I want to know the accuracy of data testing and training with the method of optimize generate (GGA)

s_na99s_na99 Member Posts: 1 Newbie
edited November 2019 in Help
I want to know the accuracy of data testing and training with the method of optimize generate (GGA), how do I do that? thank you
Tagged:

Answers

  • lionelderkrikorlionelderkrikor Moderator, RapidMiner Certified Analyst, Member Posts: 1,195 Unicorn
    Hi @s_na99,

    Here a process which performs what you want to do : 

    I put an Apply Model and a Performance operators in the training part of the Cross validation operator (to have the training error) : 



    BTW do you know that oyu can use the new Automatic Feature Engineering operator which performs automatically
    for you the Feaure selection and feature generation for you ?
    You can test it via submitting your data to AutoModel..or directly in RapidMiner  GUI...

    The process : 

    <?xml version="1.0" encoding="UTF-8"?><process version="9.5.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="6.0.002" expanded="true" name="Root" origin="GENERATED_TUTORIAL">
    <parameter key="logverbosity" value="init"/>
    <parameter key="random_seed" value="1969"/>
    <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" breakpoints="after" class="retrieve" compatibility="9.5.000" expanded="true" height="68" name="Retrieve Sonar" width="90" x="112" y="136">
        <parameter key="repository_entry" value="//Samples/data/Sonar"/>
      </operator>
      <operator activated="true" class="concurrency:cross_validation" compatibility="9.5.000" expanded="true" height="166" name="Cross Validation" width="90" x="380" y="136">
        <parameter key="split_on_batch_attribute" value="false"/>
        <parameter key="leave_one_out" value="false"/>
        <parameter key="number_of_folds" value="3"/>
        <parameter key="sampling_type" value="automatic"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
        <parameter key="enable_parallel_execution" value="true"/>
        <process expanded="true">
          <operator activated="true" class="multiply" compatibility="9.5.000" expanded="true" height="103" name="Multiply" width="90" x="45" y="34"/>
          <operator activated="true" class="optimize_by_generation_gga" compatibility="9.5.000" expanded="true" height="103" name="Generate" width="90" x="179" y="136">
            <parameter key="max_number_of_new_attributes" value="1"/>
            <parameter key="limit_max_total_number_of_attributes" value="false"/>
            <parameter key="max_total_number_of_attributes" value="1"/>
            <parameter key="use_local_random_seed" value="false"/>
            <parameter key="local_random_seed" value="1992"/>
            <parameter key="maximal_fitness" value="Infinity"/>
            <parameter key="population_size" value="5"/>
            <parameter key="maximum_number_of_generations" value="30"/>
            <parameter key="use_plus" value="true"/>
            <parameter key="use_diff" value="false"/>
            <parameter key="use_mult" value="true"/>
            <parameter key="use_div" value="false"/>
            <parameter key="reciprocal_value" value="true"/>
            <parameter key="use_early_stopping" value="false"/>
            <parameter key="generations_without_improval" value="2"/>
            <parameter key="tournament_size" value="0.25"/>
            <parameter key="start_temperature" value="1.0"/>
            <parameter key="dynamic_selection_pressure" value="true"/>
            <parameter key="keep_best_individual" value="false"/>
            <parameter key="p_initialize" value="0.5"/>
            <parameter key="p_crossover" value="0.5"/>
            <parameter key="crossover_type" value="uniform"/>
            <parameter key="p_generate" value="0.1"/>
            <parameter key="use_heuristic_mutation_probability" value="true"/>
            <process expanded="true">
              <operator activated="true" class="concurrency:cross_validation" compatibility="9.5.000" expanded="true" height="145" name="Cross Validation (2)" width="90" x="447" y="85">
                <parameter key="split_on_batch_attribute" value="false"/>
                <parameter key="leave_one_out" value="false"/>
                <parameter key="number_of_folds" value="5"/>
                <parameter key="sampling_type" value="automatic"/>
                <parameter key="use_local_random_seed" value="false"/>
                <parameter key="local_random_seed" value="1992"/>
                <parameter key="enable_parallel_execution" value="true"/>
                <process expanded="true">
                  <operator activated="true" class="k_nn" compatibility="9.5.000" expanded="true" height="82" name="k-NN" width="90" x="179" y="34">
                    <parameter key="k" value="5"/>
                    <parameter key="weighted_vote" value="true"/>
                    <parameter key="measure_types" value="MixedMeasures"/>
                    <parameter key="mixed_measure" value="MixedEuclideanDistance"/>
                    <parameter key="nominal_measure" value="NominalDistance"/>
                    <parameter key="numerical_measure" value="EuclideanDistance"/>
                    <parameter key="divergence" value="GeneralizedIDivergence"/>
                    <parameter key="kernel_type" value="radial"/>
                    <parameter key="kernel_gamma" value="1.0"/>
                    <parameter key="kernel_sigma1" value="1.0"/>
                    <parameter key="kernel_sigma2" value="0.0"/>
                    <parameter key="kernel_sigma3" value="2.0"/>
                    <parameter key="kernel_degree" value="3.0"/>
                    <parameter key="kernel_shift" value="1.0"/>
                    <parameter key="kernel_a" value="1.0"/>
                    <parameter key="kernel_b" value="0.0"/>
                  </operator>
                  <connect from_port="training set" to_op="k-NN" to_port="training set"/>
                  <connect from_op="k-NN" from_port="model" to_port="model"/>
                  <portSpacing port="source_training set" spacing="0"/>
                  <portSpacing port="sink_model" spacing="0"/>
                  <portSpacing port="sink_through 1" spacing="0"/>
                </process>
                <process expanded="true">
                  <operator activated="true" class="apply_model" compatibility="9.5.000" expanded="true" height="82" name="Apply Model" width="90" x="112" y="34">
                    <list key="application_parameters"/>
                    <parameter key="create_view" value="false"/>
                  </operator>
                  <operator activated="true" class="performance_classification" compatibility="9.5.000" expanded="true" height="82" name="Performance" width="90" x="246" y="34">
                    <parameter key="main_criterion" value="first"/>
                    <parameter key="accuracy" value="true"/>
                    <parameter key="classification_error" value="false"/>
                    <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>
                  <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" to_port="labelled data"/>
                  <connect from_op="Performance" from_port="performance" to_port="performance 1"/>
                  <portSpacing port="source_model" spacing="0"/>
                  <portSpacing port="source_test set" spacing="0"/>
                  <portSpacing port="source_through 1" spacing="0"/>
                  <portSpacing port="sink_test set results" spacing="0"/>
                  <portSpacing port="sink_performance 1" spacing="0"/>
                  <portSpacing port="sink_performance 2" spacing="0"/>
                </process>
              </operator>
              <connect from_port="example set source" to_op="Cross Validation (2)" to_port="example set"/>
              <connect from_op="Cross Validation (2)" from_port="performance 1" to_port="performance sink"/>
              <portSpacing port="source_example set source" spacing="0"/>
              <portSpacing port="sink_performance sink" spacing="0"/>
            </process>
          </operator>
          <operator activated="true" class="select_by_weights" compatibility="9.5.000" expanded="true" height="103" name="Select by Weights" width="90" x="313" y="34">
            <parameter key="weight_relation" value="greater equals"/>
            <parameter key="weight" value="1.0"/>
            <parameter key="k" value="10"/>
            <parameter key="p" value="0.5"/>
            <parameter key="deselect_unknown" value="true"/>
            <parameter key="use_absolute_weights" value="true"/>
          </operator>
          <operator activated="true" class="k_nn" compatibility="9.5.000" expanded="true" height="82" name="k-NN (2)" width="90" x="447" y="34">
            <parameter key="k" value="5"/>
            <parameter key="weighted_vote" value="true"/>
            <parameter key="measure_types" value="MixedMeasures"/>
            <parameter key="mixed_measure" value="MixedEuclideanDistance"/>
            <parameter key="nominal_measure" value="NominalDistance"/>
            <parameter key="numerical_measure" value="EuclideanDistance"/>
            <parameter key="divergence" value="GeneralizedIDivergence"/>
            <parameter key="kernel_type" value="radial"/>
            <parameter key="kernel_gamma" value="1.0"/>
            <parameter key="kernel_sigma1" value="1.0"/>
            <parameter key="kernel_sigma2" value="0.0"/>
            <parameter key="kernel_sigma3" value="2.0"/>
            <parameter key="kernel_degree" value="3.0"/>
            <parameter key="kernel_shift" value="1.0"/>
            <parameter key="kernel_a" value="1.0"/>
            <parameter key="kernel_b" value="0.0"/>
          </operator>
          <operator activated="true" class="multiply" compatibility="9.5.000" expanded="true" height="103" name="Multiply (2)" width="90" x="447" y="136"/>
          <operator activated="true" class="apply_model" compatibility="9.5.000" expanded="true" height="82" name="Apply Model (2)" width="90" x="581" y="136">
            <list key="application_parameters"/>
            <parameter key="create_view" value="false"/>
          </operator>
          <operator activated="true" class="performance_classification" compatibility="9.5.000" expanded="true" height="82" name="Training_performance" width="90" x="581" y="238">
            <parameter key="main_criterion" value="first"/>
            <parameter key="accuracy" value="true"/>
            <parameter key="classification_error" value="false"/>
            <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>
          <connect from_port="training set" to_op="Multiply" to_port="input"/>
          <connect from_op="Multiply" from_port="output 1" to_op="Select by Weights" to_port="example set input"/>
          <connect from_op="Multiply" from_port="output 2" to_op="Generate" to_port="example set in"/>
          <connect from_op="Generate" from_port="attribute weights out" to_op="Select by Weights" to_port="weights"/>
          <connect from_op="Select by Weights" from_port="example set output" to_op="k-NN (2)" to_port="training set"/>
          <connect from_op="Select by Weights" from_port="weights" to_port="through 2"/>
          <connect from_op="k-NN (2)" from_port="model" to_op="Multiply (2)" to_port="input"/>
          <connect from_op="k-NN (2)" from_port="exampleSet" to_op="Apply Model (2)" to_port="unlabelled data"/>
          <connect from_op="Multiply (2)" from_port="output 1" to_op="Apply Model (2)" to_port="model"/>
          <connect from_op="Multiply (2)" from_port="output 2" to_port="model"/>
          <connect from_op="Apply Model (2)" from_port="labelled data" to_op="Training_performance" to_port="labelled data"/>
          <connect from_op="Training_performance" from_port="performance" to_port="through 1"/>
          <portSpacing port="source_training set" spacing="0"/>
          <portSpacing port="sink_model" spacing="0"/>
          <portSpacing port="sink_through 1" spacing="0"/>
          <portSpacing port="sink_through 2" spacing="0"/>
          <portSpacing port="sink_through 3" spacing="0"/>
        </process>
        <process expanded="true">
          <operator activated="true" class="select_by_weights" compatibility="9.5.000" expanded="true" height="103" name="Select by Weights (2)" width="90" x="112" y="85">
            <parameter key="weight_relation" value="greater equals"/>
            <parameter key="weight" value="1.0"/>
            <parameter key="k" value="10"/>
            <parameter key="p" value="0.5"/>
            <parameter key="deselect_unknown" value="true"/>
            <parameter key="use_absolute_weights" value="true"/>
          </operator>
          <operator activated="true" class="apply_model" compatibility="9.5.000" expanded="true" height="82" name="Apply Model (3)" width="90" x="313" y="85">
            <list key="application_parameters"/>
            <parameter key="create_view" value="false"/>
          </operator>
          <operator activated="true" class="performance_classification" compatibility="9.5.000" expanded="true" height="82" name="Test_performance" width="90" x="313" y="187">
            <parameter key="main_criterion" value="first"/>
            <parameter key="accuracy" value="true"/>
            <parameter key="classification_error" value="false"/>
            <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>
          <connect from_port="model" to_op="Apply Model (3)" to_port="model"/>
          <connect from_port="test set" to_op="Select by Weights (2)" to_port="example set input"/>
          <connect from_port="through 1" to_port="performance 2"/>
          <connect from_port="through 2" to_op="Select by Weights (2)" to_port="weights"/>
          <connect from_op="Select by Weights (2)" from_port="example set output" to_op="Apply Model (3)" to_port="unlabelled data"/>
          <connect from_op="Apply Model (3)" from_port="labelled data" to_op="Test_performance" to_port="labelled data"/>
          <connect from_op="Test_performance" from_port="performance" to_port="performance 1"/>
          <portSpacing port="source_model" spacing="0"/>
          <portSpacing port="source_test set" spacing="0"/>
          <portSpacing port="source_through 1" spacing="0"/>
          <portSpacing port="source_through 2" spacing="0"/>
          <portSpacing port="source_through 3" spacing="0"/>
          <portSpacing port="sink_test set results" spacing="0"/>
          <portSpacing port="sink_performance 1" spacing="0"/>
          <portSpacing port="sink_performance 2" spacing="0"/>
          <portSpacing port="sink_performance 3" spacing="0"/>
        </process>
      </operator>
      <connect from_op="Retrieve Sonar" from_port="output" to_op="Cross Validation" to_port="example set"/>
      <connect from_op="Cross Validation" from_port="performance 1" to_port="result 1"/>
      <connect from_op="Cross Validation" from_port="performance 2" to_port="result 2"/>
      <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>

    Hope this helps,

    Regards,

    Lionel

    Tghadially
Sign In or Register to comment.