Hi all,
here is another thing I would need your help. Random Forest (Weighting) is giving different attributes every run (due to the random selection of attributes I guess). I would like to perform the Random Forest multiple times and average over all weights to see, when the weights converge.
Here is my basic workflow, but I do not know how to average over all weights in the paramter loop.
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.0.10" expanded="true" name="Process">
<process expanded="true" height="388" width="1065">
<operator activated="true" class="generate_data" compatibility="5.0.8" expanded="true" height="60" name="Generate Data" width="90" x="45" y="30">
<parameter key="number_examples" value="200"/>
<parameter key="number_of_attributes" value="100"/>
</operator>
<operator activated="true" class="discretize_by_user_specification" compatibility="5.0.8" expanded="true" height="94" name="Discretize" width="90" x="179" y="30">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="label"/>
<parameter key="include_special_attributes" value="true"/>
<list key="classes">
<parameter key="0" value="0.5"/>
<parameter key="1" value="1.0"/>
</list>
</operator>
<operator activated="true" class="nominal_to_binominal" compatibility="5.0.8" expanded="true" height="94" name="Nominal to Binominal" width="90" x="313" y="30">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="label"/>
<parameter key="include_special_attributes" value="true"/>
</operator>
<operator activated="true" class="generate_id" compatibility="5.0.8" expanded="true" height="76" name="Generate ID" width="90" x="447" y="30"/>
<operator activated="true" class="loop_parameters" compatibility="5.0.10" expanded="true" height="76" name="Loop Parameters" width="90" x="581" y="30">
<list key="parameters">
<parameter key="Random Forest.local_random_seed" value="[333;33333333;1000;linear]"/>
</list>
<process expanded="true" height="388" width="979">
<operator activated="true" class="random_forest" compatibility="5.0.10" expanded="true" height="76" name="Random Forest" width="90" x="45" y="30">
<parameter key="criterion" value="gini_index"/>
<parameter key="maximal_depth" value="5"/>
<parameter key="use_local_random_seed" value="true"/>
<parameter key="local_random_seed" value="1866981"/>
</operator>
<operator activated="true" class="weight_by_forest" compatibility="5.0.10" expanded="true" height="76" name="Weight by Tree Importance" width="90" x="180" y="30">
<parameter key="criterion" value="gini_index"/>
</operator>
<operator activated="true" class="weights_to_data" compatibility="5.0.10" expanded="true" height="60" name="Weights to Data" width="90" x="313" y="30"/>
<connect from_port="input 1" to_op="Random Forest" to_port="training set"/>
<connect from_op="Random Forest" from_port="model" to_op="Weight by Tree Importance" to_port="random forest"/>
<connect from_op="Weight by Tree Importance" from_port="weights" to_op="Weights to Data" to_port="attribute weights"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_performance" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
</process>
</operator>
<connect from_op="Generate Data" from_port="output" to_op="Discretize" to_port="example set input"/>
<connect from_op="Discretize" from_port="example set output" to_op="Nominal to Binominal" to_port="example set input"/>
<connect from_op="Nominal to Binominal" from_port="example set output" to_op="Generate ID" to_port="example set input"/>
<connect from_op="Generate ID" from_port="example set output" to_op="Loop Parameters" to_port="input 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
</process>
</operator>
</process>
|
