Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/11871#discussion_r56937008
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala ---
@@ -123,21 +95,74 @@ class StopWordsRemover(override val uid: String)
/** @group getParam */
def getCaseSensitive: Boolean = $(caseSensitive)
- setDefault(stopWords -> StopWords.English, caseSensitive -> false)
+ /**
+ * the language of stop words
+ * Default: "english"
+ * @group param
+ */
+ val language: Param[String] = new Param[String](this, "language",
"stopwords language")
+
+ /** @group setParam */
+ def setLanguage(value: String): this.type = {
+ val lang = value.toLowerCase
+ require(StopWords.languageMap.contains(lang), s"$lang is not in
language list")
--- End diff --
use ParamValidators.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
