"SVM and Bootstrapping"

holdwater587

Hi, i am a newbie

i have a data of 5 attributes and 200 rows and use epsilon-SVR.
First, i want to get 100 bootstrap sample and then use each sample on my SVM model.
Each SVM model will predict my test data.
And finally i want to plot these 100 predictions on the same graph.

Shortly, it is like i have 100 training data and so 100 different SVM model and i want to test all these on my test data.

Is it possible in rapidminer (can we use loop etc.)

Thx in advance

wessel

Like this?

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.1.008">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.1.008" expanded="true" name="Process">
    <process expanded="true" height="377" width="547">
      <operator activated="true" class="retrieve" compatibility="5.1.008" expanded="true" height="60" name="Retrieve" width="90" x="45" y="30">
        <parameter key="repository_entry" value="//Samples/data/Sonar"/>
      </operator>
      <operator activated="true" class="nominal_to_numerical" compatibility="5.1.008" expanded="true" height="94" name="Nominal to Numerical" width="90" x="179" y="30">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="class"/>
        <parameter key="include_special_attributes" value="true"/>
      </operator>
      <operator activated="true" class="bootstrapping_validation" compatibility="5.1.008" expanded="true" height="112" name="Validation" width="90" x="313" y="30">
        <process expanded="true" height="409" width="165">
          <operator activated="true" class="support_vector_machine_libsvm" compatibility="5.1.008" expanded="true" height="76" name="SVM" width="90" x="45" y="30">
            <parameter key="svm_type" value="epsilon-SVR"/>
            <list key="class_weights"/>
          </operator>
          <connect from_port="training" to_op="SVM" to_port="training set"/>
          <connect from_op="SVM" 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="409" width="300">
          <operator activated="true" class="apply_model" compatibility="5.1.008" expanded="true" height="76" name="Apply Model" width="90" x="45" y="30">
            <list key="application_parameters"/>
          </operator>
          <operator activated="true" class="performance" compatibility="5.1.008" expanded="true" height="76" name="Performance (2)" width="90" x="179" y="30"/>
          <connect from_port="model" to_op="Apply Model" to_port="model"/>
          <connect from_port="test set" to_op="Apply Model" to_port="unlabelled data"/>
          <connect from_op="Apply Model" from_port="labelled data" to_op="Performance (2)" to_port="labelled data"/>
          <connect from_op="Performance (2)" 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>
      <connect from_op="Retrieve" from_port="output" to_op="Nominal to Numerical" to_port="example set input"/>
      <connect from_op="Nominal to Numerical" from_port="example set output" to_op="Validation" to_port="training"/>
      <connect from_op="Validation" from_port="averagable 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>

wessel

Here is a slightly more advanced example.
This writes out predictions to a file, and retrieves them later to plot.
Might be a better way to do this.
If so, please let me know.

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.1.008">
 <context>
   <input/>
   <output/>
   <macros/>
 </context>
 <operator activated="true" class="process" compatibility="5.1.008" expanded="true" name="Process">
   <process expanded="true" height="409" width="815">
     <operator activated="true" class="retrieve" compatibility="5.1.008" expanded="true" height="60" name="Retrieve" width="90" x="45" y="30">
       <parameter key="repository_entry" value="//Samples/data/Polynomial"/>
     </operator>
     <operator activated="true" class="bootstrapping_validation" compatibility="5.1.008" expanded="true" height="112" name="Validation" width="90" x="313" y="30">
       <process expanded="true" height="409" width="165">
         <operator activated="true" class="support_vector_machine_libsvm" compatibility="5.1.008" expanded="true" height="76" name="SVM" width="90" x="45" y="30">
           <parameter key="svm_type" value="epsilon-SVR"/>
           <list key="class_weights"/>
         </operator>
         <connect from_port="training" to_op="SVM" to_port="training set"/>
         <connect from_op="SVM" 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="409" width="480">
         <operator activated="true" class="apply_model" compatibility="5.1.008" expanded="true" height="76" name="Apply Model" width="90" x="45" y="30">
           <list key="application_parameters"/>
         </operator>
         <operator activated="true" class="select_attributes" compatibility="5.1.008" expanded="true" height="76" name="Select Attributes" width="90" x="45" y="120">
           <parameter key="attribute_filter_type" value="single"/>
           <parameter key="attribute" value="prediction(label)"/>
           <parameter key="include_special_attributes" value="true"/>
         </operator>
         <operator activated="true" class="transpose" compatibility="5.1.008" expanded="true" height="76" name="Transpose" width="90" x="45" y="255"/>
         <operator activated="true" class="performance" compatibility="5.1.008" expanded="true" height="76" name="Performance (2)" width="90" x="313" y="30"/>
         <operator activated="true" class="write_special" compatibility="5.1.008" expanded="true" height="60" name="Write Special Format" width="90" x="179" y="255">
           <parameter key="example_set_file" value="C:\Users\wessel\Desktop\z"/>
           <parameter key="special_format" value="$a"/>
         </operator>
         <connect from_port="model" to_op="Apply Model" to_port="model"/>
         <connect from_port="test set" to_op="Apply Model" to_port="unlabelled data"/>
         <connect from_op="Apply Model" from_port="labelled data" to_op="Select Attributes" to_port="example set input"/>
         <connect from_op="Select Attributes" from_port="example set output" to_op="Transpose" to_port="example set input"/>
         <connect from_op="Select Attributes" from_port="original" to_op="Performance (2)" to_port="labelled data"/>
         <connect from_op="Transpose" from_port="example set output" to_op="Write Special Format" to_port="input"/>
         <connect from_op="Performance (2)" 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="read_csv" compatibility="5.1.008" expanded="true" height="60" name="Read CSV" width="90" x="45" y="255">
       <parameter key="csv_file" value="C:\Users\wessel\Desktop\z"/>
       <parameter key="column_separators" value=" "/>
       <parameter key="first_row_as_names" value="false"/>
       <list key="annotations"/>
       <list key="data_set_meta_data_information"/>
     </operator>
     <operator activated="true" class="transpose" compatibility="5.1.008" expanded="true" height="76" name="Transpose (2)" width="90" x="313" y="255"/>
     <operator activated="true" class="generate_id" compatibility="5.1.008" expanded="true" height="76" name="Generate ID (2)" width="90" x="444" y="255"/>
     <operator activated="true" class="generate_id" compatibility="5.1.008" expanded="true" height="76" name="Generate ID" width="90" x="447" y="165"/>
     <operator activated="true" class="join" compatibility="5.1.008" expanded="true" height="76" name="Join" width="90" x="581" y="210"/>
     <operator activated="true" class="rename_by_replacing" compatibility="5.1.008" expanded="true" height="76" name="Rename by Replacing" width="90" x="715" y="210">
       <parameter key="replace_what" value="att"/>
       <parameter key="replace_by" value="pred"/>
     </operator>
     <connect from_op="Retrieve" from_port="output" to_op="Validation" to_port="training"/>
     <connect from_op="Validation" from_port="training" to_op="Generate ID" to_port="example set input"/>
     <connect from_op="Validation" from_port="averagable 1" to_port="result 1"/>
     <connect from_op="Read CSV" from_port="output" to_op="Transpose (2)" to_port="example set input"/>
     <connect from_op="Transpose (2)" from_port="example set output" to_op="Generate ID (2)" to_port="example set input"/>
     <connect from_op="Generate ID (2)" from_port="example set output" to_op="Join" to_port="right"/>
     <connect from_op="Generate ID" from_port="example set output" to_op="Join" to_port="left"/>
     <connect from_op="Join" from_port="join" to_op="Rename by Replacing" to_port="example set input"/>
     <connect from_op="Rename by Replacing" from_port="example set output" to_port="result 2"/>
     <portSpacing port="source_input 1" spacing="0"/>
     <portSpacing port="sink_result 1" spacing="0"/>
     <portSpacing port="sink_result 2" spacing="216"/>
     <portSpacing port="sink_result 3" spacing="0"/>
   </process>
 </operator>
</process>

wessel

Here is the resulting plot: