org.knime.base.node.mine.regression.logistic.predict
Class LogRegPredictor

java.lang.Object
  org.knime.core.data.container.AbstractCellFactory
      org.knime.base.node.mine.regression.logistic.predict.LogRegPredictor

All Implemented Interfaces:

CellFactory

public final class LogRegPredictor
extends AbstractCellFactory

A Predictor for a logistic regression model.

Author:

Heiko Hofer

Constructor Summary

LogRegPredictor(PMMLGeneralRegressionContent content, DataTableSpec inSpec, PMMLPortObjectSpec portSpec, String targetVariableName, boolean includeProbabilites)
This constructor should be used when executing the node.

LogRegPredictor(PMMLPortObjectSpec portSpec, DataTableSpec tableSpec, boolean includeProbabilites)
This constructor should be used during the configure phase of a node.

Method Summary

static DataColumnSpec[]	createColumnSpec(PMMLPortObjectSpec portSpec, DataTableSpec tableSpec, boolean includeProbabilites) Creates the spec of the output if possible.
DataCell[]	getCells(DataRow row) Get the new cells for a given row.

Methods inherited from class org.knime.core.data.container.AbstractCellFactory

getColumnSpecs, getMaxParallelWorkers, getMaxQueueSize, isParallelProcessing, setParallelProcessing, setParallelProcessing, setProgress

Methods inherited from class java.lang.Object

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

Constructor Detail

LogRegPredictor

public LogRegPredictor(PMMLPortObjectSpec portSpec,
                       DataTableSpec tableSpec,
                       boolean includeProbabilites)
                throws InvalidSettingsException

This constructor should be used during the configure phase of a node. The created instance will give a valid spec of the output but cannot be used to compute the cells.

Parameters:

portSpec - the spec of the pmml input port

tableSpec - the spec of the data input port

includeProbabilites - add probabilities to the output

Throws:

InvalidSettingsException - when tableSpec and portSpec do not match

LogRegPredictor

public LogRegPredictor(PMMLGeneralRegressionContent content,
                       DataTableSpec inSpec,
                       PMMLPortObjectSpec portSpec,
                       String targetVariableName,
                       boolean includeProbabilites)
                throws InvalidSettingsException

This constructor should be used when executing the node. Use it when you want to compute output cells.

Parameters:

content - the general regression content

inSpec - the spec of the data input port

portSpec - the pmml port object spec

targetVariableName - the name of the target variable

includeProbabilites - add probabilities to the output

Throws:

InvalidSettingsException - when inSpec and regModel do not match

Method Detail

createColumnSpec

public static DataColumnSpec[] createColumnSpec(PMMLPortObjectSpec portSpec,
                                                DataTableSpec tableSpec,
                                                boolean includeProbabilites)
                                         throws InvalidSettingsException

Creates the spec of the output if possible.

Parameters:

portSpec - the spec of the pmml input port

tableSpec - the spec of the data input port

includeProbabilites - add probabilities to the output

Returns:

The spec of the output or null

Throws:

InvalidSettingsException - when tableSpec and portSpec do not match

getCells

public DataCell[] getCells(DataRow row)

Get the new cells for a given row. These cells are incorporated into the existing row. The way it is done is defined through the ColumnRearranger using this object.

Parameters:

row - The row of interest.

Returns:

The new cells to that row.