🎉Community Raffle - Win $25

An exclusive raffle opportunity for active members like you! Complete your profile, answer questions and get your first accepted badge to enter the raffle.

Join and Win

Getting the type of Attribute

seshadotcom

Hi Guys,

I want to write a generic workflow which can discover the type of attributes and change them accordingly on a case by case basis so that I deliver one big chunk of dataset of binomial values to my FP Growth. I did see an operator called GuessTypes but how do I get the related type of an attribute? It seems not to be delivering this in the output port.

Any Idea?

Find more posts tagged with

AI Studio

Accepted answers

All comments

MariusHelf

That is not possible out of the box. You can probably get the types via the scripting interface in the Execute Script operator.

Best regards,
Marius

Marco_Boeck

Hi,

you can use the "Execute Script" operator for that. I created an example process for you which you can extend and modifiy. For further information on how to convert various attributes, have a look at the RM sourcecode of the Type Conversion operators like com.rapidminer.operator.preprocessing.filter.NominalToBinominal.


<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.009">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.3.009" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="generate_data" compatibility="5.3.009" expanded="true" height="60" name="Generate Data" width="90" x="45" y="30">
        <parameter key="number_examples" value="1"/>
        <parameter key="number_of_attributes" value="1"/>
      </operator>
      <operator activated="true" class="execute_script" compatibility="5.3.009" expanded="true" height="76" name="Execute Script" width="90" x="179" y="30">
        <parameter key="script" value="import java.util.Map;&#10;import java.util.Map.Entry;&#10;import java.util.Iterator;&#10;import java.util.LinkedHashMap;&#10;&#10;import com.rapidminer.example.Attribute;&#10;import com.rapidminer.example.Example;&#10;import com.rapidminer.example.ExampleSet;&#10;import com.rapidminer.example.table.AttributeFactory;&#10;import com.rapidminer.tools.Ontology;&#10;&#10;ExampleSet exampleSet = input[0];&#10;Map&lt;Attribute, Attribute&gt; translationMap = new LinkedHashMap&lt;Attribute, Attribute&gt;();&#10;Iterator&lt;Attribute&gt; iterator = exampleSet.getAttributes().iterator();&#10;while (iterator.hasNext()) {&#10;&#9;Attribute oldAtt = iterator.next();&#10;&#9;if (Ontology.ATTRIBUTE_VALUE_TYPE.isA(oldAtt.getValueType(), Ontology.NUMERICAL)) {&#10;&#9;&#9;Attribute newAtt = AttributeFactory.createAttribute(Ontology.BINOMINAL);&#10;&#9;&#9;translationMap.put(oldAtt, newAtt);&#10;&#9;}&#10;&#9;// your other conditions here&#10;}&#10;// adding to table and exampleSet&#10;for (Entry&lt;Attribute, Attribute&gt; replacement: translationMap.entrySet()) {&#10;&#9;Attribute newAttribute = replacement.getValue();&#10;&#9;exampleSet.getExampleTable().addAttribute(newAttribute);&#10;&#9;exampleSet.getAttributes().addRegular(newAttribute);&#10;}&#10;&#9;&#9;&#10;// over all examples change attribute values&#10;for(Example example : exampleSet) {&#10;&#9;for(Entry&lt;Attribute, Attribute&gt; replacement: translationMap.entrySet()) {&#10;&#9;&#9;Attribute oldAttribute = replacement.getKey();&#10;&#9;&#9;Attribute newAttribute = replacement.getValue();&#10;&#9;&#9;double oldValue = example.getValue(oldAttribute);&#10;&#9;&#9;if (Double.isNaN(oldValue)) {&#10;&#9;&#9;&#9;example.setValue(newAttribute, Double.NaN);&#10;&#9;&#9;} else { // your conditions here&#10;&#9;&#9;&#9;example.setValue(newAttribute, newAttribute.getMapping().mapString(&quot;yourString&quot;));&#10;&#9;&#9;}&#10;&#9;}&#10;}&#10;&#9;&#9;&#10;// removing old attributes&#10;for (Map.Entry&lt;Attribute,Attribute&gt; entry : translationMap.entrySet()) {&#10;&#9;Attribute originalAttribute = entry.getKey();&#10;&#9;exampleSet.getAttributes().remove(originalAttribute);&#10;&#9;entry.getValue().setName(originalAttribute.getName());&#10;}&#10;&#10;return exampleSet;"/>
      </operator>
      <connect from_op="Generate Data" from_port="output" to_op="Execute Script" to_port="input 1"/>
      <connect from_op="Execute Script" from_port="output 1" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>

Regards,
Marco