src/Gargantext/Text/Terms.hs

   1 {-|
   2 Module      : Gargantext.Text.Ngrams
   3 Description : Ngrams definition and tools
   4 Copyright   : (c) CNRS, 2017 - present
   5 License     : AGPL + CECILL v3
   6 Maintainer  : team@gargantext.org
   7 Stability   : experimental
   8 Portability : POSIX
   9
  10 An @n-gram@ is a contiguous sequence of n items from a given sample of
  11 text. In Gargantext application the items are words, n is a non negative
  12 integer.
  13
  14 Using Latin numerical prefixes, an n-gram of size 1 is referred to as a
  15 "unigram"; size 2 is a "bigram" (or, less commonly, a "digram"); size
  16 3 is a "trigram". English cardinal numbers are sometimes used, e.g.,
  17 "four-gram", "five-gram", and so on.
  18
  19 Source: https://en.wikipedia.org/wiki/Ngrams
  20
  21 TODO
  22 -- Prelude.concat <$> Prelude.map (filter (\n -> _my_token_pos n == Just NP)) <$> extractNgrams  Gargantext.Core.EN   testText_en
  23
  24 group Ngrams -> Tree
  25 compute occ by node of Tree
  26 group occs according groups
  27
  28 compute cooccurrences
  29 compute graph
  30
  31 -}
  32
  33 {-# LANGUAGE NoImplicitPrelude #-}
  34
  35 module Gargantext.Text.Terms
  36   where
  37
  38 import Gargantext.Core.Types
  39
  40 ------------------------------------------------------------------------
  41 tokenTag2terms :: TokenTag -> Terms
  42 tokenTag2terms (TokenTag w t _ _) =  Terms w t
  43 ------------------------------------------------------------------------
  44