blob: c660b45630a6d9854976c1d3f4fb59dc9c787a56 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
|
package com.yahoo.example.blog
import org.apache.spark.ml.recommendation.ALSModel
import org.apache.spark.sql.SparkSession
import org.scalatest.Matchers._
import org.scalatest._
class CollaborativeFilteringTest extends FunSuite with BeforeAndAfter {
var ss: SparkSession = _
before {
ss = SparkSession
.builder()
.appName("Unit Test")
.master("local[*]")
.getOrCreate()
}
after {
ss.stop()
}
test("run method returns a MatrixFactorizationModel with latent factors of size 10 to user and item") {
val file_path = getClass.getResource("/trainingSetIndicesSample.txt")
val cf = new CollaborativeFiltering(ss)
val model = cf.run(
input_path = file_path.toString,
rank = 10,
numIterations = 10,
lambda = 0.01)
model shouldBe a [ALSModel]
val product_feature_array = model.itemFactors.first().getSeq(1)
assertResult(10){product_feature_array.length}
val user_feature_array = model.userFactors.first().getSeq(1)
assertResult(10){user_feature_array.length}
}
test("run_pipeline method returns a MatrixFactorizationModel with latent factors of size 10 to user and item") {
val file_path = getClass.getResource("/trainingSetIndicesSample.txt")
val cf = new CollaborativeFiltering(ss)
val model = cf.run_pipeline(input_path = file_path.toString, numIterations = 10)
model shouldBe a [ALSModel]
val product_feature_array = model.itemFactors.first().getSeq(1)
assertResult(10){product_feature_array.length}
val user_feature_array = model.userFactors.first().getSeq(1)
assertResult(10){user_feature_array.length}
}
}
|
