RapidMiner 9.7 is Now Available

Lots of amazing new improvements including true version control! Learn more about what's new here.

CLICK HERE TO DOWNLOAD

"Difference in Performance Logging"

tektek Member Posts: 19  Maven
edited June 2019 in Help
Hey,

in my process:

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.1.006">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.1.006" expanded="true" name="Process">
    <process expanded="true" height="444" width="563">
      <operator activated="true" class="free_memory" compatibility="5.1.006" expanded="true" height="76" name="Free Memory" width="90" x="246" y="30"/>
      <operator activated="true" class="loop_parameters" compatibility="5.1.006" expanded="true" height="76" name="Loop Parameters" width="90" x="380" y="30">
        <list key="parameters">
          <parameter key="Neural Net.learning_rate" value="0.3"/>
        </list>
        <process expanded="true" height="444" width="563">
          <operator activated="true" class="split_data" compatibility="5.1.006" expanded="true" height="94" name="Split Outer" width="90" x="45" y="30">
            <enumeration key="partitions">
              <parameter key="ratio" value="0.8"/>
              <parameter key="ratio" value="0.2"/>
            </enumeration>
          </operator>
          <operator activated="true" class="x_validation" compatibility="5.1.006" expanded="true" height="112" name="Validation" width="90" x="180" y="30">
            <parameter key="sampling_type" value="shuffled sampling"/>
            <process expanded="true" height="444" width="165">
              <operator activated="true" class="neural_net" compatibility="5.1.006" expanded="true" height="76" name="Neural Net" width="90" x="45" y="30">
                <list key="hidden_layers"/>
              </operator>
              <connect from_port="training" to_op="Neural Net" to_port="training set"/>
              <connect from_op="Neural Net" from_port="model" to_port="model"/>
              <portSpacing port="source_training" spacing="0"/>
              <portSpacing port="sink_model" spacing="0"/>
              <portSpacing port="sink_through 1" spacing="0"/>
            </process>
            <process expanded="true" height="444" width="300">
              <operator activated="true" class="apply_model" compatibility="5.1.006" expanded="true" height="76" name="CVApply" width="90" x="45" y="30">
                <list key="application_parameters"/>
              </operator>
              <operator activated="true" class="performance_regression" compatibility="5.1.006" expanded="true" height="76" name="CVPerf" width="90" x="180" y="30">
                <parameter key="absolute_error" value="true"/>
                <parameter key="relative_error" value="true"/>
                <parameter key="correlation" value="true"/>
              </operator>
              <connect from_port="model" to_op="CVApply" to_port="model"/>
              <connect from_port="test set" to_op="CVApply" to_port="unlabelled data"/>
              <connect from_op="CVApply" from_port="labelled data" to_op="CVPerf" to_port="labelled data"/>
              <connect from_op="CVPerf" from_port="performance" to_port="averagable 1"/>
              <portSpacing port="source_model" spacing="0"/>
              <portSpacing port="source_test set" spacing="0"/>
              <portSpacing port="source_through 1" spacing="0"/>
              <portSpacing port="sink_averagable 1" spacing="0"/>
              <portSpacing port="sink_averagable 2" spacing="0"/>
            </process>
          </operator>
          <operator activated="true" class="apply_model" compatibility="5.1.006" expanded="true" height="76" name="HOApply" width="90" x="315" y="30">
            <list key="application_parameters"/>
          </operator>
          <operator activated="true" class="performance_regression" compatibility="5.1.006" expanded="true" height="76" name="HOPerf" width="90" x="450" y="30">
            <parameter key="absolute_error" value="true"/>
            <parameter key="relative_error" value="true"/>
            <parameter key="correlation" value="true"/>
          </operator>
          <operator activated="true" class="log" compatibility="5.1.006" expanded="true" height="76" name="Log" width="90" x="447" y="210">
            <list key="log">
              <parameter key="CVPerformance" value="operator.CVPerf.value.performance"/>
              <parameter key="HOPerformance" value="operator.HOPerf.value.performance"/>
              <parameter key="CValidation" value="operator.Validation.value.performance"/>
            </list>
          </operator>
          <connect from_port="input 1" to_op="Split Outer" to_port="example set"/>
          <connect from_op="Split Outer" from_port="partition 1" to_op="Validation" to_port="training"/>
          <connect from_op="Split Outer" from_port="partition 2" to_op="HOApply" to_port="unlabelled data"/>
          <connect from_op="Validation" from_port="model" to_op="HOApply" to_port="model"/>
          <connect from_op="HOApply" from_port="labelled data" to_op="HOPerf" to_port="labelled data"/>
          <connect from_op="HOApply" from_port="model" to_port="result 1"/>
          <connect from_op="HOPerf" from_port="performance" to_op="Log" to_port="through 1"/>
          <portSpacing port="source_input 1" spacing="0"/>
          <portSpacing port="source_input 2" spacing="0"/>
          <portSpacing port="sink_performance" spacing="0"/>
          <portSpacing port="sink_result 1" spacing="0"/>
          <portSpacing port="sink_result 2" spacing="0"/>
        </process>
      </operator>
      <connect from_op="Free Memory" from_port="through 1" to_op="Loop Parameters" to_port="input 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
    </process>
  </operator>
</process>

I am logging 3 different performance values. Whats the difference between logging the performance criterion from "CVPerf" and "CValidation"?

It has a tremendous effect on the logged value, which surprised me. I thought that the performance of the inner performance operator should be equal to the one outputted by the x-Validation Operator?

Thanks for the help!
Tagged:
Sign In or Register to comment.