Hi,
My process is either freezing my PC or failing due to low memory. Unfortunately my dataset consists of 700 attributes, so the amount of data is really large.Therefore I already log only the top 200 models and I also free memory after every iteration. Any suggestions why it is still not running properly?
Thanks a lot in advance,
Markus
<?xml version="1.0" encoding="UTF-8" standalone="no"?> <process version="5.0"> <context> <input/> <output/> <macros/> </context> <operator activated="true" class="process" compatibility="5.0.0" expanded="true" name="Process"> <process expanded="true" height="449" width="1150"> <operator activated="true" class="generate_data" compatibility="5.0.0" expanded="true" height="60" name="Generate Data" width="90" x="45" y="30"> <parameter key="target_function" value="polynomial"/> <parameter key="number_examples" value="300"/> <parameter key="number_of_attributes" value="700"/> </operator> <operator activated="true" class="add_noise" compatibility="5.0.0" expanded="true" height="94" name="Add Noise" width="90" x="179" y="30"> <parameter key="random_attributes" value="15"/> <list key="noise"/> </operator> <operator activated="true" class="discretize_by_user_specification" compatibility="5.0.0" expanded="true" height="94" name="Discretize" 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"/> <list key="classes"> <parameter key="first" value="0.5"/> <parameter key="last" value="Infinity"/> </list> </operator> <operator activated="true" class="nominal_to_binominal" compatibility="5.0.0" expanded="true" height="94" name="Nominal to Binominal" width="90" x="447" 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="loop_attribute_subsets" compatibility="5.0.0" expanded="true" height="60" name="Loop Subsets" width="90" x="581" y="30"> <parameter key="use_exact_number" value="true"/> <parameter key="exact_number_of_attributes" value="2"/> <process expanded="true" height="372" width="817"> <operator activated="true" class="multiply" compatibility="5.0.0" expanded="true" height="94" name="Multiply" width="90" x="45" y="30"/> <operator activated="false" class="x_validation" compatibility="5.0.0" expanded="true" height="112" name="Validation" width="90" x="179" y="165"> <parameter key="number_of_validations" value="5"/> <process expanded="true" height="390" width="303"> <operator activated="false" class="decision_tree" compatibility="5.0.0" expanded="true" height="76" name="Decision Tree" width="90" x="112" y="30"> <parameter key="criterion" value="gini_index"/> <parameter key="minimal_size_for_split" value="6"/> <parameter key="minimal_leaf_size" value="3"/> <parameter key="maximal_depth" value="4"/> </operator> <connect from_port="training" to_op="Decision Tree" to_port="training set"/> <connect from_op="Decision Tree" from_port="model" to_port="model"/> <portSpacing port="source_training" spacing="0"/> <portSpacing port="sink_model" spacing="0"/> <portSpacing port="sink_through 1" spacing="0"/> </process> <process expanded="true" height="390" width="303"> <operator activated="false" class="apply_model" compatibility="5.0.0" expanded="true" height="76" name="Apply Model" width="90" x="45" y="30"> <list key="application_parameters"/> </operator> <operator activated="false" class="performance_binominal_classification" compatibility="5.0.0" expanded="true" height="76" name="Performance" width="90" x="174" y="30"> <parameter key="youden" value="true"/> <parameter key="psep" value="true"/> </operator> <connect from_port="model" to_op="Apply Model" to_port="model"/> <connect from_port="test set" to_op="Apply Model" to_port="unlabelled data"/> <connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/> <connect from_op="Performance" from_port="performance" to_port="averagable 1"/> <portSpacing port="source_model" spacing="0"/> <portSpacing port="source_test set" spacing="0"/> <portSpacing port="source_through 1" spacing="0"/> <portSpacing port="sink_averagable 1" spacing="0"/> <portSpacing port="sink_averagable 2" spacing="0"/> </process> </operator> <operator activated="true" class="decision_tree" compatibility="5.0.0" expanded="true" height="76" name="Decision Tree (2)" width="90" x="179" y="30"> <parameter key="criterion" value="gini_index"/> <parameter key="minimal_size_for_split" value="6"/> <parameter key="minimal_leaf_size" value="3"/> <parameter key="maximal_depth" value="5"/> </operator> <operator activated="true" class="apply_model" compatibility="5.0.0" expanded="true" height="76" name="Apply Model (2)" width="90" x="313" y="30"> <list key="application_parameters"/> </operator> <operator activated="true" class="performance_binominal_classification" compatibility="5.0.0" expanded="true" height="76" name="Performance (2)" width="90" x="447" y="30"> <parameter key="youden" value="true"/> <parameter key="psep" value="true"/> </operator> <operator activated="true" class="log" compatibility="5.0.0" expanded="true" height="94" name="Log" width="90" x="581" y="30"> <list key="log"> <parameter key="feature_names" value="operator.Loop Subsets.value.feature_names"/> <parameter key="youden" value="operator.Performance (2).value.youden"/> <parameter key="accuracy" value="operator.Performance (2).value.accuracy"/> </list> <parameter key="sorting_type" value="top-k"/> <parameter key="sorting_dimension" value="youden"/> <parameter key="sorting_k" value="200"/> </operator> <operator activated="true" class="free_memory" compatibility="5.0.0" expanded="true" height="76" name="Free Memory" width="90" x="717" y="30"/> <connect from_port="example set" to_op="Multiply" to_port="input"/> <connect from_op="Multiply" from_port="output 1" to_op="Decision Tree (2)" to_port="training set"/> <connect from_op="Multiply" from_port="output 2" to_op="Log" to_port="through 2"/> <connect from_op="Decision Tree (2)" from_port="model" to_op="Apply Model (2)" to_port="model"/> <connect from_op="Decision Tree (2)" from_port="exampleSet" to_op="Apply Model (2)" to_port="unlabelled data"/> <connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance (2)" to_port="labelled data"/> <connect from_op="Performance (2)" from_port="performance" to_op="Log" to_port="through 1"/> <connect from_op="Log" from_port="through 1" to_op="Free Memory" to_port="through 1"/> <portSpacing port="source_example set" spacing="0"/> </process> </operator> <operator activated="true" class="log_to_data" compatibility="5.0.0" expanded="true" height="94" name="Log to Data" width="90" x="715" y="30"/> <operator activated="true" class="store" compatibility="5.0.0" expanded="true" height="60" name="Store" width="90" x="849" y="30"> <parameter key="repository_entry" value="../Logs/Training DT 2 atts"/> </operator> <operator activated="true" class="log_to_weights" compatibility="5.0.10" expanded="true" height="60" name="Log to Weights" width="90" x="849" y="120"> <parameter key="attribute_names_column" value="feature_names"/> </operator> <operator activated="true" class="store" compatibility="5.0.10" expanded="true" height="60" name="Store (2)" width="90" x="983" y="120"> <parameter key="repository_entry" value="../weights/Training DT 2 atts"/> </operator> <connect from_op="Generate Data" from_port="output" to_op="Add Noise" to_port="example set input"/> <connect from_op="Add Noise" from_port="example set 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="Loop Subsets" to_port="example set"/> <connect from_op="Loop Subsets" from_port="example set" to_op="Log to Data" to_port="through 1"/> <connect from_op="Log to Data" from_port="exampleSet" to_op="Store" to_port="input"/> <connect from_op="Log to Weights" from_port="weights" to_op="Store (2)" to_port="input"/> <portSpacing port="source_input 1" spacing="0"/> <portSpacing port="sink_result 1" spacing="0"/> </process> </operator> </process>
|