Have log file Need multiple binomial attributes

srinivas

I have following example data (each record recording one group membership):

User, Group
bill, 1
bill, 2
bill, 3
mary, 1
mary, 2
ed, 3
...


From the above I need example data that indicates the events that a user has generated event at least once.  For example:

User, Group_1, Group_2, Group_3,...
bill, true, true, true
mary, false, true, false
ed, false, false, true


There are about about 8000 groups  (numbered 1-8000).  

The purpose of analysis is to create association rules for groups that identify connections between groups.  (e.g. "user being a member of group 1, is also likely to be a member of group 7)

Given the number of groups, perhaps there is a better way than the create association rules operator...

MartinLiebig

Hi,

attached is a quick and dirty way. For sure this is a pivot-thing. Not sure if that is the easiest way to go.

~Martin

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="7.0.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="7.0.000" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="subprocess" compatibility="7.0.000" expanded="true" height="82" name="Subprocess" width="90" x="45" y="34">
        <process expanded="true">
          <operator activated="true" class="retrieve" compatibility="7.0.000" expanded="true" height="68" name="Retrieve Iris" width="90" x="45" y="34">
            <parameter key="repository_entry" value="//Samples/data/Iris"/>
          </operator>
          <operator activated="true" class="select_attributes" compatibility="7.0.000" expanded="true" height="82" name="Select Attributes" width="90" x="179" y="34">
            <parameter key="attribute_filter_type" value="single"/>
            <parameter key="attribute" value="label"/>
            <parameter key="include_special_attributes" value="true"/>
          </operator>
          <operator activated="true" class="map" compatibility="7.0.000" expanded="true" height="82" name="Map" width="90" x="313" y="34">
            <parameter key="include_special_attributes" value="true"/>
            <list key="value_mappings">
              <parameter key="Iris-setosa" value="Bill"/>
              <parameter key="Iris-virginica" value="Mary"/>
              <parameter key="Iris-versicolor" value="Bob"/>
            </list>
          </operator>
          <operator activated="true" class="generate_attributes" compatibility="7.0.000" expanded="true" height="82" name="Generate Attributes" width="90" x="447" y="34">
            <list key="function_descriptions">
              <parameter key="Group" value="round(rand()*100)"/>
            </list>
          </operator>
          <operator activated="true" class="set_role" compatibility="7.0.000" expanded="true" height="82" name="Set Role" width="90" x="581" y="34">
            <parameter key="attribute_name" value="label"/>
            <list key="set_additional_roles"/>
          </operator>
          <operator activated="true" class="rename" compatibility="7.0.000" expanded="true" height="82" name="Rename" width="90" x="715" y="34">
            <parameter key="old_name" value="label"/>
            <parameter key="new_name" value="User"/>
            <list key="rename_additional_attributes"/>
          </operator>
          <connect from_op="Retrieve Iris" from_port="output" to_op="Select Attributes" to_port="example set input"/>
          <connect from_op="Select Attributes" from_port="example set output" to_op="Map" to_port="example set input"/>
          <connect from_op="Map" 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="Rename" to_port="example set input"/>
          <connect from_op="Rename" 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">Get a fitting Data Set</description>
      </operator>
      <operator activated="true" class="generate_id" compatibility="7.0.000" expanded="true" height="82" name="Generate ID" width="90" x="179" y="34"/>
      <operator activated="true" class="pivot" compatibility="7.0.000" expanded="true" height="82" name="Pivot" width="90" x="313" y="34">
        <parameter key="group_attribute" value="User"/>
        <parameter key="index_attribute" value="id"/>
        <parameter key="consider_weights" value="false"/>
        <parameter key="skip_constant_attributes" value="false"/>
      </operator>
      <operator activated="true" class="replace_missing_values" compatibility="7.0.000" expanded="true" height="103" name="Replace Missing Values" width="90" x="447" y="34">
        <parameter key="default" value="zero"/>
        <list key="columns"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="7.0.000" expanded="true" height="82" name="Set Role (2)" width="90" x="581" y="34">
        <parameter key="attribute_name" value="User"/>
        <parameter key="target_role" value="id"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="loop_attributes" compatibility="7.0.000" expanded="true" height="82" name="Loop Attributes" width="90" x="849" y="34">
        <process expanded="true">
          <operator activated="true" class="generate_attributes" compatibility="7.0.000" expanded="true" height="82" name="Generate Attributes (2)" width="90" x="112" y="34">
            <list key="function_descriptions">
              <parameter key="%{loop_attribute}" value="if(#{loop_attribute}==0,&quot;false&quot;,&quot;true&quot;)"/>
            </list>
          </operator>
          <connect from_port="example set" to_op="Generate Attributes (2)" to_port="example set input"/>
          <connect from_op="Generate Attributes (2)" from_port="example set output" to_port="example set"/>
          <portSpacing port="source_example set" spacing="0"/>
          <portSpacing port="sink_example set" spacing="0"/>
          <portSpacing port="sink_result 1" spacing="0"/>
        </process>
      </operator>
      <connect from_op="Subprocess" from_port="out 1" to_op="Generate ID" to_port="example set input"/>
      <connect from_op="Generate ID" from_port="example set output" to_op="Pivot" to_port="example set input"/>
      <connect from_op="Pivot" from_port="example set output" to_op="Replace Missing Values" to_port="example set input"/>
      <connect from_op="Replace Missing Values" 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="Loop Attributes" to_port="example set"/>
      <connect from_op="Loop Attributes" from_port="example 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>