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.

How to remove matched words of two lists from one of the list

AnushaAnusha Member Posts: 19 Maven
in Help
Hi All!

I have a dataset that has two columns. each column has a list of words separated by ",". I want to compare two columns and if any word is present in both columns, that should be replaced/removed from the second list.

Source:

list1                           list2
asd,ad bd,ghi           jkl,bd,ghi 
ui,ki lm,po                 op,ki,ui


Required output:

list1                           list2
asd,ad bd,ghi           jkl,bd,
ui,ki lm,po                 op,ki,

I have used regexp_replace but it is replacing substring also---it has to compare exact word match.
Even I tried with split, loop attribute and inside generate attribute used to replace/replaceAll with macro value----it's throwing error.

could anyone help me to resolve this?

Thanks in advance!


Answers

  • mharmsmharms Employee, Member Posts: 6 RM Team Member
    edited August 2021 
    <?xml version="1.0" encoding="UTF-8"?><process version="9.9.002">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.9.002" 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="9.9.002" expanded="true" height="68" name="Retrieve listData" width="90" x="45" y="34">
        <parameter key="repository_entry" value="//Demo Repository/data/listData"/>
      </operator>
      <operator activated="true" class="trim" compatibility="9.9.002" expanded="true" height="82" name="Trim" width="90" x="179" y="34">
        <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="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
      </operator>
      <operator activated="true" class="replace" compatibility="9.9.002" expanded="true" height="82" name="Set to regex format" width="90" x="313" y="34">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="list1"/>
        <parameter key="attributes" value=""/>
        <parameter key="use_except_expression" value="false"/>
        <parameter key="value_type" value="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
        <parameter key="replace_what" value=","/>
        <parameter key="replace_by" value="|"/>
      </operator>
      <operator activated="true" class="extract_macro" compatibility="9.9.002" expanded="true" height="68" name="Extract Macro" width="90" x="447" y="34">
        <parameter key="macro" value="list1"/>
        <parameter key="macro_type" value="data_value"/>
        <parameter key="statistics" value="average"/>
        <parameter key="attribute_name" value="list1"/>
        <parameter key="example_index" value="1"/>
        <list key="additional_macros"/>
      </operator>
      <operator activated="true" class="replace" compatibility="9.9.002" expanded="true" height="82" name="Replace (2)" width="90" x="581" y="34">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="list2"/>
        <parameter key="attributes" value=""/>
        <parameter key="use_except_expression" value="false"/>
        <parameter key="value_type" value="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
        <parameter key="replace_what" value="(%{list1})"/>
        <parameter key="replace_by" value=""/>
      </operator>
      <operator activated="true" class="replace" compatibility="9.9.002" expanded="true" height="82" name="Replace" width="90" x="715" y="34">
        <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="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
        <parameter key="replace_what" value=",{2,}"/>
        <parameter key="replace_by" value=","/>
      </operator>
      <operator activated="true" class="replace" compatibility="9.9.002" expanded="true" height="82" name="Set to comma format" width="90" x="849" y="34">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="list1"/>
        <parameter key="attributes" value=""/>
        <parameter key="use_except_expression" value="false"/>
        <parameter key="value_type" value="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
        <parameter key="replace_what" value="\|"/>
        <parameter key="replace_by" value=","/>
      </operator>
      <connect from_op="Retrieve listData" from_port="output" to_op="Trim" to_port="example set input"/>
      <connect from_op="Trim" from_port="example set output" to_op="Set to regex format" to_port="example set input"/>
      <connect from_op="Set to regex format" from_port="example set output" to_op="Extract Macro" to_port="example set"/>
      <connect from_op="Extract Macro" from_port="example set" to_op="Replace (2)" to_port="example set input"/>
      <connect from_op="Replace (2)" from_port="example set output" to_op="Replace" to_port="example set input"/>
      <connect from_op="Replace" from_port="example set output" to_op="Set to comma format" to_port="example set input"/>
      <connect from_op="Set to comma format" from_port="example set output" 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>

    HI Anusha,

    Try this and see how this works. This is just using the first example so you'd need to loop or use Generate Attributes etc

    Thanks,

    Mike
  • MarcoBarradasMarcoBarradas Administrator, Employee, RapidMiner Certified Analyst, Member Posts: 272 Unicorn
    Hi @Anusha

    I'm not sure if you are going to do the removal on a per exampe base. But here is a starting point that achieves what you mentioned.

    <?xml version="1.0" encoding="UTF-8"?><process version="9.9.002">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.9.002" expanded="true" name="Process">
    <parameter key="logverbosity" value="init"/>
    <parameter key="random_seed" value="-1"/>
    <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="9.9.002" expanded="true" height="68" name="Example Set A" width="90" x="112" y="34">
        <parameter key="generator_type" value="comma separated text"/>
        <parameter key="number_of_examples" value="100"/>
        <parameter key="use_stepsize" value="false"/>
        <list key="function_descriptions"/>
        <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="input_csv_text" value="list1&#10;asd,ad bd,ghi"/>
        <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="nominal_to_text" compatibility="9.9.002" expanded="true" height="82" name="Nominal to Text" width="90" x="246" y="34">
        <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="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
      </operator>
      <operator activated="true" class="text:process_document_from_data" compatibility="9.3.001" expanded="true" height="82" name="Process Documents from Data" width="90" x="380" y="34">
        <parameter key="create_word_vector" value="false"/>
        <parameter key="vector_creation" value="TF-IDF"/>
        <parameter key="add_meta_information" value="true"/>
        <parameter key="keep_text" value="false"/>
        <parameter key="prune_method" value="none"/>
        <parameter key="prune_below_percent" value="3.0"/>
        <parameter key="prune_above_percent" value="30.0"/>
        <parameter key="prune_below_rank" value="0.05"/>
        <parameter key="prune_above_rank" value="0.95"/>
        <parameter key="datamanagement" value="double_sparse_array"/>
        <parameter key="data_management" value="auto"/>
        <parameter key="select_attributes_and_weights" value="false"/>
        <list key="specify_weights"/>
        <process expanded="true">
          <operator activated="true" class="text:tokenize" compatibility="9.3.001" expanded="true" height="68" name="Tokenize" width="90" x="179" y="34">
            <parameter key="mode" value="non letters"/>
            <parameter key="characters" value=".:"/>
            <parameter key="language" value="English"/>
            <parameter key="max_token_length" value="3"/>
          </operator>
          <connect from_port="document" to_op="Tokenize" to_port="document"/>
          <connect from_op="Tokenize" from_port="document" to_port="document 1"/>
          <portSpacing port="source_document" spacing="0"/>
          <portSpacing port="sink_document 1" spacing="0"/>
          <portSpacing port="sink_document 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="text:wordlist_to_data" compatibility="9.3.001" expanded="true" height="82" name="WordList to Data" width="90" x="514" y="34"/>
      <operator activated="true" class="generate_attributes" compatibility="9.9.002" expanded="true" height="82" name="Generate Attributes" width="90" x="648" y="34">
        <list key="function_descriptions">
          <parameter key="Replace" value="&quot;&quot;"/>
        </list>
        <parameter key="keep_all" value="true"/>
      </operator>
      <operator activated="true" class="utility:create_exampleset" compatibility="9.9.002" expanded="true" height="68" name="Example Set BD" width="90" x="112" y="187">
        <parameter key="generator_type" value="comma separated text"/>
        <parameter key="number_of_examples" value="100"/>
        <parameter key="use_stepsize" value="false"/>
        <list key="function_descriptions"/>
        <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="input_csv_text" value="list2&#10;jkl,bd,ghi &#10;op,ki,ui"/>
        <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="nominal_to_text" compatibility="9.9.002" expanded="true" height="82" name="Nominal to Text (2)" width="90" x="380" y="187">
        <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="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
      </operator>
      <operator activated="true" class="replace_dictionary" compatibility="9.9.002" expanded="true" height="103" name="Replace (Dictionary)" width="90" x="648" 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="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="from_attribute" value="word"/>
        <parameter key="to_attribute" value="Replace"/>
        <parameter key="use_regular_expressions" value="false"/>
        <parameter key="convert_to_lowercase" value="false"/>
        <parameter key="first_match_only" value="false"/>
      </operator>
      <connect from_op="Example Set A" from_port="output" to_op="Nominal to Text" to_port="example set input"/>
      <connect from_op="Nominal to Text" from_port="example set output" to_op="Process Documents from Data" to_port="example set"/>
      <connect from_op="Process Documents from Data" from_port="word list" to_op="WordList to Data" to_port="word list"/>
      <connect from_op="WordList to Data" from_port="example set" to_op="Generate Attributes" to_port="example set input"/>
      <connect from_op="Generate Attributes" from_port="example set output" to_op="Replace (Dictionary)" to_port="dictionary"/>
      <connect from_op="Example Set BD" from_port="output" to_op="Nominal to Text (2)" to_port="example set input"/>
      <connect from_op="Nominal to Text (2)" from_port="example set output" to_op="Replace (Dictionary)" to_port="example set input"/>
      <connect from_op="Replace (Dictionary)" from_port="example set output" 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>


  • Edin_KlapicEdin_Klapic Employee, RMResearcher, Member Posts: 299 RM Data Scientist
    Hi @Anusha,
    a quick and dirty solution would be to utilize the Loop exa,püles Operator in combination with Split, Transpose and Set Minus.
    Please find an example setup below:

    <?xml version="1.0" encoding="UTF-8"?><process version="9.9.002">
      <context>
        <input/>
        <output/>
        <macros/>
      </context>
      <operator activated="true" class="process" compatibility="9.9.002" 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="9.9.002" expanded="true" height="68" name="Create ExampleSet" width="90" x="112" y="34">
            <parameter key="generator_type" value="comma separated text"/>
            <parameter key="number_of_examples" value="100"/>
            <parameter key="use_stepsize" value="false"/>
            <list key="function_descriptions"/>
            <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="input_csv_text" value="list1;list2&#10;asd,ad bd,ghi;jkl,bd,ghi &#10;ui,ki lm,po;op,ki,ui"/>
            <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="trim" compatibility="9.9.002" expanded="true" height="82" name="Trim" width="90" x="246" y="34">
            <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="nominal"/>
            <parameter key="use_value_type_exception" value="false"/>
            <parameter key="except_value_type" value="file_path"/>
            <parameter key="block_type" value="single_value"/>
            <parameter key="use_block_type_exception" value="false"/>
            <parameter key="except_block_type" value="single_value"/>
            <parameter key="invert_selection" value="false"/>
            <parameter key="include_special_attributes" value="false"/>
          </operator>
          <operator activated="true" class="loop_examples" compatibility="9.9.002" expanded="true" height="103" name="Loop Examples" width="90" x="380" y="34">
            <parameter key="iteration_macro" value="example"/>
            <process expanded="true">
              <operator activated="true" class="filter_example_range" compatibility="9.9.002" expanded="true" height="82" name="Filter Example Range" width="90" x="45" y="34">
                <parameter key="first_example" value="%{example}"/>
                <parameter key="last_example" value="%{example}"/>
                <parameter key="invert_filter" value="false"/>
              </operator>
              <operator activated="true" class="select_attributes" compatibility="9.9.002" expanded="true" height="82" name="Select Attributes" width="90" x="179" y="34">
                <parameter key="attribute_filter_type" value="single"/>
                <parameter key="attribute" value="list1"/>
                <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"/>
              </operator>
              <operator activated="true" class="multiply" compatibility="9.9.002" expanded="true" height="103" name="Multiply" width="90" x="313" y="34"/>
              <operator activated="true" class="select_attributes" compatibility="9.9.002" expanded="true" height="82" name="Select Attributes (4)" width="90" x="179" y="289">
                <parameter key="attribute_filter_type" value="single"/>
                <parameter key="attribute" value="list2"/>
                <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"/>
              </operator>
              <operator activated="true" class="split" compatibility="9.9.002" expanded="true" height="82" name="Split" width="90" x="380" y="187">
                <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="nominal"/>
                <parameter key="use_value_type_exception" value="false"/>
                <parameter key="except_value_type" value="file_path"/>
                <parameter key="block_type" value="single_value"/>
                <parameter key="use_block_type_exception" value="false"/>
                <parameter key="except_block_type" value="single_value"/>
                <parameter key="invert_selection" value="false"/>
                <parameter key="include_special_attributes" value="false"/>
                <parameter key="split_pattern" value=","/>
                <parameter key="split_mode" value="ordered_split"/>
              </operator>
              <operator activated="true" class="transpose" compatibility="9.9.002" expanded="true" height="82" name="Transpose" width="90" x="514" y="187"/>
              <operator activated="true" class="select_attributes" compatibility="9.9.002" expanded="true" height="82" name="Select Attributes (2)" width="90" x="648" y="187">
                <parameter key="attribute_filter_type" value="single"/>
                <parameter key="attribute" value="att_1"/>
                <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="true"/>
              </operator>
              <operator activated="true" class="blending:rename" compatibility="9.9.002" expanded="true" height="82" name="Rename" width="90" x="782" y="187">
                <list key="rename attributes">
                  <parameter key="att_1" value="source"/>
                </list>
                <parameter key="from_attribute" value=""/>
                <parameter key="to_attribute" value=""/>
              </operator>
              <operator activated="true" class="set_role" compatibility="9.9.002" expanded="true" height="82" name="Set Role" width="90" x="916" y="187">
                <parameter key="attribute_name" value="source"/>
                <parameter key="target_role" value="id"/>
                <list key="set_additional_roles"/>
              </operator>
              <operator activated="true" class="split" compatibility="9.9.002" expanded="true" height="82" name="Split (2)" width="90" x="313" y="289">
                <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="nominal"/>
                <parameter key="use_value_type_exception" value="false"/>
                <parameter key="except_value_type" value="file_path"/>
                <parameter key="block_type" value="single_value"/>
                <parameter key="use_block_type_exception" value="false"/>
                <parameter key="except_block_type" value="single_value"/>
                <parameter key="invert_selection" value="false"/>
                <parameter key="include_special_attributes" value="false"/>
                <parameter key="split_pattern" value=","/>
                <parameter key="split_mode" value="ordered_split"/>
              </operator>
              <operator activated="true" class="transpose" compatibility="9.9.002" expanded="true" height="82" name="Transpose (2)" width="90" x="447" y="289"/>
              <operator activated="true" class="select_attributes" compatibility="9.9.002" expanded="true" height="82" name="Select Attributes (3)" width="90" x="581" y="289">
                <parameter key="attribute_filter_type" value="single"/>
                <parameter key="attribute" value="att_1"/>
                <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="true"/>
              </operator>
              <operator activated="true" class="blending:rename" compatibility="9.9.002" expanded="true" height="82" name="Rename (2)" width="90" x="715" y="289">
                <list key="rename attributes">
                  <parameter key="att_1" value="target"/>
                </list>
                <parameter key="from_attribute" value=""/>
                <parameter key="to_attribute" value=""/>
              </operator>
              <operator activated="true" class="set_role" compatibility="9.9.002" expanded="true" height="82" name="Set Role (2)" width="90" x="849" y="289">
                <parameter key="attribute_name" value="target"/>
                <parameter key="target_role" value="id"/>
                <list key="set_additional_roles"/>
              </operator>
              <operator activated="true" class="set_minus" compatibility="9.9.002" expanded="true" height="82" name="Set Minus" width="90" x="983" y="289"/>
              <operator activated="true" class="aggregate" compatibility="9.9.002" expanded="true" height="82" name="Aggregate" width="90" x="1117" y="289">
                <parameter key="use_default_aggregation" 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_aggregation_function" value="average"/>
                <list key="aggregation_attributes">
                  <parameter key="target" value="concatenation"/>
                </list>
                <parameter key="group_by_attributes" value=""/>
                <parameter key="count_all_combinations" value="false"/>
                <parameter key="only_distinct" value="false"/>
                <parameter key="ignore_missings" value="true"/>
              </operator>
              <operator activated="true" class="blending:rename" compatibility="9.9.002" expanded="true" height="82" name="Rename (3)" width="90" x="1251" y="289">
                <list key="rename attributes">
                  <parameter key="concat(target)" value="list2"/>
                </list>
                <parameter key="from_attribute" value=""/>
                <parameter key="to_attribute" value=""/>
              </operator>
              <operator activated="true" class="replace" compatibility="9.9.002" expanded="true" height="82" name="Replace" width="90" x="1385" y="289">
                <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="nominal"/>
                <parameter key="use_value_type_exception" value="false"/>
                <parameter key="except_value_type" value="file_path"/>
                <parameter key="block_type" value="single_value"/>
                <parameter key="use_block_type_exception" value="false"/>
                <parameter key="except_block_type" value="single_value"/>
                <parameter key="invert_selection" value="false"/>
                <parameter key="include_special_attributes" value="false"/>
                <parameter key="replace_what" value="\|"/>
                <parameter key="replace_by" value=","/>
              </operator>
              <operator activated="true" class="operator_toolbox:merge" compatibility="2.10.000" expanded="true" height="103" name="Merge Attributes" width="90" x="1117" y="34">
                <parameter key="handling_of_duplicate_attributes" value="rename"/>
                <parameter key="handling_of_special_attributes" value="keep_first_special_other_regular"/>
                <parameter key="handling_of_duplicate_annotations" value="rename"/>
              </operator>
              <connect from_port="example set" to_op="Filter Example Range" to_port="example set input"/>
              <connect from_op="Filter Example Range" 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="Multiply" to_port="input"/>
              <connect from_op="Select Attributes" from_port="original" to_op="Select Attributes (4)" to_port="example set input"/>
              <connect from_op="Multiply" from_port="output 1" to_op="Merge Attributes" to_port="example set 1"/>
              <connect from_op="Multiply" from_port="output 2" to_op="Split" to_port="example set input"/>
              <connect from_op="Select Attributes (4)" from_port="example set output" to_op="Split (2)" to_port="example set input"/>
              <connect from_op="Split" from_port="example set output" to_op="Transpose" to_port="example set input"/>
              <connect from_op="Transpose" from_port="example set output" to_op="Select Attributes (2)" to_port="example set input"/>
              <connect from_op="Select Attributes (2)" from_port="example set output" to_op="Rename" to_port="example set input"/>
              <connect from_op="Rename" 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="Set Minus" to_port="subtrahend"/>
              <connect from_op="Split (2)" from_port="example set output" to_op="Transpose (2)" to_port="example set input"/>
              <connect from_op="Transpose (2)" from_port="example set output" to_op="Select Attributes (3)" to_port="example set input"/>
              <connect from_op="Select Attributes (3)" from_port="example set output" to_op="Rename (2)" to_port="example set input"/>
              <connect from_op="Rename (2)" from_port="example set output" to_op="Set Role (2)" to_port="example set input"/>
              <connect from_op="Set Role (2)" from_port="example set output" to_op="Set Minus" to_port="example set input"/>
              <connect from_op="Set Minus" from_port="example set output" to_op="Aggregate" to_port="example set input"/>
              <connect from_op="Aggregate" from_port="example set output" to_op="Rename (3)" to_port="example set input"/>
              <connect from_op="Rename (3)" from_port="example set output" to_op="Replace" to_port="example set input"/>
              <connect from_op="Replace" from_port="example set output" to_op="Merge Attributes" to_port="example set 2"/>
              <connect from_op="Merge Attributes" from_port="merged set" to_port="output 1"/>
              <portSpacing port="source_example set" spacing="0"/>
              <portSpacing port="sink_example set" spacing="0"/>
              <portSpacing port="sink_output 1" spacing="0"/>
              <portSpacing port="sink_output 2" spacing="0"/>
            </process>
          </operator>
          <operator activated="true" class="append" compatibility="9.9.002" expanded="true" height="82" name="Append" width="90" x="514" y="34">
            <parameter key="datamanagement" value="double_array"/>
            <parameter key="data_management" value="auto"/>
            <parameter key="merge_type" value="all"/>
          </operator>
          <connect from_op="Create ExampleSet" from_port="output" to_op="Trim" to_port="example set input"/>
          <connect from_op="Trim" from_port="example set output" to_op="Loop Examples" to_port="example set"/>
          <connect from_op="Loop Examples" from_port="output 1" to_op="Append" to_port="example set 1"/>
          <connect from_op="Append" from_port="merged set" 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>

    Happy Mining,
    Edin

Sign In or Register to comment.