Comparison of several algorithms
csoares
New Altair Community Member
Hi
I'm a newbie to RapidMiner and I'm trying to compare the performance of several algorithms. The way I found to do it is to add a OperatorSelect operator with all the algorithms I want to test as sub-operators. The problem with this approach is that I need to run the process for an algorithm, change the parameter of OperatorSelect, run the next algorithm and so on. Additionally, I need to store the results of each iteration somewhere and I couldn't find a way to analyze them simultaneously with RapidMiner.
I looked in the forum and found no answer for this although I think this is something I was expecting more people needed. So, what am I missing here?
Thanks in advance.
Cheers,
Carlos
I'm a newbie to RapidMiner and I'm trying to compare the performance of several algorithms. The way I found to do it is to add a OperatorSelect operator with all the algorithms I want to test as sub-operators. The problem with this approach is that I need to run the process for an algorithm, change the parameter of OperatorSelect, run the next algorithm and so on. Additionally, I need to store the results of each iteration somewhere and I couldn't find a way to analyze them simultaneously with RapidMiner.
I looked in the forum and found no answer for this although I think this is something I was expecting more people needed. So, what am I missing here?
Thanks in advance.
Cheers,
Carlos
Tagged:
0
Answers
-
Hi Carlos,
here is the basic setup:
Please note that you will have to adapt the parameter list of the ParameterIteration operator if you want to use more or less than three inner operators.
<operator name="Root" class="Process" expanded="yes">
<operator name="ExampleSetGenerator" class="ExampleSetGenerator">
<parameter key="number_examples" value="200"/>
<parameter key="target_function" value="sum classification"/>
</operator>
<operator name="NoiseGenerator" class="NoiseGenerator">
<list key="noise">
</list>
<parameter key="random_attributes" value="1"/>
</operator>
<operator name="ParameterIteration" class="ParameterIteration" expanded="yes">
<parameter key="keep_output" value="true"/>
<list key="parameters">
<parameter key="OperatorSelector.select_which" value="1,2,3"/>
</list>
<operator name="XValidation" class="XValidation" expanded="yes">
<parameter key="local_random_seed" value="100"/>
<operator name="OperatorSelector" class="OperatorSelector" expanded="yes">
<parameter key="select_which" value="3"/>
<operator name="DecisionTree" class="DecisionTree">
</operator>
<operator name="NaiveBayes" class="NaiveBayes">
</operator>
<operator name="LinearRegression" class="LinearRegression">
</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="which" value="operator.ParameterIteration.value.iteration"/>
<parameter key="performance" value="operator.XValidation.value.performance"/>
</list>
</operator>
</operator>
</operator>
Cheers,
Ingo0