performance by ID3

Yasmin

Hello

I have a trouble in performance of my dataset. They are real data and I collected them.

When I make a model by id3 tree, the accuracy is almost 95% but when I use of cross validation, the result will be between 50 and 60 percent in 10 folds. 

Is there any problem in my data or my process? Which accuracy can I use in my project?

The subject of my project is discover relation between student performance and personality characteristics using by decision tree and regression.

Also how can i find best attributes for making relation by id3 and what operators should i use? Can i use of select attribute?

Here is my model and validation.

 

Model:

<?xml version="1.0" encoding="UTF-8"?><process version="8.2.001">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="8.2.001" expanded="true" name="Process">
    <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="8.2.001" expanded="true" height="68" name="Read Excel" width="90" x="45" y="34">
        <parameter key="excel_file" value="C:\Users\yasamin\Documents\dataset.xlsx"/>
        <parameter key="sheet_selection" value="sheet number"/>
        <parameter key="sheet_number" value="1"/>
        <parameter key="imported_cell_range" value="A1:Q301"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="first_row_as_names" value="false"/>
        <list key="annotations">
          <parameter key="0" value="Name"/>
        </list>
        <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="field.true.integer.attribute"/>
          <parameter key="1" value="course.true.integer.attribute"/>
          <parameter key="2" value="year.true.integer.attribute"/>
          <parameter key="3" value="number of children in family.true.integer.attribute"/>
          <parameter key="4" value="which member of family?.true.integer.attribute"/>
          <parameter key="5" value="Do grandfather and grandmother live with you?.true.integer.attribute"/>
          <parameter key="6" value="Did your parents get divorced?.true.integer.attribute"/>
          <parameter key="7" value="Did your father get married again?.true.integer.attribute"/>
          <parameter key="8" value="Did your mother get married again?.true.integer.attribute"/>
          <parameter key="9" value="Information identity.true.integer.attribute"/>
          <parameter key="10" value="Normative identity.true.integer.attribute"/>
          <parameter key="11" value="Confused or avoidance identity.true.integer.attribute"/>
          <parameter key="12" value="Commitment identity.true.integer.attribute"/>
          <parameter key="13" value="Positive affection.true.integer.attribute"/>
          <parameter key="14" value="Negative affection.true.integer.attribute"/>
          <parameter key="15" value="Average of first semester in year 2016.true.polynominal.label"/>
          <parameter key="16" value="Average of previous year.true.polynominal.attribute"/>
        </list>
        <parameter key="read_not_matching_values_as_missings" value="true"/>
        <parameter key="datamanagement" value="double_array"/>
        <parameter key="data_management" value="auto"/>
      </operator>
      <operator activated="false" class="concurrency:parallel_decision_tree" compatibility="8.2.001" expanded="true" height="103" name="Decision Tree" width="90" x="45" y="238">
        <parameter key="criterion" value="gini_index"/>
        <parameter key="maximal_depth" value="10"/>
        <parameter key="apply_pruning" value="true"/>
        <parameter key="confidence" value="0.25"/>
        <parameter key="apply_prepruning" value="true"/>
        <parameter key="minimal_gain" value="0.1"/>
        <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="true" class="discretize_by_frequency" compatibility="8.2.001" expanded="true" height="103" name="Discretize" width="90" x="179" y="34">
        <parameter key="return_preprocessing_model" value="false"/>
        <parameter key="create_view" value="false"/>
        <parameter key="attribute_filter_type" value="all"/>
        <parameter key="attribute" value=""/>
        <parameter key="attributes" value=""/>
        <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="false"/>
        <parameter key="use_sqrt_of_examples" value="false"/>
        <parameter key="number_of_bins" value="2"/>
        <parameter key="range_name_type" value="long"/>
        <parameter key="automatic_number_of_digits" value="true"/>
        <parameter key="number_of_digits" value="-1"/>
      </operator>
      <operator activated="false" class="weka:W-J48" compatibility="7.3.000" expanded="true" height="82" name="W-J48" width="90" x="112" y="187">
        <parameter key="U" value="false"/>
        <parameter key="C" value="0.25"/>
        <parameter key="M" value="2.0"/>
        <parameter key="R" value="false"/>
        <parameter key="B" value="false"/>
        <parameter key="S" value="false"/>
        <parameter key="L" value="false"/>
        <parameter key="A" value="false"/>
      </operator>
      <operator activated="false" class="chaid" compatibility="8.2.001" expanded="true" height="82" name="CHAID" width="90" x="581" y="187">
        <parameter key="minimal_size_for_split" value="4"/>
        <parameter key="minimal_leaf_size" value="2"/>
        <parameter key="minimal_gain" value="0.1"/>
        <parameter key="maximal_depth" value="20"/>
        <parameter key="confidence" value="0.25"/>
        <parameter key="number_of_prepruning_alternatives" value="3"/>
        <parameter key="no_pre_pruning" value="false"/>
        <parameter key="no_pruning" value="false"/>
      </operator>
      <operator activated="false" class="discretize_by_size" compatibility="8.2.001" expanded="true" height="103" name="Discretize (3)" width="90" x="246" y="187">
        <parameter key="return_preprocessing_model" value="false"/>
        <parameter key="create_view" value="false"/>
        <parameter key="attribute_filter_type" value="all"/>
        <parameter key="attribute" value=""/>
        <parameter key="attributes" value=""/>
        <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="false"/>
        <parameter key="size_of_bins" value="3"/>
        <parameter key="sorting_direction" value="decreasing"/>
        <parameter key="range_name_type" value="long"/>
        <parameter key="automatic_number_of_digits" value="true"/>
        <parameter key="number_of_digits" value="-1"/>
      </operator>
      <operator activated="false" class="select_attributes" compatibility="8.2.001" expanded="true" height="82" name="Select Attributes" width="90" x="45" y="136">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attribute" value=""/>
        <parameter key="attributes" value="معدل ترم اول سال 96-95|رشته|سال|نتیجه عاطفه مثبت|نتیجه عاطفه منفی|هویت اطلاعاتی|هویت تعهد|هویت سردرگم یا اجتنابی|هویت هنجاری"/>
        <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="false"/>
      </operator>
      <operator activated="false" class="discretize_by_bins" compatibility="8.2.001" expanded="true" height="103" name="Discretize (4)" width="90" x="179" y="136">
        <parameter key="return_preprocessing_model" value="false"/>
        <parameter key="create_view" value="false"/>
        <parameter key="attribute_filter_type" value="all"/>
        <parameter key="attribute" value=""/>
        <parameter key="attributes" value=""/>
        <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="false"/>
        <parameter key="number_of_bins" value="4"/>
        <parameter key="define_boundaries" value="false"/>
        <parameter key="range_name_type" value="long"/>
        <parameter key="automatic_number_of_digits" value="true"/>
        <parameter key="number_of_digits" value="3"/>
      </operator>
      <operator activated="true" class="id3" compatibility="8.2.001" expanded="true" height="82" name="ID3" width="90" x="313" y="34">
        <parameter key="criterion" value="information_gain"/>
        <parameter key="minimal_size_for_split" value="4"/>
        <parameter key="minimal_leaf_size" value="2"/>
        <parameter key="minimal_gain" value="0.1"/>
      </operator>
      <operator activated="true" class="apply_model" compatibility="8.2.001" expanded="true" height="82" name="Apply Model" width="90" x="447" y="34">
        <list key="application_parameters"/>
        <parameter key="create_view" value="false"/>
      </operator>
      <operator activated="true" class="performance_classification" compatibility="8.2.001" expanded="true" height="82" name="Performance" width="90" x="581" y="34">
        <parameter key="main_criterion" value="first"/>
        <parameter key="accuracy" value="true"/>
        <parameter key="classification_error" value="true"/>
        <parameter key="kappa" value="true"/>
        <parameter key="weighted_mean_recall" value="true"/>
        <parameter key="weighted_mean_precision" value="true"/>
        <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="true"/>
        <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="input 1" to_op="Read Excel" to_port="file"/>
      <connect from_op="Read Excel" from_port="output" to_op="Discretize" to_port="example set input"/>
      <connect from_op="Discretize" from_port="example set output" to_op="ID3" to_port="training set"/>
      <connect from_op="ID3" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="ID3" from_port="exampleSet" 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="result 1"/>
      <connect from_op="Performance" from_port="example set" to_port="result 2"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="source_input 2" 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>

 

Validation:

<?xml version="1.0" encoding="UTF-8"?><process version="8.2.001">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="8.2.001" expanded="true" name="Process">
    <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="8.2.001" expanded="true" height="68" name="Read Excel" width="90" x="45" y="34">
        <parameter key="excel_file" value="C:\Users\yasamin\Documents\dataset.xlsx"/>
        <parameter key="sheet_selection" value="sheet number"/>
        <parameter key="sheet_number" value="1"/>
        <parameter key="imported_cell_range" value="A1:Q301"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="first_row_as_names" value="false"/>
        <list key="annotations">
          <parameter key="0" value="Name"/>
        </list>
        <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="field.true.nominal.attribute"/>
          <parameter key="1" value="course.true.nominal.attribute"/>
          <parameter key="2" value="year.true.nominal.attribute"/>
          <parameter key="3" value="number of children in family.true.nominal.attribute"/>
          <parameter key="4" value="which member of family?.true.nominal.attribute"/>
          <parameter key="5" value="Do grandfather and grandmother live with you?.true.nominal.attribute"/>
          <parameter key="6" value="Did your parents get divorced?.true.nominal.attribute"/>
          <parameter key="7" value="Did your father get married again?.true.nominal.attribute"/>
          <parameter key="8" value="Did your mother get married again?.true.nominal.attribute"/>
          <parameter key="9" value="Information identity.true.nominal.attribute"/>
          <parameter key="10" value="Normative identity.true.nominal.attribute"/>
          <parameter key="11" value="Confused or avoidance identity.true.nominal.attribute"/>
          <parameter key="12" value="Commitment identity.true.nominal.attribute"/>
          <parameter key="13" value="Positive affection.true.nominal.attribute"/>
          <parameter key="14" value="Negative affection.true.nominal.attribute"/>
          <parameter key="15" value="Average of first semester in year 2016.true.polynominal.label"/>
          <parameter key="16" value="Average of previous year.true.polynominal.attribute"/>
        </list>
        <parameter key="read_not_matching_values_as_missings" value="true"/>
        <parameter key="datamanagement" value="double_array"/>
        <parameter key="data_management" value="auto"/>
      </operator>
      <operator activated="true" class="concurrency:cross_validation" compatibility="8.2.001" expanded="true" height="145" name="Cross Validation" width="90" x="380" y="34">
        <parameter key="split_on_batch_attribute" value="false"/>
        <parameter key="leave_one_out" value="false"/>
        <parameter key="number_of_folds" value="10"/>
        <parameter key="sampling_type" value="stratified sampling"/>
        <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="false" class="concurrency:parallel_decision_tree" compatibility="8.2.001" expanded="true" height="103" name="Decision Tree" width="90" x="45" y="187">
            <parameter key="criterion" value="gini_index"/>
            <parameter key="maximal_depth" value="10"/>
            <parameter key="apply_pruning" value="true"/>
            <parameter key="confidence" value="0.25"/>
            <parameter key="apply_prepruning" value="true"/>
            <parameter key="minimal_gain" value="0.1"/>
            <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="weka:W-J48" compatibility="7.3.000" expanded="true" height="82" name="W-J48" width="90" x="179" y="187">
            <parameter key="U" value="false"/>
            <parameter key="C" value="0.25"/>
            <parameter key="M" value="2.0"/>
            <parameter key="R" value="false"/>
            <parameter key="B" value="false"/>
            <parameter key="S" value="false"/>
            <parameter key="L" value="false"/>
            <parameter key="A" value="false"/>
          </operator>
          <operator activated="false" class="chaid" compatibility="8.2.001" expanded="true" height="82" name="CHAID" width="90" x="179" y="136">
            <parameter key="minimal_size_for_split" value="4"/>
            <parameter key="minimal_leaf_size" value="2"/>
            <parameter key="minimal_gain" value="0.1"/>
            <parameter key="maximal_depth" value="10"/>
            <parameter key="confidence" value="0.25"/>
            <parameter key="number_of_prepruning_alternatives" value="3"/>
            <parameter key="no_pre_pruning" value="false"/>
            <parameter key="no_pruning" value="false"/>
          </operator>
          <operator activated="false" class="discretize_by_bins" compatibility="8.2.001" expanded="true" height="103" name="Discretize" width="90" x="45" y="85">
            <parameter key="return_preprocessing_model" value="false"/>
            <parameter key="create_view" value="false"/>
            <parameter key="attribute_filter_type" value="all"/>
            <parameter key="attribute" value=""/>
            <parameter key="attributes" value=""/>
            <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="false"/>
            <parameter key="number_of_bins" value="5"/>
            <parameter key="define_boundaries" value="false"/>
            <parameter key="range_name_type" value="long"/>
            <parameter key="automatic_number_of_digits" value="true"/>
            <parameter key="number_of_digits" value="3"/>
          </operator>
          <operator activated="true" class="id3" compatibility="8.2.001" expanded="true" height="82" name="ID3" width="90" x="179" y="34">
            <parameter key="criterion" value="gain_ratio"/>
            <parameter key="minimal_size_for_split" value="4"/>
            <parameter key="minimal_leaf_size" value="2"/>
            <parameter key="minimal_gain" value="0.1"/>
          </operator>
          <operator activated="false" class="weka:W-Id3" compatibility="7.3.000" expanded="true" height="82" name="W-Id3" width="90" x="45" y="187">
            <parameter key="D" value="false"/>
          </operator>
          <connect from_port="training set" to_op="ID3" to_port="training set"/>
          <connect from_op="ID3" 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="8.2.001" expanded="true" height="82" name="Apply Model" width="90" x="45" y="34">
            <list key="application_parameters"/>
            <parameter key="create_view" value="false"/>
          </operator>
          <operator activated="true" class="performance_classification" compatibility="8.2.001" expanded="true" height="82" name="Performance" width="90" x="179" 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"/>
          <connect from_op="Performance" from_port="example set" to_port="test set results"/>
          <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_op="Read Excel" from_port="output" to_op="Cross Validation" to_port="example set"/>
      <connect from_op="Cross Validation" from_port="model" to_port="result 1"/>
      <connect from_op="Cross Validation" from_port="example set" to_port="result 2"/>
      <connect from_op="Cross Validation" from_port="test result set" to_port="result 4"/>
      <connect from_op="Cross Validation" from_port="performance 1" to_port="result 3"/>
      <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"/>
      <portSpacing port="sink_result 4" spacing="0"/>
      <portSpacing port="sink_result 5" spacing="0"/>
    </process>
  </operator>
</process>

 I will be grateful that somebody help me.

Best regards

lionelderkrikor

Hi @Yasmin,

 

In reality, you have to validate the feature selection itself, so the Optimize Selection (evolutionary) has to be implemented

inside the "training part" of a Cross Validation operator.

It's going to take even longer, but it's the best way to get reliable results. To understand why you have to proceed like that, 

here a ressource written by Dr Ingo Mierswa.

Here the new process (you have to replace the data and the model(s) inside the Cross Validation operators : 

<?xml version="1.0" encoding="UTF-8"?><process version="8.2.001">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="8.2.001" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="retrieve" compatibility="8.2.001" expanded="true" height="68" name="Retrieve Sonar" width="90" x="112" y="85">
        <parameter key="repository_entry" value="//Samples/data/Sonar"/>
      </operator>
      <operator activated="true" class="concurrency:cross_validation" compatibility="8.2.001" expanded="true" height="145" name="Cross Validation" width="90" x="380" y="85">
        <parameter key="number_of_folds" value="5"/>
        <process expanded="true">
          <operator activated="true" class="multiply" compatibility="8.2.001" expanded="true" height="103" name="Multiply" width="90" x="45" y="34"/>
          <operator activated="true" class="remember" compatibility="8.2.001" expanded="true" height="68" name="Remember" width="90" x="179" y="34">
            <parameter key="name" value="trainingSet"/>
          </operator>
          <operator activated="true" class="optimize_selection_evolutionary" compatibility="8.2.001" expanded="true" height="103" name="Optimize Selection (Evolutionary)" width="90" x="179" y="187">
            <process expanded="true">
              <operator activated="true" class="concurrency:cross_validation" compatibility="8.2.001" expanded="true" height="145" name="Cross Validation (2)" width="90" x="246" y="34">
                <parameter key="number_of_folds" value="5"/>
                <process expanded="true">
                  <operator activated="true" class="naive_bayes" compatibility="8.2.001" expanded="true" height="82" name="Naive Bayes (2)" width="90" x="246" y="34"/>
                  <connect from_port="training set" to_op="Naive Bayes (2)" to_port="training set"/>
                  <connect from_op="Naive Bayes (2)" 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="8.2.001" expanded="true" height="82" name="Apply Model (2)" width="90" x="112" y="34">
                    <list key="application_parameters"/>
                  </operator>
                  <operator activated="true" class="performance_classification" compatibility="8.2.001" expanded="true" height="82" name="Performance (2)" width="90" x="246" y="34">
                    <list key="class_weights"/>
                  </operator>
                  <connect from_port="model" to_op="Apply Model (2)" to_port="model"/>
                  <connect from_port="test set" to_op="Apply Model (2)" to_port="unlabelled data"/>
                  <connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance (2)" to_port="labelled data"/>
                  <connect from_op="Performance (2)" from_port="performance" to_port="performance 1"/>
                  <connect from_op="Performance (2)" from_port="example set" to_port="test set results"/>
                  <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" to_op="Cross Validation (2)" to_port="example set"/>
              <connect from_op="Cross Validation (2)" from_port="performance 1" to_port="performance"/>
              <portSpacing port="source_example set" spacing="0"/>
              <portSpacing port="source_through 1" spacing="0"/>
              <portSpacing port="sink_performance" spacing="0"/>
            </process>
          </operator>
          <operator activated="true" class="select_by_weights" compatibility="8.2.001" expanded="true" height="103" name="Select by Weights" width="90" x="313" y="34"/>
          <operator activated="true" class="naive_bayes" compatibility="8.2.001" expanded="true" height="82" name="Naive Bayes" width="90" x="447" y="34"/>
          <connect from_port="training set" to_op="Multiply" to_port="input"/>
          <connect from_op="Multiply" from_port="output 1" to_op="Remember" to_port="store"/>
          <connect from_op="Multiply" from_port="output 2" to_op="Optimize Selection (Evolutionary)" to_port="example set in"/>
          <connect from_op="Remember" from_port="stored" to_op="Select by Weights" to_port="example set input"/>
          <connect from_op="Optimize Selection (Evolutionary)" from_port="weights" to_op="Select by Weights" to_port="weights"/>
          <connect from_op="Select by Weights" from_port="example set output" to_op="Naive Bayes" to_port="training set"/>
          <connect from_op="Select by Weights" from_port="weights" to_port="through 1"/>
          <connect from_op="Naive Bayes" 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"/>
          <portSpacing port="sink_through 2" spacing="0"/>
        </process>
        <process expanded="true">
          <operator activated="true" class="select_by_weights" compatibility="8.2.001" expanded="true" height="103" name="Select by Weights (2)" width="90" x="45" y="85"/>
          <operator activated="true" class="recall" compatibility="8.2.001" expanded="true" height="68" name="Recall (4)" width="90" x="45" y="238">
            <parameter key="name" value="trainingSet"/>
          </operator>
          <operator activated="true" class="superset" compatibility="8.2.001" expanded="true" height="82" name="Superset" width="90" x="246" y="187"/>
          <operator activated="true" class="apply_model" compatibility="8.2.001" expanded="true" height="82" name="Apply Model" width="90" x="246" y="34">
            <list key="application_parameters"/>
          </operator>
          <operator activated="true" class="performance_classification" compatibility="8.2.001" expanded="true" height="82" name="Performance" width="90" x="380" y="34">
            <list key="class_weights"/>
          </operator>
          <connect from_port="model" to_op="Apply Model" 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_op="Select by Weights (2)" to_port="weights"/>
          <connect from_op="Select by Weights (2)" from_port="example set output" to_op="Superset" to_port="example set 1"/>
          <connect from_op="Recall (4)" from_port="result" to_op="Superset" to_port="example set 2"/>
          <connect from_op="Superset" from_port="superset 1" 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"/>
          <connect from_op="Performance" from_port="example set" to_port="test set results"/>
          <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="sink_test set results" spacing="0"/>
          <portSpacing port="sink_performance 1" spacing="0"/>
          <portSpacing port="sink_performance 2" 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="model" to_port="result 2"/>
      <connect from_op="Cross Validation" from_port="example set" to_port="result 1"/>
      <connect from_op="Cross Validation" from_port="test result set" to_port="result 3"/>
      <connect from_op="Cross Validation" from_port="performance 1" to_port="result 4"/>
      <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"/>
      <portSpacing port="sink_result 4" spacing="0"/>
      <portSpacing port="sink_result 5" spacing="0"/>
      <portSpacing port="sink_result 6" spacing="0"/>
    </process>
  </operator>
</process>

I hope it helps,

 

Regards,

 

Lionel