Module datarush.analytics
Package com.pervasive.datarush.analytics.regression

Class SumOfSquares

  • All Implemented Interfaces:
    LogicalOperator
    public final class SumOfSquares
extends ExecutableOperator
    Compute the sum of squares for the given fields of the input data. The inner products are calculated distributed with a reduction at the end to produce the sum of squares matrix.

    Note that the fields must be of type double or be assignable to a double type.

    • Constructor Detail

      • SumOfSquares

        public SumOfSquares()
        Default constructor. The list of fields to use must be specified with setFieldNames(List).

      • SumOfSquares

        public SumOfSquares​(List<String> fieldNames)
        Construct with the given field names.
        Parameters:
        fieldNames - names of fields compute sum of squares

    • Method Detail

      • getInput

        public RecordPort getInput()
        Get the input port for this operator. This port contains the data used in the sum of squares calculation.
        Returns:
        input port

      • getOutput

        public SimpleModelPort<org.apache.commons.math.linear.Array2DRowRealMatrix> getOutput()
        Get the output model port of this operator. This port will contain the sum of squares for the specified fields in a matrix. Only a single token will be available on this output port.
        Returns:
        output model port

      • getFieldNames

        public List<String> getFieldNames()
        Get the list of field names to apply sum of squares.
        Returns:
        field names

      • setFieldNames

        public void setFieldNames​(List<String> fieldNames)
        Set the list of fields to apply sum of squares. The field names must be valid names within the schema of the input port. The fields types must be compatible with the double type.
        Parameters:
        fieldNames - field names

      • computeMetadata

        protected void computeMetadata​(StreamingMetadataContext ctx)
        Description copied from class: StreamingOperator
        Implementations must adhere to the following contracts

        General

        Regardless of input ports/output port types, all implementations must do the following:

        1. Validation. Validation of configuration should always be performed first.
        2. Declare parallelizability.. Implementations must declare parallelizability by calling StreamingMetadataContext.parallelize(ParallelismStrategy).

        Input record ports

        Implementations with input record ports must declare the following:
        1. Required data ordering:
          2. Implementations that have data ordering requirements must declare them by calling RecordPort#setRequiredDataOrdering, otherwise data may arrive in any order.
        2. Required data distribution (only applies to parallelizable operators):
          3. Implementations that have data distribution requirements must declare them by calling RecordPort#setRequiredDataDistribution, otherwise data will arrive in an unspecified partial distribution.
        Note that if the upstream operator's output distribution/ordering is compatible with those required, we avoid a re-sort/re-distribution which is generally a very large savings from a performance standpoint. In addition, some operators may chose to query the upstream output distribution/ordering by calling RecordPort#getSourceDataDistribution and RecordPort#getSourceDataOrdering. These should be viewed as a hints to help chose a more efficient algorithm. In such cases, though, operators must still declare data ordering and data distribution requirements; otherwise there is no guarantee that data will arrive sorted/distributed as required.

        Output record ports

        Implementations with output record ports must declare the following:
        1. Type: Implementations must declare their output type by calling RecordPort#setType.
        Implementations with output record ports may declare the following:
        1. Output data ordering: Implementations that can make guarantees as to their output ordering may do so by calling RecordPort#setOutputDataOrdering
        2. Output data distribution (only applies to parallelizable operators): Implementations that can make guarantees as to their output distribution may do so by calling RecordPort#setOutputDataDistribution
        Note that both of these properties are optional; if unspecified, performance may suffer since the framework may unnecessarily re-sort/re-distributed the data.

        Input model ports

        In general, there is nothing special to declare for input model ports. Models are implicitly duplicated to all partitions when going from non-parallel to parallel operators. The case of a model going from a parallel to a non-parallel node is a special case of a "model reducer" operator. In the case of a model reducer, the downstream operator, must declare the following:
        1. Merge handler: Model reducers must declare a merge handler by calling AbstractModelPort#setMergeHandler.
        Note that MergeModel is a convenient, re-usable model reducer, parameterized with a merge-handler.

        Output model ports

        SimpleModelPort's have no associated metadata and therefore there is never any output metadata to declare. PMMLPort's, on the other hand, do have associated metadata. For all PMMLPorts, implementations must declare the following:
        1. pmmlModelSpec: Implementations must declare the PMML model spec by calling PMMLPort.setPMMLModelSpec.
        Specified by:
        computeMetadata in class StreamingOperator
        Parameters:
        ctx - the context

      • execute

        protected void execute​(ExecutionContext ctx)
        Compute the inner product for each distributed dataflow. These products are merged together in a reduction step to produce the sum of squares for the input data. The merge takes place in the merge handler for the matrix output port.
        Specified by:
        execute in class ExecutableOperator
        Parameters:
        ctx - context in which to lookup physical ports bound to logical ports