<!-- https://mvnrepository.com/artifact/ml.dmlc/xgboost4j -->
<dependency><groupId>ml.dmlc</groupId><artifactId>xgboost4j</artifactId><version>0.81</version>
</dependency><!-- https://mvnrepository.com/artifact/ml.dmlc/xgboost4j-spark -->
<dependency><groupId>ml.dmlc</groupId><artifactId>xgboost4j-spark</artifactId><version>0.81</version>
</dependency>

import org.apache.spark.ml.feature.{StringIndexer}
import org.apache.spark.sql.types.{DoubleType, StringType, StructField, StructType}
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.sql. SparkSession
import ml.dmlc.xgboost4j.scala.spark.{XGBoostClassificationModel, XGBoostClassifier}
/*** author  ：wy* todo    ： xgboost鸢尾花分类* Created by pc-admin on 2020-03-12 11:21**/
object xgboostIrisDataTest {def main(args: Array[String]): Unit = {val ss = SparkSession.builder().master("local[4]").appName("xgboostRisiDataTest").getOrCreate()val dataPath = "iris.data"val schema = new StructType(Array(StructField("sepal lenght", DoubleType, true),StructField("sepal width", DoubleType, true),StructField("petal lenght", DoubleType, true),StructField("petal width", DoubleType, true),StructField("class", StringType, true)))val rawInput = ss.read.schema(schema).csv(dataPath)// 把字符串class转换成数字数字classval stringIndexer = new StringIndexer().setInputCol("class").setOutputCol("classIndex").fit(rawInput)// 执行进行转换,并把原有的字符串class删除掉val labelTransformed = stringIndexer.transform(rawInput).drop("class")// 将多个字段合并成在一起,组成futureval vectorAssembler = new VectorAssembler().setInputCols(Array("sepal lenght", "sepal width", "petal lenght", "petal width")).setOutputCol("features")//将数据集切分成训集和测试集val xgbInput = vectorAssembler.transform(labelTransformed).select("features", "classIndex")val splitXgbInput = xgbInput.randomSplit(Array(0.9, 0.1))val trainXgbInput = splitXgbInput(0)val testXgbInput = splitXgbInput(1)// 注意!!!这个num_workers 必须小于等于 local[4] 线程数,否则会出现程序卡死现象.val xgbParam = Map("eta" -> 0.1f,"max_depth" -> 2,"objective" -> "multi:softprob","num_class" -> 3,"num_round" -> 100,"num_workers" -> 4)// 创建xgboost函数,指定特征向量和标签val xgbClassifier = new XGBoostClassifier(xgbParam).setFeaturesCol("features").setLabelCol("classIndex")// 开始训练val xgbClassificationModel: XGBoostClassificationModel = xgbClassifier.fit(trainXgbInput)// 预测val result = xgbClassificationModel.transform(testXgbInput)// 展示 result.show(1000)ss.stop()}
}

Exception in thread "main" ml.dmlc.xgboost4j.java.XGBoostError: XGBoostModel training failed
atml.dmlc.xgboost4j.scala.spark.XGBoost$.postTrackerReturnProcessing(XGBoost.scala:363)
at ml.dmlc.xgboost4j.scala.spark.XGBoost$.trainDistributed(XGBoost.scala:334)
at ml.dmlc.xgboost4j.scala.spark.XGBoostEstimator.train(XGBoostEstimator.scala:139)
at ml.dmlc.xgboost4j.scala.spark.XGBoostEstimator.train(XGBoostEstimator.scala:36)
at org.apache.spark.ml.Predictor.fit(Predictor.scala:90)
at ml.dmlc.xgboost4j.scala.spark.XGBoost$.trainWithDataFrame(XGBoost.scala:191)