Github user MLnick commented on a diff in the pull request:
https://github.com/apache/spark/pull/11553#discussion_r59172573
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
---
@@ -17,78 +17,59 @@
package org.apache.spark.ml.feature
-import org.apache.spark.{SparkContext, SparkFunSuite}
-import org.apache.spark.ml.attribute.{Attribute, NominalAttribute}
+import org.apache.spark.SparkFunSuite
import org.apache.spark.ml.util.DefaultReadWriteTest
import org.apache.spark.mllib.util.MLlibTestSparkContext
-import org.apache.spark.sql.{Row, SQLContext}
+import org.apache.spark.sql.SQLContext
class QuantileDiscretizerSuite
extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
- import org.apache.spark.ml.feature.QuantileDiscretizerSuite._
-
- test("Test quantile discretizer") {
- checkDiscretizedData(sc,
- Array[Double](1, 2, 3, 3, 3, 3, 3, 3, 3),
- 10,
- Array[Double](1, 2, 3, 3, 3, 3, 3, 3, 3),
- Array("-Infinity, 1.0", "1.0, 2.0", "2.0, 3.0", "3.0, Infinity"))
-
- checkDiscretizedData(sc,
- Array[Double](1, 2, 3, 3, 3, 3, 3, 3, 3),
- 4,
- Array[Double](1, 2, 3, 3, 3, 3, 3, 3, 3),
- Array("-Infinity, 1.0", "1.0, 2.0", "2.0, 3.0", "3.0, Infinity"))
-
- checkDiscretizedData(sc,
- Array[Double](1, 2, 3, 3, 3, 3, 3, 3, 3),
- 3,
- Array[Double](0, 1, 2, 2, 2, 2, 2, 2, 2),
- Array("-Infinity, 2.0", "2.0, 3.0", "3.0, Infinity"))
+ test("Test observed number of buckets and their sizes match expected
values") {
+ val sqlCtx = SQLContext.getOrCreate(sc)
+ import sqlCtx.implicits._
- checkDiscretizedData(sc,
- Array[Double](1, 2, 3, 3, 3, 3, 3, 3, 3),
- 2,
- Array[Double](0, 1, 1, 1, 1, 1, 1, 1, 1),
- Array("-Infinity, 2.0", "2.0, Infinity"))
+ val datasetSize = 100000
+ val numBuckets = 5
+ val df = sc.parallelize(1.0 to datasetSize by
1.0).map(Tuple1.apply).toDF("input")
+ val discretizer = new QuantileDiscretizer()
+ .setInputCol("input")
+ .setOutputCol("result")
+ .setNumBuckets(numBuckets)
+ val result = discretizer.fit(df).transform(df)
- }
+ val observedNumBuckets = result.select("result").distinct.count
+ assert(observedNumBuckets === numBuckets,
+ "Observed number of buckets does not equal expected number of
buckets.")
- test("Test getting splits") {
- val splitTestPoints = Array(
- Array[Double]() -> Array(Double.NegativeInfinity, 0,
Double.PositiveInfinity),
- Array(Double.NegativeInfinity) -> Array(Double.NegativeInfinity, 0,
Double.PositiveInfinity),
- Array(Double.PositiveInfinity) -> Array(Double.NegativeInfinity, 0,
Double.PositiveInfinity),
- Array(Double.NegativeInfinity, Double.PositiveInfinity)
- -> Array(Double.NegativeInfinity, 0, Double.PositiveInfinity),
- Array(0.0) -> Array(Double.NegativeInfinity, 0,
Double.PositiveInfinity),
- Array(1.0) -> Array(Double.NegativeInfinity, 1,
Double.PositiveInfinity),
- Array(0.0, 1.0) -> Array(Double.NegativeInfinity, 0, 1,
Double.PositiveInfinity)
- )
- for ((ori, res) <- splitTestPoints) {
- assert(QuantileDiscretizer.getSplits(ori) === res, "Returned splits
are invalid.")
+ val relativeError = discretizer.getRelativeError
+ val isGoodBucket = org.apache.spark.sql.functions.udf {
+ (size: Int) => math.abs( size - (datasetSize / numBuckets)) <=
(relativeError * datasetSize)
}
+ val numGoodBuckets =
result.groupBy("result").count.filter(isGoodBucket($"count")).count
+ assert(numGoodBuckets === numBuckets,
+ "Bucket sizes are not as expected.")
--- End diff --
Could we make this a bit more clear, like `Bucket sizes are not within
expected relative error tolerance` or something similar
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
