preprocessing:
  lowercase: true
  remove_urls: true
  remove_mentions: true
  remove_emojis: true
  remove_special_chars: true
  remove_stopwords: true
  lemmatize: true
  min_token_length: 2
  language: en
  custom_stopwords:
    - youtube
    - video
    - watch
    - like
    - comment
    - channel
    - stefan
    - peggy
    - masri
    - ferguson
    - cigar
    - hubbard

vectorization:
  method: tfidf  # tfidf | bow | both
  tfidf:
    max_features: 5000
    ngram_range: [1, 2]
    sublinear_tf: true
    min_df: 3
  bow:
    max_features: 5000
    ngram_range: [1, 1]
    min_df: 3