marking2/danube_test3.scala
author Christian Urban <urbanc@in.tum.de>
Wed, 30 Oct 2019 14:21:16 +0000
changeset 289 08b5ddbc7e55
parent 284 9a04eb6a2291
permissions -rw-r--r--
updated
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
284
9a04eb6a2291 updated
Christian Urban <urbanc@in.tum.de>
parents: 259
diff changeset
     1
import CW7b._
9a04eb6a2291 updated
Christian Urban <urbanc@in.tum.de>
parents: 259
diff changeset
     2
259
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
     3
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
     4
// first test 
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
     5
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
     6
val ls1_urban = List(("1", "a"), ("2", "a"), ("1", "c"), ("2", "a"), ("1", "c"))
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
     7
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
     8
val m_urban = groupById(ls1_urban, Map())
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
     9
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    10
assert(m_urban.getOrElse("1", Nil).count(_ == "c") == 2)
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    11
assert(m_urban.getOrElse("1", Nil).count(_ == "a") == 1)
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    12
assert(m_urban.getOrElse("2", Nil) == List("a", "a"))
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    13
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    14
// second test
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    15
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    16
def urban_gb(ratings: List[(String, String)]) = 
284
9a04eb6a2291 updated
Christian Urban <urbanc@in.tum.de>
parents: 259
diff changeset
    17
  ratings.groupBy(_._1).view.mapValues(_.map(_._2).toSet).toMap 
259
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    18
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    19
def urban_gb2(ratings: List[(String, String)]) = 
284
9a04eb6a2291 updated
Christian Urban <urbanc@in.tum.de>
parents: 259
diff changeset
    20
  ratings.groupBy(_._1).view.mapValues(_.map(_._2)).toMap 
259
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    21
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    22
def urban_ck(ratings: List[(String, String)]) =
284
9a04eb6a2291 updated
Christian Urban <urbanc@in.tum.de>
parents: 259
diff changeset
    23
  urban_gb(ratings) == groupById(ratings, Map()).view.mapValues(_.toSet).toMap
259
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    24
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    25
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    26
val ls2_urban = List(("1", "a"), ("1", "b"), ("2", "x"), ("3", "a"), ("2", "y"), ("3", "c"))
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    27
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    28
assert(urban_ck(ls2_urban))
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    29
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    30
// thrird test
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    31
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    32
val ls3_urban = (1 to 1000).map(_.toString).toList
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    33
val ls4_urban = ls3_urban zip ls3_urban.tail
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    34
val ls5_urban = ls4_urban ::: ls4_urban.reverse
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    35
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    36
assert(urban_ck(ls5_urban))
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    37
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    38
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    39
/*
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    40
import io.Source
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    41
import scala.util._
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    42
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    43
def urban_get_csv_file(name: String) : List[String] = {
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    44
  val csv = Source.fromFile(name)
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    45
  csv.mkString.split("\n").toList.drop(1)
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    46
}
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    47
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    48
def urban_process_ratings(lines: List[String]) : List[(String, String)] = {
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    49
  for (cols <- lines.map(_.split(",").toList); 
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    50
       if (cols(2).toFloat >= 4)) yield (cols(0), cols(1))  
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    51
}
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    52
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    53
val urban_ratings = urban_process_ratings(urban_get_csv_file("ratings.csv").take(1000))
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    54
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    55
assert(urban_ck(urban_ratings))
43995ea34fe7 updated
Christian Urban <urbanc@in.tum.de>
parents:
diff changeset
    56
*/