gistfile1.hs

import Data.Map((!), intersection, fromList, keys, Map(..))
import Data.List(sort)

type Preferences = Map String (Map String Double)
type Similarity = Preferences -> String -> String -> Double

critics :: Preferences
critics = fromList [
  ("Lisa Rose", fromList
    [("Lady in the Water" , 2.5),
     ("Snakes on a Plane" , 3.5),
     ("Just My Luck"      , 3.0), 
     ("Superman Returns"  , 3.5), 
     ("You, Me and Dupree", 2.5), 
     ("The Night Listener", 3.0)
     ]),                      

  ("Gene Seymour", fromList
    [("Lady in the Water" , 3.0), 
     ("Snakes on a Plane" , 3.5), 
     ("Just My Luck"      , 1.5),
     ("Superman Returns"  , 5.0), 
     ("The Night Listener", 3.0), 
     ("You, Me and Dupree", 3.5)
     ]),
                   
  ("Michael Phillips", fromList
    [("Lady in the Water" , 2.5), 
     ("Snakes on a Plane" , 3.0),
     ("Superman Returns"  , 3.5),
     ("The Night Listener", 4.0)
     ]), 

  ("Claudia Puig", fromList
    [("Snakes on a Plane" , 3.5),
     ("Just My Luck"      , 3.0),
     ("The Night Listener", 4.5),
     ("Superman Returns"  , 4.0), 
     ("You, Me and Dupree", 2.5)
     ]), 

  ("Mick LaSalle", fromList
    [("Lady in the Water" , 3.0),
     ("Snakes on a Plane" , 4.0), 
     ("Just My Luck"      , 2.0),
     ("Superman Returns"  , 3.0),
     ("The Night Listener", 3.0),
     ("You, Me and Dupree", 2.0)
     ]),

  ("Jack Matthews", fromList
    [("Lady in the Water" , 3.0),
     ("Snakes on a Plane" , 4.0),
     ("The Night Listener", 3.0),
     ("Superman Returns"  , 5.0),
     ("You, Me and Dupree", 3.5)
     ]),

  ("Matt", fromList
    [("Snakes on a Plane" ,4.5),
     ("You, Me and Dupree",1.0),
     ("Superman Returns"  ,4.0)
     ])
 ]
 
sim_distance :: Preferences -> String -> String -> Double
sim_distance prefs p1 p2 =
 	let si = keys $ intersection (prefs ! p1) (prefs ! p2)
 	in case si of
 		[] -> 0
 		otherwise -> 
 		  1 / (1 + sqrt sum_of_squares)
 		    where sum_of_squares = 
 		            sum [((prefs ! p1 ! item) - (prefs ! p2 ! item)) ^ 2 | item <- si]
 		               	       
sim_pearson :: Preferences -> String -> String -> Double
sim_pearson prefs p1 p2 =
  let si = keys $ intersection (prefs ! p1) (prefs ! p2) 
      n  = fromIntegral $ length si
  in case n of
      0 -> 0
      otherwise -> 
        let sum1 = sum [prefs ! p1 ! item | item <- si]
            sum2 = sum [prefs ! p2 ! item | item <- si]
            sum1Sq = sum [prefs ! p1 ! item ^ 2 | item <- si]
            sum2Sq = sum [prefs ! p2 ! item ^ 2 | item <- si]
            pSum = sum [(prefs ! p1 ! item) * (prefs ! p2 ! item) | item <- si]
            num = pSum - (sum1 * sum2 / n)
            den = sqrt ((sum1Sq - sum1 ^ 2 / n) *
                        (sum2Sq - sum2 ^ 2 / n))
        in case den of
          0 -> 0
          otherwise -> num / den
                       
topMatches :: Preferences -> String -> Int -> Similarity -> [(Double, String)]
topMatches prefs person n similarity =
	take n $ 
	  reverse $ 
	    sort [(similarity prefs person other, other) | 
	           other <- keys prefs, 
	           other /= person]