comparison between different classifier in different dataset

m_r_nour

Hi

I'm looking for a way to compare performance of different classifier (like MLP, SVM, simplecartTree,..) with each other in different dataset (e.g. a dataset with  outliers and a dataset without them). I know we can do that in Weka by experimenter but about Rapidminer?

any Idea?

Moreover, I'd appreciate if there is any template to do that,send it to me.

thank you for your time and consideration


Regards
REZA

land

Hi,
if I understood you correct, you are going to iterate over several files and test on each file how well a classifier will work? Then you could use the FileIterator to iterate over arbitrary files and then insert the macro containing the filename into an ExampleSource.
Then you could use the ParameterIteration and a Operator selector to iterate over the different learning algorithms.

Although this might sound confusing this should be very easy for everyone ever seen a for loop. The process then looks like that:

<operator name="Root" class="Process" expanded="yes">
    <operator name="FileIterator" class="FileIterator" expanded="yes">
        <parameter key="directory"	value="c:\data"/>
        <operator name="CSVExampleSource" class="CSVExampleSource">
            <parameter key="filename"	value="%{file_name}"/>
            <parameter key="label_name"	value="label"/>
        </operator>
        <operator name="ParameterIteration" class="ParameterIteration" expanded="yes">
            <list key="parameters">
              <parameter key="OperatorSelector.select_which"	value="[1.0;3.0;3;linear]"/>
            </list>
            <operator name="XValidation" class="XValidation" expanded="no">
                <operator name="OperatorSelector" class="OperatorSelector" expanded="no">
                    <operator name="DecisionTree" class="DecisionTree">
                    </operator>
                    <operator name="NaiveBayes" class="NaiveBayes">
                    </operator>
                    <operator name="JMySVMLearner" class="JMySVMLearner">
                    </operator>
                </operator>
                <operator name="OperatorChain" class="OperatorChain" expanded="yes">
                    <operator name="ModelApplier" class="ModelApplier">
                        <list key="application_parameters">
                        </list>
                    </operator>
                    <operator name="Performance" class="Performance">
                    </operator>
                </operator>
            </operator>
            <operator name="ProcessLog" class="ProcessLog">
                <list key="log">
                  <parameter key="File"	value="operator.CSVExampleSource.parameter.filename"/>
                  <parameter key="Learner"	value="operator.OperatorSelector.parameter.select_which"/>
                  <parameter key="Performance"	value="operator.XValidation.value.performance"/>
                  <parameter key="Deviation"	value="operator.XValidation.value.deviation"/>
                </list>
            </operator>
        </operator>
    </operator>
</operator>

Greetings,
  Sebastian

m_r_nour

hi

first of all thank you

but it doesn't work. because FileIterator find the file but CSVExampleSource looks for that file in other directory.( in the current directory of Rapidminer not in the directory the file is located)  !!!!!!!


Regards
REZA

land

Hi,
there's another macro in the FileIterator, which will deliver the complete path. You should use this, because whenever there's only given the file name, it will be resolved relative to the process file's location.

Greetings,
  Sebastian

m_r_nour

Hi

thanks a lotttttttttttttt


regards
REZA