Skip to content
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.

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

[SPARK-48892][ML] Avoid per-row param read in Tokenizer #47342

Closed
wants to merge 2 commits into from
Closed
Changes from all commits
Commits
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
19 changes: 12 additions & 7 deletions mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
Original file line number Diff line number Diff line change
Expand Up @@ -141,14 +141,19 @@ class RegexTokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)

setDefault(minTokenLength -> 1, gaps -> true, pattern -> "\\s+", toLowercase -> true)

override protected def createTransformFunc: String => Seq[String] = { originStr =>
override protected def createTransformFunc: String => Seq[String] = {
val re = $(pattern).r
// scalastyle:off caselocale
val str = if ($(toLowercase)) originStr.toLowerCase() else originStr
// scalastyle:on caselocale
val tokens = if ($(gaps)) re.split(str).toImmutableArraySeq else re.findAllIn(str).toSeq
val minLength = $(minTokenLength)
tokens.filter(_.length >= minLength)
val localToLowercase = $(toLowercase)
val localGaps = $(gaps)
val localMinTokenLength = $(minTokenLength)

(originStr: String) => {
// scalastyle:off caselocale
val str = if (localToLowercase) originStr.toLowerCase() else originStr
// scalastyle:on caselocale
val tokens = if (localGaps) re.split(str).toImmutableArraySeq else re.findAllIn(str).toSeq
tokens.filter(_.length >= localMinTokenLength)
}
}

override protected def validateInputType(inputType: DataType): Unit = {
Expand Down