Я хотел бы токенизировать и применить фильтр стоп-слов к комментариям Twitter, содержащимся в базе данных, но Process Document ничего не делает. Что я делаю не так?
Моя цель — применить эти фильтры, но сохранить комментарии в строках, а не в одном векторе слов.
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.015">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.3.015" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="read_database" compatibility="5.3.015" expanded="true" height="60" name="Server Connection (2)" width="90" x="45" y="30">
<parameter key="connection" value="sqlserver2014"/>
<parameter key="query" value="select top 60 tweetid,content from [Tweets General]"/>
<enumeration key="parameters"/>
</operator>
<operator activated="true" class="text:data_to_documents" compatibility="5.3.002" expanded="true" height="60" name="Data to Documents" width="90" x="246" y="30">
<parameter key="select_attributes_and_weights" value="true"/>
<list key="specify_weights"/>
</operator>
<operator activated="true" class="text:process_documents" compatibility="5.3.002" expanded="true" height="94" name="Process Documents" width="90" x="447" y="30">
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (3)" width="90" x="246" y="75"/>
<connect from_port="document" to_op="Tokenize (3)" to_port="document"/>
<connect from_op="Tokenize (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>
<connect from_op="Server Connection (2)" from_port="output" to_op="Data to Documents" to_port="example set"/>
<connect from_op="Data to Documents" from_port="documents" to_op="Process Documents" to_port="documents 1"/>
<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>