Page History

/**
 * A Graph, which acts as an estimator. A Graph consists of a DAG of stages, each of which is either
 * an Estimator or a Transformer. When `Graph::fit` is called, the stages are executed in a
 * topologically-sorted order. If a stage is an Estimator, its `Estimator::fit` method will be
 * called on the input tables (from the input edges) to fit a model. Then the model, which is a
 * transformer, will be used to transform the input tables to produce output tables to the output
 * edges. If a stage is a transformer, its `Transformer::transform` method will be called on the
 * input tables to produce output tables to the output edges. The fitted model from a Graph is a
 * GraphModel consisting of fitted models and transformers, wherewith those stages havehaving 1-1 mapping to the 
 * stages in the original Graph.
 */
@PublicEvolving
public final class Graph implements Estimator<Graph, GraphModel> {
    public Graph(...) {...}

    @Override
    public GraphModel fit(Table... inputs) {...}

    @Override
    public TableSchema[] transformSchemas(TableSchema... schemas) {
        return schemas;
    }

    /** Skipped a few methods, including the implementations of some Estimator APIs. */
}

/**
 * A GraphModel, which acts as a Transformer. A GraphModel consists of a DAG of transformers. When
 * `GraphModel::transform` is called, the stages are executed in a topologically-sorted order. When
 * a stage is executed, its `Transformer::transform` method will be called on the input tables (from
 * the input edges) to produce output tables to the output edges.
 */
public final class GraphModel implements Transformer<GraphModel> {
    /** Skipped a few methods, including the implementations of the Transformer APIs. */
}

/** A GraphBuilder provides APIs to build Graph and GraphModel from a DAG of Estimator and Transformer instances. */
@PublicEvolving
public final class GraphBuilder {
    /**
     * Specifies the upper bound (could be loose) of the number of output tables that can be
     * returned by the Transformer::getStateStreams and Transformer::transform methods, for any
     * stage involved in this Graph.
     *
     * <p>The default upper bound is 20.
     */
    public GraphBuilder setMaxOutputLength(int maxOutputLength) {...}

    /**
     * Creates a TableId associated with this GraphBuilder. It can be used to specify the passing of
     * tables between stages, as well as the input/output tables of the Graph/GraphModel generated
     * by this builder.
     */
    public TableId createTableId() {...}

    /**
     * If the stage is an Estimator, both its fit method and the transform method of its fitted Transformer would be
     * invoked with the given inputs when the graph runs.
     *
     * If this stage is a Transformer, its transform method would be invoked with the given inputs when the graph runs.
     *
     * Returns a list of TableIds, which represents outputs of the Transformer::transform invocation.
     */
    public TableId[] getOutputs(Stage<?> stage, TableId... inputs) {...}

    /**
     * If this stage is an Estimator, its fit method would be invoked with estimatorInputs, and the transform method
     * of its fitted Transformer would be invoked with transformerInputs, when the graph runs.
     *
     * This method throws Exception if the stage is a Transformer.
     *
     * This method is useful when the state is an Estimator AND the Estimator::fit needs to take a different list of
     * Tables from the Transformer::transform of the fitted Transformer.
     *
     * Returns a list of TableIds, which represents outputs of the Transformer::transform invocation.
     */
    public TableId[] getOutputs(Stage<?> stage, TableId[] estimatorInputs, TableId[] transformerInputs) {...}

    /**
     * The GraphModel::setStateStreams should invoke the setStateStreams of the corresponding stage
     * with the corresponding inputs.
     */
    void setStateStreams(Stage<?> stage, TableId... inputs) {...}

    /**
     * The GraphModel::getStateStreams should invoke the getStateStreams of the corresponding stage.
     *
     * <p>Returns a list of TableIds, which represents outputs of the getStateStreams invocation.
     */
    TableId[] getStateStreams(Stage<?> stage) {...}

    /**
     * Returns a Graph instance which the following API specification:
     *
     * 1) Graph::fit should take inputs and returns a GraphModel with the following specification.
     *
     * 2) GraphModel::transform should take inputs and return outputs.
     *
     * 3) GraphModel::setStateStreams should take inputStates.
     *
     * 4) GraphModel::getStateStreams should return outputStates.
     *
     * The fit/transform/setStateStreams/getStateStreams should invoke the APIs of the internal stages in the order specified by the DAG of stages.
     */
    Graph build(TableId[] inputs, TableId[] outputs, TableId[] inputStates, TableId[] outputStates) {...}

    /**
     * Returns a Graph instance which the following API specification:
     *
     * 1) Graph::fit should take estimatorInputs and returns a GraphModel with the following specification.
     *
     * 2) GraphModel::transform should take transformerInputs and return outputs.
     *
     * 3) GraphModel::setStateStreams should take inputStates.
     *
     * 4) GraphModel::getStateStreams should return outputStates.
     *
     * The fit/transform/setStateStreams/getStateStreams should invoke the APIs of the internal stages in the order specified by the DAG of stages.
     *
     * This method is useful when the Graph::fit needs to take a different list of Tables from the GraphModel::transform of the fitted GraphModel.
     */
    Graph build(TableId[] estimatorInputs, TableId[] transformerInputs, TableId[] outputs, TableId[] inputStates, TableId[] outputStates) {...}

    /**
     * Returns a GraphModel instance which the following API specification:
     *
     * 1) GraphModel::transform should take inputs and returns outputs.
     *
     * 2) GraphModel::setStateStreams should take inputStates.
     *
     * 3) GraphModel::getStateStreams should return outputStates.
     *
     * The transform/setStateStreams/getStateStreams should invoke the APIs of the internal  stages in the order specified by the DAG of stages.
     *
     * This method throws Exception if any stage of this graph is an Estimator.
     */
    GraphModel buildModel(TableId[] inputs, TableId[] outputs, TableId[] inputStates, TableId[] outputStates) {...}

    // The TableId is necessary to pass the inputs/outputs of various API calls across the
    // Graph/GraphModel stags.
    static class TableId {}

}