How one would go about writing Performance Results to an Excel File?

pblack476
pblack476 New Altair Community Member
edited November 2024 in Community Q&A
I have means of writing ExampleSets to excel, but there is no PerformanceVector To ExampleSet operator. How can I accomplish this?
Tagged:

Best Answer

  • scharpenberg
    scharpenberg New Altair Community Member
    Answer ✓
    Hi pblack476,

    I would like to add to David_A's solution that you can also directly get an exampleset via the Performance to Data operator.
    However there are no options and you will always simply get all selected criteria with their values, standard deviations and variances.

Answers

  • David_A
    David_A New Altair Community Member
    edited November 2019

    you can use the "log" operator to get the Performance vector. Then you can either write the log directly to disc or you can later in your process chain use the "Log to Data" operator to get an example set.

    Check the attached sample process for an example on how to use these two operators.

    Best,
    David



    <?xml version="1.0" encoding="UTF-8"?><process version="9.5.001">
      <

    context>
        <input/>
        <output/>
        <macros/>
      </context>
     
     <operator activated="true" class="process" compatibility="9.4.000"
    expanded="true" name="Process" origin="GENERATED_TUTORIAL">
        <parameter key="logverbosity" value="init"/>
        <parameter key="random_seed" value="2001"/>
        <parameter key="send_mail" value="never"/>
        <parameter key="notification_email" value=""/>
        <parameter key="process_duration_for_mail" value="30"/>
        <parameter key="encoding" value="SYSTEM"/>
        <process expanded="true">
         
     <operator activated="true" class="retrieve" compatibility="9.5.001"
    expanded="true" height="68" name="Weighting" origin="GENERATED_TUTORIAL"
     width="90" x="112" y="34">
            <parameter key="repository_entry" value="//Samples/data/Weighting"/>
          </operator>
         
     <operator activated="true" class="concurrency:loop_parameters"
    compatibility="8.2.000" expanded="true" height="82" name="Loop
    Parameters" origin="GENERATED_TUTORIAL" width="90" x="380" y="34">
            <list key="parameters">
              <parameter key="SVM.C" value="[0.001;100000;25;logarithmic]"/>
            </list>
            <parameter key="error_handling" value="fail on error"/>
            <parameter key="log_performance" value="true"/>
            <parameter key="log_all_criteria" value="false"/>
            <parameter key="synchronize" value="false"/>
            <parameter key="enable_parallel_execution" value="true"/>
            <process expanded="true">
             
     <operator activated="true" class="split_data"
    compatibility="9.5.001" expanded="true" height="103" name="Split Data"
    origin="GENERATED_TUTORIAL" width="90" x="45" y="120">
                <enumeration key="partitions">
                  <parameter key="ratio" value="0.5"/>
                  <parameter key="ratio" value="0.5"/>
                </enumeration>
                <parameter key="sampling_type" value="automatic"/>
                <parameter key="use_local_random_seed" value="false"/>
                <parameter key="local_random_seed" value="1992"/>
              </operator>
             
     <operator activated="true" class="support_vector_machine_libsvm"
    compatibility="9.5.001" expanded="true" height="82" name="SVM"
    origin="GENERATED_TUTORIAL" width="90" x="179" y="300">
                <parameter key="svm_type" value="C-SVC"/>
                <parameter key="kernel_type" value="rbf"/>
                <parameter key="degree" value="3"/>
                <parameter key="gamma" value="0.0"/>
                <parameter key="coef0" value="0.0"/>
                <parameter key="C" value="100000.0"/>
                <parameter key="nu" value="0.5"/>
                <parameter key="cache_size" value="80"/>
                <parameter key="epsilon" value="0.001"/>
                <parameter key="p" value="0.1"/>
                <list key="class_weights"/>
                <parameter key="shrinking" value="true"/>
                <parameter key="calculate_confidences" value="false"/>
                <parameter key="confidence_for_multiclass" value="true"/>
              </operator>
             
     <operator activated="true" class="multiply" compatibility="9.5.001"
    expanded="true" height="103" name="Multiply" origin="GENERATED_TUTORIAL"
     width="90" x="313" y="210"/>
              <operator
    activated="true" class="apply_model" compatibility="9.5.001"
    expanded="true" height="82" name="Apply Model (2)"
    origin="GENERATED_TUTORIAL" width="90" x="514" y="75">
                <list key="application_parameters"/>
                <parameter key="create_view" value="false"/>
              </operator>
             
     <operator activated="true" class="apply_model"
    compatibility="9.5.001" expanded="true" height="82" name="Apply Model"
    origin="GENERATED_TUTORIAL" width="90" x="514" y="300">
                <list key="application_parameters"/>
                <parameter key="create_view" value="false"/>
              </operator>
             
     <operator activated="true" class="performance_classification"
    compatibility="9.5.001" expanded="true" height="82" name="Performance"
    origin="GENERATED_TUTORIAL" width="90" x="648" y="300">
                <parameter key="main_criterion" value="first"/>
                <parameter key="accuracy" value="false"/>
                <parameter key="classification_error" value="true"/>
                <parameter key="kappa" value="false"/>
                <parameter key="weighted_mean_recall" value="false"/>
                <parameter key="weighted_mean_precision" value="false"/>
                <parameter key="spearman_rho" value="false"/>
                <parameter key="kendall_tau" value="false"/>
                <parameter key="absolute_error" value="false"/>
                <parameter key="relative_error" value="false"/>
                <parameter key="relative_error_lenient" value="false"/>
                <parameter key="relative_error_strict" value="false"/>
                <parameter key="normalized_absolute_error" value="false"/>
                <parameter key="root_mean_squared_error" value="false"/>
                <parameter key="root_relative_squared_error" value="false"/>
                <parameter key="squared_error" value="false"/>
                <parameter key="correlation" value="false"/>
                <parameter key="squared_correlation" value="false"/>
                <parameter key="cross-entropy" value="false"/>
                <parameter key="margin" value="false"/>
                <parameter key="soft_margin_loss" value="false"/>
                <parameter key="logistic_loss" value="false"/>
                <parameter key="skip_undefined_labels" value="true"/>
                <parameter key="use_example_weights" value="true"/>
                <list key="class_weights"/>
              </operator>
             
     <operator activated="true" class="performance_classification"
    compatibility="9.5.001" expanded="true" height="82" name="Performance
    (2)" origin="GENERATED_TUTORIAL" width="90" x="648" y="75">
                <parameter key="main_criterion" value="first"/>
                <parameter key="accuracy" value="false"/>
                <parameter key="classification_error" value="true"/>
                <parameter key="kappa" value="false"/>
                <parameter key="weighted_mean_recall" value="false"/>
                <parameter key="weighted_mean_precision" value="false"/>
                <parameter key="spearman_rho" value="false"/>
                <parameter key="kendall_tau" value="false"/>
                <parameter key="absolute_error" value="false"/>
                <parameter key="relative_error" value="false"/>
                <parameter key="relative_error_lenient" value="false"/>
                <parameter key="relative_error_strict" value="false"/>
                <parameter key="normalized_absolute_error" value="false"/>
                <parameter key="root_mean_squared_error" value="false"/>
                <parameter key="root_relative_squared_error" value="false"/>
                <parameter key="squared_error" value="false"/>
                <parameter key="correlation" value="false"/>
                <parameter key="squared_correlation" value="false"/>
                <parameter key="cross-entropy" value="false"/>
                <parameter key="margin" value="false"/>
                <parameter key="soft_margin_loss" value="false"/>
                <parameter key="logistic_loss" value="false"/>
                <parameter key="skip_undefined_labels" value="true"/>
                <parameter key="use_example_weights" value="true"/>
                <list key="class_weights"/>
              </operator>
             
     <operator activated="true" class="log" compatibility="9.5.001"
    expanded="true" height="82" name="Log" origin="GENERATED_TUTORIAL"
    width="90" x="782" y="75">
                <list key="log">
                  <parameter key="Count" value="operator.Loop Parameters.value.iteration_number"/>
                  <parameter key="Training Error" value="operator.Performance.value.classification_error"/>
                  <parameter key="Testing Error" value="operator.Performance (2).value.classification_error"/>
                  <parameter key="SVM C" value="operator.SVM.parameter.C"/>
                </list>
                <parameter key="sorting_type" value="none"/>
                <parameter key="sorting_k" value="100"/>
                <parameter key="persistent" value="false"/>
              </operator>
              <connect from_port="input 1" to_op="Split Data" to_port="example set"/>
              <connect from_op="Split Data" from_port="partition 1" to_op="Apply Model (2)" to_port="unlabelled data"/>
              <connect from_op="Split Data" from_port="partition 2" to_op="SVM" to_port="training set"/>
              <connect from_op="SVM" from_port="model" to_op="Multiply" to_port="input"/>
              <connect from_op="SVM" from_port="exampleSet" to_op="Apply Model" to_port="unlabelled data"/>
              <connect from_op="Multiply" from_port="output 1" to_op="Apply Model (2)" to_port="model"/>
              <connect from_op="Multiply" from_port="output 2" to_op="Apply Model" to_port="model"/>
              <connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance (2)" to_port="labelled data"/>
              <connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
              <connect from_op="Performance (2)" from_port="performance" to_op="Log" to_port="through 1"/>
              <portSpacing port="source_input 1" spacing="90"/>
              <portSpacing port="source_input 2" spacing="90"/>
              <portSpacing port="sink_performance" spacing="90"/>
              <portSpacing port="sink_output 1" spacing="0"/>
              <portSpacing port="sink_output 2" spacing="0"/>
            </process>
          </operator>
         
     <operator activated="true" class="log_to_data"
    compatibility="9.5.001" expanded="true" height="103" name="Log to Data"
    width="90" x="648" y="34">
            <parameter key="log_name" value="Log"/>
           
     <description align="center" color="transparent" colored="false"
    width="126">The &amp;quot;Log Name&amp;quot; parameter is the
     exact name of the log operator you want to extract</description>
          </operator>
          <connect from_op="Weighting" from_port="output" to_op="Loop Parameters" to_port="input 1"/>
          <connect from_op="Loop Parameters" from_port="output 1" to_op="Log to Data" to_port="through 1"/>
          <connect from_op="Log to Data" from_port="exampleSet" 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>
  • scharpenberg
    scharpenberg New Altair Community Member
    Answer ✓
    Hi pblack476,

    I would like to add to David_A's solution that you can also directly get an exampleset via the Performance to Data operator.
    However there are no options and you will always simply get all selected criteria with their values, standard deviations and variances.
  • pblack476
    pblack476 New Altair Community Member
    Thanks! I really don't need any customization done. Just getting it to Excel is fine and I can do the rest there, so I'll stick to scharpenberg's solution for starters.

Categories