Save model in ubj as the default. (#9947)

jvm-packages/xgboost4j-spark/src/main/scala/org/apache/spark/ml/util/XGBoostReadWrite.scala

@@ -30,9 +30,6 @@ import org.apache.spark.ml.param.Params
 import org.apache.spark.ml.util.DefaultParamsReader.Metadata
 
 abstract class XGBoostWriter extends MLWriter {
-
-  /** Currently it's using the "deprecated" format as
-   * default, which will be changed into `ubj` in future releases. */
   def getModelFormat(): String = {
     optionMap.getOrElse("format", JBooster.DEFAULT_FORMAT)
   }

jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostClassifierSuite.scala

@@ -1,5 +1,5 @@
 /*
- Copyright (c) 2014-2022 by Contributors
+ Copyright (c) 2014-2024 by Contributors
 
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
@@ -432,6 +432,7 @@ class XGBoostClassifierSuite extends AnyFunSuite with PerTest with TmpFolderPerS
     val xgb = new XGBoostClassifier(paramMap)
     val model = xgb.fit(trainingDF)
 
+    // test json
     val modelPath = new File(tempDir.toFile, "xgbc").getPath
     model.write.option("format", "json").save(modelPath)
     val nativeJsonModelPath = new File(tempDir.toFile, "nativeModel.json").getPath
@@ -439,21 +440,21 @@ class XGBoostClassifierSuite extends AnyFunSuite with PerTest with TmpFolderPerS
     assert(compareTwoFiles(new File(modelPath, "data/XGBoostClassificationModel").getPath,
       nativeJsonModelPath))
 
-    // test default "deprecated"
+    // test ubj
     val modelUbjPath = new File(tempDir.toFile, "xgbcUbj").getPath
     model.write.save(modelUbjPath)
-    val nativeDeprecatedModelPath = new File(tempDir.toFile, "nativeModel").getPath
-    model.nativeBooster.saveModel(nativeDeprecatedModelPath)
+    val nativeUbjModelPath = new File(tempDir.toFile, "nativeModel.ubj").getPath
+    model.nativeBooster.saveModel(nativeUbjModelPath)
     assert(compareTwoFiles(new File(modelUbjPath, "data/XGBoostClassificationModel").getPath,
-      nativeDeprecatedModelPath))
+      nativeUbjModelPath))
 
     // json file should be indifferent with ubj file
     val modelJsonPath = new File(tempDir.toFile, "xgbcJson").getPath
     model.write.option("format", "json").save(modelJsonPath)
-    val nativeUbjModelPath = new File(tempDir.toFile, "nativeModel1.ubj").getPath
-    model.nativeBooster.saveModel(nativeUbjModelPath)
+    val nativeUbjModelPath1 = new File(tempDir.toFile, "nativeModel1.ubj").getPath
+    model.nativeBooster.saveModel(nativeUbjModelPath1)
     assert(!compareTwoFiles(new File(modelJsonPath, "data/XGBoostClassificationModel").getPath,
-      nativeUbjModelPath))
+      nativeUbjModelPath1))
   }
 
   test("native json model file should store feature_name and feature_type") {

jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostRegressorSuite.scala

@@ -1,5 +1,5 @@
 /*
- Copyright (c) 2014-2022 by Contributors
+ Copyright (c) 2014-2024 by Contributors
 
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
@@ -333,21 +333,24 @@ class XGBoostRegressorSuite extends AnyFunSuite with PerTest with TmpFolderPerSu
     assert(compareTwoFiles(new File(modelPath, "data/XGBoostRegressionModel").getPath,
       nativeJsonModelPath))
 
-    // test default "deprecated"
+    // test default "ubj"
     val modelUbjPath = new File(tempDir.toFile, "xgbcUbj").getPath
     model.write.save(modelUbjPath)
-    val nativeDeprecatedModelPath = new File(tempDir.toFile, "nativeModel").getPath
-    model.nativeBooster.saveModel(nativeDeprecatedModelPath)
-    assert(compareTwoFiles(new File(modelUbjPath, "data/XGBoostRegressionModel").getPath,
-      nativeDeprecatedModelPath))
 
-    // json file should be indifferent with ubj file
-    val modelJsonPath = new File(tempDir.toFile, "xgbcJson").getPath
-    model.write.option("format", "json").save(modelJsonPath)
-    val nativeUbjModelPath = new File(tempDir.toFile, "nativeModel1.ubj").getPath
+    val nativeUbjModelPath = new File(tempDir.toFile, "nativeModel.ubj").getPath
     model.nativeBooster.saveModel(nativeUbjModelPath)
-    assert(!compareTwoFiles(new File(modelJsonPath, "data/XGBoostRegressionModel").getPath,
-      nativeUbjModelPath))
-  }
 
+    assert(compareTwoFiles(new File(modelUbjPath, "data/XGBoostRegressionModel").getPath,
+      nativeUbjModelPath))
+
+    // test the deprecated format
+    val modelDeprecatedPath = new File(tempDir.toFile, "modelDeprecated").getPath
+    model.write.option("format", "deprecated").save(modelDeprecatedPath)
+
+    val nativeDeprecatedModelPath = new File(tempDir.toFile, "nativeModel.deprecated").getPath
+    model.nativeBooster.saveModel(nativeDeprecatedModelPath)
+
+    assert(compareTwoFiles(new File(modelDeprecatedPath, "data/XGBoostRegressionModel").getPath,
+      nativeDeprecatedModelPath))
+  }
 }

jvm-packages/xgboost4j/src/main/java/ml/dmlc/xgboost4j/java/Booster.java

@@ -34,7 +34,7 @@ import org.apache.commons.logging.LogFactory;
  * Booster for xgboost, this is a model API that support interactive build of a XGBoost Model
  */
 public class Booster implements Serializable, KryoSerializable {
-  public static final String DEFAULT_FORMAT = "deprecated";
+  public static final String DEFAULT_FORMAT = "ubj";
   private static final Log logger = LogFactory.getLog(Booster.class);
   // handle to the booster.
   private long handle = 0;
@@ -788,8 +788,7 @@ public class Booster implements Serializable, KryoSerializable {
   }
 
   /**
-   * Save model into raw byte array. Currently it's using the deprecated format as
-   * default, which will be changed into `ubj` in future releases.
+   * Save model into raw byte array in the UBJSON ("ubj") format.
    *
    * @return the saved byte array
    * @throws XGBoostError native error

jvm-packages/xgboost4j/src/main/scala/ml/dmlc/xgboost4j/scala/Booster.scala

@@ -337,8 +337,7 @@ class Booster private[xgboost4j](private[xgboost4j] var booster: JBooster)
   }
 
   /**
-    * Save model into a raw byte array. Currently it's using the deprecated format as
-   *  default, which will be changed into `ubj` in future releases.
+    * Save model into a raw byte array in the UBJSON ("ubj") format.
     */
   @throws(classOf[XGBoostError])
   def toByteArray: Array[Byte] = {