|
1 |
|
2 import CW7b._ |
|
3 |
|
4 // first test |
|
5 |
|
6 def urban_groupById(ratings: List[(String, String)], |
|
7 m: Map[String, List[String]]) : Map[String, List[String]] = ratings match { |
|
8 case Nil => m |
|
9 case (id, mov) :: rest => { |
|
10 val old_ratings = m.getOrElse (id, Nil) |
|
11 val new_ratings = m + (id -> (mov :: old_ratings)) |
|
12 urban_groupById(rest, new_ratings) |
|
13 } |
|
14 } |
|
15 //def urban_groupById(ratings: List[(String, String)]) = |
|
16 // ratings.groupBy(_._1).view.mapValues(_.map(_._2)).toMap |
|
17 |
|
18 def urban_get_csv_file(name: String) : List[String] = { |
|
19 import io.Source |
|
20 import scala.util._ |
|
21 val csv = Source.fromFile(name)("ISO-8859-1") |
|
22 csv.mkString.split("\n").toList.drop(1) |
|
23 } |
|
24 |
|
25 def urban_process_ratings(lines: List[String]) : List[(String, String)] = { |
|
26 for (cols <- lines.map(_.split(",").toList); |
|
27 if (cols(2).toInt >= 4)) yield (cols(0), cols(1)) |
|
28 } |
|
29 |
|
30 def urban_process_movies(lines: List[String]) : List[(String, String)] = { |
|
31 for (cols <- lines.map(_.split(",").toList)) yield (cols(0), cols(1)) |
|
32 } |
|
33 |
|
34 |
|
35 val urban_good_ratings = urban_process_ratings(urban_get_csv_file("ratings.csv")) |
|
36 val urban_movie_names = urban_process_movies(urban_get_csv_file("movies.csv")) |
|
37 |
|
38 val urban_movie_names_map = urban_movie_names.toMap |
|
39 val urban_ratings_map = urban_groupById(urban_good_ratings, Map()) |
|
40 //val urban_ratings_map = groupById(urban_good_ratings, Map()) |
|
41 |
|
42 val urban_ratings_map2 = for ((k, v) <- urban_ratings_map) yield (k, v.take(2)) |
|
43 |
|
44 assert(most_recommended(urban_ratings_map2, urban_movie_names_map).take(3) == |
|
45 List(("M*A*S*H (a.k.a. MASH) (1970)",15), |
|
46 ("Star Trek: First Contact (1996)",10), |
|
47 ("Inception (2010)",9))) |
|
48 |