I would like to inquire about the 'Prescriptive Optimization' operator settings

kimjk3559

Referring to the tutorial, I created the process as follows:

<?xml version="1.0" encoding="UTF-8"?><process version="10.1.002">

  <context>

    <input/>

    <output/>

    <macros/>

  </context>

  <operator activated="true" class="process" compatibility="10.1.002" 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="read_excel" compatibility="10.1.002" expanded="true" height="68" name="Read Excel" width="90" x="179" y="34">

        <parameter key="excel_file" value="C:\Users\kimjk\OneDrive\문서\RapidMiner\Local Repository\data\sw_hitec\sw_hitec.xlsx"/>

        <parameter key="sheet_selection" value="sheet number"/>

        <parameter key="sheet_number" value="1"/>

        <parameter key="imported_cell_range" value="A1"/>

        <parameter key="encoding" value="SYSTEM"/>

        <parameter key="first_row_as_names" value="true"/>

        <list key="annotations"/>

        <parameter key="date_format" value=""/>

        <parameter key="time_zone" value="SYSTEM"/>

        <parameter key="locale" value="English (United States)"/>

        <parameter key="read_all_values_as_polynominal" value="false"/>

        <list key="data_set_meta_data_information">

          <parameter key="0" value="Νο.false.integer.attribute"/>

          <parameter key="1" value="A.true.real.attribute"/>

          <parameter key="2" value="B.true.real.attribute"/>

          <parameter key="3" value="C.true.real.attribute"/>

          <parameter key="4" value="D.true.real.attribute"/>

          <parameter key="5" value="kg.true.real.attribute"/>

          <parameter key="6" value="kN.true.real.attribute"/>

        </list>

        <parameter key="read_not_matching_values_as_missings" value="false"/>

      </operator>

      <operator activated="true" breakpoints="after" class="blending:set_role" compatibility="10.1.002" expanded="true" height="82" name="Set Role" origin="GENERATED_TUTORIAL" width="90" x="313" y="34">

        <list key="set_roles">

          <parameter key="kg" value="metadata"/>

          <parameter key="kN" value="metadata"/>

        </list>

      </operator>

      <operator activated="true" class="multiply" compatibility="10.1.002" expanded="true" height="103" name="Multiply" width="90" x="447" y="34"/>

      <operator activated="true" class="filter_example_range" compatibility="10.1.002" expanded="true" height="82" name="Filter Example Range (3)" width="90" x="648" y="34">

        <parameter key="first_example" value="3"/>

        <parameter key="last_example" value="3"/>

        <parameter key="invert_filter" value="false"/>

      </operator>

      <operator activated="true" class="time_series:multi_label_model_learner" compatibility="10.1.000" expanded="true" height="82" name="Multi Label Modeling" origin="GENERATED_TUTORIAL" width="90" x="648" y="136">

        <parameter key="attribute_filter_type" value="subset"/>

        <parameter key="attribute" value=""/>

        <parameter key="attributes" value="kg|kN"/>

        <parameter key="use_except_expression" value="false"/>

        <parameter key="value_type" value="attribute_value"/>

        <parameter key="use_value_type_exception" value="false"/>

        <parameter key="except_value_type" value="time"/>

        <parameter key="block_type" value="attribute_block"/>

        <parameter key="use_block_type_exception" value="false"/>

        <parameter key="except_block_type" value="value_matrix_row_start"/>

        <parameter key="invert_selection" value="false"/>

        <parameter key="include_special_attributes" value="true"/>

        <parameter key="add_macros" value="true"/>

        <parameter key="current_label_name_macro" value="current_label_attribute"/>

        <parameter key="current_label_type_macro" value="current_label_type"/>

        <parameter key="enable_parallel_execution" value="true"/>

        <process expanded="true">

          <operator activated="true" class="branch" compatibility="10.1.002" expanded="true" height="103" name="Branch" origin="GENERATED_TUTORIAL" width="90" x="514" y="34">

            <parameter key="condition_type" value="expression"/>

            <parameter key="expression" value="contains(%{current_label_type},&quot;nominal&quot;)"/>

            <parameter key="io_object" value="ANOVAMatrix"/>

            <parameter key="return_inner_output" value="true"/>

            <process expanded="true">

              <operator activated="true" class="filter_examples" compatibility="10.1.002" expanded="true" height="103" name="Filter Examples (2)" origin="GENERATED_TUTORIAL" width="90" x="179" y="34">

                <parameter key="parameter_expression" value=""/>

                <parameter key="condition_class" value="no_missing_labels"/>

                <parameter key="invert_filter" value="false"/>

                <list key="filters_list">

                  <parameter key="filters_entry_key" value="%{current_label_attribute}.is_not_missing."/>

                </list>

                <parameter key="filters_logic_and" value="true"/>

                <parameter key="filters_check_metadata" value="true"/>

                <description align="center" color="transparent" colored="false" width="126">As the GLM cannot handle missing label values, we remove these Examples</description>

              </operator>

              <operator activated="true" class="concurrency:parallel_decision_tree" compatibility="10.1.002" expanded="true" height="103" name="Decision Tree" origin="GENERATED_TUTORIAL" width="90" x="380" y="34">

                <parameter key="criterion" value="gain_ratio"/>

                <parameter key="maximal_depth" value="10"/>

                <parameter key="apply_pruning" value="true"/>

                <parameter key="confidence" value="0.1"/>

                <parameter key="apply_prepruning" value="true"/>

                <parameter key="minimal_gain" value="0.01"/>

                <parameter key="minimal_leaf_size" value="2"/>

                <parameter key="minimal_size_for_split" value="4"/>

                <parameter key="number_of_prepruning_alternatives" value="3"/>

                <description align="center" color="transparent" colored="false" width="126">Train a Decision Tree for the nominal label attributes&lt;br/&gt;&lt;br/&gt;The warning can be ignored, cause in the Meta Data only one label attribute can be shown. This is in this case a numerical label attribute</description>

              </operator>

              <connect from_port="input 1" to_op="Filter Examples (2)" to_port="example set input"/>

              <connect from_op="Filter Examples (2)" from_port="example set output" to_op="Decision Tree" to_port="training set"/>

              <connect from_op="Decision Tree" from_port="model" to_port="input 1"/>

              <portSpacing port="source_condition" spacing="0"/>

              <portSpacing port="source_input 1" spacing="0"/>

              <portSpacing port="source_input 2" spacing="0"/>

              <portSpacing port="sink_input 1" spacing="0"/>

              <portSpacing port="sink_input 2" spacing="0"/>

            </process>

            <process expanded="true">

              <operator activated="true" class="blending:select_attributes" compatibility="10.1.002" expanded="true" height="82" name="Select Attributes (3)" origin="GENERATED_TUTORIAL" width="90" x="45" y="34">

                <parameter key="type" value="include attributes"/>

                <parameter key="attribute_filter_type" value="a subset"/>

                <parameter key="select_attribute" value=""/>

                <parameter key="select_subset" value="A␞B␞C␞D␞kg␞kN"/>

                <parameter key="also_apply_to_special_attributes_(id,_label..)" value="false"/>

                <description align="center" color="transparent" colored="false" width="126">Remove ID like attributes</description>

              </operator>

              <operator activated="true" class="filter_examples" compatibility="10.1.002" expanded="true" height="103" name="Filter Examples" origin="GENERATED_TUTORIAL" width="90" x="179" y="34">

                <parameter key="parameter_expression" value=""/>

                <parameter key="condition_class" value="no_missing_labels"/>

                <parameter key="invert_filter" value="false"/>

                <list key="filters_list">

                  <parameter key="filters_entry_key" value="%{current_label_attribute}.is_not_missing."/>

                </list>

                <parameter key="filters_logic_and" value="true"/>

                <parameter key="filters_check_metadata" value="true"/>

                <description align="center" color="transparent" colored="false" width="126">As the GLM cannot handle missing label values, we remove these Examples</description>

              </operator>

              <operator activated="true" class="multiply" compatibility="10.1.002" expanded="true" height="82" name="Multiply (2)" width="90" x="313" y="34"/>

              <operator activated="true" class="h2o:generalized_linear_model" compatibility="10.1.000" expanded="true" height="124" name="Generalized Linear Model" origin="GENERATED_TUTORIAL" width="90" x="447" y="34">

                <parameter key="family" value="AUTO"/>

                <parameter key="link" value="family_default"/>

                <parameter key="solver" value="AUTO"/>

                <parameter key="reproducible" value="false"/>

                <parameter key="maximum_number_of_threads" value="4"/>

                <parameter key="use_regularization" value="true"/>

                <parameter key="lambda_search" value="false"/>

                <parameter key="number_of_lambdas" value="0"/>

                <parameter key="lambda_min_ratio" value="0.0"/>

                <parameter key="early_stopping" value="true"/>

                <parameter key="stopping_rounds" value="3"/>

                <parameter key="stopping_tolerance" value="0.001"/>

                <parameter key="standardize" value="true"/>

                <parameter key="non-negative_coefficients" value="false"/>

                <parameter key="add_intercept" value="true"/>

                <parameter key="compute_p-values" value="false"/>

                <parameter key="remove_collinear_columns" value="false"/>

                <parameter key="missing_values_handling" value="MeanImputation"/>

                <parameter key="max_iterations" value="0"/>

                <parameter key="specify_beta_constraints" value="false"/>

                <list key="beta_constraints"/>

                <parameter key="max_runtime_seconds" value="0"/>

                <list key="expert_parameters"/>

                <description align="center" color="transparent" colored="false" width="126">We train a GLM for the non-nominal attributes</description>

              </operator>

              <operator activated="false" class="linear_regression" compatibility="10.1.002" expanded="true" height="103" name="Linear Regression" width="90" x="380" y="238">

                <parameter key="feature_selection" value="M5 prime"/>

                <parameter key="alpha" value="0.05"/>

                <parameter key="max_iterations" value="10"/>

                <parameter key="forward_alpha" value="0.05"/>

                <parameter key="backward_alpha" value="0.05"/>

                <parameter key="eliminate_colinear_features" value="true"/>

                <parameter key="min_tolerance" value="0.05"/>

                <parameter key="use_bias" value="true"/>

                <parameter key="ridge" value="1.0E-8"/>

              </operator>

              <operator activated="false" class="concurrency:parallel_decision_tree" compatibility="10.1.002" expanded="true" height="103" name="Decision Tree (2)" origin="GENERATED_TUTORIAL" width="90" x="380" y="340">

                <parameter key="criterion" value="least_square"/>

                <parameter key="maximal_depth" value="10"/>

                <parameter key="apply_pruning" value="true"/>

                <parameter key="confidence" value="0.1"/>

                <parameter key="apply_prepruning" value="true"/>

                <parameter key="minimal_gain" value="0.01"/>

                <parameter key="minimal_leaf_size" value="2"/>

                <parameter key="minimal_size_for_split" value="4"/>

                <parameter key="number_of_prepruning_alternatives" value="3"/>

              </operator>

              <operator activated="false" class="h2o:deep_learning" compatibility="10.1.000" expanded="true" height="103" name="Deep Learning" width="90" x="380" y="442">

                <parameter key="activation" value="Rectifier"/>

                <enumeration key="hidden_layer_sizes">

                  <parameter key="hidden_layer_sizes" value="50"/>

                  <parameter key="hidden_layer_sizes" value="50"/>

                </enumeration>

                <enumeration key="hidden_dropout_ratios"/>

                <parameter key="reproducible_(uses_1_thread)" value="false"/>

                <parameter key="use_local_random_seed" value="false"/>

                <parameter key="local_random_seed" value="1992"/>

                <parameter key="epochs" value="10.0"/>

                <parameter key="compute_variable_importances" value="false"/>

                <parameter key="train_samples_per_iteration" value="-2"/>

                <parameter key="adaptive_rate" value="true"/>

                <parameter key="epsilon" value="1.0E-8"/>

                <parameter key="rho" value="0.99"/>

                <parameter key="learning_rate" value="0.005"/>

                <parameter key="learning_rate_annealing" value="1.0E-6"/>

                <parameter key="learning_rate_decay" value="1.0"/>

                <parameter key="momentum_start" value="0.0"/>

                <parameter key="momentum_ramp" value="1000000.0"/>

                <parameter key="momentum_stable" value="0.0"/>

                <parameter key="nesterov_accelerated_gradient" value="true"/>

                <parameter key="standardize" value="true"/>

                <parameter key="L1" value="1.0E-5"/>

                <parameter key="L2" value="0.0"/>

                <parameter key="max_w2" value="10.0"/>

                <parameter key="loss_function" value="Automatic"/>

                <parameter key="distribution_function" value="AUTO"/>

                <parameter key="early_stopping" value="false"/>

                <parameter key="stopping_rounds" value="1"/>

                <parameter key="stopping_metric" value="AUTO"/>

                <parameter key="stopping_tolerance" value="0.001"/>

                <parameter key="missing_values_handling" value="MeanImputation"/>

                <parameter key="max_runtime_seconds" value="0"/>

                <list key="expert_parameters"/>

                <list key="expert_parameters_"/>

              </operator>

              <connect from_port="input 1" to_op="Select Attributes (3)" to_port="example set input"/>

              <connect from_op="Select Attributes (3)" from_port="example set output" to_op="Filter Examples" to_port="example set input"/>

              <connect from_op="Filter Examples" from_port="example set output" to_op="Multiply (2)" to_port="input"/>

              <connect from_op="Multiply (2)" from_port="output 1" to_op="Generalized Linear Model" to_port="training set"/>

              <connect from_op="Generalized Linear Model" from_port="model" to_port="input 1"/>

              <portSpacing port="source_condition" spacing="0"/>

              <portSpacing port="source_input 1" spacing="0"/>

              <portSpacing port="source_input 2" spacing="0"/>

              <portSpacing port="sink_input 1" spacing="0"/>

              <portSpacing port="sink_input 2" spacing="0"/>

            </process>

            <description align="center" color="transparent" colored="false" width="126">nominal / real label</description>

          </operator>

          <connect from_port="training set" to_op="Branch" to_port="input 1"/>

          <connect from_op="Branch" from_port="input 1" to_port="model"/>

          <portSpacing port="source_training set" spacing="0"/>

          <portSpacing port="source_input 1" spacing="0"/>

          <portSpacing port="sink_model" spacing="0"/>

          <portSpacing port="sink_output 1" spacing="0"/>

        </process>

      </operator>

      <operator activated="true" class="prescriptive_analytics:prescriptive_optimization" compatibility="0.1.006" expanded="true" height="124" name="Prescriptive Optimization (3)" width="90" x="849" y="34">

        <parameter key="attribute_filter_type" value="subset"/>

        <parameter key="attribute" value=""/>

        <parameter key="attributes" value="|A|B|C|D"/>

        <parameter key="use_except_expression" value="false"/>

        <parameter key="value_type" value="numeric"/>

        <parameter key="use_value_type_exception" value="false"/>

        <parameter key="except_value_type" value="real"/>

        <parameter key="block_type" value="value_series"/>

        <parameter key="use_block_type_exception" value="false"/>

        <parameter key="except_block_type" value="value_series_end"/>

        <parameter key="invert_selection" value="false"/>

        <parameter key="include_special_attributes" value="true"/>

        <parameter key="optimization_method" value="Grid"/>

        <parameter key="number_of_candidates" value="1"/>

        <parameter key="method_for_start_values" value="input example"/>

        <parameter key="reference_example_index" value="0"/>

        <list key="configure_bounds">

          <parameter key="kg" value="3\.0.3\.2"/>

          <parameter key="kN" value="22\.0.25\.0"/>

          <parameter key="A" value="25\.0.40\.0"/>

          <parameter key="B" value="5\.0.11\.0"/>

          <parameter key="C" value="10\.0.21\.0"/>

          <parameter key="D" value="1\.0.4\.0"/>

        </list>

        <parameter key="use_interpolation_points_default" value="true"/>

        <parameter key="number_of_interpolation_points" value="10"/>

        <parameter key="max_evaluations" value="10000"/>

        <parameter key="initial_radius" value="10.0"/>

        <parameter key="stopping_radius" value="1.0E-8"/>

        <parameter key="max_generations" value="100"/>

        <parameter key="use_early_stopping" value="false"/>

        <parameter key="generations_without_improval" value="2"/>

        <parameter key="specify_population_size" value="true"/>

        <parameter key="population_size" value="5"/>

        <parameter key="keep_best" value="true"/>

        <parameter key="mutation_type" value="gaussian_mutation"/>

        <parameter key="selection_type" value="tournament"/>

        <parameter key="tournament_fraction" value="0.25"/>

        <parameter key="crossover_prob" value="0.9"/>

        <parameter key="use_local_random_seed" value="false"/>

        <parameter key="local_random_seed" value="1992"/>

        <parameter key="show_convergence_plot" value="true"/>

        <parameter key="steps" value="5"/>

        <parameter key="sigma_factor" value="1.0"/>

        <parameter key="stopping_threshold" value="0.001"/>

        <parameter key="active_cma" value="true"/>

        <parameter key="number_of_diagonal_iterations" value="0"/>

        <parameter key="relative_stopping_threshold" value="0.001"/>

        <process expanded="true">

          <operator activated="true" class="apply_model" compatibility="10.1.002" expanded="true" height="82" name="Apply Model (5)" origin="GENERATED_TUTORIAL" width="90" x="246" y="34">

            <list key="application_parameters"/>

          </operator>

          <operator activated="true" class="blending:generate_columns" compatibility="10.1.002" expanded="true" height="82" name="Generate Attributes (4)" width="90" x="447" y="34">

            <list key="function_descriptions">

              <parameter key="amount" value="kN - kg"/>

            </list>

            <parameter key="keep_all_columns" value="true"/>

          </operator>

          <operator activated="true" class="extract_performance" compatibility="10.1.002" expanded="true" height="82" name="Performance (5)" origin="GENERATED_TUTORIAL" width="90" x="648" y="34">

            <parameter key="performance_type" value="data_value"/>

            <parameter key="statistics" value="min"/>

            <parameter key="attribute_name" value="amount"/>

            <parameter key="example_index" value="1"/>

            <parameter key="optimization_direction" value="maximize"/>

          </operator>

          <connect from_port="training set" to_op="Apply Model (5)" to_port="unlabelled data"/>

          <connect from_port="in 1" to_op="Apply Model (5)" to_port="model"/>

          <connect from_op="Apply Model (5)" from_port="labelled data" to_op="Generate Attributes (4)" to_port="table input"/>

          <connect from_op="Generate Attributes (4)" from_port="table output" to_op="Performance (5)" to_port="example set"/>

          <connect from_op="Performance (5)" from_port="performance" to_port="Performance Vector"/>

          <portSpacing port="source_training set" spacing="0"/>

          <portSpacing port="source_in 1" spacing="0"/>

          <portSpacing port="source_in 2" spacing="0"/>

          <portSpacing port="sink_Performance Vector" spacing="0"/>

        </process>

      </operator>

      <connect from_op="Read Excel" from_port="output" to_op="Set Role" to_port="example set input"/>

      <connect from_op="Set Role" from_port="example set output" to_op="Multiply" to_port="input"/>

      <connect from_op="Multiply" from_port="output 1" to_op="Filter Example Range (3)" to_port="example set input"/>

      <connect from_op="Multiply" from_port="output 2" to_op="Multi Label Modeling" to_port="training set"/>

      <connect from_op="Filter Example Range (3)" from_port="example set output" to_op="Prescriptive Optimization (3)" to_port="example set input"/>

      <connect from_op="Filter Example Range (3)" from_port="original" to_op="Prescriptive Optimization (3)" to_port="ref"/>

      <connect from_op="Multi Label Modeling" from_port="model" to_op="Prescriptive Optimization (3)" to_port="in 1"/>

      <connect from_op="Prescriptive Optimization (3)" from_port="exa" to_port="result 1"/>

      <connect from_op="Prescriptive Optimization (3)" from_port="per" 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>

To explain briefly:

The data is a multi-label model that predicts kg and kN values using four variable values from A to D.

What I ultimately want is to find the values of variables A~D that minimize the kg value and maximize the kN value
based on the learned model.

First, I loaded the data and then designated the label values as meta data.

After multiplying the data, one part created a model.

Actually, don't understand the remaining part, but I made it by following the tutorial. (filter example)

I connected the model and the above filter data to Prescriptive Optimization,

After assigning attributes A to D, I set the bounds of the variables.

Inside the operator, apply model and performance are connected.

Lastly, I used the generate attributes operator by specifying kN - kg = amount and maximizing the amount value.

However, when I run it, I see that only certain values are repeated.

Could you please confirm which part is wrong?

I think the simulator's optimization function and this Prescriptive Optimization operator will be very helpful to me.

thank you

MartinLiebig

Hi,

I think you want to optimize prediction(kN)-prediction(kg). Because otherwise the values are just contant.

Best,

Martin

MartinLiebig

Hi,

I think you want to optimize prediction(kN)-prediction(kg). Because otherwise the values are just contant.

Best,

Martin