RapidMiner - 将数据表行作为文档处理

时间:2014-02-27 20:27:11

标签: mysql rapidminer

我需要关于以下问题的帮助:我将处理从Read Database获取的数据表(示例集结构(label[datatype]): mid[int], body[text])中的每一行作为文档。这样我可以应用一些过滤器每个文件(停用词,过滤器等)。任何人都可以帮助我吗?

<?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" width="90" x="112" y="120">
        <parameter key="connection" value="Server"/>
        <parameter key="query" value="SELECT `mid`, `body` FROM `message` WHERE `mid` &lt; 10 ORDER BY `mid`"/>
        <enumeration key="parameters"/>
      </operator>
      <operator activated="true" class="loop_data_sets" compatibility="5.3.015" expanded="true" height="76" name="Loop Data Sets" width="90" x="111" y="210">
        <process expanded="true">
          <operator activated="true" class="text:extract_document" compatibility="5.3.002" expanded="true" name="Extract Document (2)">
            <parameter key="attribute_name" value="body"/>
            <parameter key="example_index" value="1"/>
          </operator>
          <operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" name="Transform Cases (2)"/>
          <operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" name="Tokenize (2)"/>
          <operator activated="true" class="text:filter_stopwords_dictionary" compatibility="5.3.002" expanded="true" name="Filter Stopwords (2)">
            <parameter key="file" value="C:\User\stopwords.txt"/>
          </operator>
          <operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" name="Filter Tokens (2)">
            <parameter key="min_chars" value="2"/>
          </operator>
          <connect from_port="example set" to_op="Extract Document (2)" to_port="example set"/>
          <connect from_op="Extract Document (2)" 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="Filter Tokens (2)" to_port="document"/>
          <connect from_op="Filter Tokens (2)" from_port="document" to_port="output 1"/>
          <portSpacing port="source_example set" spacing="0"/>
          <portSpacing port="sink_performance" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
          <portSpacing port="sink_output 2" spacing="0"/>
        </process>
      </operator>
      <connect from_op="Server Connection" from_port="output" to_op="Loop Data Sets" to_port="example set 1"/>
      <connect from_op="Loop Data Sets" from_port="output 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>

1 个答案:

答案 0 :(得分:0)

我终于找到了解决方案:

   <?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" width="90" x="45" y="75">
            <parameter key="connection" value="Server"/>
            <parameter key="query" value="SELECT `mid`, `body` FROM `message` WHERE `mid` &lt; 10 ORDER BY `mid`"/>
            <enumeration key="parameters"/>
          </operator>
          <operator activated="true" class="text:process_document_from_data" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Data (2)" width="90" x="45" y="165">
            <parameter key="create_word_vector" value="false"/>
            <parameter key="add_meta_information" value="false"/>
            <parameter key="keep_text" value="true"/>
            <list key="specify_weights"/>
            <process expanded="true">
              <operator activated="true" class="web:extract_html_text_content" compatibility="5.3.001" expanded="true" height="60" name="Extract Content" width="90" x="45" y="30">
                <parameter key="minimum_text_block_length" value="3"/>
              </operator>
              <operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases" width="90" x="45" y="120"/>
              <operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (3)" width="90" x="45" y="210"/>
              <operator activated="true" class="text:filter_stopwords_dictionary" compatibility="5.3.002" expanded="true" height="76" name="Filter Stopwords (3)" width="90" x="45" y="300">
                <parameter key="file" value="C:\User\stopwords.txt"/>
              </operator>
              <operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (3)" width="90" x="45" y="390">
                <parameter key="min_chars" value="3"/>
              </operator>
              <operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Delete links" width="90" x="45" y="480">
                <parameter key="mode" value="regular expression"/>
                <parameter key="expression" value="(http[s]?://[a-z_\.A-Z0-9\-]*)"/>
              </operator>
              <connect from_port="document" to_op="Extract Content" to_port="document"/>
              <connect from_op="Extract Content" from_port="document" to_op="Transform Cases" to_port="document"/>
              <connect from_op="Transform Cases" 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="Filter Tokens (3)" to_port="document"/>
              <connect from_op="Filter Tokens (3)" from_port="document" to_op="Delete links" to_port="document"/>
              <connect from_op="Delete links" 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="generate_id" compatibility="5.3.015" expanded="true" height="76" name="Generate ID" width="90" x="179" y="165"/>
          <connect from_op="Server Connection" from_port="output" to_op="Process Documents from Data (2)" to_port="example set"/>
          <connect from_op="Process Documents from Data (2)" from_port="example set" to_op="Generate ID" to_port="example set input"/>
          <connect from_op="Generate ID" from_port="example set output" 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>