Updated test resources

After upgrading from XGBoost 1.7(.6) to 2.0(.1), it seems that XGBoost estimators no longer require setting the 'num_workers' and 'tracker_conf' parameters.
jpmml · Dec 29, 2023 · 88aec17 · 88aec17
1 parent 4225cce
commit 88aec17
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 12 deletions.
diff --git a/pmml-sparkml-xgboost/src/test/resources/XGBoostAudit.scala b/pmml-sparkml-xgboost/src/test/resources/XGBoostAudit.scala
@@ -1,6 +1,6 @@
 import java.io.File
 
-import ml.dmlc.xgboost4j.scala.spark.{TrackerConf, XGBoostClassifier}
+import ml.dmlc.xgboost4j.scala.spark.XGBoostClassifier
 import org.apache.spark.ml.Pipeline
 import org.apache.spark.ml.feature._
 import org.apache.spark.ml.linalg.Vector
@@ -25,8 +25,7 @@ val assembler = new VectorAssembler().setInputCols(ohe.getOutputCols ++ cont_col
 
 val sparse2dense = new SparseToDenseTransformer().setInputCol(assembler.getOutputCol).setOutputCol("denseFeatureVec")
 
-val trackerConf = TrackerConf(0, "scala")
-val classifier = new XGBoostClassifier(Map("objective" -> "binary:logistic", "num_round" -> 101, "tracker_conf" -> trackerConf)).setLabelCol(labelIndexer.getOutputCol).setFeaturesCol(sparse2dense.getOutputCol)
+val classifier = new XGBoostClassifier(Map("objective" -> "binary:logistic", "num_round" -> 101)).setLabelCol(labelIndexer.getOutputCol).setFeaturesCol(sparse2dense.getOutputCol)
 
 val pipeline = new Pipeline().setStages(Array(labelIndexer, indexer, ohe, assembler, sparse2dense, classifier))
 val pipelineModel = pipeline.fit(df)

diff --git a/pmml-sparkml-xgboost/src/test/resources/XGBoostAuto.scala b/pmml-sparkml-xgboost/src/test/resources/XGBoostAuto.scala
@@ -1,6 +1,6 @@
 import java.io.File
 
-import ml.dmlc.xgboost4j.scala.spark.{TrackerConf, XGBoostRegressor}
+import ml.dmlc.xgboost4j.scala.spark.XGBoostRegressor
 import org.apache.spark.ml.Pipeline
 import org.apache.spark.ml.feature._
 import org.apache.spark.sql.types.{FloatType, StringType}
@@ -21,8 +21,7 @@ val assembler = new VectorAssembler().setInputCols(ohe.getOutputCols ++ cont_col
 
 val sparse2dense = new SparseToDenseTransformer().setInputCol(assembler.getOutputCol).setOutputCol("denseFeatureVec")
 
-val trackerConf = TrackerConf(0, "scala")
-val regressor = new XGBoostRegressor(Map("objective" -> "reg:squarederror", "num_round" -> 101, "num_workers" -> 1, "tracker_conf" -> trackerConf)).setLabelCol("mpg").setFeaturesCol(sparse2dense.getOutputCol)
+val regressor = new XGBoostRegressor(Map("objective" -> "reg:squarederror", "num_round" -> 101)).setLabelCol("mpg").setFeaturesCol(sparse2dense.getOutputCol)
 
 val pipeline = new Pipeline().setStages(Array(indexer, ohe, assembler, sparse2dense, regressor))
 val pipelineModel = pipeline.fit(df)

diff --git a/pmml-sparkml-xgboost/src/test/resources/XGBoostHousing.scala b/pmml-sparkml-xgboost/src/test/resources/XGBoostHousing.scala
@@ -1,6 +1,6 @@
 import java.io.File
 
-import ml.dmlc.xgboost4j.scala.spark.{TrackerConf, XGBoostRegressor}
+import ml.dmlc.xgboost4j.scala.spark.XGBoostRegressor
 import org.apache.spark.ml.Pipeline
 import org.apache.spark.ml.feature._
 import org.apache.spark.sql.types.FloatType
@@ -16,8 +16,7 @@ val cont_cols = Array("CRIM", "ZN", "INDUS", "NOX", "RM", "AGE", "DIS", "PTRATIO
 val assembler = new VectorAssembler().setInputCols(cat_cols ++ cont_cols).setOutputCol("featureVector")
 val indexer = new VectorIndexer().setInputCol(assembler.getOutputCol).setOutputCol("catFeatureVector")
 
-val trackerConf = TrackerConf(0, "scala")
-val regressor = new XGBoostRegressor(Map("objective" -> "reg:squarederror", "num_round" -> 101, "num_workers" -> 1, "tracker_conf" -> trackerConf)).setMissing(-1).setLabelCol("MEDV").setFeaturesCol(indexer.getOutputCol)
+val regressor = new XGBoostRegressor(Map("objective" -> "reg:squarederror", "num_round" -> 101)).setMissing(-1).setLabelCol("MEDV").setFeaturesCol(indexer.getOutputCol)
 
 val pipeline = new Pipeline().setStages(Array(assembler, indexer, regressor))
 val pipelineModel = pipeline.fit(df)

diff --git a/pmml-sparkml-xgboost/src/test/resources/XGBoostIris.scala b/pmml-sparkml-xgboost/src/test/resources/XGBoostIris.scala
@@ -1,6 +1,6 @@
 import java.io.File
 
-import ml.dmlc.xgboost4j.scala.spark.{TrackerConf, XGBoostClassifier}
+import ml.dmlc.xgboost4j.scala.spark.XGBoostClassifier
 import org.apache.spark.ml.Pipeline
 import org.apache.spark.ml.feature._
 import org.apache.spark.ml.linalg.Vector
@@ -22,8 +22,7 @@ val labelIndexerModel = labelIndexer.fit(df)
 
 val assembler = new VectorAssembler().setInputCols(Array("Sepal_Length", "Sepal_Width", "Petal_Length", "Petal_Width")).setOutputCol("featureVector")
 
-val trackerConf = TrackerConf(0, "scala")
-val classifier = new XGBoostClassifier(Map("objective" -> "multi:softprob", "num_class" -> 3, "num_round" -> 17, "tracker_conf" -> trackerConf)).setLabelCol(labelIndexer.getOutputCol).setFeaturesCol(assembler.getOutputCol)
+val classifier = new XGBoostClassifier(Map("objective" -> "multi:softprob", "num_class" -> 3)).setLabelCol(labelIndexer.getOutputCol).setFeaturesCol(assembler.getOutputCol)
 
 val pipeline = new Pipeline().setStages(Array(labelIndexer, assembler, classifier))
 val pipelineModel = pipeline.fit(df)