TextRank

require 'text_rank'

text = <<-END
  In a castle of Westphalia, belonging to the Baron of Thunder-ten-Tronckh, lived
  a youth, whom nature had endowed with the most gentle manners. His countenance
  was a true picture of his soul. He combined a true judgment with simplicity of
  spirit, which was the reason, I apprehend, of his being called Candide. The old
  servants of the family suspected him to have been the son of the Baron's
  sister, by a good, honest gentleman of the neighborhood, whom that young lady
  would never marry because he had been able to prove only seventy-one
  quarterings, the rest of his genealogical tree having been lost through the
  injuries of time.
END

# Default, basic keyword extraction.  Try this first:
keywords = TextRank.extract_keywords(text)

# Keyword extraction with all of the bells and whistles:
keywords = TextRank.extract_keywords_advanced(text)

# Fully customized extraction:
extractor = TextRank::KeywordExtractor.new(
  strategy:   :sparse,  # Specify PageRank strategy (dense or sparse)
  damping:    0.85,     # The probability of following the graph vs. randomly choosing a new node
  tolerance:  0.0001,   # The desired accuracy of the results
  char_filters: [...],  # A list of filters to be applied prior to tokenization
  tokenizers: [...],    # A list of tokenizers to perform tokenization
  token_filters: [...], # A list of filters to be applied to each token after tokenization
  graph_strategy: ...,  # A class or strategy instance for producing a graph from tokens
  rank_filters: [...],  # A list of filters to be applied to the keyword ranks after keyword extraction
)

# Add another filter to the end of the char_filter chain
extractor.add_char_filter(:AsciiFolding)

# Add a part of speech filter to the token_filter chain BEFORE the Stopwords filter
pos_filter = TextRank::TokenFilter::PartOfSpeech.new(parts_to_keep: %w[nn])
extractor.add_token_filter(pos_filter, before: :Stopwords)

# Perform the extraction with at most 100 iterations
extractor.extract(text, max_iterations: 100)

require 'page_rank'

PageRank.calculate(strategy: :sparse, damping: 0.8, tolerance: 0.00001) do
  add('node_a', 'node_b', weight: 3.2)
  add('node_b', 'node_d', weight: 2.1)
  add('node_b', 'node_e', weight: 4.7)
  add('node_e', 'node_a', weight: 1.3)
end