🎉Community Raffle - Win $25

An exclusive raffle opportunity for active members like you! Complete your profile, answer questions and get your first accepted badge to enter the raffle.
Join and Win

Help for Missing KNN Variable

User: "ferdinand_papa"
New Altair Community Member
Updated by Jocelyn
Hey guys, I uploaded the following process of mine. Everything worked well so far. Goal was to predict the variables H N U .. I get a perfect result for the variables H N but not a single U . But I know for sure that you can predict U as well.  Maybe decision tree is also a good alternative? 


If someone could have a look at it and come up with a solution I would be very grateful.

cheers 


<?xml version="1.0" encoding="UTF-8"?><process version="9.1.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.1.000" 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="retrieve" compatibility="9.1.000" expanded="true" height="68" name="Retrieve retouren_class" width="90" x="45" y="391">
        <parameter key="repository_entry" value="retouren_class"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="9.1.000" expanded="true" height="82" name="Set Role (2)" width="90" x="179" y="391">
        <parameter key="attribute_name" value="KDNR"/>
        <parameter key="target_role" value="id"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="replace_missing_values" compatibility="9.1.000" expanded="true" height="103" name="Replace Missing Values (2)" width="90" x="380" y="391">
        <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="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"/>
        <parameter key="default" value="average"/>
        <list key="columns"/>
      </operator>
      <operator activated="true" class="retrieve" compatibility="9.1.000" expanded="true" height="68" name="Retrieve retouren_train" width="90" x="45" y="187">
        <parameter key="repository_entry" value="retouren_train"/>
      </operator>
      <operator activated="true" class="replace_missing_values" compatibility="9.1.000" expanded="true" height="103" name="Replace Missing Values" 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="no_missing_values"/>
        <parameter key="attribute" value=""/>
        <parameter key="attributes" value=""/>
        <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"/>
        <parameter key="default" value="average"/>
        <list key="columns"/>
      </operator>
      <operator activated="true" class="generate_attributes" compatibility="9.1.000" expanded="true" height="82" name="Generate Attributes" width="90" x="313" y="136">
        <list key="function_descriptions">
          <parameter key="Retourenquote" value="RETOUREN_MENGE/LIEFER_MENGE"/>
          <parameter key="Zuordnung" value="if(Retourenquote&lt;0.18,&quot;N&quot;,if(Retourenquote&gt;0.40,&quot;H&quot;,&quot;U&quot;))"/>
        </list>
        <parameter key="keep_all" value="true"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="9.1.000" expanded="true" height="82" name="Set Role" width="90" x="447" y="136">
        <parameter key="attribute_name" value="KDNR"/>
        <parameter key="target_role" value="id"/>
        <list key="set_additional_roles">
          <parameter key="Zuordnung" value="label"/>
        </list>
      </operator>
      <operator activated="true" class="select_attributes" compatibility="9.1.000" expanded="true" height="82" name="Select Attributes" width="90" x="514" y="238">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attribute" value=""/>
        <parameter key="attributes" value="AADSEIT|AATELKZ|APLZ5ST|APLZAAH|APLZAKH|APLZBVD|APLZEIN|APLZFLH|APLZFLI|APLZKKE|BBH0001|BBH0002|BBW0001|BBW0002|BBW0003|BEB0001|BLB0001|BRP0001|BRP0002|BRP0003|BRP0004|BRQ0001|BRQ0002|BRQ0003|BRQ0004|BRW0001|LRQ0001|LRQ0002|LRQ0003|LRQ0004|PALTERK|PANREDK|PRSANZW|WRQ0001|WRQ0002|WRQ0003|WRQ0004|WRQ0005|WRQ0006|WRQ0007|WRQ0008|WRQ0009|WRQ0010|WRQ0011|WRQ0012|WRQ0013|WRQ0014|WRQ0015|WRQ0016|WRW0001|WRW0002|WRW0003|WRW0004|WRW0005|WRW0006|WRW0007|WRW0008|WRW0009|WRW0010|WRW0011|WRW0012|WRW0013|WRW0014|WRW0015|WRW0016|KDNR"/>
        <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="true" class="concurrency:optimize_parameters_grid" compatibility="9.1.000" expanded="true" height="124" name="Optimize Parameters (Grid)" width="90" x="700" y="136">
        <list key="parameters">
          <parameter key="k-NN.k" value="[1.0;100.0;10;linear]"/>
        </list>
        <parameter key="error_handling" value="fail on error"/>
        <parameter key="log_performance" value="true"/>
        <parameter key="log_all_criteria" value="false"/>
        <parameter key="synchronize" value="false"/>
        <parameter key="enable_parallel_execution" value="true"/>
        <process expanded="true">
          <operator activated="true" class="concurrency:cross_validation" compatibility="9.1.000" expanded="true" height="145" name="Cross Validation" width="90" x="112" y="187">
            <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="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="normalize" compatibility="9.1.000" expanded="true" height="103" name="Normalize" width="90" x="45" y="238">
                <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="method" value="Z-transformation"/>
                <parameter key="min" value="0.0"/>
                <parameter key="max" value="1.0"/>
                <parameter key="allow_negative_values" value="false"/>
              </operator>
              <operator activated="true" class="k_nn" compatibility="9.1.000" expanded="true" height="82" name="k-NN" width="90" x="246" y="238">
                <parameter key="k" value="100"/>
                <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="group_models" compatibility="9.1.000" expanded="true" height="103" name="Group Models" width="90" x="139" y="34"/>
              <connect from_port="training set" to_op="Normalize" to_port="example set input"/>
              <connect from_op="Normalize" from_port="example set output" to_op="k-NN" to_port="training set"/>
              <connect from_op="Normalize" from_port="preprocessing model" to_op="Group Models" to_port="models in 1"/>
              <connect from_op="k-NN" from_port="model" to_op="Group Models" to_port="models in 2"/>
              <connect from_op="Group Models" from_port="model out" 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="9.1.000" expanded="true" height="82" name="Apply Model (2)" width="90" x="45" y="85">
                <list key="application_parameters"/>
                <parameter key="create_view" value="false"/>
              </operator>
              <operator activated="true" class="performance_classification" compatibility="9.1.000" expanded="true" height="82" name="Performance" width="90" x="112" 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="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" 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="input 1" to_op="Cross Validation" to_port="example set"/>
          <connect from_op="Cross Validation" from_port="model" to_port="model"/>
          <connect from_op="Cross Validation" from_port="performance 1" to_port="performance"/>
          <portSpacing port="source_input 1" spacing="0"/>
          <portSpacing port="source_input 2" spacing="0"/>
          <portSpacing port="sink_performance" spacing="0"/>
          <portSpacing port="sink_model" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="apply_model" compatibility="9.1.000" expanded="true" height="82" name="Apply Model" width="90" x="581" y="391">
        <list key="application_parameters"/>
        <parameter key="create_view" value="false"/>
      </operator>
      <operator activated="true" class="write_excel" compatibility="9.1.000" expanded="true" height="82" name="Write Excel" width="90" x="700" y="340">
        <parameter key="excel_file" value="/Users/Admin1/Desktop/Du huan.xlsx"/>
        <parameter key="file_format" value="xlsx"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="sheet_name" value="RapidMiner Data"/>
        <parameter key="date_format" value="yyyy-MM-dd HH:mm:ss"/>
        <parameter key="number_format" value="#.0"/>
      </operator>
      <connect from_op="Retrieve retouren_class" from_port="output" to_op="Set Role (2)" to_port="example set input"/>
      <connect from_op="Set Role (2)" from_port="example set output" to_op="Replace Missing Values (2)" to_port="example set input"/>
      <connect from_op="Replace Missing Values (2)" from_port="example set output" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Retrieve retouren_train" from_port="output" to_op="Replace Missing Values" to_port="example set input"/>
      <connect from_op="Replace Missing Values" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/>
      <connect from_op="Generate Attributes" from_port="example set output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Select Attributes" to_port="example set input"/>
      <connect from_op="Select Attributes" from_port="example set output" to_op="Optimize Parameters (Grid)" to_port="input 1"/>
      <connect from_op="Optimize Parameters (Grid)" from_port="performance" to_port="result 1"/>
      <connect from_op="Optimize Parameters (Grid)" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Write Excel" to_port="input"/>
      <connect from_op="Write Excel" from_port="through" 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>

Find more posts tagged with