@Step(id="KF",
image="KNWFL.svg",
name="Knowledge Flow",
description="Executes a Knowledge Flow data mining process",
documentationUrl="http://wiki.pentaho.com/display/EAI/Knowledge+Flow",
categoryDescription="Data Mining")
public class KFMeta
extends org.pentaho.di.trans.step.BaseStepMeta
implements org.pentaho.di.trans.step.StepMetaInterface
Modifier and Type | Field and Description |
---|---|
protected org.pentaho.dm.commons.ArffMeta[] |
m_injectFields
Meta data for the ARFF instances input to the inject step
|
protected static Class<?> |
PKG |
static String |
XML_TAG
XML tag for the KF step
|
Constructor and Description |
---|
KFMeta() |
Modifier and Type | Method and Description |
---|---|
protected void |
allocate(int num)
Allocate an array to hold meta data for the ARFF instances
|
void |
check(List<org.pentaho.di.core.CheckResultInterface> remarks,
org.pentaho.di.trans.TransMeta transmeta,
org.pentaho.di.trans.step.StepMeta stepMeta,
org.pentaho.di.core.row.RowMetaInterface prev,
String[] input,
String[] output,
org.pentaho.di.core.row.RowMetaInterface info)
Check the settings of this step and put findings in a remarks list.
|
Object |
clone()
Clone this step's meta data
|
boolean |
equals(Object obj)
Check for equality
|
protected String |
getClassAttributeName()
Get the name of the attribute to be set as the class attribute.
|
String |
getDialogClassName() |
void |
getFields(org.pentaho.di.core.row.RowMetaInterface row,
String origin,
org.pentaho.di.core.row.RowMetaInterface[] info,
org.pentaho.di.trans.step.StepMeta nextStep,
org.pentaho.di.core.variables.VariableSpace space)
Generates row meta data to represent the fields output by this step
|
protected String |
getFlow()
Get the knowledgeflow flow to be run.
|
protected Vector<Vector<?>> |
getFlow(String xml,
org.pentaho.di.core.variables.VariableSpace space)
Load the flow (if we can).
|
protected String |
getInjectEventName()
Get the name of the event to use for injecting.
|
protected org.pentaho.dm.commons.ArffMeta[] |
getInjectFields()
Get the meta data for the inject step
|
protected weka.gui.beans.BeanInstance |
getInjectStep(Vector flow)
Return the inject step from the supplied flow (or null if not found).
|
protected String |
getInjectStepName()
Get the name of the step to inject data into.
|
protected String |
getOutputEventName()
Get the name of the event to use for output.
|
protected String |
getOutputStepName()
Get the name of the step to listen to for output.
|
protected boolean |
getPassRowsThrough()
Get whether incoming kettle rows are to be passed through to any downstream kettle steps (rather than output of
knowledge flow being passed on)
|
protected String |
getRandomSeed()
Get the random seed to use for sampling.
|
protected String |
getSampleRelationName()
Get the relation name to use for the sampled data.
|
protected String |
getSampleSize()
Get the number of rows to randomly sample.
|
protected String |
getSerializedFlowFileName()
Get the file name of the serialized Weka flow to load/import from.
|
protected boolean |
getSetClass()
Get whether a class index is to be set in the sampled data.
|
org.pentaho.di.trans.step.StepInterface |
getStep(org.pentaho.di.trans.step.StepMeta stepMeta,
org.pentaho.di.trans.step.StepDataInterface stepDataInterface,
int cnr,
org.pentaho.di.trans.TransMeta tr,
org.pentaho.di.trans.Trans trans)
Get the executing step, needed by Trans to launch a step.
|
org.pentaho.di.trans.step.StepDataInterface |
getStepData()
Get a new instance of the appropriate data class.
|
protected boolean |
getStoreFlowInStepMetaData()
Get whether to store the XML flow description as part of the step meta data.
|
protected boolean |
getStreamData()
Get whether data is to be streamed to the knowledge flow when injecting rather than batch injected.
|
String |
getXML()
Return the XML describing this (configured) step
|
boolean |
isOutputStructureDetermined()
Returns whether we have been able to successfully determine the structure of the output (in advance of seeing all
the input rows).
|
void |
loadXML(Node stepnode,
List<org.pentaho.di.core.database.DatabaseMeta> dbs,
Map<String,org.pentaho.di.core.Counter> counters)
Loads the meta data for this (configured) step from XML.
|
void |
readRep(org.pentaho.di.repository.Repository rep,
org.pentaho.di.repository.ObjectId id_step,
List<org.pentaho.di.core.database.DatabaseMeta> dbs,
Map<String,org.pentaho.di.core.Counter> counters)
Read this step's configuration from a repository
|
void |
saveRep(org.pentaho.di.repository.Repository rep,
org.pentaho.di.repository.ObjectId id_transformation,
org.pentaho.di.repository.ObjectId id_step)
Save this step's meta data to a repository
|
protected void |
setClassAttributeName(String ca)
Set the name of the attribute to be set as the class attribute.
|
void |
setDefault() |
protected void |
setFlow(String flow)
Set the actual knowledgeflow flows to run.
|
protected void |
setInjectEventName(String ien)
Set the name of the event to use for injecting.
|
protected void |
setInjectFields(org.pentaho.dm.commons.ArffMeta[] am)
Set the array of meta data for the inject step
|
protected void |
setInjectStepName(String isn)
Set the name of the step to inject data into.
|
protected void |
setOutputEventName(String oen)
Set the name of the event to use for output.
|
protected void |
setOutputStepName(String osn)
Set the name of the step to listen to for output.
|
protected void |
setPassRowsThrough(boolean p)
Set whether incoming kettle rows are to be passed through to any downstream kettle steps (rather than output of the
knowledge flow being passed on).
|
protected void |
setRandomSeed(String seed)
Set the random seed to use for sampling rows.
|
protected void |
setSampleRelationName(String relationName)
Set the relation name to use for the sampled data.
|
protected void |
setSampleSize(String size)
Set the number of rows to randomly sample.
|
protected void |
setSerializedFlowFileName(String fFile)
Set the file name of the serialized Weka flow to load/import from.
|
protected void |
setSetClass(boolean sc)
Set whether to set a class index in the sampled data.
|
protected void |
setStoreFlowInStepMetaData(boolean s)
Set whether to store the XML flow description as part of the step meta data.
|
protected void |
setStreamData(boolean sd)
Set whether data should be streamed to the knowledge flow when injecting rather than batch injected.
|
protected void |
setUpMetaData(weka.core.Instances insts,
org.pentaho.di.core.row.RowMetaInterface row)
Set up the outgoing row meta data from the supplied Instances object.
|
analyseImpact, analyseImpact, cancelQueries, check, check, createEntry, excludeFromCopyDistributeVerification, excludeFromRowLayoutVerification, exportResources, exportResources, extractStepMetadataEntries, findAttribute, findParent, findParentEntry, getActiveReferencedObjectDescription, getDescription, getFields, getLog, getLogChannelId, getName, getObjectCopy, getObjectId, getObjectRevision, getObjectType, getOptionalStreams, getParent, getParentStepMeta, getReferencedObjectDescriptions, getRepCode, getRepositoryDirectory, getRequiredFields, getRequiredFields, getResourceDependencies, getSQLStatements, getSQLStatements, getStepInjectionMetadataEntries, getStepIOMeta, getStepIOMeta, getStepMetaInjectionInterface, getSupportedTransformationTypes, getTableFields, getTooltip, getUsedArguments, getUsedDatabaseConnections, getUsedLibraries, getXmlCode, handleStreamSelection, hasChanged, hasRepositoryReferences, isBasic, isDebug, isDetailed, isReferencedObjectEnabled, isRowLevel, loadReferencedObject, loadReferencedObject, loadStepAttributes, loadXML, loadXML, logBasic, logBasic, logDebug, logDebug, logDetailed, logDetailed, logError, logError, logError, logMinimal, logMinimal, logRowlevel, logRowlevel, lookupRepositoryReferences, readRep, readRep, resetStepIoMeta, saveRep, searchInfoAndTargetSteps, setChanged, setChanged, setParentStepMeta, setStepIOMeta, supportsErrorHandling
finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
analyseImpact, analyseImpact, cancelQueries, check, cleanAfterHopFromRemove, cleanAfterHopFromRemove, cleanAfterHopToRemove, excludeFromCopyDistributeVerification, excludeFromRowLayoutVerification, exportResources, exportResources, extractStepMetadataEntries, fetchTransMeta, getActiveReferencedObjectDescription, getFields, getOptionalStreams, getParentStepMeta, getReferencedObjectDescriptions, getRequiredFields, getResourceDependencies, getSQLStatements, getSQLStatements, getStepIOMeta, getStepMetaInjectionInterface, getSupportedTransformationTypes, getTableFields, getUsedArguments, getUsedDatabaseConnections, getUsedLibraries, handleStreamSelection, hasChanged, hasRepositoryReferences, isReferencedObjectEnabled, loadReferencedObject, loadXML, lookupRepositoryReferences, passDataToServletOutput, readRep, resetStepIoMeta, saveRep, searchInfoAndTargetSteps, setChanged, setParentStepMeta, supportsErrorHandling
protected static Class<?> PKG
public static final String XML_TAG
protected org.pentaho.dm.commons.ArffMeta[] m_injectFields
protected void setStoreFlowInStepMetaData(boolean s)
s
- true if the flow should be stored in the step meta dataprotected boolean getStoreFlowInStepMetaData()
protected void setSampleRelationName(String relationName)
relationName
- the relation name to useprotected String getSampleRelationName()
protected String getSampleSize()
protected void setSampleSize(String size)
size
- the number of rows to sampleprotected String getRandomSeed()
protected void setRandomSeed(String seed)
seed
- the seed to useprotected boolean getPassRowsThrough()
protected void setPassRowsThrough(boolean p)
p
- true if rows are to be passed on to downstream kettle stepsprotected void setSerializedFlowFileName(String fFile)
fFile
- the file nameprotected String getSerializedFlowFileName()
protected void setFlow(String flow)
flow
- the flows to runprotected String getFlow()
protected void setInjectStepName(String isn)
isn
- the name of the step to inject data intoprotected String getInjectStepName()
protected void setInjectEventName(String ien)
ien
- the name of the event to use for injectingprotected String getInjectEventName()
protected void setOutputStepName(String osn)
osn
- the name of the step to listen to for outputprotected String getOutputStepName()
protected void setOutputEventName(String oen)
oen
- the name of the event to use for outputprotected String getOutputEventName()
protected void setSetClass(boolean sc)
sc
- true if a class index is to be set in the dataprotected boolean getSetClass()
protected void setClassAttributeName(String ca)
ca
- the name of the class attributeprotected String getClassAttributeName()
protected void setStreamData(boolean sd)
sd
- true if data should be streamedprotected boolean getStreamData()
protected weka.gui.beans.BeanInstance getInjectStep(Vector flow)
flow
- the flow to searchprotected void allocate(int num)
num
- number of meta data objects to allocateprotected void setInjectFields(org.pentaho.dm.commons.ArffMeta[] am)
am
- an array of ArffMetaprotected org.pentaho.dm.commons.ArffMeta[] getInjectFields()
public String getXML()
getXML
in interface org.pentaho.di.trans.step.StepMetaInterface
getXML
in class org.pentaho.di.trans.step.BaseStepMeta
String
containing the XMLpublic void loadXML(Node stepnode, List<org.pentaho.di.core.database.DatabaseMeta> dbs, Map<String,org.pentaho.di.core.Counter> counters) throws org.pentaho.di.core.exception.KettleXMLException
loadXML
in interface org.pentaho.di.trans.step.StepMetaInterface
loadXML
in class org.pentaho.di.trans.step.BaseStepMeta
stepnode
- the step to loadorg.pentaho.di.core.exception.KettleXMLException
- if an error occursprotected Vector<Vector<?>> getFlow(String xml, org.pentaho.di.core.variables.VariableSpace space) throws Exception
Exception
- if there is a problem loading the flowpublic void readRep(org.pentaho.di.repository.Repository rep, org.pentaho.di.repository.ObjectId id_step, List<org.pentaho.di.core.database.DatabaseMeta> dbs, Map<String,org.pentaho.di.core.Counter> counters) throws org.pentaho.di.core.exception.KettleException
readRep
in interface org.pentaho.di.trans.step.StepMetaInterface
readRep
in class org.pentaho.di.trans.step.BaseStepMeta
rep
- the repository to accessid_step
- the id for this steporg.pentaho.di.core.exception.KettleException
- if an error occurspublic void saveRep(org.pentaho.di.repository.Repository rep, org.pentaho.di.repository.ObjectId id_transformation, org.pentaho.di.repository.ObjectId id_step) throws org.pentaho.di.core.exception.KettleException
saveRep
in interface org.pentaho.di.trans.step.StepMetaInterface
saveRep
in class org.pentaho.di.trans.step.BaseStepMeta
rep
- the repository to save toid_transformation
- transformation idid_step
- step idorg.pentaho.di.core.exception.KettleException
- if an error occursprotected void setUpMetaData(weka.core.Instances insts, org.pentaho.di.core.row.RowMetaInterface row)
insts
- the Instances to use for setting up the outgoing row meta datarow
- holds the final outgoing row meta datapublic void getFields(org.pentaho.di.core.row.RowMetaInterface row, String origin, org.pentaho.di.core.row.RowMetaInterface[] info, org.pentaho.di.trans.step.StepMeta nextStep, org.pentaho.di.core.variables.VariableSpace space) throws org.pentaho.di.core.exception.KettleStepException
getFields
in interface org.pentaho.di.trans.step.StepMetaInterface
getFields
in class org.pentaho.di.trans.step.BaseStepMeta
row
- the meta data for the output producedorigin
- the name of the step to be used as the origininfo
- The input rows metadata that enters the step through the specified channels in the same order as in method
getInfoSteps(). The step metadata can then choose what to do with it: ignore it or not.nextStep
- if this is a non-null value, it's the next step in the transformation. The one who's asking, the step
where the data is targetted towards.space
- not sure what this is :-)org.pentaho.di.core.exception.KettleStepException
- if an error occurspublic boolean isOutputStructureDetermined()
public boolean equals(Object obj)
public Object clone()
clone
in interface org.pentaho.di.trans.step.StepMetaInterface
clone
in class org.pentaho.di.trans.step.BaseStepMeta
public void setDefault()
setDefault
in interface org.pentaho.di.trans.step.StepMetaInterface
public void check(List<org.pentaho.di.core.CheckResultInterface> remarks, org.pentaho.di.trans.TransMeta transmeta, org.pentaho.di.trans.step.StepMeta stepMeta, org.pentaho.di.core.row.RowMetaInterface prev, String[] input, String[] output, org.pentaho.di.core.row.RowMetaInterface info)
check
in interface org.pentaho.di.trans.step.StepMetaInterface
check
in class org.pentaho.di.trans.step.BaseStepMeta
remarks
- the list to put the remarks in. see org.pentaho.di.core.CheckResult
transmeta
- the transform meta datastepMeta
- the step meta dataprev
- the fields coming from a previous stepinput
- the input step namesoutput
- the output step namesinfo
- the fields that are used as information by the steppublic String getDialogClassName()
getDialogClassName
in interface org.pentaho.di.trans.step.StepMetaInterface
getDialogClassName
in class org.pentaho.di.trans.step.BaseStepMeta
public org.pentaho.di.trans.step.StepInterface getStep(org.pentaho.di.trans.step.StepMeta stepMeta, org.pentaho.di.trans.step.StepDataInterface stepDataInterface, int cnr, org.pentaho.di.trans.TransMeta tr, org.pentaho.di.trans.Trans trans)
getStep
in interface org.pentaho.di.trans.step.StepMetaInterface
stepMeta
- the step infostepDataInterface
- the step data interface linked to this step. Here the step can store temporary data, database connections,
etc.cnr
- the copy number to get.tr
- the transformation info.trans
- the launching transformationStepInterface
valuepublic org.pentaho.di.trans.step.StepDataInterface getStepData()
getStepData
in interface org.pentaho.di.trans.step.StepMetaInterface
StepDataInterface
valueCopyright © 2002–2019 Hitachi Vantara. All rights reserved.