oracle.dmt.odm.task
Class MiningApplyTask

java.lang.Object
  |
  +--oracle.dmt.odm.MiningObject
        |
        +--oracle.dmt.odm.LocatableObject
              |
              +--oracle.dmt.odm.task.MiningTask
                    |
                    +--oracle.dmt.odm.task.MiningDataTask
                          |
                          +--oracle.dmt.odm.task.MiningApplyTask

All Implemented Interfaces:

java.io.Serializable

public class MiningApplyTask

extends MiningDataTask

An instance of MiningApplyTask is used for applying a model to a data set to make predictions, classifications, and to provide associated probabilities. The apply task can be performed using any supervised model or clustering model supported by ODM.

ODM supports flexible ways to create the apply output table. The MiningApplyOutput (MAO) object is used to specify the apply output table format using ApplyContentItem. The MAO provides the ability to specify the computation of top N scores of the target attribute and associated probability. It also provides the user the ability to specify the computation of probability of a specified target attribute category (a.k.a class value).

The input data for a MiningApplyTask must have all the active attributes used in building the associated supervised model. Input data must also have all source attributes specified in the MAO. If the task input data is not compatible with the specified input model and MAO, the execution of apply task fails with an exception.

After constructing a valid MiningApplyTask instance, the task must be persisted in the database using store(dmsConn, taskName) method before executing. The task name must be unique in the in the user schema task name space.

After successful completion of the apply task, the apply output table will be avaliable in the user-specified location. MiningApplyResults object can be used to retrieve the result details of the apply task. To remove the mining apply task object in the database, call the remove(dmsConn, taskName) method.

Since:

ODM 9.2.0

See Also:

Serialized Form

Constructor Summary

MiningApplyTask(PhysicalDataSpecification taskInputData, java.lang.String inputModelName, MiningApplyOutput applyOutput, LocationAccessData applyOutputLoc, java.lang.String applyResultName)
Creates an instance of the apply task from the given mining data (as a set of records), the model to which the data is applied, and the apply output.

Method Summary

MiningApplyOutput	getApplyOutput() Returns the apply output specification used in performing the apply operation.
java.lang.String	getApplyResultName() Returns the apply result name.
LocationAccessData	getOutputDataLocation() Returns location of the apply output table.
static MiningApplyTask	restore(Connection dmsConn, java.lang.String taskName) Restores the user-specified mining apply task object from the database.

Methods inherited from class oracle.dmt.odm.task.MiningDataTask

getInputModelName, getTaskInputData

Methods inherited from class oracle.dmt.odm.task.MiningTask

execute, getActiveExecutionHandle, getCurrentStatus, getExecutionDuration, getExecutionHandle, getLatestExecutionHandle, getName, getStatusHistory, getTaskType, getType, listTasks, remove, rename, store, terminate, waitForCompletion, waitForCompletion

Methods inherited from class java.lang.Object

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

Constructor Detail

MiningApplyTask

public MiningApplyTask(PhysicalDataSpecification taskInputData,
                       java.lang.String inputModelName,
MiningApplyOutput applyOutput,
LocationAccessData applyOutputLoc,
                       java.lang.String applyResultName)
                throws InvalidArgumentException,
ODMException

Creates an instance of the apply task from the given mining data (as a set of records), the model to which the data is applied, and the apply output.

Parameters:

taskInputData - Physical data specification of the input data

inputModelName - Input mining model name in the data mining server

applyOutput - Apply output specification. For more details refer to oracle.dmt.odm.result.MiningApplyOutput

applyResultName - Apply result name

Throws:

InvalidArgumentException - is thrown
- when any of the input arguments are null
- when the inputModelName/applyResultName length >25 bytes
- when the taskInputData does not have location access data
- when the applyOutput is not valid

InvalidArgumentException

ODMException

Method Detail

getApplyOutput

public MiningApplyOutput getApplyOutput()

Returns the apply output specification used in performing the apply operation.

Returns:

apply output object

getApplyResultName

public java.lang.String getApplyResultName()

Returns the apply result name.

Returns:

apply result name.

getOutputDataLocation

public LocationAccessData getOutputDataLocation()

Returns location of the apply output table. This table is created once the apply task is successful.

Returns:

apply output table location.

restore

public static MiningApplyTask restore(Connection dmsConn,
                                      java.lang.String taskName)
                                                   throws InvalidArgumentException,
MiningTaskException,
                                                          java.sql.SQLException,
ODMException

Restores the user-specified mining apply task object from the database.

Parameters:

dmsConn - Data mining server connection.

taskName - Name of the apply task.

Returns:

Restored mining apply task.

Throws:

InvalidArgumentException - is thrown
- when the dmsConn/taskName are null
- when the taskName length >64 characters

MiningTaskException - is thrown
- when the restore fails

SQLException - is thrown
- when there is a failure in JDBC calls

InvalidArgumentException

MiningTaskException

java.sql.SQLException

ODMException