Skip to content

[SPARK-58637][ML] Optimize HashingTF transform closure #57845

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zhengruifeng wants to merge 1 commit into from
+42 −5
Closed

[SPARK-58637][ML] Optimize HashingTF transform closure #57845

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 30 additions & 5 deletions mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,12 +91,37 @@ class HashingTF @Since("3.0.0") private[ml] (
override def transform(dataset: Dataset[_]): DataFrame = {
val outputSchema = transformSchema(dataset.schema)
val n = $(numFeatures)
val updateFunc = if ($(binary)) (v: Double) => 1.0 else (v: Double) => v + 1.0
def binaryHashUDF(hashFunc: Any => Int) = udf { terms: Seq[_] =>
val map = new OpenHashMap[Int, Int]
terms.foreach { term =>
map.update(Utils.nonNegativeMod(hashFunc(term), n), 1)
}
Vectors.sparse(n, map.iterator.map { case (index, count) =>
(index, count.toDouble)
}.toSeq)
}

def countHashUDF(hashFunc: Any => Int) = udf { terms: Seq[_] =>
val map = new OpenHashMap[Int, Int]
terms.foreach { term =>
val index = Utils.nonNegativeMod(hashFunc(term), n)
map.changeValue(index, 1, _ + 1)
}
Vectors.sparse(n, map.iterator.map { case (index, count) =>
(index, count.toDouble)
}.toSeq)
}

val hashUDF = udf { terms: Seq[_] =>
val map = new OpenHashMap[Int, Double]()
terms.foreach { term => map.changeValue(indexOf(term), 1.0, updateFunc) }
Vectors.sparse(n, map.toSeq)
val hashUDF = ($(binary), hashFuncVersion) match {
case (true, HashingTF.SPARK_2_MURMUR3_HASH) =>
binaryHashUDF(OldHashingTF.murmur3Hash)
case (false, HashingTF.SPARK_2_MURMUR3_HASH) =>
countHashUDF(OldHashingTF.murmur3Hash)
case (true, HashingTF.SPARK_3_MURMUR3_HASH) =>
binaryHashUDF(FeatureHasher.murmur3Hash)
case (false, HashingTF.SPARK_3_MURMUR3_HASH) =>
countHashUDF(FeatureHasher.murmur3Hash)
case _ => throw new IllegalArgumentException("Illegal hash function version setting.")
}

dataset.withColumn($(outputCol), hashUDF(col($(inputCol))),
Expand Down
12 changes: 12 additions & 0 deletions mllib/src/test/scala/org/apache/spark/ml/feature/HashingTFSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,6 +97,18 @@ class HashingTFSuite extends MLTest with DefaultReadWriteTest {
assert(loadedHashingTF.indexOf("c") === mLlibHashingTF.indexOf("c"))
assert(loadedHashingTF.indexOf("d") === mLlibHashingTF.indexOf("d"))

mLlibHashingTF.setBinary(loadedHashingTF.getBinary)
val terms = "a a b b c d".split(" ").toSeq
val df = Seq(Tuple1(terms)).toDF("words")
val features = loadedHashingTF
.setInputCol("words")
.setOutputCol("features")
.transform(df)
.select("features")
.first()
.getAs[Vector](0)
assert(features ~== mLlibHashingTF.transform(terms).asML absTol 1e-14)

val metadata = spark.read.json(s"$hashingTFPath/metadata")
val sparkVersionStr = metadata.select("sparkVersion").first().getString(0)
assert(sparkVersionStr === "2.4.4")
Expand Down