Ada boost issue

B_Miner

Hi Guys-

Looks like the ada boost operator has an error. I can run the process without issue by using the Weka Ada boost and Weka decision stump.

Below is the code and then the error message.

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input>
      <location/>
    </input>
    <output>
      <location/>
      <location/>
      <location/>
    </output>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="546" width="386">
      <operator activated="true" class="read_csv" expanded="true" height="60" name="Read CSV" width="90" x="45" y="30">
        <parameter key="file_name" value="C:\Documents and Settings\aiufh35\Desktop\misc\PLAT\PLAT.csv"/>
      </operator>
      <operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="112" y="30">
        <parameter key="name" value="PLAT"/>
        <parameter key="target_role" value="label"/>
      </operator>
      <operator activated="true" class="numerical_to_binominal" expanded="true" height="76" name="Numerical to Binominal" width="90" x="271" y="-12">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="PLAT"/>
        <parameter key="include_special_attributes" value="true"/>
      </operator>
      <operator activated="true" class="read_csv" expanded="true" height="60" name="Read CSV (2)" width="90" x="45" y="210">
        <parameter key="file_name" value="C:\Documents and Settings\aiufh35\Desktop\misc\PLAT\PLAT_VAL.csv"/>
      </operator>
      <operator activated="true" class="set_role" expanded="true" height="76" name="Set Role (2)" width="90" x="45" y="300">
        <parameter key="name" value="PLAT"/>
        <parameter key="target_role" value="label"/>
      </operator>
      <operator activated="true" class="numerical_to_binominal" expanded="true" height="76" name="Numerical to Binominal (2)" width="90" x="45" y="390">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="PLAT"/>
        <parameter key="include_special_attributes" value="true"/>
      </operator>
      <operator activated="true" class="work_on_subset" expanded="true" height="76" name="Work on Subset" width="90" x="45" y="120">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="weight"/>
        <parameter key="attributes" value="torder_dum|sq_DAYSFROMAPPTOORD|SQ_SKUSPURCHASED|SQ_RCSPONORED|SQ_FULLCADENCE|RCSPONORED2_1|PRNT_PERSONALCAREREV|PRNT_NUTRITIONREV|PRNT_HOMECAREREV|PRNT_DURABLESREV|PRNT_BEAUTYREV|PLAT|PERSONALCAREREV|Ord2_1|NUTRITIONREV|LN_TOTALORDERS|LN_GROSSIBOPRICE|IBOSPONORED2_1|IBOSPONORED|HOMECAREREV|DaysIBO90|DURABLESREV|Cadence2_1|BEAUTYREV"/>
        <parameter key="invert_selection" value="true"/>
        <parameter key="include_special_attributes" value="true"/>
        <process expanded="true">
          <connect from_port="exampleSet" to_port="example set"/>
          <portSpacing port="source_exampleSet" spacing="0"/>
          <portSpacing port="sink_example set" spacing="0"/>
          <portSpacing port="sink_through 1" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="adaboost" expanded="true" height="76" name="AdaBoost" width="90" x="179" y="120">
        <process expanded="true" height="368" width="368">
          <operator activated="true" class="decision_stump" expanded="true" height="76" name="Decision Stump" width="90" x="65" y="42"/>
          <connect from_port="training set" to_op="Decision Stump" to_port="training set"/>
          <connect from_op="Decision Stump" from_port="model" to_port="model"/>
          <portSpacing port="source_training set" spacing="0"/>
          <portSpacing port="sink_model" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="196" y="243">
        <list key="application_parameters"/>
      </operator>
      <operator activated="true" class="performance" expanded="true" height="76" name="Performance" width="90" x="313" y="120"/>
      <connect from_op="Read CSV" from_port="output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Numerical to Binominal" to_port="example set input"/>
      <connect from_op="Numerical to Binominal" from_port="example set output" to_op="Work on Subset" to_port="example set"/>
      <connect from_op="Read CSV (2)" from_port="output" to_op="Set Role (2)" to_port="example set input"/>
      <connect from_op="Set Role (2)" from_port="example set output" to_op="Numerical to Binominal (2)" to_port="example set input"/>
      <connect from_op="Numerical to Binominal (2)" from_port="example set output" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Work on Subset" from_port="example set" to_op="AdaBoost" to_port="training set"/>
      <connect from_op="AdaBoost" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="AdaBoost" from_port="example set" to_port="result 2"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
      <connect from_op="Performance" from_port="performance" 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"/>
      <portSpacing port="sink_result 3" spacing="0"/>
    </process>
  </operator>
</process>

error:

Message: Cannot clone com.rapidminer.example.set.RemappedExampleSet: java.lang.reflect.InvocationTargetException. Target: java.lang.UnsupportedOperationException: The method getNominalMapping() is not supported by numerical attributes! You probably tried to execute an operator on a numerical data which is only able to handle nominal values. You could use one of the discretization operators before this application.. Cause: java.lang.UnsupportedOperationException: The method getNominalMapping() is not supported by numerical attributes! You probably tried to execute an operator on a numerical data which is only able to handle nominal values. You could use one of the discretization operators before this application..

haddock

Hi there,

The error message more probably indicates that something is awry with your data, rather than the operator; if you replace your datasources with a generator the problem disappears, like this..

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input>
      <location/>
    </input>
    <output>
      <location/>
      <location/>
      <location/>
    </output>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="478" width="915">
      <operator activated="true" class="generate_nominal_data" expanded="true" height="60" name="Generate Nominal Data" width="90" x="-8" y="79"/>
      <operator activated="true" class="multiply" expanded="true" height="94" name="Multiply" width="90" x="45" y="255"/>
      <operator activated="true" class="adaboost" expanded="true" height="76" name="AdaBoost" width="90" x="179" y="120">
        <process expanded="true" height="478" width="915">
          <operator activated="true" class="decision_stump" expanded="true" height="76" name="Decision Stump" width="90" x="65" y="42"/>
          <connect from_port="training set" to_op="Decision Stump" to_port="training set"/>
          <connect from_op="Decision Stump" from_port="model" to_port="model"/>
          <portSpacing port="source_training set" spacing="0"/>
          <portSpacing port="sink_model" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="196" y="243">
        <list key="application_parameters"/>
      </operator>
      <operator activated="true" class="performance" expanded="true" height="76" name="Performance" width="90" x="313" y="120"/>
      <connect from_op="Generate Nominal Data" from_port="output" to_op="Multiply" to_port="input"/>
      <connect from_op="Multiply" from_port="output 1" to_op="AdaBoost" to_port="training set"/>
      <connect from_op="Multiply" from_port="output 2" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="AdaBoost" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="AdaBoost" from_port="example set" to_port="result 2"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
      <connect from_op="Performance" from_port="performance" 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"/>
      <portSpacing port="sink_result 3" spacing="0"/>
    </process>
  </operator>
</process>

Perhaps you could put in a break to check your data - as far as I can make out your numerical to binominal operators just fill numerical columns with "true", which may not be what you want, like this..

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input>
      <location/>
    </input>
    <output>
      <location/>
      <location/>
    </output>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="478" width="915">
      <operator activated="true" breakpoints="after" class="generate_data" expanded="true" height="60" name="Generate Data" width="90" x="50" y="34"/>
      <operator activated="true" class="numerical_to_binominal" expanded="true" height="76" name="Numerical to Binominal" width="90" x="217" y="33"/>
      <connect from_op="Generate Data" from_port="output" to_op="Numerical to Binominal" to_port="example set input"/>
      <connect from_op="Numerical to Binominal" from_port="example set output" 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>

Anyways, good luck!

B_Miner

Hmmm thanks Haddock, I'll look at this. I thought since the process worked with other model operators as well as the Weka Ada boost the data was not at fault.

Regarding the numeric to binomial operator I had a target column coded 0,1 but it came through csv operator as numeric so I was <I thought> changing it to a type of nominal...