@PublicEvolving
interface Stage<T extends Stage<T>> extends WithParams<T>, Serializable {
    /**
     * This method checks the compatibility between input schemas, stage's parameters and stage's
     * logic. It should raise an exception if there is any mismatch, e.g. the number of input
     * schemas is wrong, or if a required field is missing from a schema.
     *
     * <p>If there is no mismatch, the method derives and returns the output schemas from the input
     * schemas.
     *
     * <p>Note that the output schemas of a given Estimator instance should equal the output schemas
     * of the Transformer instance fitted by this Estimator instance, suppose the same list of input
     * schemas are used as inputs to the fit/transform methods respectively.
     *
     * @param schemas the list of schemas of the input tables.
     * @return the list of schemas of the output tables.
     */
    TableSchema[] transformSchemas(TableSchema... schemas);

    /** Skipped */
    default String toJson() {...}

    /** Skipped */
    default void loadJson(String json) {...}
}

@PublicEvolving
public interface Transformer<T extends Transformer<T>> extends Stage<T> {

    /**
     * Applies the Transformer on the given input tables, and returns the result tables.
     *
     * @param inputs a list of tables
     * @return a list of tables
     */
    Table[] transform(Table... inputs);

    /**
     * Uses the given list of tables to update internal states. This can be useful for e.g. online
     * learning where an Estimator fits an infinite stream of training samples and streams the model
     * diff data to this Transformer.
     *
     * <p>This method may be called at most once.
     *
     * @param inputs a list of tables
     */
    default void setStateStreams(Table... inputs) {
        throw new UnsupportedOperationException("this method is not implemented");
    }

    /**
     * Gets a list of tables representing changes of internal states of this Transformer. These
     * tables might come from the Estimator that instantiated this Transformer.
     *
     * @return a list of tables
     */
    default Table[] getStateStreams() {
        throw new UnsupportedOperationException("this method is not implemented");
    }
}

@PublicEvolving
public interface Estimator<E extends Estimator<E, M>, M extends Transformer<M>> extends Stage<E> {

    /**
     * Trains on the given inputs and produces a Transformer. If this Estimator may be used to
     * compose a Pipeline, the transform method of the returned Transformer should be able to accept
     * a list of tables of the same length and schemas as the fit method of this Estimator.
     *
     * @param inputs a list of tables
     * @return a Transformer
     */
    M fit(Table... inputs);
}

@PublicEvolving
public final class Pipeline implements Estimator<Pipeline, PipelineModel> {

    public Pipeline(List<Stage<?>> stages) {...}

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

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

@PublicEvolving
public final class PipelineModel implements Transformer<PipelineModel> {

    public PipelineModel(List<Transformer<?>> transformers) {...}

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

/**
 * A Graph acts as an Estimator. It consists of a DAG of stages, each of which is either an
 * Estimator or Transformer.
 */
@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 acts as a Transformer. It consists of a DAG of Transformers. */
@PublicEvolving
public final class GraphModel implements Transformer<GraphModel> {
    /** Skipped a few methods, including the implementations of the Transformer APIs. */
}

/** A GraphBuilder helps connect Stage instances into a Graph or GraphModel. */
@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 {}

}

GraphBuilder builder = new GraphBuilder();

// Creates nodes
Stage<?> stage1 = new TransformerA();
Stage<?> stage2 = new TransformerA();
Stage<?> stage3 = new EstimatorB();
// Creates inputs and inputStates
TableId input1 = builder.createTableId();
TableId input2 = builder.createTableId();
// Feeds inputs to nodes and gets outputs.
TableId output1 = builder.getOutputs(stage1, input1)[0];
TableId output2 = builder.getOutputs(stage2, input2)[0];
TableId output3 = builder.getOutputs(stage3, output1, output2)[0];

// Specifies the ordered lists of inputs, outputs, input states and output states that will
// be used as the inputs/outputs of the corresponding Graph and GraphModel APIs.
TableId[] inputs = new TableId[] {input1, input2};
TableId[] outputs = new TableId[] {output3};

// Generates the Graph instance.
Graph graph = builder.build(inputs, outputs, new TableId[]{}, new TableId[]{});
// The fit method takes 2 tables which are mapped to input1 and input2.
GraphModel model = graph.fit(...);
// The transform method takes 2 tables which are mapped to input1 and input2.
Table[] results = model.transform(...);

void runTrainingOnClusterA(...) {
  // Creates the training stream from a Kafka topic.
  Table training_stream = ...;

  Estimator estimator = new EstimatorA(...);
  Transformer transformer = estimator.fit(training_stream);
  Table state_stream = transformer.getStateStreams()[0];
  String transformer_json = transformer.toJson();

  // Writes the state_stream to a Kafka topicA.
  // Writes transformer_json to a remote file.

  // Executes the operators generated by the Estimator::fit(...), which reads from training_stream and writes to state_stream.
  env.execute()
}

void runInferenceOnWebServer(...) {

  // Reads the transformer_json from the same remote file written by the above code snippet.
  String transformer_json = ...;
  // Creates the state stream from Kafka topicA which is written by the above code snippet. 
  Table state_stream = ...;
  // Creates the input stream that needs inference.
  Table input_stream = ...;

  Transformer transformer = new Transformer(...);
  transformer.loadJson(transformer_json);
  transformer.setStateStreams(new Table[]{state_stream});
  Table output_stream = transformer.transform(input_stream);

  // Do something with the output_stream.

  // Executes the operators generated by the Transformer::transform(...), which reads from state_stream to update its parameters. It also does inference on input_stream and produces results to the output_stream.
  env.execute()
}

GraphBuilder builder = new GraphBuilder();

// Creates nodes
Stage<?> stage1 = new EstimatorA();
Stage<?> stage2 = new TransformerB();
// Creates inputs
TableId estimatorInput1 = builder.createTableId();
TableId estimatorInput2 = builder.createTableId();
TableId transformerInput1 = builder.createTableId();

// Feeds inputs to nodes and gets outputs.
TableId output1 = builder.getOutputs(stage1, new TableId[] {estimatorInput1, estimatorInput2}, new TableId[] {transformerInput1})[0];
TableId output2 = builder.getOutputs(stage2, output1)[0];

// Specifies the ordered lists of estimator inputs, transformer inputs, outputs, input states and output states
// that will be used as the inputs/outputs of the corresponding Graph and GraphModel APIs.
TableId[] estimatorInputs = new TableId[] {estimatorInput1, estimatorInput2};
TableId[] transformerInputs = new TableId[] {transformerInput1};
TableId[] outputs = new TableId[] {output2};
TableId[] inputStates = new TableId[] {};
TableId[] outputStates = new TableId[] {};

// Generates the Graph instance.
Graph graph = builder.build(estimatorInputs, transformerInputs, outputs, inputStates, outputStates);
// The fit method takes 2 tables which are mapped to estimatorInput1 and estimatorInput2.
GraphModel model = graph.fit(...);
// The transform method takes 1 table which is mapped to transformerInput1.
Table[] results = model.transform(...);