pipeline_name: "tm_preprocessing_step"
doc: |
  Pre-processing steps before applying LDA.
steps:
- module_type: table.cut_column
  step_id: get_column
- module_type: tokenize.texts_array
  step_id: tokenization
  input_links: 
    texts_array: get_column.array
- module_type: create.stopwords_list
  step_id: stopwords
- module_type: preprocess.tokens_array
  step_id: preprocessing
  input_links:
    tokens_array: tokenization.tokens_array
    remove_stopwords: stopwords.stopwords_list
- module_type: kiara_plugin.playground.playground.mariella.add_column
  step_id: reassemble_column
  input_links:
    array_input: preprocessing.tokens_array