Classification of multi label dataset using SVM
cazzi123
New Altair Community Member
I am trying to apply SVM to the 20 newsgroups dataset without success. I have applied some preprocessing such as tokenize, stemming and changed case. The process has nested the SVM operator in a Polynominal by Binaminal classification operator. It runs for hours before finally giving up due to memory.
I have applied Naive Bayes and K-NN without an issue and both complete pretty quickly.
Can you please take a look at the process below and make any suggestions on how I could speed up the classification using SVM.
The dataset has twenty labels.
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.015">
<context>
<input>
<location>//RM_Repository/Project/Newsgroups_TrainVector</location>
</input>
<output>
<location>Newsgroups_TrainVectorTH</location>
<location>Newsgroups_TrainVector</location>
</output>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.3.015" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="text:process_document_from_file" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Files (2)" width="90" x="112" y="75">
<list key="text_directories">
<parameter key="alt.atheism" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\alt.atheism"/>
<parameter key="comp.graphics" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.graphics"/>
<parameter key="misc.forsale" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\misc.forsale"/>
<parameter key="rec.autos" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.autos"/>
<parameter key="comp.os.ms-windows.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.os.ms-windows.misc"/>
<parameter key="comp.sys.ibm.pc.hardware" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.sys.ibm.pc.hardware"/>
<parameter key="comp.windows.x" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.windows.x"/>
<parameter key="rec.motorcycles" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.motorcycles"/>
<parameter key="rec.sport.baseball" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.sport.baseball"/>
<parameter key="rec.sport.hockey" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.sport.hockey"/>
<parameter key="sci.crypt" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\sci.crypt"/>
<parameter key="sci.electronics" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\sci.electronics"/>
<parameter key="sci.med" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\sci.med"/>
<parameter key="sci.space" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\sci.space"/>
<parameter key="soc.religion.christian" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\soc.religion.christian"/>
<parameter key="talk.politics.guns" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\talk.politics.guns"/>
<parameter key="talk.politics.mideast" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\talk.politics.mideast"/>
<parameter key="talk.politics.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\talk.politics.misc"/>
<parameter key="talk.religion.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\talk.religion.misc"/>
<parameter key="comp.sys.mac.hardware" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.sys.mac.hardware"/>
</list>
<parameter key="prune_method" value="absolute"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="1000"/>
<process expanded="true">
<operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases (2)" width="90" x="45" y="30"/>
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (2)" width="90" x="180" y="30"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.3.002" expanded="true" height="60" name="Filter Stopwords (2)" width="90" x="313" y="30"/>
<operator activated="true" class="text:stem_snowball" compatibility="5.3.002" expanded="true" height="60" name="Stem (2)" width="90" x="447" y="30"/>
<operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (2)" width="90" x="581" y="30">
<parameter key="min_chars" value="2"/>
</operator>
<connect from_port="document" to_op="Transform Cases (2)" to_port="document"/>
<connect from_op="Transform Cases (2)" from_port="document" to_op="Tokenize (2)" to_port="document"/>
<connect from_op="Tokenize (2)" from_port="document" to_op="Filter Stopwords (2)" to_port="document"/>
<connect from_op="Filter Stopwords (2)" from_port="document" to_op="Stem (2)" to_port="document"/>
<connect from_op="Stem (2)" from_port="document" to_op="Filter Tokens (2)" to_port="document"/>
<connect from_op="Filter Tokens (2)" from_port="document" to_port="document 1"/>
<portSpacing port="source_document" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="x_validation" compatibility="5.3.015" expanded="true" height="112" name="Validation" width="90" x="380" y="75">
<parameter key="number_of_validations" value="5"/>
<process expanded="true">
<operator activated="false" class="k_nn" compatibility="5.3.015" expanded="true" height="76" name="k-NN" width="90" x="179" y="165">
<parameter key="k" value="5"/>
</operator>
<operator activated="false" class="naive_bayes" compatibility="5.3.015" expanded="true" height="76" name="Naive Bayes" width="90" x="179" y="300"/>
<operator activated="true" class="polynomial_by_binomial_classification" compatibility="5.3.015" expanded="true" height="76" name="Polynominal by Binominal Classification" width="90" x="112" y="30">
<parameter key="classification_strategies" value="exhaustive code (ECOC)"/>
<process expanded="true">
<operator activated="true" class="support_vector_machine" compatibility="5.3.015" expanded="true" height="112" name="SVM (2)" width="90" x="313" y="75"/>
<connect from_port="training set" to_op="SVM (2)" to_port="training set"/>
<connect from_op="SVM (2)" from_port="model" to_port="model"/>
<portSpacing port="source_training set" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
</process>
</operator>
<operator activated="false" class="support_vector_machine_libsvm" compatibility="5.3.015" expanded="true" height="76" name="SVM" width="90" x="179" y="435">
<list key="class_weights"/>
</operator>
<connect from_port="training" to_op="Polynominal by Binominal Classification" to_port="training set"/>
<connect from_op="Polynominal by Binominal Classification" 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="5.3.015" expanded="true" height="76" name="Apply Model" width="90" x="112" y="30">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="performance_classification" compatibility="5.3.015" expanded="true" height="76" name="Performance" width="90" x="313" y="30">
<parameter key="main_criterion" value="accuracy"/>
<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="text:process_document_from_file" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Files (3)" width="90" x="112" y="345">
<list key="text_directories">
<parameter key="alt.atheism" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\alt.atheism"/>
<parameter key="comp.graphics" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.graphics"/>
<parameter key="misc.forsale" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\misc.forsale"/>
<parameter key="rec.autos" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.autos"/>
<parameter key="comp.os.ms-windows.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.os.ms-windows.misc"/>
<parameter key="comp.sys.ibm.pc.hardware" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.sys.ibm.pc.hardware"/>
<parameter key="comp.windows.x" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.windows.x"/>
<parameter key="rec.motorcycles" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\rec.motorcycles"/>
<parameter key="rec.sport.baseball" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\rec.sport.baseball"/>
<parameter key="rec.sport.hockey" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\rec.sport.hockey"/>
<parameter key="sci.crypt" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\sci.crypt"/>
<parameter key="sci.electronics" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\sci.electronics"/>
<parameter key="sci.med" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\sci.med"/>
<parameter key="sci.space" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\sci.space"/>
<parameter key="soc.religion.christian" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\soc.religion.christian"/>
<parameter key="talk.politics.guns" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\talk.politics.guns"/>
<parameter key="talk.politics.mideast" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\talk.politics.mideast"/>
<parameter key="talk.politics.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\talk.politics.misc"/>
<parameter key="talk.religion.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\talk.religion.misc"/>
<parameter key="comp.sys.mac.hardware" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\comp.sys.mac.hardware"/>
</list>
<parameter key="prune_method" value="absolute"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="1000"/>
<process expanded="true">
<operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases (3)" width="90" x="45" y="30"/>
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (3)" width="90" x="180" y="30"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.3.002" expanded="true" height="60" name="Filter Stopwords (3)" width="90" x="315" y="30"/>
<operator activated="true" class="text:stem_snowball" compatibility="5.3.002" expanded="true" height="60" name="Stem (3)" width="90" x="450" y="30"/>
<operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (3)" width="90" x="571" y="30">
<parameter key="min_chars" value="2"/>
</operator>
<connect from_port="document" to_op="Transform Cases (3)" to_port="document"/>
<connect from_op="Transform Cases (3)" from_port="document" to_op="Tokenize (3)" to_port="document"/>
<connect from_op="Tokenize (3)" from_port="document" to_op="Filter Stopwords (3)" to_port="document"/>
<connect from_op="Filter Stopwords (3)" from_port="document" to_op="Stem (3)" to_port="document"/>
<connect from_op="Stem (3)" from_port="document" to_op="Filter Tokens (3)" to_port="document"/>
<connect from_op="Filter Tokens (3)" from_port="document" to_port="document 1"/>
<portSpacing port="source_document" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="apply_model" compatibility="5.3.015" expanded="true" height="76" name="Apply Model (2)" width="90" x="514" y="300">
<list key="application_parameters"/>
</operator>
<connect from_op="Process Documents from Files (2)" from_port="example set" to_op="Validation" to_port="training"/>
<connect from_op="Validation" from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_op="Validation" from_port="training" to_port="result 2"/>
<connect from_op="Process Documents from Files (3)" from_port="example set" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Apply Model (2)" from_port="labelled data" 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"/>
<portSpacing port="sink_result 3" spacing="0"/>
</process>
</operator>
</process>
I have applied Naive Bayes and K-NN without an issue and both complete pretty quickly.
Can you please take a look at the process below and make any suggestions on how I could speed up the classification using SVM.
The dataset has twenty labels.
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.015">
<context>
<input>
<location>//RM_Repository/Project/Newsgroups_TrainVector</location>
</input>
<output>
<location>Newsgroups_TrainVectorTH</location>
<location>Newsgroups_TrainVector</location>
</output>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.3.015" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="text:process_document_from_file" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Files (2)" width="90" x="112" y="75">
<list key="text_directories">
<parameter key="alt.atheism" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\alt.atheism"/>
<parameter key="comp.graphics" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.graphics"/>
<parameter key="misc.forsale" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\misc.forsale"/>
<parameter key="rec.autos" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.autos"/>
<parameter key="comp.os.ms-windows.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.os.ms-windows.misc"/>
<parameter key="comp.sys.ibm.pc.hardware" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.sys.ibm.pc.hardware"/>
<parameter key="comp.windows.x" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.windows.x"/>
<parameter key="rec.motorcycles" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.motorcycles"/>
<parameter key="rec.sport.baseball" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.sport.baseball"/>
<parameter key="rec.sport.hockey" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.sport.hockey"/>
<parameter key="sci.crypt" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\sci.crypt"/>
<parameter key="sci.electronics" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\sci.electronics"/>
<parameter key="sci.med" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\sci.med"/>
<parameter key="sci.space" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\sci.space"/>
<parameter key="soc.religion.christian" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\soc.religion.christian"/>
<parameter key="talk.politics.guns" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\talk.politics.guns"/>
<parameter key="talk.politics.mideast" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\talk.politics.mideast"/>
<parameter key="talk.politics.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\talk.politics.misc"/>
<parameter key="talk.religion.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\talk.religion.misc"/>
<parameter key="comp.sys.mac.hardware" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.sys.mac.hardware"/>
</list>
<parameter key="prune_method" value="absolute"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="1000"/>
<process expanded="true">
<operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases (2)" width="90" x="45" y="30"/>
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (2)" width="90" x="180" y="30"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.3.002" expanded="true" height="60" name="Filter Stopwords (2)" width="90" x="313" y="30"/>
<operator activated="true" class="text:stem_snowball" compatibility="5.3.002" expanded="true" height="60" name="Stem (2)" width="90" x="447" y="30"/>
<operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (2)" width="90" x="581" y="30">
<parameter key="min_chars" value="2"/>
</operator>
<connect from_port="document" to_op="Transform Cases (2)" to_port="document"/>
<connect from_op="Transform Cases (2)" from_port="document" to_op="Tokenize (2)" to_port="document"/>
<connect from_op="Tokenize (2)" from_port="document" to_op="Filter Stopwords (2)" to_port="document"/>
<connect from_op="Filter Stopwords (2)" from_port="document" to_op="Stem (2)" to_port="document"/>
<connect from_op="Stem (2)" from_port="document" to_op="Filter Tokens (2)" to_port="document"/>
<connect from_op="Filter Tokens (2)" from_port="document" to_port="document 1"/>
<portSpacing port="source_document" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="x_validation" compatibility="5.3.015" expanded="true" height="112" name="Validation" width="90" x="380" y="75">
<parameter key="number_of_validations" value="5"/>
<process expanded="true">
<operator activated="false" class="k_nn" compatibility="5.3.015" expanded="true" height="76" name="k-NN" width="90" x="179" y="165">
<parameter key="k" value="5"/>
</operator>
<operator activated="false" class="naive_bayes" compatibility="5.3.015" expanded="true" height="76" name="Naive Bayes" width="90" x="179" y="300"/>
<operator activated="true" class="polynomial_by_binomial_classification" compatibility="5.3.015" expanded="true" height="76" name="Polynominal by Binominal Classification" width="90" x="112" y="30">
<parameter key="classification_strategies" value="exhaustive code (ECOC)"/>
<process expanded="true">
<operator activated="true" class="support_vector_machine" compatibility="5.3.015" expanded="true" height="112" name="SVM (2)" width="90" x="313" y="75"/>
<connect from_port="training set" to_op="SVM (2)" to_port="training set"/>
<connect from_op="SVM (2)" from_port="model" to_port="model"/>
<portSpacing port="source_training set" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
</process>
</operator>
<operator activated="false" class="support_vector_machine_libsvm" compatibility="5.3.015" expanded="true" height="76" name="SVM" width="90" x="179" y="435">
<list key="class_weights"/>
</operator>
<connect from_port="training" to_op="Polynominal by Binominal Classification" to_port="training set"/>
<connect from_op="Polynominal by Binominal Classification" 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="5.3.015" expanded="true" height="76" name="Apply Model" width="90" x="112" y="30">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="performance_classification" compatibility="5.3.015" expanded="true" height="76" name="Performance" width="90" x="313" y="30">
<parameter key="main_criterion" value="accuracy"/>
<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="text:process_document_from_file" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Files (3)" width="90" x="112" y="345">
<list key="text_directories">
<parameter key="alt.atheism" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\alt.atheism"/>
<parameter key="comp.graphics" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.graphics"/>
<parameter key="misc.forsale" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\misc.forsale"/>
<parameter key="rec.autos" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\rec.autos"/>
<parameter key="comp.os.ms-windows.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.os.ms-windows.misc"/>
<parameter key="comp.sys.ibm.pc.hardware" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.sys.ibm.pc.hardware"/>
<parameter key="comp.windows.x" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-train\comp.windows.x"/>
<parameter key="rec.motorcycles" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\rec.motorcycles"/>
<parameter key="rec.sport.baseball" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\rec.sport.baseball"/>
<parameter key="rec.sport.hockey" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\rec.sport.hockey"/>
<parameter key="sci.crypt" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\sci.crypt"/>
<parameter key="sci.electronics" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\sci.electronics"/>
<parameter key="sci.med" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\sci.med"/>
<parameter key="sci.space" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\sci.space"/>
<parameter key="soc.religion.christian" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\soc.religion.christian"/>
<parameter key="talk.politics.guns" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\talk.politics.guns"/>
<parameter key="talk.politics.mideast" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\talk.politics.mideast"/>
<parameter key="talk.politics.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\talk.politics.misc"/>
<parameter key="talk.religion.misc" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\talk.religion.misc"/>
<parameter key="comp.sys.mac.hardware" value="E:\Year 2\Text Mining\Practical\20news-bydate\20news-bydate-test\comp.sys.mac.hardware"/>
</list>
<parameter key="prune_method" value="absolute"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="1000"/>
<process expanded="true">
<operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases (3)" width="90" x="45" y="30"/>
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (3)" width="90" x="180" y="30"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.3.002" expanded="true" height="60" name="Filter Stopwords (3)" width="90" x="315" y="30"/>
<operator activated="true" class="text:stem_snowball" compatibility="5.3.002" expanded="true" height="60" name="Stem (3)" width="90" x="450" y="30"/>
<operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (3)" width="90" x="571" y="30">
<parameter key="min_chars" value="2"/>
</operator>
<connect from_port="document" to_op="Transform Cases (3)" to_port="document"/>
<connect from_op="Transform Cases (3)" from_port="document" to_op="Tokenize (3)" to_port="document"/>
<connect from_op="Tokenize (3)" from_port="document" to_op="Filter Stopwords (3)" to_port="document"/>
<connect from_op="Filter Stopwords (3)" from_port="document" to_op="Stem (3)" to_port="document"/>
<connect from_op="Stem (3)" from_port="document" to_op="Filter Tokens (3)" to_port="document"/>
<connect from_op="Filter Tokens (3)" from_port="document" to_port="document 1"/>
<portSpacing port="source_document" spacing="0"/>
<portSpacing port="sink_document 1" spacing="0"/>
<portSpacing port="sink_document 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="apply_model" compatibility="5.3.015" expanded="true" height="76" name="Apply Model (2)" width="90" x="514" y="300">
<list key="application_parameters"/>
</operator>
<connect from_op="Process Documents from Files (2)" from_port="example set" to_op="Validation" to_port="training"/>
<connect from_op="Validation" from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_op="Validation" from_port="training" to_port="result 2"/>
<connect from_op="Process Documents from Files (3)" from_port="example set" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Apply Model (2)" from_port="labelled data" 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"/>
<portSpacing port="sink_result 3" spacing="0"/>
</process>
</operator>
</process>
Tagged:
0