Results with Original Nominal Values

WebclipperWebclipper Member Posts: 2 Contributor I
edited November 2018 in Help
Data is read in, nominal values are converted to numerical, the model is built and applied. All works okay, but my Results table has the converted nominal values and I would like to see the original nominal values alongside the predicted results instead.

Can someone give me a hint related to which operator(s) might help with generating a prediction result table with original nominal values? Thanks.

Webclipper

Answers

  • landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,531 Unicorn
    Hi,
    if you are going to use a regression learner for classification, you just could use the ClassificationByRegression MetaLearner, which will hide the mapping to numerical and back. So you can use your learner without manually mapping the values.
    But there are many learners, which are able to cope directly with nominal values, even polynomial values. For example the LibSVM.

    I post an example below:
    <operator name="Root" class="Process" expanded="yes">
        <operator name="ExampleSetGenerator" class="ExampleSetGenerator">
            <parameter key="target_function" value="sum classification"/>
        </operator>
        <operator name="XValidation" class="XValidation" expanded="yes">
            <operator name="ClassificationByRegression" class="ClassificationByRegression" expanded="yes">
                <operator name="LinearRegression" class="LinearRegression">
                </operator>
            </operator>
            <operator name="OperatorChain" class="OperatorChain" expanded="yes">
                <operator name="ModelApplier" class="ModelApplier">
                    <list key="application_parameters">
                    </list>
                </operator>
                <operator name="Performance" class="Performance">
                </operator>
            </operator>
        </operator>
    </operator>
    Greetings,
      Sebastian
Sign In or Register to comment.