pipeline_name: topic_modeling
doc: Example topic-modeling end-to-end workflow.
steps:
  - module_type: create.table.from.file_bundle
    step_id: create_text_corpus
  - module_type: table.pick.column
    step_id: extract_texts_column
    input_links:
      table: create_text_corpus.table
  - module_type: tokenize.texts_array
    step_id: tokenize_content
    input_links:
      texts_array: extract_texts_column.array
  - module_type: create.stopwords_list
    step_id: create_stopwords_list
  - module_type: preprocess.tokens_array
    step_id: preprocess_corpus
    input_links:
      tokens_array: tokenize_content.tokens_array
      remove_stopwords: create_stopwords_list.stopwords_list
  - module_type: generate.LDA.for.tokens_array
    step_id: generate_lda
    input_links:
      tokens_array: preprocess_corpus.tokens_array