Discretization Problems [Solved]

sukotto

Ok, so I thought I got past getting stuck using discretization, as I have used it many times, but i am stuck. I have looked at my prior processes and the samples and I am not sure what I am doing wrong. It will not discretize...

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="386" width="660">
      <operator activated="true" class="read_access" expanded="true" height="60" name="Read Access" width="90" x="45" y="30">
        <parameter key="database_file" value="C:\Users\Scott\Documents\My Dropbox\IT-Catalyst\other\oilily\oililyMktwks\oilily.mdb"/>
        <parameter key="table_name" value="TestingData"/>
      </operator>
      <operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="179" y="30">
        <parameter key="name" value="customer_id"/>
        <parameter key="target_role" value="id"/>
      </operator>
      <operator activated="true" class="set_role" expanded="true" height="76" name="Set Role (2)" width="90" x="293" y="72">
        <parameter key="name" value="isRecent"/>
        <parameter key="target_role" value="label"/>
      </operator>
      <operator activated="true" class="select_attributes" expanded="true" height="76" name="Select Attributes" width="90" x="439" y="45">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="VI/MC|Cash|C_99|C_95|C_91|C_90|C_9|C_89|C_80|C_8|C_70|C_61|C_60|C_55|C_54|C_53|C_52|C_41|C_40|C_39|C_31|C_30|C_29|C_28|C_21|C_20|C_2|C_19|C_18|C_11|C_10|C_1|Amex|create_source|customer_id|households|hwIDR|hwc|isRecent|medianInc|multistore|population|post_code|sales_associate_no|store_no|ttlSales|ttlTxn"/>
        <parameter key="include_special_attributes" value="true"/>
      </operator>
      <operator activated="true" class="numerical_to_real" expanded="true" height="76" name="Numerical to Real" width="90" x="463" y="117">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="ttlSales"/>
      </operator>
      <operator activated="true" class="discretize_by_user_specification" expanded="true" height="94" name="Discretize" width="90" x="514" y="165">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="ttlSales"/>
        <parameter key="attributes" value="ttlSales"/>
        <list key="classes">
          <parameter key="first" value="1000.0"/>
          <parameter key="second" value="2000.0"/>
          <parameter key="third" value="3000.0"/>
          <parameter key="fourth" value="4000.0"/>
          <parameter key="fifth" value="5000.0"/>
          <parameter key="over5k" value="1000000.0"/>
        </list>
      </operator>
      <connect from_op="Read Access" from_port="output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" 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="Select Attributes" to_port="example set input"/>
      <connect from_op="Select Attributes" from_port="example set output" to_op="Numerical to Real" to_port="example set input"/>
      <connect from_op="Numerical to Real" from_port="example set output" to_op="Discretize" to_port="example set input"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
    </process>
  </operator>
</process>

SebastianLoh

Hi sukotto,

did you just forget to connect the Discretize operator to a result output?

I remodel you process with other data and it works (btw, you do not need the numerical to real operator):

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="406" width="567">
      <operator activated="false" class="read_access" expanded="true" height="60" name="Read Access" width="90" x="45" y="30">
        <parameter key="database_file" value="C:\Users\Scott\Documents\My Dropbox\IT-Catalyst\other\oilily\oililyMktwks\oilily.mdb"/>
      </operator>
      <operator activated="true" class="retrieve" expanded="true" height="60" name="Retrieve (2)" width="90" x="45" y="300">
        <parameter key="repository_entry" value="//Samples/data/Sonar"/>
      </operator>
      <operator activated="true" class="rename" expanded="true" height="76" name="Rename" width="90" x="179" y="300">
        <parameter key="old_name" value="attribute_1"/>
        <parameter key="new_name" value="ttlSales"/>
      </operator>
      <operator activated="false" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="313" y="30">
        <parameter key="name" value="customer_id"/>
        <parameter key="target_role" value="id"/>
      </operator>
      <operator activated="false" class="set_role" expanded="true" height="76" name="Set Role (2)" width="90" x="447" y="30">
        <parameter key="name" value="isRecent"/>
        <parameter key="target_role" value="label"/>
      </operator>
      <operator activated="false" class="select_attributes" expanded="true" height="76" name="Select Attributes" width="90" x="45" y="165">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="VI/MC|Cash|C_99|C_95|C_91|C_90|C_9|C_89|C_80|C_8|C_70|C_61|C_60|C_55|C_54|C_53|C_52|C_41|C_40|C_39|C_31|C_30|C_29|C_28|C_21|C_20|C_2|C_19|C_18|C_11|C_10|C_1|Amex|create_source|customer_id|households|hwIDR|hwc|isRecent|medianInc|multistore|population|post_code|sales_associate_no|store_no|ttlSales|ttlTxn"/>
        <parameter key="include_special_attributes" value="true"/>
      </operator>
      <operator activated="true" class="numerical_to_real" expanded="true" height="76" name="Numerical to Real" width="90" x="313" y="210">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="ttlSales"/>
      </operator>
      <operator activated="true" class="discretize_by_user_specification" expanded="true" height="94" name="Discretize" width="90" x="447" y="210">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="ttlSales"/>
        <parameter key="attributes" value="ttlSales"/>
        <list key="classes">
          <parameter key="first" value="1000.0"/>
          <parameter key="second" value="2000.0"/>
          <parameter key="third" value="3000.0"/>
          <parameter key="fourth" value="4000.0"/>
          <parameter key="fifth" value="5000.0"/>
          <parameter key="over5k" value="1000000.0"/>
        </list>
      </operator>
      <connect from_op="Read Access" from_port="output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Retrieve (2)" from_port="output" to_op="Rename" to_port="example set input"/>
      <connect from_op="Rename" from_port="example set output" to_op="Numerical to Real" to_port="example set input"/>
      <connect from_op="Set Role" 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="Select Attributes" to_port="example set input"/>
      <connect from_op="Numerical to Real" from_port="example set output" to_op="Discretize" to_port="example set input"/>
      <connect from_op="Discretize" 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>

Ciao Sebastian

sukotto

Why, yes I did forget.... :-[
Thanks a ton!!!