diff -r ca9c1cf929fa -r e5453add7df6 testing2/danube.scala --- a/testing2/danube.scala Tue Nov 26 01:22:36 2019 +0000 +++ b/testing2/danube.scala Tue Dec 03 01:22:16 2019 +0000 @@ -2,114 +2,118 @@ // at Danube.co.uk //=========================================== +object CW7b { + import io.Source import scala.util._ -object CW7b { // for purposes of generating a jar - // (1) Implement the function get_csv_url which takes an url-string // as argument and requests the corresponding file. The two urls // of interest are ratings_url and movies_url, which correspond // to CSV-files. -// The function should ReTurn the CSV file appropriately broken +// +// The function should ReTurn the CSV-file appropriately broken // up into lines, and the first line should be dropped (that is without -// the header of the CSV file). The result is a list of strings (lines +// the header of the CSV-file). The result is a list of strings (lines // in the file). def get_csv_url(url: String) : List[String] = { - val csv = Source.fromURL(url)("ISO-8859-1") - csv.mkString.split("\n").toList.drop(1) + Try(Source.fromURL(url)("UTF-8").mkString.split("\n").toList.tail).getOrElse(List()) } + val ratings_url = """https://nms.kcl.ac.uk/christian.urban/ratings.csv""" val movies_url = """https://nms.kcl.ac.uk/christian.urban/movies.csv""" -// test cases - -//val ratings = get_csv_url(ratings_url) -//val movies = get_csv_url(movies_url) +// testcases +//----------- +// val ratings = get_csv_url(ratings_url) +// val movies = get_csv_url(movies_url) //ratings.length // 87313 //movies.length // 9742 -// (2) Implement two functions that process the CSV files. The ratings + + +// (2) Implement two functions that process the CSV-files from (1). The ratings // function filters out all ratings below 4 and ReTurns a list of // (userID, movieID) pairs. The movies function just ReTurns a list -// of (movieId, title) pairs. +// of (movieID, title) pairs. def process_ratings(lines: List[String]) : List[(String, String)] = { - for (cols <- lines.map(_.split(",").toList); - if (cols(2).toFloat >= 4)) yield (cols(0), cols(1)) + val filteredLines = lines.filter(line => line.split(",")(2).toInt >= 4) + filteredLines.map(line => (line.split(",")(0), line.split(",")(1))) } def process_movies(lines: List[String]) : List[(String, String)] = { - for (cols <- lines.map(_.split(",").toList)) yield (cols(0), cols(1)) + lines.map(line => (line.split(",")(0), line.split(",")(1))) } -// test cases -//val good_ratings = process_ratings(ratings) -//val movie_names = process_movies(movies) +// testcases +//----------- +// val good_ratings = process_ratings(ratings) +// val movie_names = process_movies(movies) //good_ratings.length //48580 //movie_names.length // 9742 -//============================================== -// Do not change anything below, unless you want -// to submit the file for the advanced part 3! -//============================================== - - -// (3) Implement a grouping function that calulates a map -// containing the userIds and all the corresponding recommendations -// (list of movieIds). This should be implemented in a tail -// recursive fashion, using a map m as accumulator. This map -// is set to Map() at the beginning of the claculation. - -def groupById(ratings: List[(String, String)], - m: Map[String, List[String]]) : Map[String, List[String]] = ratings match { - case Nil => m - case (id, mov) :: rest => { - val old_ratings = m.getOrElse (id, Nil) - val new_ratings = m + (id -> (mov :: old_ratings)) - groupById(rest, new_ratings) - } -} - -// -//val ls = List(("1", "a"), ("2", "a"), ("1", "c"), ("2", "a"), ("1", "c")) -// -//val m = groupById(ls, Map()) -// -//m.getOrElse("1", Nil).count(_ == "c") // => 2 -//m.getOrElse("1", Nil).count(_ == "a") // => 1 - -// test cases -//val ratings_map = groupById(good_ratings, Map()) -//groupById(good_ratings, Map()).get("214") -//groupById(good_ratings, Map()).toList.minBy(_._2.length) -//val movies_map = movie_names.toMap - -//ratings_map.get("414").get.map(movies_map.get(_)) // most prolific recommender with 1227 positive ratings -//ratings_map.get("474").get.map(movies_map.get(_)) // second-most prolific recommender with 787 positive ratings -//ratings_map.get("214").get.map(movies_map.get(_)) // least prolific recommender with only 1 positive rating -//(4) Implement a function that takes a ratings map and a movie_name as argument. -// The function calculates all suggestions containing -// the movie mov in its recommendations. It ReTurns a list of all these -// recommendations (each of them is a list and needs to have mov deleted, -// otherwise it might happen we recommend the same movie). +// (3) Implement a grouping function that calculates a Map +// containing the userIDs and all the corresponding recommendations +// (list of movieIDs). This should be implemented in a tail +// recursive fashion, using a Map m as accumulator. This Map m +// is set to Map() at the beginning of the calculation. -def favourites(m: Map[String, List[String]], mov: String) : List[List[String]] = - (for (id <- m.keys.toList; - if m(id).contains(mov)) yield m(id).filter(_ != mov)) +def groupById(ratings: List[(String, String)], + m: Map[String, List[String]]) : Map[String, List[String]] = { + if (ratings.length == 0) m + else { + val firstUser = ratings(0)._1 + val userRatings = ratings.filter(r => r._1 == firstUser) + val movieIds = userRatings.map(r => r._2) + val newMap = m + (firstUser -> movieIds) + groupById(ratings.filter(r => r._1 != firstUser), newMap) + } +} + + +// testcases +//----------- +//val ratings_map = groupById(good_ratings, Map()) +//val movies_map = movie_names.toMap + +//ratings_map.get("414").get.map(movies_map.get(_)) +// => most prolific recommender with 1227 positive ratings + +//ratings_map.get("474").get.map(movies_map.get(_)) +// => second-most prolific recommender with 787 positive ratings + +//ratings_map.get("214").get.map(movies_map.get(_)) +// => least prolific recommender with only 1 positive rating -// test cases +// (4) Implement a function that takes a ratings map and a movie_name as argument. +// The function calculates all suggestions containing +// the movie in its recommendations. It ReTurns a list of all these +// recommendations (each of them is a list and needs to have the movie deleted, +// otherwise it might happen we recommend the same movie). + + +def favourites(m: Map[String, List[String]], mov: String) : List[List[String]] = { + val movieLists = m.map(r => r._2).toList.filter(_.contains(mov)) + for (movieList <- movieLists) yield { + movieList.filter(_!=mov) + } +} + + +// testcases +//----------- // movie ID "912" -> Casablanca (1942) // "858" -> Godfather // "260" -> Star Wars: Episode IV - A New Hope (1977) @@ -121,45 +125,53 @@ // 52 a good rating to movies 260, 318, 593. -// (5) Implement a suggestions function which takes a rating -// map and a movie_name as arguments. It calculates all the recommended -// movies sorted according to the most frequently suggested movie(s) first. -// needed in Scala 2.13. - -def mapValues[S, T, R](m: Map[S, T], f: T => R) = - m.map { case (x, y) => (x, f(y)) } +// (5) Implement a suggestions function which takes a rating +// map and a movie_name as arguments. It calculates all the recommended +// movies sorted according to the most frequently suggested movie(s) first. + def suggestions(recs: Map[String, List[String]], - mov_name: String) : List[String] = { - val favs = favourites(recs, mov_name).flatten - val favs_counted = mapValues(favs.groupBy(identity), (v:List[String]) => v.size).toList - val favs_sorted = favs_counted.sortBy(_._2).reverse - favs_sorted.map(_._1) + mov_name: String) : List[String] = { + val favs = favourites(recs, mov_name).flatten + favs.map(x => (x, favs.count(_==x))) + .sortBy(_._1) + .reverse + .sortBy(_._2) + .reverse + .distinct + .map(_._1) } -// check -// groupMap is equivalent to groupBy(key).mapValues(_.map(f)) -// test cases +// testcases +//----------- //suggestions(ratings_map, "912") //suggestions(ratings_map, "912").length // => 4110 suggestions with List(858, 260, 318, 593, ...) // being the most frequently suggested movies -// (6) Implement recommendations functions which generates at most -// *two* of the most frequently suggested movies. It Returns the -// actual movie names, not the movieIDs. + + +// (6) Implement a recommendations function which generates at most +// *two* of the most frequently suggested movies. It ReTurns the +// actual movie names, not the movieIDs. + def recommendations(recs: Map[String, List[String]], - movs: Map[String, String], - mov_name: String) : List[String] = - suggestions(recs, mov_name).take(2).map(movs.get(_).get) + movs: Map[String, String], + mov_name: String) : List[String] = { + val sug = suggestions(recs, mov_name) + val toptwo = sug.take(2) + if (toptwo.length == 0) Nil + else toptwo.map(movs(_)) +} + // testcases - +//----------- // recommendations(ratings_map, movies_map, "912") // => List(Godfather, Star Wars: Episode IV - A NewHope (1977)) @@ -177,11 +189,11 @@ // => List(Shawshank Redemption, Forrest Gump (1994)) // recommendations(ratings_map, movies_map, "4") -// => Nil (there are three ratings fro this movie in ratings.csv but they are not positive) +// => Nil (there are three ratings for this movie in ratings.csv but they are not positive) -// If you want to calculate the recomendations for all movies. -// Will take a few seconds calculation time. +// If you want to calculate the recommendations for all movies, +// then use this code (it will take a few seconds calculation time). //val all = for (name <- movie_names.map(_._1)) yield { // recommendations(ratings_map, movies_map, name) @@ -193,4 +205,32 @@ //List(1,2).take(2) //List(1,2,3).take(2) + + } + +// val ratings_url = """https://nms.kcl.ac.uk/christian.urban/ratings.csv""" +// val movies_url = """https://nms.kcl.ac.uk/christian.urban/movies.csv""" + +// val ratings = CW7b.get_csv_url(ratings_url) +// val movies = CW7b.get_csv_url(movies_url) + +// println(movies.length) +// val good_ratings = CW7b.process_ratings(ratings) +// val movie_names = CW7b.process_movies(movies) + +// val ratings_map = CW7b.groupById(good_ratings, Map()) +// val movies_map = movie_names.toMap + + + +//println(CW7b.recommendations(ratings_map, movies_map, "912")) +/* +val ratings_url = """https://nms.kcl.ac.uk/christian.urban/ratings.csv""" + +val ratings = CW7b.get_csv_url(ratings_url) + +val good_ratings = CW7b.process_ratings(ratings) +val ratings_map = CW7b.groupById(good_ratings, Map()) + +println(CW7b.suggestions(ratings_map, "912").length)*/