gistfile1.ml

#light

let critics = 
  Map.of_list [("Lisa Rose", 
                Map.of_list [("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", 
                Map.of_list [("Lady in the Water", 3.0);("Snakes on a Plane", 3.5);
                             ("Just My Luck", 1.5);("Superman Returns", 5.0);
                             ("You, Me and Dupree", 3.5);("The Night Listener", 3.0)];);
               ("Michael Phillips", 
                Map.of_list [("Lady in the Water", 2.5);("Snakes on a Plane", 3.0);
                             ("Superman Returns", 3.5);("The Night Listener", 4.0)];);
               ("Claudia Puig", 
                Map.of_list [("Snakes on a Plane", 3.5);("Just My Luck", 2.0);
                             ("Superman Returns", 4.0);("You, Me and Dupree", 2.5);
                             ("The Night Listener", 4.0)];);
               ("Mick LaSalle", 
                Map.of_list [("Lady in the Water", 3.0);("Snakes on a Plane", 4.0);
                             ("Just My Luck", 2.0);("Superman Returns", 3.0);
                             ("You, Me and Dupree", 2.0);("The Night Listener", 3.0)];);
               ("Jack Matthews", 
                Map.of_list [("Lady in the Water", 3.0);("Snakes on a Plane", 4.0);
                             ("Superman Returns", 5.0);("You, Me and Dupree", 3.5);
                             ("The Night Listener", 3.0)];);        
               ("Matt", 
                Map.of_list [("Snakes on a Plane", 4.5);("Superman Returns", 4.0);
                             ("You, Me and Dupree", 1.0)];);]                                                                                                                                   

// Returns the Pearson correlation coefficient for p1 and p2
let sim_pearson (prefs:Map<string, Map<string, float>>) (p1:string) (p2:string) : float =
  // Get the list of mutually rated items
  let si = Map.fold_right (fun k _ acc -> 
                             if prefs.[p2].ContainsKey k then
                               Set.add k acc
                             else acc) prefs.[p1] Set.empty
  
  // if they are no ratings in common, return 0
  let n = float si.Count
  if n = 0. then 0.
  else
    // Sums of all the preferences
    // Set.fold_left (fun acc key -> acc + prefs.[p1].[key]) 0. si
    let sum1 =  List.sum [for it in si -> prefs.[p1].[it]]
    let sum2 =  List.sum [for it in si -> prefs.[p2].[it]]    
    
    // Sums of the squares
    // Set.fold_left (fun acc key -> acc + (pown prefs.[p1].[key] 2)) 0. si
    let sum1Sq = List.sum [for it in si -> pown prefs.[p1].[it] 2]
    let sum2Sq = List.sum [for it in si -> pown prefs.[p2].[it] 2]  
    
    // Sum of the products
    // Set.fold_left (fun acc key -> acc + (prefs.[p1].[key] * prefs.[p2].[key])) 0. si
    let pSum = List.sum [for it in si -> prefs.[p1].[it] * prefs.[p2].[it]]
    
    // Calculate r (Pearson score)
    let num = pSum - (sum1 * sum2 / n)
    let den = sqrt ((sum1Sq - (pown sum1 2) / n) * (sum2Sq - (pown sum2 2) / n ))
    if den = 0. then 0.
    else
      num / den

// Returns the best matches for person from the prefs dictionary
let topMatches 
  (prefs:Map<string, Map<string, float>>) 
  (person:string) (n:int) 
  (similarity:Map<string, Map<string, float>> -> string -> string -> float) 
  : seq<(float * string)> =
  
  prefs 
    |> Seq.choose (fun kvp -> if kvp.Key <> person then 
                                Some(similarity prefs person kvp.Key, kvp.Key) 
                              else None) 
    |> List.of_seq
    |> List.sort_by fst
    |> List.rev
    |> Seq.take n