How to apply GSP patterns on new example?

Holger1984

Hi,

I'm trying to generate sequences and apply the results on a new example dataset for a new customer ID.
What I want to know, is whether sequences from my GSP.pattern results (stored in the local repository) are found in that new example.

I actually would like to get something similar to the Apply Association Rules Operator as used in the following code, just for GSP patterns.

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.013">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.3.013" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" breakpoints="after" class="subprocess" compatibility="5.3.013" expanded="true" height="94" name="Subprocess" width="90" x="45" y="30">
        <process expanded="true">
          <operator activated="true" class="retrieve" compatibility="5.3.013" expanded="true" height="60" name="Iris" width="90" x="45" y="30">
            <parameter key="repository_entry" value="//Samples/data/Iris"/>
          </operator>
          <operator activated="true" class="select_attributes" compatibility="5.3.013" expanded="true" height="76" name="Select Attributes" width="90" x="179" y="30">
            <parameter key="attribute_filter_type" value="single"/>
            <parameter key="attribute" value="label"/>
            <parameter key="invert_selection" value="true"/>
            <parameter key="include_special_attributes" value="true"/>
          </operator>
          <operator activated="true" class="discretize_by_frequency" compatibility="5.3.013" expanded="true" height="94" name="Discretize by Frequency" width="90" x="313" y="30">
            <parameter key="number_of_bins" value="5"/>
            <parameter key="range_name_type" value="short"/>
          </operator>
          <operator activated="true" class="nominal_to_binominal" compatibility="5.3.013" expanded="true" height="94" name="Nominal to Binominal" width="90" x="447" y="30">
            <parameter key="transform_binominal" value="true"/>
            <parameter key="use_underscore_in_name" value="true"/>
          </operator>
          <operator activated="true" class="split_data" compatibility="5.3.013" expanded="true" height="94" name="Split Data" width="90" x="581" y="30">
            <enumeration key="partitions">
              <parameter key="ratio" value="0.5"/>
              <parameter key="ratio" value="0.5"/>
            </enumeration>
          </operator>
          <operator activated="true" class="fp_growth" compatibility="5.3.013" expanded="true" height="76" name="FPGrowth" width="90" x="715" y="30">
            <parameter key="find_min_number_of_itemsets" value="false"/>
            <parameter key="min_number_of_itemsets" value="1"/>
            <parameter key="min_support" value="0.1"/>
          </operator>
          <operator activated="true" class="create_association_rules" compatibility="5.3.013" expanded="true" height="76" name="Create Association Rules" width="90" x="849" y="30"/>
          <connect from_op="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="Discretize by Frequency" to_port="example set input"/>
          <connect from_op="Discretize by Frequency" from_port="example set output" to_op="Nominal to Binominal" to_port="example set input"/>
          <connect from_op="Nominal to Binominal" from_port="example set output" to_op="Split Data" to_port="example set"/>
          <connect from_op="Split Data" from_port="partition 1" to_op="FPGrowth" to_port="example set"/>
          <connect from_op="Split Data" from_port="partition 2" to_port="out 2"/>
          <connect from_op="FPGrowth" from_port="frequent sets" to_op="Create Association Rules" to_port="item sets"/>
          <connect from_op="Create Association Rules" from_port="rules" to_port="out 1"/>
          <portSpacing port="source_in 1" spacing="0"/>
          <portSpacing port="sink_out 1" spacing="0"/>
          <portSpacing port="sink_out 2" spacing="144"/>
          <portSpacing port="sink_out 3" spacing="144"/>
        </process>
      </operator>
      <operator activated="true" class="apply_association_rules" compatibility="5.3.013" expanded="true" height="76" name="Apply Association Rules" width="90" x="447" y="30"/>
      <connect from_op="Subprocess" from_port="out 1" to_op="Apply Association Rules" to_port="association rules"/>
      <connect from_op="Subprocess" from_port="out 2" to_op="Apply Association Rules" to_port="example set"/>
      <connect from_op="Apply Association Rules" 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>

I hope that description is understandable...  

Thanks,
Holger

Holger1984

Hi,

does really nobody know the answer to this? I find it strange that there is an Apply Association Rules Operator, but no Apply Generalizes Sequential Patterns Operator.

Thanks
Holger

usct01

Hi
Did you get any solutions for this, please share if yes?

Thanks

Holger1984

Hi,

no, unfortunately not...

Sorry