DBScan epsilon parameter cannot be logged with version 5.1

Andrew2

Hello all,

I'm trying to investigate how DBScan behaves as eplison and min_points are varied but I noticed warnings when the process attempts to log the min_points parameter of the DBScan operator.

"No such parameter in 'com.rapidminer.parameter.ParameterTypeValue$OperatorValueSelection@1bfa971b"

And sure enough, there are missing values in the log output.

I just upgraded to 5.1 and I'm fairly sure this worked with the last 5.0 version.

I'm working on a macro driven workaround which I will post when I get it working.

regards

Andrew

Andrew2

Here it is

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.1.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.1.000" expanded="true" name="Process">
    <process expanded="true" height="476" width="815">
      <operator activated="true" class="generate_data" compatibility="5.1.000" expanded="true" height="60" name="Generate Data" width="90" x="45" y="75">
        <parameter key="target_function" value="three ring clusters"/>
        <parameter key="number_of_attributes" value="2"/>
      </operator>
      <operator activated="true" class="normalize" compatibility="5.1.000" expanded="true" height="94" name="Normalize" width="90" x="246" y="75">
        <parameter key="method" value="range transformation"/>
      </operator>
      <operator activated="true" class="set_macros" compatibility="5.1.000" expanded="true" height="76" name="Set Macros" width="90" x="447" y="75">
        <list key="macros">
          <parameter key="epsilonStart" value="0.005"/>
          <parameter key="epsilonIncrement" value="0.002"/>
          <parameter key="loopCounter" value="0"/>
          <parameter key="maxLoop" value="10"/>
        </list>
      </operator>
      <operator activated="true" class="loop" compatibility="5.1.000" expanded="true" height="76" name="Loop" width="90" x="648" y="75">
        <parameter key="iterations" value="%{maxLoop}"/>
        <process expanded="true" height="579" width="984">
          <operator activated="true" class="generate_macro" compatibility="5.1.000" expanded="true" height="76" name="Generate Macro" width="90" x="112" y="30">
            <list key="function_descriptions">
              <parameter key="epsilon" value="%{epsilonStart}+%{epsilonIncrement}*%{loopCounter}"/>
              <parameter key="loopCounter" value="%{loopCounter}+1"/>
            </list>
          </operator>
          <operator activated="true" class="provide_macro_as_log_value" compatibility="5.1.000" expanded="true" height="76" name="Provide Macro as Log Value (2)" width="90" x="246" y="30">
            <parameter key="macro_name" value="epsilon"/>
          </operator>
          <operator activated="true" class="optimize_parameters_grid" compatibility="5.1.000" expanded="true" height="94" name="Optimize Parameters (Grid)" width="90" x="380" y="30">
            <list key="parameters">
              <parameter key="Clustering.min_points" value="[2;21;20;linear]"/>
            </list>
            <process expanded="true" height="579" width="984">
              <operator activated="true" class="dbscan" compatibility="5.1.000" expanded="true" height="76" name="Clustering" width="90" x="179" y="165">
                <parameter key="epsilon" value="%{epsilon}"/>
                <parameter key="min_points" value="21"/>
              </operator>
              <operator activated="true" class="cluster_count_performance" compatibility="5.1.000" expanded="true" height="76" name="Count" width="90" x="313" y="165"/>
              <operator activated="true" class="provide_macro_as_log_value" compatibility="5.1.000" expanded="true" height="76" name="Provide Macro as Log Value" width="90" x="514" y="165">
                <parameter key="macro_name" value="loopCounter"/>
              </operator>
              <operator activated="true" class="log" compatibility="5.1.000" expanded="true" height="76" name="Log (3)" width="90" x="715" y="165">
                <list key="log">
                  <parameter key="epsilon" value="operator.Provide Macro as Log Value (2).value.macro_value"/>
                  <parameter key="epsilonMissingFromDBSCAN" value="operator.Clustering.parameter."/>
                  <parameter key="minPoints" value="operator.Clustering.parameter.min_points"/>
                  <parameter key="loopCounter" value="operator.Provide Macro as Log Value.value.macro_value"/>
                  <parameter key="clusterNumber" value="operator.Count.value.clusternumber"/>
                </list>
              </operator>
              <connect from_port="input 1" to_op="Clustering" to_port="example set"/>
              <connect from_op="Clustering" from_port="cluster model" to_op="Count" to_port="cluster model"/>
              <connect from_op="Count" from_port="performance" to_op="Provide Macro as Log Value" to_port="through 1"/>
              <connect from_op="Provide Macro as Log Value" from_port="through 1" to_op="Log (3)" to_port="through 1"/>
              <connect from_op="Log (3)" from_port="through 1" to_port="performance"/>
              <portSpacing port="source_input 1" spacing="0"/>
              <portSpacing port="source_input 2" spacing="0"/>
              <portSpacing port="sink_performance" spacing="180"/>
              <portSpacing port="sink_result 1" spacing="0"/>
            </process>
          </operator>
          <connect from_port="input 1" to_op="Generate Macro" to_port="through 1"/>
          <connect from_op="Generate Macro" from_port="through 1" to_op="Provide Macro as Log Value (2)" to_port="through 1"/>
          <connect from_op="Provide Macro as Log Value (2)" from_port="through 1" to_op="Optimize Parameters (Grid)" to_port="input 1"/>
          <connect from_op="Optimize Parameters (Grid)" from_port="performance" to_port="output 1"/>
          <portSpacing port="source_input 1" spacing="0"/>
          <portSpacing port="source_input 2" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
          <portSpacing port="sink_output 2" spacing="0"/>
        </process>
      </operator>
      <connect from_op="Generate Data" from_port="output" to_op="Normalize" to_port="example set input"/>
      <connect from_op="Normalize" from_port="example set output" to_op="Set Macros" to_port="through 1"/>
      <connect from_op="Set Macros" from_port="through 1" to_op="Loop" to_port="input 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
    </process>
  </operator>
</process>

Andrew