Revert Tokenized words back to sentences

ChloronicChloronic Member Posts: 3 Newbie
Hello, I would like to ask. How do I change my tokenized words attribute back into my own text attribute in Excel file? I was doing tokenized words for correcting many mistakes in my text by using Stem (Dictionary) and many other operators within Process Documents from Data. The thing is that I can't find any operator that can export my fixed tokenized words to replace all faulty sentences in my excel file.
Is there a way to export it back into excel? but in this case is with my sentences, not tokenized one.

Here's my XML file:
<?xml version="1.0" encoding="UTF-8"?><process version="9.10.011">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.10.011" 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="read_excel" compatibility="9.10.011" expanded="true" height="68" name="Read Excel" width="90" x="112" y="34">
        <parameter key="excel_file" value="C:\Users\wille\Documents\Dataset Pemilu 2024 (New)\2. Preprocessing\Pemilu 2024 Final Res 2.xlsx"/>
        <parameter key="sheet_selection" value="sheet number"/>
        <parameter key="sheet_number" value="1"/>
        <parameter key="imported_cell_range" value="D1:D10485776"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="first_row_as_names" value="true"/>
        <list key="annotations"/>
        <parameter key="date_format" value=""/>
        <parameter key="time_zone" value="SYSTEM"/>
        <parameter key="locale" value="English (United States)"/>
        <parameter key="read_all_values_as_polynominal" value="false"/>
        <list key="data_set_meta_data_information">
          <parameter key="0" value="Text.true.polynominal.attribute"/>
        </list>
        <parameter key="read_not_matching_values_as_missings" value="false"/>
      </operator>
      <operator activated="true" class="nominal_to_text" compatibility="9.10.011" expanded="true" height="82" name="Nominal to Text" width="90" x="246" y="34">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="Text"/>
        <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="9.4.000" 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="TF-IDF"/>
        <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="9.4.000" expanded="true" height="68" name="Tokenize" width="90" x="45" 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="9.4.000" expanded="true" height="68" name="Transform Cases" width="90" x="179" y="34">
            <parameter key="transform_to" value="lower case"/>
          </operator>
          <operator activated="true" class="text:filter_stopwords_dictionary" compatibility="9.4.000" expanded="true" height="82" name="Filter Stopwords (Dictionary)" width="90" x="313" y="34">
            <parameter key="file" value="C:/Users/wille/Documents/Dataset Pemilu 2024 (New)/Misc/Cleaning/stopwordbahasa.csv"/>
            <parameter key="case_sensitive" value="false"/>
            <parameter key="encoding" value="SYSTEM"/>
          </operator>
          <operator activated="true" class="text:filter_by_length" compatibility="9.4.000" expanded="true" height="68" name="Filter Tokens (by Length)" width="90" x="447" y="34">
            <parameter key="min_chars" value="3"/>
            <parameter key="max_chars" value="15"/>
          </operator>
          <operator activated="true" class="text:stem_dictionary" compatibility="9.4.000" expanded="true" height="82" name="Stem (Dictionary)" width="90" x="581" y="34">
            <parameter key="file" value="C:/Users/wille/Documents/Dataset Pemilu 2024 (New)/2. Preprocessing/stemming.txt"/>
          </operator>
          <operator activated="true" class="text:tokenize" compatibility="9.4.000" expanded="true" height="68" name="Tokenize (2)" width="90" x="715" 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>
          <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 (Dictionary)" to_port="document"/>
          <connect from_op="Filter Stopwords (Dictionary)" from_port="document" to_op="Filter Tokens (by Length)" to_port="document"/>
          <connect from_op="Filter Tokens (by Length)" from_port="document" to_op="Stem (Dictionary)" to_port="document"/>
          <connect from_op="Stem (Dictionary)" from_port="document" to_op="Tokenize (2)" to_port="document"/>
          <connect from_op="Tokenize (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>
      <connect from_port="input 1" to_op="Read Excel" to_port="file"/>
      <connect from_op="Read Excel" 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_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="source_input 2" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>

I also attached my dataset "Pemilu 2024..." and my stemming file .txt.

Answers

  • ruhailaruhaila Member Posts: 48 Guru
    Hi, I tried running it but there is a missing file named "stopwordbahasa.csv".
  • ChloronicChloronic Member Posts: 3 Newbie
    Sorry, for that, I already found the answer. Thanks for trying to help me out.
Sign In or Register to comment.