cSvmSink

Description

This is an example of a cDataSink descendant. It reads data from the data memory and prints it to the console. This component is intended as a template for developers.

Type hierarchy

cDataSinkcSvmSink

Fields

  • model (string) [default: None]

    The name of the model file.

  • printParseableResult (numeric) [default: 0.0]

    1 = print easily parseable classification/regression result to stdout

  • printResult (numeric) [default: 0.0]

    1 = print classification/regression result to log

  • saveResult (string) [default: None]

    filename of text file the result(s) will be saved to

  • instanceName (string) [default: None]

    If set, print instance name field to CSV (first column) when saveResult=1, with the given value.

  • append (numeric) [default: 0.0]

    1 = append to CSV file, in case of saveResult=1, instead of overwriting the file (default).

  • resultRecp (string) [default: None]

    List of component(s) to send 'classificationResult' messages to (use , to separate multiple recepients), leave blank (NULL) to not send any messages

  • resultMessageName (string) [default: svm_result]

    Freely defineable name that is sent with 'classificationResult' message

  • showStatsDebug (numeric) [default: 0.0]

    1 = show internal values for debugging and sanity checks.

  • ignoreLogitModel (numeric) [default: 0.0]

    1 = don't use a logistic model for probability estimates, if one is contained in the model.

  • winningClassMethodName (string) [default: vote]

    prob = use probabilties instead of votes to determine the winning class, if a logistic model is used. vote = use the standard majority voting based on the distance