Text Mining - Unnammed error in Apply Model (Documents) Operator

Titzaaa
Titzaaa New Altair Community Member
edited November 5 in Community Q&A
Dear community,
this is the first time I try to build a text mining process and I cannot find my mistake: When trying to run the process, I get a error message saying "unnamed error. no message". Can you help?
Here is my code:
<?xml version="1.0" encoding="UTF-8"?><process version="9.3.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.3.000" 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"/>
    <process expanded="true">
      <operator activated="true" class="retrieve" compatibility="9.3.000" expanded="true" height="68" name="Retrieve" width="90" x="45" y="34">
        <parameter key="repository_entry" value="//Masterarbeit/Data/Finanzen.net"/>
      </operator>
      <operator activated="true" class="nominal_to_text" compatibility="9.3.000" expanded="true" height="82" name="Nominal to Text" width="90" x="179" y="34">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="Titel"/>
        <parameter key="attributes" value=""/>
        <parameter key="use_except_expression" value="false"/>
        <parameter key="value_type" value="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
      </operator>
      <operator activated="true" class="text:process_document_from_data" compatibility="8.2.000" expanded="true" height="82" name="Process Documents from Data" width="90" x="380" y="34">
        <parameter key="create_word_vector" value="true"/>
        <parameter key="vector_creation" value="Binary Term Occurrences"/>
        <parameter key="add_meta_information" value="true"/>
        <parameter key="keep_text" value="false"/>
        <parameter key="prune_method" value="none"/>
        <parameter key="prune_below_percent" value="3.0"/>
        <parameter key="prune_above_percent" value="30.0"/>
        <parameter key="prune_below_rank" value="0.05"/>
        <parameter key="prune_above_rank" value="0.95"/>
        <parameter key="datamanagement" value="double_sparse_array"/>
        <parameter key="data_management" value="auto"/>
        <parameter key="select_attributes_and_weights" value="false"/>
        <list key="specify_weights"/>
        <process expanded="true">
          <operator activated="true" class="text:tokenize" compatibility="8.2.000" expanded="true" height="68" name="Tokenize" width="90" x="179" y="34">
            <parameter key="mode" value="non letters"/>
            <parameter key="characters" value=".:"/>
            <parameter key="language" value="English"/>
            <parameter key="max_token_length" value="3"/>
          </operator>
          <operator activated="true" class="text:transform_cases" compatibility="8.2.000" expanded="true" height="68" name="Transform Cases" width="90" x="313" y="34">
            <parameter key="transform_to" value="lower case"/>
          </operator>
          <operator activated="true" class="text:filter_stopwords_german" compatibility="8.2.000" expanded="true" height="68" name="Filter Stopwords (German)" width="90" x="447" y="34">
            <parameter key="stop_word_list" value="Standard"/>
          </operator>
          <operator activated="true" class="text:filter_by_length" compatibility="8.2.000" expanded="true" height="68" name="Filter Tokens (by Length)" width="90" x="648" y="34">
            <parameter key="min_chars" value="3"/>
            <parameter key="max_chars" value="10000"/>
          </operator>
          <operator activated="false" class="text:generate_n_grams_terms" compatibility="8.2.000" expanded="true" height="68" name="Generate n-Grams (Terms)" width="90" x="246" y="238">
            <parameter key="max_length" value="2"/>
          </operator>
          <connect from_port="document" to_op="Tokenize" to_port="document"/>
          <connect from_op="Tokenize" from_port="document" to_op="Transform Cases" to_port="document"/>
          <connect from_op="Transform Cases" from_port="document" to_op="Filter Stopwords (German)" to_port="document"/>
          <connect from_op="Filter Stopwords (German)" from_port="document" to_op="Filter Tokens (by Length)" to_port="document"/>
          <connect from_op="Filter Tokens (by Length)" 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="retrieve" compatibility="9.3.000" expanded="true" height="68" name="Retrieve GRESD" width="90" x="45" y="238">
        <parameter key="repository_entry" value="../Data/GRESD"/>
      </operator>
      <operator activated="true" class="retrieve" compatibility="9.3.000" expanded="true" height="68" name="Retrieve Negationsliste" width="90" x="45" y="391">
        <parameter key="repository_entry" value="../Data/Negationsliste"/>
      </operator>
      <operator activated="true" class="operator_toolbox:dictionary_sentiment_learner" compatibility="2.0.001" expanded="true" height="82" name="Dictionary-Based Sentiment (Documents)" width="90" x="246" y="289">
        <parameter key="value_attribute" value="Klassifizierung"/>
        <parameter key="key_attribute" value="Wort"/>
        <parameter key="negation_attribute" value="Negationen"/>
        <parameter key="negation_window_size" value="1"/>
        <parameter key="use_symmetric_negation_window" value="false"/>
      </operator>
      <operator activated="true" class="text:data_to_documents" compatibility="8.2.000" expanded="true" height="68" name="Data to Documents" width="90" x="514" y="85">
        <parameter key="select_attributes_and_weights" value="false"/>
        <list key="specify_weights"/>
      </operator>
      <operator activated="true" class="operator_toolbox:apply_model_documents" compatibility="2.0.001" expanded="true" height="103" name="Apply Model (Documents)" width="90" x="447" y="289">
        <list key="application_parameters"/>
      </operator>
      <connect from_op="Retrieve" from_port="output" to_op="Nominal to Text" to_port="example set input"/>
      <connect from_op="Nominal to Text" from_port="example set output" to_op="Process Documents from Data" to_port="example set"/>
      <connect from_op="Process Documents from Data" from_port="example set" to_op="Data to Documents" to_port="example set"/>
      <connect from_op="Retrieve GRESD" from_port="output" to_op="Dictionary-Based Sentiment (Documents)" to_port="exa"/>
      <connect from_op="Retrieve Negationsliste" from_port="output" to_op="Dictionary-Based Sentiment (Documents)" to_port="neg"/>
      <connect from_op="Dictionary-Based Sentiment (Documents)" from_port="mod" to_op="Apply Model (Documents)" to_port="mod"/>
      <connect from_op="Data to Documents" from_port="documents" to_op="Apply Model (Documents)" to_port="doc"/>
      <connect from_op="Apply Model (Documents)" from_port="exa" 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 a lot on advance!

Tagged:

Best Answer

  • MartinLiebig
    MartinLiebig
    Altair Employee
    Answer ✓
    Hi,

    good one. not sure what i mixed up there. Any chance you can share the data (privatly)? Feel free to connect with me via mschmitz at rapidminer dot com. Feel free to use german :)

    Cheers,
    Martin

Answers

Categories