Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.

Random Forest

FlixportFlixport Member Posts: 33 Contributor II
in Help
Hey RM Family,

I want to use the Random Forest here, as a result I get several trees displayed, understandable. But I saw in a tutorial that I can lead them to a result. Meaning, for example, I would need 80% training and 20% testing, so does the approach I brought here via the Split Data Operator work 20/80? I am looking forward to the answers

<?xml version="1.0" encoding="UTF-8"?><process version="9.2.001">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.2.001" 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="UTF-8"/>
    <process expanded="true">
      <operator activated="false" class="retrieve" compatibility="9.2.001" expanded="true" height="68" name="Retrieve data_out_select_by_pca_weights" width="90" x="45" y="85">
        <parameter key="repository_entry" value="data/data_out_select_by_pca_weights"/>
      </operator>
      <operator activated="true" class="retrieve" compatibility="9.2.001" expanded="true" height="68" name="Retrieve data_out_select_by_chisq_weights" width="90" x="45" y="238">
        <parameter key="repository_entry" value="data/data_out_select_by_chisq_weights"/>
      </operator>
      <operator activated="true" class="retrieve" compatibility="9.2.001" expanded="true" height="68" name="Retrieve data_out_pca" width="90" x="45" y="391">
        <parameter key="repository_entry" value="data/data_out_pca"/>
      </operator>
      <operator activated="true" class="concurrency:join" compatibility="9.2.001" expanded="true" height="82" name="Join (2)" width="90" x="179" y="289">
        <parameter key="remove_double_attributes" value="true"/>
        <parameter key="join_type" value="inner"/>
        <parameter key="use_id_attribute_as_key" value="true"/>
        <list key="key_attributes"/>
        <parameter key="keep_both_join_attributes" value="false"/>
      </operator>
      <operator activated="true" class="multiply" compatibility="9.2.001" expanded="true" height="103" name="Multiply" width="90" x="313" y="136"/>
      <operator activated="true" class="filter_examples" compatibility="9.2.001" expanded="true" height="103" name="Filter Examples" width="90" x="514" y="85">
        <parameter key="parameter_expression" value=""/>
        <parameter key="condition_class" value="custom_filters"/>
        <parameter key="invert_filter" value="false"/>
        <list key="filters_list">
          <parameter key="filters_entry_key" value="Category.equals.financial"/>
          <parameter key="filters_entry_key" value="Category.equals.political"/>
        </list>
        <parameter key="filters_logic_and" value="false"/>
        <parameter key="filters_check_metadata" value="true"/>
      </operator>
      <operator activated="true" class="filter_examples" compatibility="9.2.001" expanded="true" height="103" name="Category == Economis" width="90" x="514" y="391">
        <parameter key="parameter_expression" value=""/>
        <parameter key="condition_class" value="custom_filters"/>
        <parameter key="invert_filter" value="false"/>
        <list key="filters_list">
          <parameter key="filters_entry_key" value="Category.equals.economic"/>
        </list>
        <parameter key="filters_logic_and" value="true"/>
        <parameter key="filters_check_metadata" value="true"/>
      </operator>
      <operator activated="true" class="split_data" compatibility="9.2.001" expanded="true" height="82" name="20%" width="90" x="648" y="391">
        <enumeration key="partitions">
          <parameter key="ratio" value="0.25"/>
          <parameter key="ratio" value="0.75"/>
        </enumeration>
        <parameter key="sampling_type" value="shuffled sampling"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
      </operator>
      <operator activated="true" class="append" compatibility="9.2.001" expanded="true" height="103" name="Append" width="90" x="782" y="238">
        <parameter key="datamanagement" value="double_array"/>
        <parameter key="data_management" value="auto"/>
        <parameter key="merge_type" value="all"/>
      </operator>
      <operator activated="true" class="split_data" compatibility="9.2.001" expanded="true" height="103" name="Split Data" width="90" x="916" y="289">
        <enumeration key="partitions">
          <parameter key="ratio" value="0.8"/>
          <parameter key="ratio" value="0.2"/>
        </enumeration>
        <parameter key="sampling_type" value="shuffled sampling"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
      </operator>
      <operator activated="true" class="x_validation" compatibility="5.1.002" expanded="true" height="124" name="Validation" width="90" x="1050" y="85">
        <parameter key="create_complete_model" value="false"/>
        <parameter key="average_performances_only" value="true"/>
        <parameter key="leave_one_out" value="false"/>
        <parameter key="number_of_validations" value="5"/>
        <parameter key="sampling_type" value="2"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
        <process expanded="true">
          <operator activated="true" class="concurrency:parallel_random_forest" compatibility="9.2.001" expanded="true" height="103" name="Random Forest" width="90" x="179" y="34">
            <parameter key="number_of_trees" value="100"/>
            <parameter key="criterion" value="gain_ratio"/>
            <parameter key="maximal_depth" value="10"/>
            <parameter key="apply_pruning" value="false"/>
            <parameter key="confidence" value="0.1"/>
            <parameter key="apply_prepruning" value="false"/>
            <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"/>
            <parameter key="random_splits" value="false"/>
            <parameter key="guess_subset_ratio" value="true"/>
            <parameter key="subset_ratio" value="0.2"/>
            <parameter key="voting_strategy" value="confidence vote"/>
            <parameter key="use_local_random_seed" value="false"/>
            <parameter key="local_random_seed" value="1992"/>
            <parameter key="enable_parallel_execution" value="true"/>
          </operator>
          <connect from_port="training" to_op="Random Forest" to_port="training set"/>
          <connect from_op="Random Forest" from_port="model" to_port="model"/>
          <portSpacing port="source_training" spacing="0"/>
          <portSpacing port="sink_model" spacing="0"/>
          <portSpacing port="sink_through 1" spacing="0"/>
        </process>
        <process expanded="true">
          <operator activated="true" class="apply_model" compatibility="7.1.001" 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" compatibility="9.2.001" expanded="true" height="82" name="Performance" width="90" x="246" y="136">
            <parameter key="use_example_weights" value="true"/>
          </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="averagable 1"/>
          <portSpacing port="source_model" spacing="0"/>
          <portSpacing port="source_test set" spacing="0"/>
          <portSpacing port="source_through 1" spacing="0"/>
          <portSpacing port="sink_averagable 1" spacing="0"/>
          <portSpacing port="sink_averagable 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="apply_model" compatibility="9.2.001" expanded="true" height="82" name="Apply Model (2)" width="90" x="1184" y="289">
        <list key="application_parameters"/>
        <parameter key="create_view" value="false"/>
      </operator>
      <operator activated="true" class="performance_classification" compatibility="9.2.001" expanded="true" height="82" name="Performance (2)" width="90" x="1318" y="391">
        <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_op="Retrieve data_out_select_by_chisq_weights" from_port="output" to_op="Join (2)" to_port="left"/>
      <connect from_op="Retrieve data_out_pca" from_port="output" to_op="Join (2)" to_port="right"/>
      <connect from_op="Join (2)" from_port="join" to_op="Multiply" to_port="input"/>
      <connect from_op="Multiply" from_port="output 1" to_op="Filter Examples" to_port="example set input"/>
      <connect from_op="Multiply" from_port="output 2" to_op="Category == Economis" to_port="example set input"/>
      <connect from_op="Filter Examples" from_port="example set output" to_op="Append" to_port="example set 1"/>
      <connect from_op="Category == Economis" from_port="example set output" to_op="20%" to_port="example set"/>
      <connect from_op="20%" from_port="partition 1" to_op="Append" to_port="example set 2"/>
      <connect from_op="Append" from_port="merged set" to_op="Split Data" to_port="example set"/>
      <connect from_op="Split Data" from_port="partition 1" to_op="Validation" to_port="training"/>
      <connect from_op="Split Data" from_port="partition 2" to_op="Apply Model (2)" to_port="unlabelled data"/>
      <connect from_op="Validation" from_port="model" to_op="Apply Model (2)" 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 (2)" from_port="model" to_port="result 3"/>
      <connect from_op="Performance (2)" from_port="performance" to_port="result 1"/>
      <connect from_op="Performance (2)" from_port="example set" 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"/>
      <portSpacing port="sink_result 4" spacing="0"/>
    </process>
  </operator>
</process>





Tagged:

Best Answer

  • varunm1varunm1 Member Posts: 1,207 Unicorn
    edited April 2019 Solution Accepted
    Hi @Flixport

    I saw your process. Yes, you are splitting data into 80 :20 using split data operator.




    Regards,
    Varun
    https://www.varunmandalapu.com/

    Be Safe. Follow precautions and Maintain Social Distancing

Sign In or Register to comment.