Options
Log not recognised by Log to data operator
Unicornhi,
I have this process:
<?xml version="1.0" encoding="UTF-8"?><process version="7.2.003">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="6.0.002" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="loop_files" compatibility="6.4.000" expanded="true" height="82" name="Loop Dataset" width="90" x="112" y="136">
<parameter key="directory" value="D:\Work\Development\RapidMiner\RapidChapter\Datasets"/>
<parameter key="filter" value=".*[.]aml"/>
<parameter key="file_name_macro" value="dataset_name"/>
<parameter key="file_path_macro" value="dataset_path"/>
<parameter key="recursive" value="true"/>
<process expanded="true">
<operator activated="true" class="retrieve" compatibility="7.2.003" expanded="true" height="68" name="Retrieve Golf" width="90" x="112" y="34">
<parameter key="repository_entry" value="//Samples/data/Golf"/>
</operator>
<operator activated="true" class="loop" compatibility="7.2.003" expanded="true" height="82" name="Loop Algorithm" width="90" x="246" y="30">
<parameter key="set_iteration_macro" value="true"/>
<parameter key="macro_name" value="AlgorithmNo"/>
<parameter key="iterations" value="5"/>
<process expanded="true">
<operator activated="true" class="x_validation" compatibility="7.2.003" expanded="true" height="112" name="X-validation" width="90" x="112" y="30">
<parameter key="sampling_type" value="stratified sampling"/>
<process expanded="true">
<operator activated="true" class="select_subprocess" compatibility="7.2.003" expanded="true" height="76" name="Select Subprocess" width="90" x="216" y="30">
<parameter key="select_which" value="%{AlgorithmNo}"/>
<process expanded="true">
<operator activated="true" class="decision_tree" compatibility="7.2.003" expanded="true" height="76" name="Decision Tree (2)" width="90" x="44" y="30"/>
<connect from_port="input 1" to_op="Decision Tree (2)" to_port="training set"/>
<connect from_op="Decision Tree (2)" from_port="model" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="k_nn" compatibility="7.2.003" expanded="true" height="76" name="k-NN" width="90" x="44" y="30"/>
<connect from_port="input 1" to_op="k-NN" to_port="training set"/>
<connect from_op="k-NN" from_port="model" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="naive_bayes" compatibility="7.2.003" expanded="true" height="76" name="Naive Bayes" width="90" x="44" y="30"/>
<connect from_port="input 1" to_op="Naive Bayes" to_port="training set"/>
<connect from_op="Naive Bayes" from_port="model" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="nominal_to_numerical" compatibility="7.1.001" expanded="true" height="94" name="Nominal to Numerical" width="90" x="45" y="30">
<list key="comparison_groups"/>
</operator>
<operator activated="true" class="support_vector_machine" compatibility="7.2.003" expanded="true" height="112" name="SVM" width="90" x="111" y="30">
<parameter key="convergence_epsilon" value="0.0010"/>
</operator>
<connect from_port="input 1" to_op="Nominal to Numerical" to_port="example set input"/>
<connect from_op="Nominal to Numerical" from_port="example set output" to_op="SVM" to_port="training set"/>
<connect from_op="SVM" from_port="model" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="random_forest" compatibility="7.2.003" expanded="true" height="76" name="Random Forest (2)" width="90" x="44" y="30"/>
<connect from_port="input 1" to_op="Random Forest (2)" to_port="training set"/>
<connect from_op="Random Forest (2)" from_port="model" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
</operator>
<connect from_port="training" to_op="Select Subprocess" to_port="input 1"/>
<connect from_op="Select Subprocess" from_port="output 1" 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">
<operator activated="true" class="apply_model" compatibility="7.1.001" expanded="true" height="76" name="Apply Model" width="90" x="45" y="30">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="performance_classification" compatibility="7.2.003" expanded="true" height="76" name="Performance" width="90" x="283" y="30">
<list key="class_weights"/>
</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="subprocess" compatibility="7.2.003" expanded="true" height="76" name="Logging" width="90" x="380" y="30">
<process expanded="true">
<operator activated="true" class="provide_macro_as_log_value" compatibility="7.2.003" expanded="true" height="76" name="LogDataset" width="90" x="45" y="30">
<parameter key="macro_name" value="dataset_name"/>
</operator>
<operator activated="true" class="provide_macro_as_log_value" compatibility="7.2.003" expanded="true" height="76" name="LogAlgorithm" width="90" x="179" y="30">
<parameter key="macro_name" value="AlgorithmNo"/>
</operator>
<operator activated="true" class="log" compatibility="7.2.003" expanded="true" height="76" name="Log" width="90" x="447" y="30">
<list key="log">
<parameter key="Dataset" value="operator.LogDataset.value.macro_value"/>
<parameter key="AlgorithmNo" value="operator.LogAlgorithm.value.macro_value"/>
<parameter key="Accuracy" value="operator.X-validation.value.performance"/>
</list>
</operator>
<connect from_port="in 1" to_op="LogDataset" to_port="through 1"/>
<connect from_op="LogDataset" from_port="through 1" to_op="LogAlgorithm" to_port="through 1"/>
<connect from_op="LogAlgorithm" from_port="through 1" to_op="Log" to_port="through 1"/>
<connect from_op="Log" from_port="through 1" to_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
</process>
</operator>
<connect from_port="input 1" to_op="X-validation" to_port="training"/>
<connect from_op="X-validation" from_port="averagable 1" to_op="Logging" to_port="in 1"/>
<connect from_op="Logging" from_port="out 1" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
</operator>
<connect from_op="Retrieve Golf" from_port="output" to_op="Loop Algorithm" to_port="input 1"/>
<connect from_op="Loop Algorithm" from_port="output 1" to_port="out 1"/>
<portSpacing port="source_file object" spacing="0"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="subprocess" compatibility="7.2.003" expanded="true" height="82" name="Log to Dataset" width="90" x="313" y="30">
<process expanded="true">
<operator activated="true" class="log_to_data" compatibility="7.2.003" expanded="true" height="103" name="Log to Data" width="90" x="112" y="34">
<parameter key="log_name" value="Log"/>
</operator>
<operator activated="true" class="pivot" compatibility="7.2.003" expanded="true" height="82" name="Pivot" width="90" x="246" y="30">
<parameter key="group_attribute" value="Dataset"/>
<parameter key="index_attribute" value="AlgorithmNo"/>
</operator>
<operator activated="true" class="rename" compatibility="7.2.003" expanded="true" height="82" name="Rename" width="90" x="375" y="30">
<parameter key="old_name" value="Accuracy_1"/>
<parameter key="new_name" value="Decision Tree"/>
<list key="rename_additional_attributes">
<parameter key="Accuracy_2" value="k-NN"/>
<parameter key="Accuracy_3" value="Naive Bayes"/>
<parameter key="Accuracy_4" value="SVN"/>
<parameter key="Accuracy_5" value="Random Forests"/>
</list>
</operator>
<connect from_port="in 1" to_op="Log to Data" to_port="through 1"/>
<connect from_op="Log to Data" from_port="exampleSet" to_op="Pivot" to_port="example set input"/>
<connect from_op="Pivot" from_port="example set output" to_op="Rename" to_port="example set input"/>
<connect from_op="Rename" from_port="example set output" to_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
</process>
</operator>
<connect from_op="Loop Dataset" from_port="out 1" to_op="Log to Dataset" to_port="in 1"/>
<connect from_op="Log to Dataset" from_port="out 1" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
</process>
</operator>
</process>
but my Log operator is not recognised in my Log to data Operator.. why?
0
Answers
hello?
can someone reproduce the problem by this process? I still dont know why this is so
has anyone an idea?
Have you check out this thread? http://community.rapidminer.com/t5/RapidMiner-Studio/Log-to-Data-Missing-Attribute-Names/td-p/34059
It might be a metadata issue.