How to increase the number our exampleset?

mansour_ebrahim

Hi all
Is there any operator in RapidMiner to increase the number of example in the dataset? I mean an operator which generate more samples from all groups and increase the total numbers of example in my dataset. I am running a DL model on my dataset but the number of samples is not enough and cannot get more samples and have to generate and produce more samples from all groups. 
Also, I do not want to balance the number of samples in classes; just increasing the size of dataset let's say threefold.
Regards.
Mansour

lionelderkrikor

Hi @mansour_ebrahim,

You can play with the SMOTE Upsampling operator to increase the number of examples in your dataset.
Here an example of process with such operator : 

<?xml version="1.0" encoding="UTF-8"?><process version="9.4.000-BETA">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.4.000-BETA" 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="utility:create_exampleset" compatibility="9.4.000-BETA" expanded="true" height="68" name="Create ExampleSet" width="90" x="179" y="85">
        <parameter key="generator_type" value="attribute functions"/>
        <parameter key="number_of_examples" value="100"/>
        <parameter key="use_stepsize" value="false"/>
        <list key="function_descriptions">
          <parameter key="test" value="10*rand()"/>
          <parameter key="label" value="if(test&lt;5,0,1)"/>
        </list>
        <parameter key="add_id_attribute" value="false"/>
        <list key="numeric_series_configuration"/>
        <list key="date_series_configuration"/>
        <list key="date_series_configuration (interval)"/>
        <parameter key="date_format" value="yyyy-MM-dd HH:mm:ss"/>
        <parameter key="time_zone" value="SYSTEM"/>
        <parameter key="column_separator" value=","/>
        <parameter key="parse_all_as_nominal" value="false"/>
        <parameter key="decimal_point_character" value="."/>
        <parameter key="trim_attribute_names" value="true"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="9.4.000-BETA" expanded="true" height="82" name="Set Role" width="90" x="313" y="85">
        <parameter key="attribute_name" value="label"/>
        <parameter key="target_role" value="label"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" breakpoints="after" class="numerical_to_binominal" compatibility="9.4.000-BETA" expanded="true" height="82" name="Numerical to Binominal" width="90" x="447" y="85">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="label"/>
        <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="true"/>
        <parameter key="min" value="0.0"/>
        <parameter key="max" value="0.0"/>
      </operator>
      <operator activated="true" class="operator_toolbox:smote" compatibility="2.1.000" expanded="true" height="82" name="SMOTE Upsampling" width="90" x="581" y="85">
        <parameter key="number_of_neighbours" value="5"/>
        <parameter key="normalize" value="true"/>
        <parameter key="equalize_classes" value="false"/>
        <parameter key="upsampling_size" value="1000"/>
        <parameter key="auto_detect_minority_class" value="true"/>
        <parameter key="round_integers" value="true"/>
        <parameter key="nominal_change_rate" value="0.5"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
      </operator>
      <connect from_op="Create ExampleSet" from_port="output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Numerical to Binominal" to_port="example set input"/>
      <connect from_op="Numerical to Binominal" from_port="example set output" to_op="SMOTE Upsampling" to_port="exa"/>
      <connect from_op="SMOTE Upsampling" from_port="ups" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>

Hope this helps,

Regards,

Lionel