[SOLVED] Joining ExampleSets of a collection

tennenrishin

Is there any way to perform a join of all ExampleSets in a collection of ExampleSets?

tennenrishin

Here is a solution that uses Remember/Recall operators. It feels like a hack. Does anyone have a better idea?

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.2.006">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.2.006" expanded="true" name="Process">
    <process expanded="true" height="479" width="924">
      <operator activated="true" class="generate_data_user_specification" compatibility="5.2.006" expanded="true" height="60" name="Generate Data by User Specification" width="90" x="45" y="75">
        <list key="attribute_values"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="generate_id" compatibility="5.2.006" expanded="true" height="76" name="Generate ID" width="90" x="179" y="75"/>
      <operator activated="true" class="filter_examples" compatibility="5.2.006" expanded="true" height="76" name="Filter Examples" width="90" x="313" y="75">
        <parameter key="invert_filter" value="true"/>
      </operator>
      <operator activated="true" class="remember" compatibility="5.2.006" expanded="true" height="60" name="Remember (3)" width="90" x="447" y="75">
        <parameter key="name" value="partial_join"/>
        <parameter key="io_object" value="ExampleSet"/>
      </operator>
      <operator activated="true" class="loop_collection" compatibility="5.2.006" expanded="true" height="60" name="Loop Collection" width="90" x="581" y="30">
        <process expanded="true" height="479" width="924">
          <operator activated="true" class="recall" compatibility="5.2.006" expanded="true" height="60" name="Recall" width="90" x="112" y="75">
            <parameter key="name" value="partial_join"/>
            <parameter key="io_object" value="ExampleSet"/>
          </operator>
          <operator activated="true" class="join" compatibility="5.2.006" expanded="true" height="76" name="Join" width="90" x="246" y="30">
            <parameter key="join_type" value="outer"/>
            <list key="key_attributes"/>
          </operator>
          <operator activated="true" class="remember" compatibility="5.2.006" expanded="true" height="60" name="Remember" width="90" x="380" y="30">
            <parameter key="name" value="partial_join"/>
            <parameter key="io_object" value="ExampleSet"/>
          </operator>
          <connect from_port="single" to_op="Join" to_port="left"/>
          <connect from_op="Recall" from_port="result" to_op="Join" to_port="right"/>
          <connect from_op="Join" from_port="join" to_op="Remember" to_port="store"/>
          <portSpacing port="source_single" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="recall" compatibility="5.2.006" expanded="true" height="60" name="Recall (2)" width="90" x="720" y="30">
        <parameter key="name" value="partial_join"/>
        <parameter key="io_object" value="ExampleSet"/>
      </operator>
      <connect from_port="input 1" to_op="Loop Collection" to_port="collection"/>
      <connect from_op="Generate Data by User Specification" from_port="output" to_op="Generate ID" to_port="example set input"/>
      <connect from_op="Generate ID" from_port="example set output" to_op="Filter Examples" to_port="example set input"/>
      <connect from_op="Filter Examples" from_port="example set output" to_op="Remember (3)" to_port="store"/>
      <connect from_op="Recall (2)" from_port="result" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="source_input 2" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>