Correlation - need help getting started

RCL1

Folks- I've just started using Rapid Miner and am trying to calculate a correlation coefficient as a first test.

My data set includes three columns, the first is the key, so the role is set to "id". The second column would be my dependent variable, so I set role to "label". Finally, the third column I set to "regular".

In the Designer, I piped a "retrieve" of the data to a "Correlation Matrix" operator.

When I run the process, the results perspective does not show correlation in the Meta Data View. Under the Statistics column, it only shows avg = 1235 +/- 123, as well as a Range column.

Can anyone tell me how to get it to calculate and display a Pearson correlation coefficient?

Thanks,

RCL1

RCL1

Still trying to square what I'm reading in the manual with my test example. Re-imported the data:

Four columns: IP ID (Integer, ID); Income (integer, weight); Expenditure (integer, attribute); WC QT (integer, attribute)

Now when I pipe this data retrieve to the correlation matrix, I only get average and range for statistics under Meta Data View.

Where do I calculate a correlation coefficient?

Thanks,

RL

MariusHelf

Hi, did you connect the mat output of Correlation Matrix to the process output? Please have a look at the process below. If that does not solve your problem, please attach your process setup as described in this thread: http://rapid-i.com/rapidforum/index.php/topic,4782.0.html

Best,
Marius

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.2.002">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.2.002" expanded="true" name="Process">
    <process expanded="true" height="638" width="716">
      <operator activated="true" class="generate_data" compatibility="5.2.002" expanded="true" height="60" name="Generate Data" width="90" x="112" y="30">
        <parameter key="target_function" value="random classification"/>
      </operator>
      <operator activated="true" class="correlation_matrix" compatibility="5.2.002" expanded="true" height="94" name="Correlation Matrix" width="90" x="313" y="30"/>
      <connect from_op="Generate Data" from_port="output" to_op="Correlation Matrix" to_port="example set"/>
      <connect from_op="Correlation Matrix" from_port="example set" to_port="result 1"/>
      <connect from_op="Correlation Matrix" from_port="matrix" to_port="result 2"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
      <portSpacing port="sink_result 3" spacing="0"/>
    </process>
  </operator>
</process>

RCL1

Ok, I took a look. Other than some style differences I'm not seeing any glaring problems.

This is my process:

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.2.000">
  <context>
    <input>
      <location>//RapdMinerNewLocalRepository/CorrTest</location>
    </input>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.2.000"
expanded="true" name="Process">
    <process expanded="true" height="435" width="413">
      <operator activated="true" class="retrieve"
compatibility="5.2.000" expanded="true" height="60" name="Retrieve"
width="90" x="87" y="237">
        <parameter key="repository_entry" value="corrTest2"/>
      </operator>
      <operator activated="true" class="correlation_matrix"
compatibility="5.2.000" expanded="true" height="94" name="Correlation
Matrix" width="90" x="338" y="221">
        <parameter key="squared_correlation" value="true"/>
      </operator>
      <connect from_op="Retrieve" from_port="output"
to_op="Correlation Matrix" to_port="example set"/>
      <connect from_op="Correlation Matrix" from_port="example set"
to_port="result 1"/>
      <connect from_op="Correlation Matrix" from_port="matrix"
to_port="result 2"/>
      <portSpacing port="source_input 1" spacing="54"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>

RCL1

I changed port spacing from 54 to 0 on result 2.

<portSpacing port="source_input 1" spacing="0"/>

I'm getting a pairwise table now...

MariusHelf

The port spacing should not influence the results at all, it's just for the visualization of the process.

RCL1 wrote:
I'm getting a pairwise table now...

Is that what you want?