Generate combination for all values in example

Hey onlin360,

can i assume that tv is always in the first attribute for all tv synomyms?

If yes, you can do loop values, transpose, cartesian product and filter out the duplicates - i think.

~Martin

Hi Martin!

Well there is always a word in the first attribute, but there are about 950 rows.

And each of them is a different pair of synonyms, so not always "tv".

Regards,

Steven

Hi,

have a look at the attached process. That should work.

~Martin

<?xml version="1.0" encoding="UTF-8"?><process version="7.3.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="7.3.000" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="subprocess" compatibility="7.3.000" expanded="true" height="82" name="Subprocess" width="90" x="45" y="34">
        <process expanded="true">
          <operator activated="true" class="generate_data_user_specification" compatibility="7.3.000" expanded="true" height="68" name="Generate Data by User Specification" width="90" x="45" y="34">
            <list key="attribute_values">
              <parameter key="syn1" value="&quot;tv&quot;"/>
              <parameter key="syn2" value="&quot;television&quot;"/>
              <parameter key="syn3" value="&quot;led-tv&quot;"/>
              <parameter key="syn4" value="&quot;plasma-tv&quot;"/>
            </list>
            <list key="set_additional_roles"/>
          </operator>
          <operator activated="true" class="generate_data_user_specification" compatibility="7.3.000" expanded="true" height="68" name="Generate Data by User Specification (2)" width="90" x="45" y="136">
            <list key="attribute_values">
              <parameter key="syn1" value="&quot;cable&quot;"/>
              <parameter key="syn2" value="&quot;cord&quot;"/>
              <parameter key="syn3" value="&quot;hawser&quot;"/>
              <parameter key="syn4" value="&quot;lead&quot;"/>
            </list>
            <list key="set_additional_roles"/>
          </operator>
          <operator activated="true" class="append" compatibility="7.3.000" expanded="true" height="103" name="Append" width="90" x="179" y="34"/>
          <connect from_op="Generate Data by User Specification" from_port="output" to_op="Append" to_port="example set 1"/>
          <connect from_op="Generate Data by User Specification (2)" from_port="output" to_op="Append" to_port="example set 2"/>
          <connect from_op="Append" from_port="merged set" to_port="out 1"/>
          <portSpacing port="source_in 1" spacing="0"/>
          <portSpacing port="sink_out 1" spacing="0"/>
          <portSpacing port="sink_out 2" spacing="0"/>
        </process>
        <description align="center" color="transparent" colored="false" width="126">Get a data set</description>
      </operator>
      <operator activated="true" class="loop_values" compatibility="7.3.000" expanded="true" height="82" name="Loop Values" width="90" x="179" y="34">
        <parameter key="attribute" value="syn1"/>
        <process expanded="true">
          <operator activated="true" class="filter_examples" compatibility="7.3.000" expanded="true" height="103" name="Filter Examples" width="90" x="112" y="34">
            <parameter key="parameter_expression" value="syn1 == %{loop_value}"/>
            <parameter key="condition_class" value="expression"/>
            <list key="filters_list">
              <parameter key="filters_entry_key" value="syn1.equals.%{loop_attribute}"/>
            </list>
          </operator>
          <operator activated="true" class="transpose" compatibility="7.3.000" expanded="true" height="82" name="Transpose" width="90" x="246" y="34"/>
          <operator activated="true" class="select_attributes" compatibility="7.3.000" expanded="true" height="82" name="Select Attributes" width="90" x="380" y="34">
            <parameter key="attribute_filter_type" value="single"/>
            <parameter key="attribute" value="id"/>
            <parameter key="invert_selection" value="true"/>
            <parameter key="include_special_attributes" value="true"/>
          </operator>
          <operator activated="true" class="multiply" compatibility="7.3.000" expanded="true" height="103" name="Multiply" width="90" x="514" y="34"/>
          <operator activated="true" class="cartesian_product" compatibility="7.3.000" expanded="true" height="82" name="Cartesian" width="90" x="648" y="34">
            <parameter key="remove_double_attributes" value="false"/>
          </operator>
          <operator activated="true" class="rename" compatibility="7.3.000" expanded="true" height="82" name="Rename" width="90" x="782" y="34">
            <parameter key="old_name" value="att_1"/>
            <parameter key="new_name" value="att1"/>
            <list key="rename_additional_attributes">
              <parameter key="att_1_from_ES2" value="att2"/>
            </list>
          </operator>
          <operator activated="true" class="generate_attributes" compatibility="7.3.000" expanded="true" height="82" name="Generate Attributes" width="90" x="916" y="34">
            <list key="function_descriptions">
              <parameter key="dup1" value="if(compare(att1,att2),concat(att1,att2),concat(att2,att1))"/>
            </list>
          </operator>
          <operator activated="true" class="remove_duplicates" compatibility="7.3.000" expanded="true" height="82" name="Remove Duplicates" width="90" x="1050" y="34">
            <parameter key="attribute_filter_type" value="single"/>
            <parameter key="attribute" value="dup1"/>
          </operator>
          <operator activated="false" class="filter_examples" compatibility="7.3.000" expanded="true" height="103" name="Filter Examples (2)" width="90" x="782" y="187">
            <parameter key="parameter_expression" value="att_1==att_1_from_ES2"/>
            <parameter key="condition_class" value="expression"/>
            <parameter key="invert_filter" value="true"/>
            <list key="filters_list"/>
            <description align="center" color="transparent" colored="false" width="126">Remove duplicates</description>
          </operator>
          <operator activated="true" class="select_attributes" compatibility="7.3.000" expanded="true" height="82" name="Select Attributes (2)" width="90" x="1184" y="34">
            <parameter key="attribute_filter_type" value="single"/>
            <parameter key="attribute" value="dup1"/>
            <parameter key="invert_selection" value="true"/>
          </operator>
          <connect from_port="example set" to_op="Filter Examples" to_port="example set input"/>
          <connect from_op="Filter Examples" 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" to_port="example set input"/>
          <connect from_op="Select Attributes" from_port="example set output" to_op="Multiply" to_port="input"/>
          <connect from_op="Multiply" from_port="output 1" to_op="Cartesian" to_port="left"/>
          <connect from_op="Multiply" from_port="output 2" to_op="Cartesian" to_port="right"/>
          <connect from_op="Cartesian" from_port="join" to_op="Rename" to_port="example set input"/>
          <connect from_op="Rename" 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="Remove Duplicates" to_port="example set input"/>
          <connect from_op="Remove Duplicates" 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_port="out 1"/>
          <portSpacing port="source_example set" spacing="0"/>
          <portSpacing port="sink_out 1" spacing="0"/>
          <portSpacing port="sink_out 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="append" compatibility="7.3.000" expanded="true" height="82" name="Append (2)" width="90" x="380" y="34"/>
      <connect from_op="Subprocess" from_port="out 1" to_op="Loop Values" to_port="example set"/>
      <connect from_op="Loop Values" from_port="out 1" to_op="Append (2)" to_port="example set 1"/>
      <connect from_op="Append (2)" 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>

@BalazsBarany educated me that there is a way easier way to this using De-Pivot. Attached is a process demonstrating it.

~Martin

<?xml version="1.0" encoding="UTF-8"?><process version="7.3.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="7.3.000" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="subprocess" compatibility="7.3.000" expanded="true" height="82" name="Subprocess" width="90" x="45" y="34">
        <process expanded="true">
          <operator activated="true" class="generate_data_user_specification" compatibility="7.3.000" expanded="true" height="68" name="Generate Data by User Specification" width="90" x="45" y="34">
            <list key="attribute_values">
              <parameter key="syn1" value="&quot;tv&quot;"/>
              <parameter key="syn2" value="&quot;television&quot;"/>
              <parameter key="syn3" value="&quot;led-tv&quot;"/>
              <parameter key="syn4" value="&quot;plasma-tv&quot;"/>
            </list>
            <list key="set_additional_roles"/>
          </operator>
          <operator activated="true" class="generate_data_user_specification" compatibility="7.3.000" expanded="true" height="68" name="Generate Data by User Specification (2)" width="90" x="45" y="136">
            <list key="attribute_values">
              <parameter key="syn1" value="&quot;cable&quot;"/>
              <parameter key="syn2" value="&quot;cord&quot;"/>
              <parameter key="syn3" value="&quot;hawser&quot;"/>
              <parameter key="syn4" value="&quot;lead&quot;"/>
            </list>
            <list key="set_additional_roles"/>
          </operator>
          <operator activated="true" class="append" compatibility="7.3.000" expanded="true" height="103" name="Append" width="90" x="179" y="34"/>
          <connect from_op="Generate Data by User Specification" from_port="output" to_op="Append" to_port="example set 1"/>
          <connect from_op="Generate Data by User Specification (2)" from_port="output" to_op="Append" to_port="example set 2"/>
          <connect from_op="Append" from_port="merged set" to_port="out 1"/>
          <portSpacing port="source_in 1" spacing="0"/>
          <portSpacing port="sink_out 1" spacing="0"/>
          <portSpacing port="sink_out 2" spacing="0"/>
        </process>
        <description align="center" color="transparent" colored="false" width="126">Get a data set</description>
      </operator>
      <operator activated="true" class="rename" compatibility="7.3.000" expanded="true" height="82" name="Rename (2)" width="90" x="246" y="34">
        <parameter key="old_name" value="syn1"/>
        <parameter key="new_name" value="id"/>
        <list key="rename_additional_attributes"/>
      </operator>
      <operator activated="true" class="de_pivot" compatibility="7.3.000" expanded="true" height="82" name="De-Pivot" width="90" x="380" y="34">
        <list key="attribute_name">
          <parameter key="attribute" value="syn.*"/>
        </list>
        <parameter key="index_attribute" value="xx"/>
      </operator>
      <connect from_op="Subprocess" from_port="out 1" to_op="Rename (2)" to_port="example set input"/>
      <connect from_op="Rename (2)" from_port="example set output" to_op="De-Pivot" to_port="example set input"/>
      <connect from_op="De-Pivot" 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>

If you have your data in the described format (value;value1;value2 etc.), the easiest way to get Martin's data structure is with the Split operator.