adams.flow.transformer.MOARegressing
Uses a serialized MOA model to perform predictions on the data being passed through.
The following order is used to obtain the model (when using AUTO):
1. model file present?
2. source actor present?
3. storage item present?
Optionally, the model can be updated with data being passed through.
Flow input/output:
- input: com.yahoo.labs.samoa.instances.Instance
- output: adams.flow.container.MOAPredictionContainer, com.yahoo.labs.samoa.instances.Instance
Container information:
- adams.flow.container.MOAPredictionContainer:
- Instance: data row used for prediction; com.yahoo.labs.samoa.instances.Instance
- Classification: predicted value; java.lang.Double
- Classification label: predicted label; java.lang.String
- Distribution: class distribution; array of double
- Range check: range check; java.lang.String
- Abstention classification: predicted value that made classifier abstain; java.lang.Double
- Abstention classification label: predicted label that made classifier abstain; java.lang.String
- Abstention distribution: class distribution that made classifier abstain; array of double
- Report: report for storing meta-data; adams.data.report.Report
The logging level for outputting errors and debugging output.
command-line | -logging-level <OFF|SEVERE|WARNING|INFO|CONFIG|FINE|FINER|FINEST> |
default | WARNING |
min-user-mode | Expert |
The name of the actor.
command-line | -name <java.lang.String> |
default | MOARegressing |
The annotations to attach to this actor.
command-line | -annotation <adams.core.base.BaseAnnotation> |
default |
|
If set to true, transformation is skipped and the input token is just forwarded as it is.
command-line | -skip <boolean> |
default | false |
If set to true, the flow execution at this level gets stopped in case this actor encounters an error; the error gets propagated; useful for critical actors.
command-line | -stop-flow-on-error <boolean> |
default | false |
min-user-mode | Expert |
If enabled, then no errors are output in the console; Note: the enclosing actor handler must have this enabled as well.
command-line | -silent <boolean> |
default | false |
min-user-mode | Expert |
Determines how to load the model, in case of AUTO, first the model file is checked, then the callable actor and then the storage.
command-line | -model-loading-type <AUTO|FILE|SOURCE_ACTOR|STORAGE> |
default | AUTO |
The file to load the model from, ignored if pointing to a directory.
command-line | -model <adams.core.io.PlaceholderFile> |
default | ${CWD} |
The callable actor (source) to obtain the model from, ignored if not present.
command-line | -model-actor <adams.flow.core.CallableActorReference> |
default |
|
The storage item to obtain the model from, ignored if not present.
command-line | -model-storage <adams.flow.control.StorageName> |
default | storage |
If set to true, the model file is not required to be present at set up time (eg if built on the fly), only at execution time.
command-line | -on-the-fly <boolean> |
default | false |
If enabled, chnages to the specified variable are monitored in order to reset the model, eg when a storage model changed.
command-line | -use-model-reset-variable <boolean> |
default | false |
The variable to monitor for changes in order to reset the model, eg when a storage model changed.
command-line | -model-reset-variable <adams.core.VariableName> |
default | variable |
Whether to output weka.core.Instance objects or PredictionContainer objects.
command-line | -output-instance <boolean> |
default | false |
Whether to update the model with the Instance (in case its class value isn't missing) after making the prediction.
command-line | -update-model <boolean> |
default | false |