(spark) branch master updated: [SPARK-49805][SQL][ML] Remove private[xxx] functions from `function.scala`

[yangjie01]

This is an automated email from the ASF dual-hosted git repository.

yangjie01 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/master by this push:
     new f18c4e7722b4 [SPARK-49805][SQL][ML] Remove private[xxx] functions from 
`function.scala`
f18c4e7722b4 is described below

commit f18c4e7722b46e8573e959f5f3b063ed0efa5d23
Author: Ruifeng Zheng <ruife...@apache.org>
AuthorDate: Fri Sep 27 15:27:34 2024 +0800

    [SPARK-49805][SQL][ML] Remove private[xxx] functions from `function.scala`
    
    ### What changes were proposed in this pull request?
    Remove private[xxx] functions from `function.scala`
    
    ### Why are the changes needed?
    internal functions can be directly invoked by `Column.internalFn`, no need 
to add them in `function.scala`
    
    ### Does this PR introduce _any_ user-facing change?
    no
    
    ### How was this patch tested?
    ci
    
    ### Was this patch authored or co-authored using generative AI tooling?
    no
    
    Closes #48276 from zhengruifeng/move_private_func.
    
    Authored-by: Ruifeng Zheng <ruife...@apache.org>
    Signed-off-by: yangjie01 <yangji...@baidu.com>
---
 mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala    | 5 ++++-
 .../scala/org/apache/spark/ml/recommendation/CollectTopKSuite.scala  | 3 ++-
 sql/api/src/main/scala/org/apache/spark/sql/functions.scala          | 3 ---
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala 
b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala
index 1a004f71749e..5899bf891ec9 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala
@@ -517,7 +517,7 @@ class ALSModel private[ml] (
     )
 
     ratings.groupBy(srcOutputColumn)
-      .agg(collect_top_k(struct(ratingColumn, dstOutputColumn), num, false))
+      .agg(ALSModel.collect_top_k(struct(ratingColumn, dstOutputColumn), num, 
false))
       .as[(Int, Seq[(Float, Int)])]
       .map(t => (t._1, t._2.map(p => (p._2, p._1))))
       .toDF(srcOutputColumn, recommendColumn)
@@ -546,6 +546,9 @@ object ALSModel extends MLReadable[ALSModel] {
   private val Drop = "drop"
   private[recommendation] final val supportedColdStartStrategies = Array(NaN, 
Drop)
 
+  private[recommendation] def collect_top_k(e: Column, num: Int, reverse: 
Boolean): Column =
+    Column.internalFn("collect_top_k", e, lit(num), lit(reverse))
+
   @Since("1.6.0")
   override def read: MLReader[ALSModel] = new ALSModelReader
 
diff --git 
a/mllib/src/test/scala/org/apache/spark/ml/recommendation/CollectTopKSuite.scala
 
b/mllib/src/test/scala/org/apache/spark/ml/recommendation/CollectTopKSuite.scala
index b79e10d0d267..bd83d5498ae6 100644
--- 
a/mllib/src/test/scala/org/apache/spark/ml/recommendation/CollectTopKSuite.scala
+++ 
b/mllib/src/test/scala/org/apache/spark/ml/recommendation/CollectTopKSuite.scala
@@ -17,9 +17,10 @@
 
 package org.apache.spark.ml.recommendation
 
+import org.apache.spark.ml.recommendation.ALSModel.collect_top_k
 import org.apache.spark.ml.util.MLTest
 import org.apache.spark.sql.DataFrame
-import org.apache.spark.sql.functions.{col, collect_top_k, struct}
+import org.apache.spark.sql.functions.{col, struct}
 
 class CollectTopKSuite extends MLTest {
 
diff --git a/sql/api/src/main/scala/org/apache/spark/sql/functions.scala 
b/sql/api/src/main/scala/org/apache/spark/sql/functions.scala
index 93bff2262105..e6fd06f2ec63 100644
--- a/sql/api/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/api/src/main/scala/org/apache/spark/sql/functions.scala
@@ -401,9 +401,6 @@ object functions {
   def count_min_sketch(e: Column, eps: Column, confidence: Column): Column =
     count_min_sketch(e, eps, confidence, lit(SparkClassUtils.random.nextLong))
 
-  private[spark] def collect_top_k(e: Column, num: Int, reverse: Boolean): 
Column =
-    Column.internalFn("collect_top_k", e, lit(num), lit(reverse))
-
   /**
    * Aggregate function: returns the Pearson Correlation Coefficient for two 
columns.
    *


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org