The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
"Loop SubSet (Brute Force) for SVM models"
Contributor I
Hello,
First, I am a newbie in machine learning and RapidMiner is fantastic to quickly learn the methods without code learning !
I try scikit and R but I prefer Rapidminer to get more time for real work...
In my case, I got a good model (SVM, RBF) for a set of 26 samples (13 in each class, 2 classes) with 15 features by choosing only two features...how I choose the two good ones ? by making a naive bayes classification and looking at their probabilty curves and keep only those with the most separated ones.
To be more academic, I wanted to try brute force and log some values of the svm models like precision, accuracy, recall, class precision but the only I can get is three values performance1, performance2 and variance from this workflow :
Thanks in advance,
L.T
First, I am a newbie in machine learning and RapidMiner is fantastic to quickly learn the methods without code learning !
I try scikit and R but I prefer Rapidminer to get more time for real work...
In my case, I got a good model (SVM, RBF) for a set of 26 samples (13 in each class, 2 classes) with 15 features by choosing only two features...how I choose the two good ones ? by making a naive bayes classification and looking at their probabilty curves and keep only those with the most separated ones.
To be more academic, I wanted to try brute force and log some values of the svm models like precision, accuracy, recall, class precision but the only I can get is three values performance1, performance2 and variance from this workflow :
Any idea, first to get what I wanted and then about what are performance1,performance2 and variance ont the output of validation process?
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="6.5.002">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="6.0.002" expanded="true" name="Process">
<parameter key="logverbosity" value="init"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="never"/>
<parameter key="notification_email" value=""/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="parallelize_main_process" value="true"/>
<process expanded="true">
<operator activated="true" class="read_excel" compatibility="6.5.002" expanded="true" height="60" name="Read Excel" width="90" x="45" y="30">
<parameter key="excel_file" value="/home/toto/Bureau/Modelisation/Travail/BETA-IL.xls"/>
<parameter key="sheet_number" value="2"/>
<parameter key="imported_cell_range" value="A1:IV27"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="first_row_as_names" value="false"/>
<list key="annotations">
<parameter key="0" value="Name"/>
</list>
<parameter key="date_format" value=""/>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="French"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="ID.false.integer.attribute"/>
<parameter key="1" value="NOM.false.polynominal.attribute"/>
<parameter key="2" value="Malade.true.polynominal.attribute"/>
<parameter key="3" value="Age.false.integer.attribute"/>
<parameter key="4" value="LM-HDMB.false.polynominal.attribute"/>
<parameter key="5" value="LM.true.polynominal.attribute"/>
<parameter key="6" value="sexe.false.polynominal.attribute"/>
<parameter key="7" value="Statut.false.polynominal.attribute"/>
<parameter key="8" value="D-PHON-LH-22.true.real.attribute"/>
<parameter key="9" value="D-PHON-RH-22.true.real.attribute"/>
<parameter key="10" value="D-PHON-LH-44.true.real.attribute"/>
<parameter key="11" value="D-PHON-RH-44.true.numeric.attribute"/>
<parameter key="12" value="D-PHON-LH-45.true.real.attribute"/>
<parameter key="13" value="D-PHON-RH-45.true.real.attribute"/>
<parameter key="14" value="D-SEM-LH-21.true.real.attribute"/>
<parameter key="15" value="D-SEM-RH-21.true.real.attribute"/>
<parameter key="16" value="D-SEM-LH-47.true.real.attribute"/>
<parameter key="17" value="D-SEM-RH-47.true.real.attribute"/>
<parameter key="18" value="IL025-44.true.real.attribute"/>
<parameter key="19" value="IL025-45.true.real.attribute"/>
<parameter key="20" value="IL025-47.true.real.attribute"/>
<parameter key="21" value="IL025-22.true.real.attribute"/>
<parameter key="22" value="IL025-21.true.real.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="true"/>
<parameter key="datamanagement" value="double_array"/>
</operator>
<operator activated="true" class="select_attributes" compatibility="6.5.002" expanded="true" height="76" name="Select Attributes" width="90" x="179" y="30">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value="Malade|IL025-47|IL025-45|IL025-44|IL025-22|IL025-21|D-SEM-RH-47|D-SEM-RH-21|D-SEM-LH-47|D-SEM-LH-21|D-PHON-RH-45|D-PHON-RH-44|D-PHON-RH-22|D-PHON-LH-45|D-PHON-LH-44|D-PHON-LH-22"/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="attribute_value"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="time"/>
<parameter key="block_type" value="attribute_block"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_row_start"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
</operator>
<operator activated="true" class="set_role" compatibility="6.5.002" expanded="true" height="76" name="Set Role (3)" width="90" x="313" y="30">
<parameter key="attribute_name" value="Malade"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="normalize" compatibility="6.5.002" expanded="true" height="94" name="Normalize" width="90" x="447" y="30">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="all"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value="|IL025-45|IL025-44"/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="real"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
<parameter key="method" value="range transformation"/>
<parameter key="min" value="-1.0"/>
<parameter key="max" value="1.0"/>
</operator>
<operator activated="true" class="loop_attribute_subsets" compatibility="6.5.002" expanded="true" height="60" name="Loop Subsets" width="90" x="581" y="30">
<parameter key="use_exact_number" value="false"/>
<parameter key="exact_number_of_attributes" value="-1"/>
<parameter key="min_number_of_attributes" value="2"/>
<parameter key="limit_max_number" value="false"/>
<parameter key="max_number_of_attributes" value="-1"/>
<parameter key="parallelize_subprocess" value="true"/>
<process expanded="true">
<operator activated="true" class="x_validation" compatibility="6.5.002" expanded="true" height="112" name="Validation (2)" width="90" x="313" y="30">
<parameter key="create_complete_model" value="false"/>
<parameter key="average_performances_only" value="true"/>
<parameter key="leave_one_out" value="true"/>
<parameter key="number_of_validations" value="3"/>
<parameter key="sampling_type" value="stratified sampling"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="parallelize_training" value="true"/>
<parameter key="parallelize_testing" value="true"/>
<process expanded="true">
<operator activated="true" class="polynomial_by_binomial_classification" compatibility="6.5.002" expanded="true" height="76" name="Polynominal by Binominal Classification (2)" width="90" x="184" y="30">
<parameter key="classification_strategies" value="1 against all"/>
<parameter key="random_code_multiplicator" value="2.0"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="parallelize_learning_process" value="true"/>
<process expanded="true">
<operator activated="true" class="support_vector_machine_libsvm" compatibility="6.5.002" expanded="true" height="76" name="SVM" width="90" x="447" y="30">
<parameter key="svm_type" value="C-SVC"/>
<parameter key="kernel_type" value="rbf"/>
<parameter key="degree" value="3"/>
<parameter key="gamma" value="0.5"/>
<parameter key="coef0" value="0.0"/>
<parameter key="C" value="1000.0"/>
<parameter key="nu" value="0.5"/>
<parameter key="cache_size" value="80"/>
<parameter key="epsilon" value="0.001"/>
<parameter key="p" value="0.1"/>
<list key="class_weights"/>
<parameter key="shrinking" value="true"/>
<parameter key="calculate_confidences" value="false"/>
<parameter key="confidence_for_multiclass" value="true"/>
</operator>
<connect from_port="training set" to_op="SVM" to_port="training set"/>
<connect from_op="SVM" from_port="model" to_port="model"/>
<portSpacing port="source_training set" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
</process>
</operator>
<connect from_port="training" to_op="Polynominal by Binominal Classification (2)" to_port="training set"/>
<connect from_op="Polynominal by Binominal Classification (2)" 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">
<operator activated="true" class="apply_model" compatibility="6.5.002" expanded="true" height="76" name="Apply Model (2)" width="90" x="45" y="30">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="performance" compatibility="6.5.002" expanded="true" height="76" name="Performance (2)" width="90" x="246" y="30">
<parameter key="use_example_weights" value="true"/>
</operator>
<connect from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_port="test set" 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_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="log" compatibility="6.5.002" expanded="true" height="112" name="Log" width="90" x="715" y="30">
<parameter key="filename" value="/home/toto/Bureau/Modelisation/Travail/subset.log"/>
<list key="log">
<parameter key="Iteration" value="operator.Loop Subsets.value.iteration"/>
<parameter key="Attributes" value="operator.Loop Subsets.value.feature_names"/>
<parameter key="Performance" value="operator.Performance (2).value.performance"/>
<parameter key="Performance1" value="operator.Validation (2).value.performance1"/>
<parameter key="Performance2" value="operator.Validation (2).value.performance2"/>
<parameter key="Variance" value="operator.Validation (2).value.variance"/>
</list>
<parameter key="sorting_type" value="none"/>
<parameter key="sorting_k" value="100"/>
<parameter key="persistent" value="false"/>
</operator>
<connect from_port="example set" to_op="Validation (2)" to_port="training"/>
<connect from_op="Validation (2)" from_port="model" to_op="Log" to_port="through 1"/>
<connect from_op="Validation (2)" from_port="training" to_op="Log" to_port="through 3"/>
<connect from_op="Validation (2)" from_port="averagable 1" to_op="Log" to_port="through 2"/>
<portSpacing port="source_example set" spacing="0"/>
</process>
</operator>
<connect from_op="Read Excel" from_port="output" to_op="Select Attributes" to_port="example set input"/>
<connect from_op="Select Attributes" from_port="example set output" to_op="Set Role (3)" to_port="example set input"/>
<connect from_op="Set Role (3)" from_port="example set output" to_op="Normalize" to_port="example set input"/>
<connect from_op="Normalize" from_port="example set output" to_op="Loop Subsets" to_port="example set"/>
<connect from_op="Loop Subsets" from_port="example set" 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>
Thanks in advance,
L.T
Tagged:
0
Answers
maybe this can help you. It is a bit more fexible than the logging.
Be careful with the parallelization. The remember recall works like a goto.
Regards,
Martin
Dortmund, Germany
Thanks a lot for your answer !
I tried this workflow and tried to solve an issue when I executed it but without success...I do not really well undestrand the recall/append structure ???
The issue is a message from Recall(2) : No object name Performance was found during retrieval from obejct store.
I have read in an other post, this could be a default in the order of the tasks, but Recall(2) is the first in the Tree View of the workflow...any idea ?
3 options:
1. You can drag the Recall operator in the tree view you show here to the end of your process.
2. If you go to the menu bar Process -> Operator Execution Order -> Order Execution you can right click and change the order the process is executed.
3. You can add a subprocess with the recall inside and force the order to occur as part of the process chain. (See below example as this is the method I favour).
Hi, Thanks a lot !
Unfortunately, I tried and I got the same error...I will try to understand the recall process later I think :-\
In the same time, I have found the trouble in my first workflow without recall process, it was the wrong "Performance" process, I use now the "Performance (Binomial Classification)" and I have access to recall, precision and accuracy parameters for logging.
But
Anyone see my beginner's mystake ?