Bindiscretization problem

shoehorn_63shoehorn_63 Member Posts: 1 Contributor I
edited November 2018 in Help
First of all I am new to Rapidminer.
I do have the following problem:

i have 3 different columns with key perfomance indicators. Rapidminer does a great job , putting those numers into different bins using Bindiscretization. The only problem is that the original 3 columns are now replaced by the new discretizised colums. It would help a lot if Rapidminer would keep the original columns and would add the 3 discretizised ones to the data set, endig up with 6 columns ( 3 original + 3 discretizised. Any idea how this could me done. Any help is appreciated
Best wishes Michael


  • Options
    landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,531 Unicorn
    welcome aboard.

    Although the DiscretizationOperators don't provide this option, you can use a combination of operators to achiev the desired result.
    Also I have already three different ways in my mind, I will past the most easiest, to aviod shocking you :)

    Here is what the process does:
    Copies the three attributes, this is straight forward
    Then it uses a regular expression to exclude the copied attributes from being part of the attributes' subset which is processed by the child operator.
    This child operator discretizes the three attributes matching the regular expression
    After processing, the results are merged, so that the desired combination is available.
    <operator name="Root" class="Process" expanded="yes">
        <operator name="ExampleSetGenerator" class="ExampleSetGenerator">
            <parameter key="target_function" value="interaction classification"/>
            <parameter key="number_of_attributes" value="3"/>
        <operator name="AttributeCopy" class="AttributeCopy">
            <parameter key="attribute_name" value="att1"/>
            <parameter key="new_name" value="att1_copy"/>
        <operator name="AttributeCopy (2)" class="AttributeCopy">
            <parameter key="attribute_name" value="att2"/>
            <parameter key="new_name" value="att2_copy"/>
        <operator name="AttributeCopy (3)" class="AttributeCopy">
            <parameter key="attribute_name" value="att3"/>
            <parameter key="new_name" value="att3_copy"/>
        <operator name="AttributeSubsetPreprocessing" class="AttributeSubsetPreprocessing" expanded="yes">
            <parameter key="condition_class" value="attribute_name_filter"/>
            <parameter key="attribute_name_regex" value="att."/>
            <operator name="BinDiscretization" class="BinDiscretization">
                <parameter key="number_of_bins" value="3"/>
Sign In or Register to comment.