src/Gargantext/Ext/IMT.hs

   1 {-|
   2 Module      : Gargantext.API
   3 Description : Server API
   4 Copyright   : (c) CNRS, 2017-Present
   5 License     : AGPL + CECILL v3
   6 Maintainer  : team@gargantext.org
   7 Stability   : experimental
   8 Portability : POSIX
   9 -}
  10
  11 {-# LANGUAGE NoImplicitPrelude    #-}
  12 {-# LANGUAGE OverloadedStrings    #-}
  13
  14 module Gargantext.Ext.IMT where
  15
  16 import Gargantext.Prelude
  17 import Data.Text (Text, splitOn)
  18 import Data.Map (Map)
  19
  20 import qualified Data.Set    as S
  21 import qualified Data.List   as DL
  22 import qualified Data.Vector as DV
  23 import qualified Data.Map    as M
  24
  25 import Gargantext.Text.Metrics.Freq as F
  26 import Gargantext.Text.Parsers.CSV as CSV
  27
  28 data School = School { school_shortName :: Text
  29                      , school_longName  :: Text
  30                      , school_id        :: Text
  31 } deriving (Show, Read, Eq)
  32
  33 schools :: [School]
  34 schools = [ School
  35             ("Mines Albi-Carmaux")
  36             ("Mines Albi-Carmaux - École nationale supérieure des Mines d'Albi‐Carmaux")
  37             ("469216")
  38           , School
  39             ("Mines Alès")
  40             ("EMA - École des Mines d'Alès")
  41             ("6279")
  42           , School
  43             ("Mines Douai")
  44             ("Mines Douai EMD - École des Mines de Douai")
  45             ("224096")
  46           , School
  47             ("Mines Lille")
  48             ("Mines Lille - École des Mines de Lille")
  49             ("144103")
  50           , School
  51             ("IMT Lille Douai")
  52             ("IMT Lille Douai")
  53             ("497330")
  54           , School
  55             ("Mines Nantes")
  56             ("Mines Nantes - Mines Nantes")
  57             ("84538")
  58           , School
  59             ("Télécom Bretagne")
  60             ("Télécom Bretagne")
  61             ("301262")
  62           , School
  63             ("IMT Atlantique")
  64             ("IMT Atlantique - IMT Atlantique Bretagne-Pays de la Loire")
  65             ("481355")
  66           , School
  67             ("Mines Saint-Étienne")
  68             ("Mines Saint-Étienne MSE - École des Mines de Saint-Étienne")
  69             ("29212")
  70           , School
  71             ("Télécom École de Management")
  72             ("TEM - Télécom Ecole de Management")
  73             ("301442")
  74           , School
  75             ("IMT Business School")
  76             ("IMT Business School")
  77             ("542824")
  78           , School
  79             ("Télécom ParisTech")
  80             ("Télécom ParisTech")
  81             ("300362")
  82           , School
  83             ("Télécom SudParis")
  84             ("TSP - Télécom SudParis")
  85             ("352124")
  86           , School
  87             ("ARMINES")
  88             ("ARMINES")
  89             ("300362")
  90           , School
  91             ("Eurecom")
  92             ("Eurecom")
  93             ("421532")
  94           , School
  95             ("Mines ParisTech")
  96             ("MINES ParisTech - École nationale supérieure des mines de Paris")
  97             ("301492")
  98             ]
  99
 100 mapIdSchool :: Map Text Text
 101 mapIdSchool = M.fromList $ Gargantext.Prelude.map (\(School n _ i) -> (i,n)) schools
 102
 103 hal_data :: IO (DV.Vector CsvHal)
 104 hal_data = snd <$> CSV.readCsvHal "doc/corpus_imt/Gargantext_Corpus.csv"
 105
 106 names :: S.Set Text
 107 names = S.fromList $ Gargantext.Prelude.map (\s -> school_id s) schools
 108
 109 toSchoolName :: Text -> Text
 110 toSchoolName t = case M.lookup t mapIdSchool of
 111   Nothing -> t
 112   Just t' -> t'
 113
 114 publisBySchool :: DV.Vector CsvHal -> [(Maybe Text, Int)]
 115 publisBySchool hal_data' = Gargantext.Prelude.map (\(i,n) -> (M.lookup i mapIdSchool, n))
 116                         $ DL.filter (\i -> S.member  (fst i) names)
 117                         $ DL.reverse
 118                         $ DL.sortOn snd
 119                         $ M.toList
 120                         $ F.freq
 121                         $ DL.concat
 122                         $ DV.toList
 123                         $ DV.map (\n -> splitOn ( ", ") (csvHal_instStructId_i n) )
 124                         $ DV.filter (\n -> csvHal_publication_year n == 2017) hal_data'
 125
 126