L'opérateur Process Documents
a une option d'élagage où, avec quelques réglages minutieux des paramètres, vous pouvez supprimer les attributs communs et rares.
Voici un exemple de jouet pour le montrer fonctionner.
<?xml version="1.0" encoding="UTF-8"?><process version="7.5.000">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="7.5.000" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="text:create_document" compatibility="7.4.001" expanded="true" height="68" name="Create Document" width="90" x="179" y="187">
<parameter key="text" value="the cat sat on the mat the dog barked at the man the cow ate the grass the man sat on the grass"/>
</operator>
<operator activated="true" class="text:create_document" compatibility="7.4.001" expanded="true" height="68" name="Create Document (2)" width="90" x="179" y="289">
<parameter key="text" value="the cat sat on the mat the man sat on the grass the rain in spain falls mainly on the plain"/>
</operator>
<operator activated="true" class="text:create_document" compatibility="7.4.001" expanded="true" height="68" name="Create Document (3)" width="90" x="179" y="391">
<parameter key="text" value="the world is round"/>
</operator>
<operator activated="true" class="text:process_documents" compatibility="7.4.001" expanded="true" height="145" name="Process Documents" width="90" x="447" y="187">
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="prune_method" value="absolute"/>
<parameter key="prune_above_percent" value="40.0"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="5"/>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="7.4.001" expanded="true" height="68" name="Tokenize" width="90" x="246" y="34"/>
<connect from_port="document" to_op="Tokenize" to_port="document"/>
<connect from_op="Tokenize" 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>
<connect from_op="Create Document" from_port="output" to_op="Process Documents" to_port="documents 1"/>
<connect from_op="Create Document (2)" from_port="output" to_op="Process Documents" to_port="documents 2"/>
<connect from_op="Create Document (3)" from_port="output" to_op="Process Documents" to_port="documents 3"/>
<connect from_op="Process Documents" 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>
Il faut des soins pour l'obtenir juste, mais nous espérons que cela vous permettra de démarrer.
merci. va l'essayer –