How can i generate new attribute giving some condition.

pallav

Say suppose we have dataset having attribute procesing_month and month1.   I want to generate new attribute if value of processing_month is "1" then dont create any attribute. If the value is "2" then create new attribute "month2", if value is "3" then create 2 attribute "Month2" and "month3" if value is 4 then create 3 attribute "month2" , "Month3" and "month4".

sgenzer

how does this work for you?

<?xml version="1.0" encoding="UTF-8"?><process version="9.6.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.6.000" 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="subprocess" compatibility="9.6.000" expanded="true" height="82" name="Subprocess" width="90" x="45" y="34">
        <process expanded="true">
          <operator activated="true" class="generate_data" compatibility="9.6.000" expanded="true" height="68" name="Generate Data" width="90" x="45" y="34">
            <parameter key="target_function" value="random"/>
            <parameter key="number_examples" value="100"/>
            <parameter key="number_of_attributes" value="1"/>
            <parameter key="attributes_lower_bound" value="-10.0"/>
            <parameter key="attributes_upper_bound" value="10.0"/>
            <parameter key="gaussian_standard_deviation" value="10.0"/>
            <parameter key="largest_radius" value="10.0"/>
            <parameter key="use_local_random_seed" value="false"/>
            <parameter key="local_random_seed" value="1992"/>
            <parameter key="datamanagement" value="double_array"/>
            <parameter key="data_management" value="auto"/>
          </operator>
          <operator activated="true" class="generate_attributes" compatibility="9.6.000" expanded="true" height="82" name="Generate Attributes" width="90" x="179" y="34">
            <list key="function_descriptions">
              <parameter key="processing_month" value="rint(abs(10*label))"/>
              <parameter key="Month_1" value="rint(abs(1000*att1))"/>
            </list>
            <parameter key="keep_all" value="true"/>
          </operator>
          <operator activated="true" class="select_attributes" compatibility="9.6.000" expanded="true" height="82" name="Select Attributes" width="90" x="313" y="34">
            <parameter key="attribute_filter_type" value="subset"/>
            <parameter key="attribute" value=""/>
            <parameter key="attributes" value="Month_1|processing_month"/>
            <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="numerical_to_polynominal" compatibility="9.6.000" expanded="true" height="82" name="Numerical to Polynominal" width="90" x="447" y="34">
            <parameter key="attribute_filter_type" value="single"/>
            <parameter key="attribute" value="processing_month"/>
            <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"/>
          </operator>
          <operator activated="true" class="order_attributes" compatibility="9.6.000" expanded="true" height="82" name="Reorder Attributes" width="90" x="581" y="34">
            <parameter key="sort_mode" value="user specified"/>
            <parameter key="attribute_ordering" value="processing_month|Month_1"/>
            <parameter key="use_regular_expressions" value="false"/>
            <parameter key="handle_unmatched" value="append"/>
            <parameter key="sort_direction" value="ascending"/>
          </operator>
          <connect from_op="Generate Data" from_port="output" to_op="Generate Attributes" to_port="example set input"/>
          <connect from_op="Generate Attributes" 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="Numerical to Polynominal" to_port="example set input"/>
          <connect from_op="Numerical to Polynominal" from_port="example set output" to_op="Reorder Attributes" to_port="example set input"/>
          <connect from_op="Reorder Attributes" from_port="example set output" 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">sample data with only Month_1</description>
      </operator>
      <operator activated="true" class="concurrency:loop_values" compatibility="9.6.000" expanded="true" height="82" name="Loop Values" width="90" x="179" y="34">
        <parameter key="attribute" value="processing_month"/>
        <parameter key="iteration_macro" value="processing_month"/>
        <parameter key="reuse_results" value="false"/>
        <parameter key="enable_parallel_execution" value="false"/>
        <process expanded="true">
          <operator activated="true" class="filter_examples" compatibility="9.6.000" expanded="true" height="103" name="Filter Examples" width="90" x="45" y="34">
            <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="processing_month.equals.%{processing_month}"/>
            </list>
            <parameter key="filters_logic_and" value="true"/>
            <parameter key="filters_check_metadata" value="true"/>
            <description align="center" color="transparent" colored="false" width="126">filter for %{processing_month}</description>
          </operator>
          <operator activated="true" class="generate_macro" compatibility="9.6.000" expanded="true" height="82" name="Generate Macro (2)" width="90" x="179" y="34">
            <list key="function_descriptions">
              <parameter key="loop_attribute_check" value="concat(&quot;Month_&quot;,%{processing_month})"/>
            </list>
            <description align="center" color="transparent" colored="false" width="126">%{loop_attribute_ check}</description>
          </operator>
          <operator activated="true" class="branch" compatibility="9.6.000" expanded="true" height="82" name="Branch" width="90" x="313" y="34">
            <parameter key="condition_type" value="attribute_available"/>
            <parameter key="condition_value" value="%{loop_attribute_check}"/>
            <parameter key="expression" value="if(%{processing_month}==1,TRUE,FALSE)"/>
            <parameter key="io_object" value="ANOVAMatrix"/>
            <parameter key="return_inner_output" value="true"/>
            <process expanded="true">
              <connect from_port="condition" to_port="input 1"/>
              <portSpacing port="source_condition" spacing="0"/>
              <portSpacing port="source_input 1" spacing="0"/>
              <portSpacing port="sink_input 1" spacing="0"/>
              <portSpacing port="sink_input 2" spacing="0"/>
              <description align="center" color="yellow" colored="false" height="105" resized="false" width="180" x="129" y="20">%{processing_month} = 1</description>
            </process>
            <process expanded="true">
              <operator activated="true" class="generate_macro" compatibility="9.6.000" expanded="true" height="82" name="Generate Macro" width="90" x="112" y="85">
                <list key="function_descriptions">
                  <parameter key="newName" value="concat(&quot;Month_&quot;,%{processing_month})"/>
                </list>
                <description align="center" color="transparent" colored="false" width="126">%{newName}</description>
              </operator>
              <operator activated="true" class="rename" compatibility="9.6.000" expanded="true" height="82" name="Rename" width="90" x="246" y="85">
                <parameter key="old_name" value="Month_1"/>
                <parameter key="new_name" value="%{newName}"/>
                <list key="rename_additional_attributes"/>
              </operator>
              <connect from_port="condition" to_op="Generate Macro" to_port="through 1"/>
              <connect from_op="Generate Macro" from_port="through 1" to_op="Rename" to_port="example set input"/>
              <connect from_op="Rename" from_port="example set output" to_port="input 1"/>
              <portSpacing port="source_condition" spacing="0"/>
              <portSpacing port="source_input 1" spacing="0"/>
              <portSpacing port="sink_input 1" spacing="0"/>
              <portSpacing port="sink_input 2" spacing="0"/>
              <description align="center" color="yellow" colored="false" height="105" resized="false" width="180" x="132" y="20">all other cases</description>
            </process>
            <description align="center" color="transparent" colored="false" width="126">checking if %{loop_attribute _check} is present</description>
          </operator>
          <connect from_port="input 1" to_op="Filter Examples" to_port="example set input"/>
          <connect from_op="Filter Examples" from_port="example set output" to_op="Generate Macro (2)" to_port="through 1"/>
          <connect from_op="Generate Macro (2)" from_port="through 1" to_op="Branch" to_port="condition"/>
          <connect from_op="Branch" from_port="input 1" to_port="output 1"/>
          <portSpacing port="source_input 1" spacing="0"/>
          <portSpacing port="source_input 2" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
          <portSpacing port="sink_output 2" spacing="0"/>
        </process>
        <description align="center" color="transparent" colored="false" width="126">loop by processing_month</description>
      </operator>
      <operator activated="true" class="operator_toolbox:advanced_append" compatibility="2.3.000" expanded="true" height="82" name="Append (Superset)" width="90" x="313" y="34"/>
      <operator activated="true" class="subprocess" compatibility="9.6.000" expanded="true" height="82" name="Subprocess (2)" width="90" x="45" y="238">
        <process expanded="true">
          <operator activated="true" class="generate_data" compatibility="9.6.000" expanded="true" height="68" name="Generate Data (2)" width="90" x="45" y="34">
            <parameter key="target_function" value="random"/>
            <parameter key="number_examples" value="100"/>
            <parameter key="number_of_attributes" value="1"/>
            <parameter key="attributes_lower_bound" value="-10.0"/>
            <parameter key="attributes_upper_bound" value="10.0"/>
            <parameter key="gaussian_standard_deviation" value="10.0"/>
            <parameter key="largest_radius" value="10.0"/>
            <parameter key="use_local_random_seed" value="false"/>
            <parameter key="local_random_seed" value="1992"/>
            <parameter key="datamanagement" value="double_array"/>
            <parameter key="data_management" value="auto"/>
          </operator>
          <operator activated="true" class="generate_attributes" compatibility="9.6.000" expanded="true" height="82" name="Generate Attributes (2)" width="90" x="179" y="34">
            <list key="function_descriptions">
              <parameter key="processing_month" value="rint(abs(10*label))"/>
              <parameter key="Month_1" value="rint(abs(1000*att1))"/>
              <parameter key="Month_2" value="rint(abs(1000*att1))"/>
            </list>
            <parameter key="keep_all" value="true"/>
          </operator>
          <operator activated="true" class="select_attributes" compatibility="9.6.000" expanded="true" height="82" name="Select Attributes (2)" width="90" x="313" y="34">
            <parameter key="attribute_filter_type" value="subset"/>
            <parameter key="attribute" value=""/>
            <parameter key="attributes" value="Month_1|processing_month"/>
            <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="numerical_to_polynominal" compatibility="9.6.000" expanded="true" height="82" name="Numerical to Polynominal (2)" width="90" x="447" y="34">
            <parameter key="attribute_filter_type" value="single"/>
            <parameter key="attribute" value="processing_month"/>
            <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"/>
          </operator>
          <operator activated="true" class="order_attributes" compatibility="9.6.000" expanded="true" height="82" name="Reorder Attributes (2)" width="90" x="581" y="34">
            <parameter key="sort_mode" value="user specified"/>
            <parameter key="attribute_ordering" value="processing_month|Month_1"/>
            <parameter key="use_regular_expressions" value="false"/>
            <parameter key="handle_unmatched" value="append"/>
            <parameter key="sort_direction" value="ascending"/>
          </operator>
          <connect from_op="Generate Data (2)" from_port="output" to_op="Generate Attributes (2)" to_port="example set input"/>
          <connect from_op="Generate Attributes (2)" 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="Numerical to Polynominal (2)" to_port="example set input"/>
          <connect from_op="Numerical to Polynominal (2)" from_port="example set output" to_op="Reorder Attributes (2)" to_port="example set input"/>
          <connect from_op="Reorder Attributes (2)" from_port="example set output" 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">sample data with Month_1 and Month_2</description>
      </operator>
      <operator activated="true" class="concurrency:loop_values" compatibility="9.6.000" expanded="true" height="82" name="Loop Values (2)" width="90" x="179" y="238">
        <parameter key="attribute" value="processing_month"/>
        <parameter key="iteration_macro" value="processing_month"/>
        <parameter key="reuse_results" value="false"/>
        <parameter key="enable_parallel_execution" value="false"/>
        <process expanded="true">
          <operator activated="true" class="filter_examples" compatibility="9.6.000" expanded="true" height="103" name="Filter Examples (2)" width="90" x="45" y="34">
            <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="processing_month.equals.%{processing_month}"/>
            </list>
            <parameter key="filters_logic_and" value="true"/>
            <parameter key="filters_check_metadata" value="true"/>
            <description align="center" color="transparent" colored="false" width="126">filter for %{processing_month}</description>
          </operator>
          <operator activated="true" class="generate_macro" compatibility="9.6.000" expanded="true" height="82" name="Generate Macro (3)" width="90" x="179" y="34">
            <list key="function_descriptions">
              <parameter key="loop_attribute_check" value="concat(&quot;Month_&quot;,%{processing_month})"/>
            </list>
            <description align="center" color="transparent" colored="false" width="126">%{loop_attribute_ check}</description>
          </operator>
          <operator activated="true" class="branch" compatibility="9.6.000" expanded="true" height="82" name="Branch (2)" width="90" x="313" y="34">
            <parameter key="condition_type" value="attribute_available"/>
            <parameter key="condition_value" value="%{loop_attribute_check}"/>
            <parameter key="expression" value="if(%{processing_month}==1,TRUE,FALSE)"/>
            <parameter key="io_object" value="ANOVAMatrix"/>
            <parameter key="return_inner_output" value="true"/>
            <process expanded="true">
              <connect from_port="condition" to_port="input 1"/>
              <portSpacing port="source_condition" spacing="0"/>
              <portSpacing port="source_input 1" spacing="0"/>
              <portSpacing port="sink_input 1" spacing="0"/>
              <portSpacing port="sink_input 2" spacing="0"/>
              <description align="center" color="yellow" colored="false" height="105" resized="false" width="180" x="129" y="20">%{processing_month} = 1</description>
            </process>
            <process expanded="true">
              <operator activated="true" class="generate_macro" compatibility="9.6.000" expanded="true" height="82" name="Generate Macro (4)" width="90" x="112" y="85">
                <list key="function_descriptions">
                  <parameter key="newName" value="concat(&quot;Month_&quot;,%{processing_month})"/>
                </list>
                <description align="center" color="transparent" colored="false" width="126">%{newName}</description>
              </operator>
              <operator activated="true" class="rename" compatibility="9.6.000" expanded="true" height="82" name="Rename (2)" width="90" x="246" y="85">
                <parameter key="old_name" value="Month_1"/>
                <parameter key="new_name" value="%{newName}"/>
                <list key="rename_additional_attributes"/>
              </operator>
              <connect from_port="condition" to_op="Generate Macro (4)" to_port="through 1"/>
              <connect from_op="Generate Macro (4)" from_port="through 1" to_op="Rename (2)" to_port="example set input"/>
              <connect from_op="Rename (2)" from_port="example set output" to_port="input 1"/>
              <portSpacing port="source_condition" spacing="0"/>
              <portSpacing port="source_input 1" spacing="0"/>
              <portSpacing port="sink_input 1" spacing="0"/>
              <portSpacing port="sink_input 2" spacing="0"/>
              <description align="center" color="yellow" colored="false" height="105" resized="false" width="180" x="132" y="20">all other cases</description>
            </process>
            <description align="center" color="transparent" colored="false" width="126">checking if %{loop_attribute _check} is present</description>
          </operator>
          <connect from_port="input 1" to_op="Filter Examples (2)" to_port="example set input"/>
          <connect from_op="Filter Examples (2)" from_port="example set output" to_op="Generate Macro (3)" to_port="through 1"/>
          <connect from_op="Generate Macro (3)" from_port="through 1" to_op="Branch (2)" to_port="condition"/>
          <connect from_op="Branch (2)" from_port="input 1" to_port="output 1"/>
          <portSpacing port="source_input 1" spacing="0"/>
          <portSpacing port="source_input 2" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
          <portSpacing port="sink_output 2" spacing="0"/>
        </process>
        <description align="center" color="transparent" colored="false" width="126">loop by processing_month</description>
      </operator>
      <operator activated="true" class="operator_toolbox:advanced_append" compatibility="2.3.000" expanded="true" height="82" name="Append (Superset) (2)" width="90" x="313" y="238"/>
      <connect from_op="Subprocess" from_port="out 1" to_op="Loop Values" to_port="input 1"/>
      <connect from_op="Loop Values" from_port="output 1" to_op="Append (Superset)" to_port="example set 1"/>
      <connect from_op="Append (Superset)" from_port="merged set" to_port="result 1"/>
      <connect from_op="Subprocess (2)" from_port="out 1" to_op="Loop Values (2)" to_port="input 1"/>
      <connect from_op="Loop Values (2)" from_port="output 1" to_op="Append (Superset) (2)" to_port="example set 1"/>
      <connect from_op="Append (Superset) (2)" from_port="merged 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="168"/>
      <portSpacing port="sink_result 3" spacing="42"/>
    </process>
  </operator>
</process>