Replace Missing Values

jaysonpryde

Hi,
    I'll just ask on how to use the "Replace Missing Values" operator. After the Apply Model operator, I am dropping some predictions using "Drop Uncertain Predictions" leading to a "?" value on the prediction(class) attribute.
  What I want to do is change this "?" to a different string. What I've done so far, which unfortunately is not working is the ff:

    1. Use Replace Missing Values operator
    2. Set the attribute filter type to "single"
    3. On the attribute field, I inputted "prediction(class)"
    4. I ticked the "include special attributes" check box
    5. On the default field, i selected "none". I also tried "zero" and "value". But none of them work as I expected
    6. Edit the columns field and place prediction(calss) and value on the "attribute" and "replace with fields", respectively.
    7. Under replinishment value, i placed there the string that will changed the "?" value. (e.g. "vague")

How should I do this? Your ideas are greatly appreciated.
Thank you! 

jaysonpryde

Any help is greatly appreciated...

haddock

Hi there,

Apparently this bug was fixed... see here http://rapid-i.com/rapidforum/index.php/topic,4653.msg16823.html#msg16823

But it still appears on my 5.2.

At least it is in hand.

Nils_Woehler

Hi,

according to the post by Marco he has fixed the bug shortly  after the release of 5.2. Thus it is not yet contained in the current 5.2 release but  it should be fixed with the next bugfix release.

Best,
Nils

jaysonpryde

Given what you mentioned, yeah, i think the fix was not included.
But is this the root cause? I mean, based on my explanation/step by step description, haven't I committed some errors?

jaysonpryde

Any more inputs? Both "Replace Values" and "Replace Missing Values" are not working.
Thanks!

Nils_Woehler

Apart from the invalid learning and testing this process works with the current SVN version:

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.2.001">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.2.001" expanded="true" name="Process">
    <process expanded="true" height="606" width="705">
      <operator activated="true" class="retrieve" compatibility="5.2.001" expanded="true" height="60" name="Retrieve" width="90" x="45" y="30">
        <parameter key="repository_entry" value="//Samples/data/Iris"/>
      </operator>
      <operator activated="true" class="k_nn" compatibility="5.2.001" expanded="true" height="76" name="k-NN" width="90" x="180" y="30">
        <parameter key="k" value="10"/>
      </operator>
      <operator activated="true" class="apply_model" compatibility="5.2.001" expanded="true" height="76" name="Apply Model" width="90" x="315" y="30">
        <list key="application_parameters"/>
      </operator>
      <operator activated="true" class="drop_uncertain_predictions" compatibility="5.2.001" expanded="true" height="76" name="Drop Uncertain Predictions" width="90" x="450" y="30">
        <parameter key="min_confidence" value="0.9"/>
        <list key="min_confidences"/>
      </operator>
      <operator activated="true" class="replace_missing_values" compatibility="5.2.001" expanded="true" height="94" name="Replace Missing Values" width="90" x="581" y="30">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="prediction(label)"/>
        <parameter key="include_special_attributes" value="true"/>
        <parameter key="default" value="value"/>
        <list key="columns"/>
        <parameter key="replenishment_value" value="none"/>
      </operator>
      <connect from_op="Retrieve" from_port="output" to_op="k-NN" to_port="training set"/>
      <connect from_op="k-NN" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="k-NN" from_port="exampleSet" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Drop Uncertain Predictions" to_port="example set input"/>
      <connect from_op="Drop Uncertain Predictions" 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_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>

But as i have stated above you have to be a little more patient and wait until a bugfix release is released or you just can download the current svn release via

svn co https://rapidminer.svn.sourceforge.net/svnroot/rapidminer rapidminer

There the fix for the problem should already be included.

Greetings Nils