.String	getEdgeTargetPropertyName() Gets the edge target property name
LossFunction	getLossFunctionClass() Gets the loss function
GraphWisePredictionLayerConfig[]	getPredictionLayerConfigs() Gets the configuration objects for the prediction layers
java.util.List<java.util.Set<java.lang.String>>	getTargetEdgeLabels() Gets the target vertex labels
PgxFrame	infer(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Blocking version of inferAsync(PgxGraph, Iterable).
PgxFrame	infer(PgxGraph graph, java.lang.Iterable<PgxEdge> edges, float threshold) Blocking version of inferAsync(PgxGraph, Iterable, float).
PgxFuture<PgxFrame>	inferAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Does inference for the specified edges.
PgxFuture<PgxFrame>	inferAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges, float threshold) Does the inference for the specified edges.
PgxFuture<PgxFrame>	inferEmbeddingsAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Infers the embeddings for the specified edges.
PgxFrame	inferLabels(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Blocking version of inferLabelsAsync(PgxGraph, Iterable).
PgxFrame	inferLabels(PgxGraph graph, java.lang.Iterable<PgxEdge> edges, float threshold) Blocking version of inferLabelsAsync(PgxGraph, Iterable, float).
PgxFuture<PgxFrame>	inferLabelsAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Infers the labels for the specified edges.
PgxFuture<PgxFrame>	inferLabelsAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges, float threshold) Infers the labels for the specified edges.
PgxFrame	inferLogits(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Blocking version of inferLogitsAsync(PgxGraph, Iterable).
PgxFuture<PgxFrame>	inferLogitsAsync(PgxGraph graph, java.lang.Iterable<PgxEdge> edges) Infers the prediction logits for the specified edges.
void	store(java.lang.String path, java.lang.String key) Blocking version of storeAsync(String, String).
void	store(java.lang.String path, java.lang.String key, boolean overwrite) Blocking version of storeAsync(String, String).
PgxFuture<java.lang.Void>	storeAsync(java.lang.String path, java.lang.String key) Stores the GraphWise model in the specified path, with encryption.
PgxFuture<java.lang.Void>	storeAsync(java.lang.String path, java.lang.String key, boolean overwrite) Stores the GraphWise model in the specified path, with encryption.

Methods inherited from class oracle.pgx.api.mllib.EdgeWiseModel

destroy, destroyAsync, fit, getBatchSize, getConfig, getConvLayerConfigs, getEdgeCombinationMethod, getEdgeInputFeatureDim, getEdgeInputPropertyNames, getEmbeddingDim, getInputFeatureDim, getLearningRate, getNumEpochs, getSeed, getTrainingLoss, getVertexInputPropertyNames, inferEmbeddings, isFitted

Methods inherited from class oracle.pgx.api.mllib.Model

close, export

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

ALGORITHM_NAME

public static final java.lang.String ALGORITHM_NAME

See Also:

Constant Field Values

Constructor Detail

SupervisedEdgeWiseModel

public SupervisedEdgeWiseModel(PgxSession session,
                               oracle.pgx.api.internal.Core core,
                               java.util.function.Supplier<java.lang.String> keystorePathSupplier,
                               java.util.function.Supplier<char[]> keystorePasswordSupplier,
                               java.util.function.BiFunction<PgxSession,oracle.pgx.api.internal.Graph,PgxGraph> graphConstructor,
                               oracle.pgx.api.internal.mllib.ModelMetadata modelMetadata)

SupervisedEdgeWiseModel

public SupervisedEdgeWiseModel(PgxSession session,
                               oracle.pgx.api.internal.Core core,
                               java.util.function.Supplier<java.lang.String> keystorePathSupplier,
                               java.util.function.Supplier<char[]> keystorePasswordSupplier,
                               java.util.function.BiFunction<PgxSession,oracle.pgx.api.internal.Graph,PgxGraph> graphConstructor,
                               oracle.pgx.api.internal.mllib.SupervisedEdgeWiseModelMetadata modelMetadata)

This constructor should never be used to get a model. Use SupervisedEdgeWiseModelBuilder instead.

Parameters:

session - PgxSession to which the model is connected

core - Core to which the model is connected

graphConstructor - Constructor for a PgxGraph

modelMetadata - Metadata concerning the different hyper-parameters of the EdgeWise Model

Since:

23.1

Method Detail

evaluate

public PgxFrame evaluate(PgxGraph graph,
                         java.lang.Iterable<PgxEdge> edges)

Blocking version of evaluateAsync(PgxGraph, Iterable). Evaluates performance statistics for the specified edges.

Parameters:

graph - the input graph

edges - the edges to evaluate the model on

Returns:

PgxFrame containing the metrics

Since:

23.1

evaluate

public PgxFrame evaluate(PgxGraph graph,
                         java.lang.Iterable<PgxEdge> edges,
                         float threshold)

Blocking version of evaluateAsync(PgxGraph, Iterable, float). Evaluates performance statistics for the specified edges.

Parameters:

graph - the input graph

edges - the edges to evaluate the model on

threshold - decision threshold

Returns:

PgxFrame containing the labels for each edge.

Since:

23.1

evaluateAsync

public PgxFuture<PgxFrame> evaluateAsync(PgxGraph graph,
                                         java.lang.Iterable<PgxEdge> edges)

Evaluates performance statistics for the specified edges.

Parameters:

graph - the input graph

edges - the edges to evaluate the model on

Returns:

PgxFrame containing the metrics

Since:

23.1

evaluateAsync

public PgxFuture<PgxFrame> evaluateAsync(PgxGraph graph,
                                         java.lang.Iterable<PgxEdge> edges,
                                         float threshold)

Evaluates performance statistics for the specified vertices.

Parameters:

graph - the input graph

edges - the edges to evaluate the model on

threshold - decision threshold for classification (unused for regression)

Returns:

PgxFrame containing the labels for each edge.

Since:

23.1

evaluateLabels

public PgxFrame evaluateLabels(PgxGraph graph,
                               java.lang.Iterable<PgxEdge> edges)

Blocking version of evaluateLabelsAsync(PgxGraph, Iterable). Evaluates (macro averaged) classification performance statistics for the specified edges.

Parameters:

graph - the input graph

edges - the edges to evaluate the model on

Returns:

PgxFrame containing the metrics

Since:

23.1

evaluateLabels

public PgxFrame evaluateLabels(PgxGraph graph,
                               java.lang.Iterable<PgxEdge> edges,
                               float threshold)

Blocking version of evaluateLabelsAsync(PgxGraph, Iterable, float). Evaluates (macro averaged) classification performance statistics for the specified edges.

Parameters:

graph - the input graph

edges - the edges to evaluate the model on

threshold - decision threshold

Returns:

PgxFrame containing the labels for each edge.

Since:

23.1

evaluateLabelsAsync

public PgxFuture<PgxFrame> evaluateLabelsAsync(PgxGraph graph,
                                               java.lang.Iterable<PgxEdge> edges)

Evaluates (macro averaged) classification performance statistics for the specified edges.

Parameters:

graph - the input graph

edges - the edges to evaluate the model on

Returns:

PgxFrame containing the metrics

Since:

23.1

evaluateLabelsAsync

public PgxFuture<PgxFrame> evaluateLabelsAsync(PgxGraph graph,
                                               java.lang.Iterable<PgxEdge> edges,
                                               float threshold)

Evaluates (macro averaged) classification performance statistics for the specified vertices.

Parameters:

graph - the input graph

edges - the edges to evaluate the model on

threshold - decision threshold for classification (unused for regression)

Returns:

PgxFrame containing the labels for each edge.

Since:

23.1

fitAsync

public PgxFuture<java.lang.Double> fitAsync(PgxGraph graph)

Trains the EdgeWise model on the input graph.

Specified by:

fitAsync in class EdgeWiseModel<SupervisedEdgeWiseModelConfig,oracle.pgx.api.internal.mllib.SupervisedEdgeWiseModelMetadata,SupervisedEdgeWiseModel>

Parameters:

graph - input graph to fit on.

Since:

23.1

getClassWeights

public java.util.Map<?,java.lang.Float> getClassWeights()

Gets the class weights

Returns:

class weights

Since:

23.1

getEdgeTargetPropertyName

public java.lang.String getEdgeTargetPropertyName()

Gets the edge target property name

Returns:

edge target property name

getLossFunctionClass

public LossFunction getLossFunctionClass()

Gets the loss function

Returns:

loss function

Since:

23.1

getPredictionLayerConfigs

public GraphWisePredictionLayerConfig[] getPredictionLayerConfigs()

Gets the configuration objects for the prediction layers

Returns:

configurations

Since:

23.1

getTargetEdgeLabels

public java.util.List<java.util.Set<java.lang.String>> getTargetEdgeLabels()

Gets the target vertex labels

Returns:

target vertex labels

Since:

23.1

infer

public PgxFrame infer(PgxGraph graph,
                      java.lang.Iterable<PgxEdge> edges)

Blocking version of inferAsync(PgxGraph, Iterable). Does inference for the specified edges.

Parameters:

graph - the input graph

edges - the edges to do inference for

Returns:

PgxFrame containing the inference for each edge.

Since:

23.1

infer

public PgxFrame infer(PgxGraph graph,
                      java.lang.Iterable<PgxEdge> edges,
                      float threshold)

Blocking version of inferAsync(PgxGraph, Iterable, float). Does inference for the specified edges.

Parameters:

graph - the input graph

edges - the edges to do inference to

threshold - decision threshold

Returns:

PgxFrame containing the inference for each edge.

Since:

23.1

inferAsync

public PgxFuture<PgxFrame> inferAsync(PgxGraph graph,
                                      java.lang.Iterable<PgxEdge> edges)

Does inference for the specified edges.

Parameters:

graph - the input graph

edges - the edges to do inference to

Returns:

PgxFrame containing the inference for each edge.

Since:

23.1

inferAsync

public PgxFuture<PgxFrame> inferAsync(PgxGraph graph,
                                      java.lang.Iterable<PgxEdge> edges,
                                      float threshold)

Does the inference for the specified edges.

Parameters:

graph - the input graph

edges - the edges to do inference for

threshold - decision threshold for classification (unused for regression)

Returns:

PgxFrame containing the inference for each edge.

Since:

23.1

inferEmbeddingsAsync

public PgxFuture<PgxFrame> inferEmbeddingsAsync(PgxGraph graph,
                                                java.lang.Iterable<PgxEdge> edges)

Infers the embeddings for the specified edges.

Specified by:

inferEmbeddingsAsync in class EdgeWiseModel<SupervisedEdgeWiseModelConfig,oracle.pgx.api.internal.mllib.SupervisedEdgeWiseModelMetadata,SupervisedEdgeWiseModel>

Parameters:

graph - the input graph

edges - the edges to produce embeddings to

Returns:

PgxFrame containing the embeddings for each edge.

Since:

23.1

inferLabels

public PgxFrame inferLabels(PgxGraph graph,
                            java.lang.Iterable<PgxEdge> edges)

Blocking version of inferLabelsAsync(PgxGraph, Iterable). Infers the labels for the specified edges.

Parameters:

graph - the input graph

edges - the edges to produce labels for

Returns:

PgxFrame containing the labels for each edge.

Since:

23.1

inferLabels

public PgxFrame inferLabels(PgxGraph graph,
                            java.lang.Iterable<PgxEdge> edges,
                            float threshold)

Blocking version of inferLabelsAsync(PgxGraph, Iterable, float). Infers the labels for the specified edges.

Parameters:

graph - the input graph

edges - the edges to produce labels to

threshold - decision threshold

Returns:

PgxFrame containing the labels for each edge.

Since:

23.1

inferLabelsAsync

public PgxFuture<PgxFrame> inferLabelsAsync(PgxGraph graph,
                                            java.lang.Iterable<PgxEdge> edges)

Infers the labels for the specified edges.

Parameters:

graph - the input graph

edges - the vertices to produce labels to

Returns:

PgxFrame containing the labels for each edge.

Since:

23.1

inferLabelsAsync

public PgxFuture<PgxFrame> inferLabelsAsync(PgxGraph graph,
                                            java.lang.Iterable<PgxEdge> edges,
                                            float threshold)

Infers the labels for the specified edges.

Parameters:

graph - the input graph

edges - the edges to produce labels for

threshold - decision threshold for classification (unused for regression)

Returns:

PgxFrame containing the labels for each edge.

Since:

23.1

inferLogits

public PgxFrame inferLogits(PgxGraph graph,
                            java.lang.Iterable<PgxEdge> edges)

Blocking version of inferLogitsAsync(PgxGraph, Iterable). Infers the prediction logits for the specified edges.

Parameters:

graph - the input graph

edges - the edges to produce logits for

Returns:

PgxFrame containing the logits for each vertex.

Since:

23.1

inferLogitsAsync

public PgxFuture<PgxFrame> inferLogitsAsync(PgxGraph graph,
                                            java.lang.Iterable<PgxEdge> edges)

Infers the prediction logits for the specified edges.

Parameters:

graph - the input graph

edges - the edges to produce logits for

Returns:

PgxFrame containing the logits for each edge.

Since:

23.1

store

public void store(java.lang.String path,
                  java.lang.String key)
           throws java.util.concurrent.ExecutionException,
                  java.lang.InterruptedException

Blocking version of storeAsync(String, String). Calls storeAsync(String, String) and waits for the returned PgxFuture to complete.

Throws:

java.lang.InterruptedException - if the caller thread gets interrupted while waiting for completion.

java.util.concurrent.ExecutionException - if any exception occurred during asynchronous execution. The actual exception will be nested.

Since:

23.1

store

public void store(java.lang.String path,
                  java.lang.String key,
                  boolean overwrite)
           throws java.util.concurrent.ExecutionException,
                  java.lang.InterruptedException

Blocking version of storeAsync(String, String). Calls storeAsync(String, String) and waits for the returned PgxFuture to complete.

Throws:

java.lang.InterruptedException - if the caller thread gets interrupted while waiting for completion.

java.util.concurrent.ExecutionException - if any exception occurred during asynchronous execution. The actual exception will be nested.

Since:

23.1

storeAsync

public PgxFuture<java.lang.Void> storeAsync(java.lang.String path,
                                            java.lang.String key)
                                     throws java.util.concurrent.ExecutionException,
                                            java.lang.InterruptedException

Stores the GraphWise model in the specified path, with encryption.

Parameters:

path - path to store the model

key - the encryption key, or null if no encryption should be used.

Throws:

java.util.concurrent.ExecutionException

java.lang.InterruptedException

Since:

23.1

storeAsync

public PgxFuture<java.lang.Void> storeAsync(java.lang.String path,
                                            java.lang.String key,
                                            boolean overwrite)

Stores the GraphWise model in the specified path, with encryption.

Parameters:

path - path to store the model

key - the encryption key, or null if no encryption should be used.

Since:

23.1