Skip to content

[SPARK-59152][ML] Create CountVectorizer broadcast per transform #58452

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 3 commits into from
Closed

[SPARK-59152][ML] Create CountVectorizer broadcast per transform #58452

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
452dca2
[SPARK-59152][ML] Create CountVectorizer broadcast per transform
zhengruifeng Sep 1, 2026
5bf8e25
[SPARK-59152][ML] Rename CountVectorizer broadcast variable
zhengruifeng Sep 1, 2026
8b26508
[SPARK-59152][ML] Clarify local CountVectorizer dictionary name
zhengruifeng Sep 1, 2026
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
25 changes: 9 additions & 16 deletions mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ import java.util.{HashMap => JHashMap}
import org.apache.hadoop.fs.Path

import org.apache.spark.annotation.Since
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.ml.{Estimator, Model}
import org.apache.spark.ml.attribute.{Attribute, AttributeGroup, NumericAttribute}
import org.apache.spark.ml.linalg.{SQLDataTypes, Vectors}
Expand Down Expand Up @@ -297,31 +296,25 @@ class CountVectorizerModel(
@Since("2.0.0")
def setBinary(value: Boolean): this.type = set(binary, value)

/** Dictionary created from [[vocabulary]] and its indices, broadcast once for [[transform()]] */
private var broadcastDict: Option[Broadcast[JHashMap[String, Integer]]] = None

@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
val outputSchema = transformSchema(dataset.schema, logging = true)
if (broadcastDict.isEmpty) {
val dict = new JHashMap[String, Integer](math.ceil(vocabulary.length / 0.75).toInt)
var index = 0
while (index < vocabulary.length) {
dict.put(vocabulary(index), index)
index += 1
}
broadcastDict = Some(dataset.sparkSession.sparkContext.broadcast(dict))
val dict = new JHashMap[String, Integer](math.ceil(vocabulary.length / 0.75).toInt)
var index = 0
while (index < vocabulary.length) {
dict.put(vocabulary(index), index)
index += 1
}
val dictBr = broadcastDict.get
val bcDict = dataset.sparkSession.sparkContext.broadcast(dict)
val localMinTF = $(minTF)
val localBinary = $(binary)
val vectorizer = udf { document: Seq[String] =>
val dict = dictBr.value
val dictSize = dict.size()
val localDict = bcDict.value
val dictSize = localDict.size()
val termCounts = new OpenHashMap[Int, Int]
var tokenCount = 0L
document.foreach { term =>
val index = dict.get(term)
val index = localDict.get(term)
if (index != null) {
termCounts.changeValue(index.intValue(), 1, _ + 1)
}
Expand Down