java.lang.IllegalArgumentException: Transformer class org.apache.spark.ml.feature.VectorAssembler is not supported
	at org.shaded.jpmml.sparkml.ConverterFactory.newConverter(ConverterFactory.java:53)
	at org.shaded.jpmml.sparkml.PMMLBuilder.build(PMMLBuilder.java:109)
	at com.iqiyi.columbus.joint_prevent.model.pmml.PMMLModelLocal$.saveModelAndEvaluate(PMMLModelLocal.scala:93)
	at com.iqiyi.columbus.joint_prevent.model.pmml.PMMLModelLocal$.main(PMMLModelLocal.scala:134)
	at com.iqiyi.columbus.joint_prevent.model.pmml.PMMLModelLocal.main(PMMLModelLocal.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:635)

val pipelineModel = trainPipelineModel(data, trainingData)
val pmml = new PMMLBuilder(schema, pipelineModel).build()

mapper = DataFrameMapper([
  ("Sepal.Length", ContinuousDomain(missing_value_treatment = "as_is", invalid_value_treatment = "as_is"))
])

from pyspark.ml import Pipeline
from pyspark.ml.classification import RandomForestClassifier
from pyspark.ml.feature import *

def updateFlightsSchema(dataSet):
    return ( dataSet.withColumn("DepDelay_Double",  dataSet["DepDelay"].cast("Double"))
                    .withColumn("DepDelay",         dataSet["DepDelay"].cast("Double"))
                    .withColumn("ArrDelay",         dataSet["ArrDelay"].cast("Double"))
                    .withColumn("Month",            dataSet["Month"].cast("Double"))
                    .withColumn("DayofMonth",       dataSet["DayofMonth"].cast("Double"))
                    .withColumn("CRSDepTime",       dataSet["CRSDepTime"].cast("Double"))
                    .withColumn("Distance",         dataSet["Distance"].cast("Double"))
                    .withColumn("AirTime",          dataSet["AirTime"].cast("Double"))
            )
    
data2007 = updateFlightsSchema(sqlContext.read.format("com.databricks.spark.csv").option("header", "true").option("mode", "DROPMALFORMED").load("2007_short.csv"))

removeCancelled = SQLTransformer(statement="select * from __THIS__ where Cancelled = \"0\" AND Diverted = \"0\"")
data2007 = removeCancelled.transform(data2007)

binarizer = Binarizer(threshold=15.0, inputCol="DepDelay_Double", outputCol="DepDelay_Bin")
featuresAssembler = VectorAssembler(inputCols=["Month", "CRSDepTime", "Distance"], outputCol="features")
rfc3 = RandomForestClassifier(labelCol="DepDelay_Bin", featuresCol="features", numTrees=3, maxDepth=5, seed=10305)

pipelineRF3 = Pipeline(stages=[binarizer, featuresAssembler, rfc3])

model3 = pipelineRF3.fit(data2007)

from py4j.java_gateway import JavaClass
from pyspark.ml.common import _py2java

javaDF = _py2java(sc, data2007)
javaSchema = javaDF.schema.__call__()

jvm = sc._gateway.jvm

javaConverter = sc._gateway.jvm.org.jpmml.sparkml.ConverterUtil
if(not isinstance(javaConverter, JavaClass)):
    raise RuntimeError("JPMML-SparkML not found on classpath")

pmml = jvm.org.jpmml.sparkml.ConverterUtil.toPMMLByteArray(javaSchema, model3._to_java())

py4j.protocol.Py4JJavaError: An error occurred while calling z:org.jpmml.sparkml.ConverterUtil.toPMMLByteArray.
: java.lang.NullPointerException
	at org.jpmml.converter.CategoricalLabel.<init>(CategoricalLabel.java:35)
	at org.jpmml.sparkml.ModelConverter.encodeSchema(ModelConverter.java:82)
	at org.jpmml.sparkml.ModelConverter.registerModel(ModelConverter.java:162)
	at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:86)
	at org.jpmml.sparkml.ConverterUtil.toPMMLByteArray(ConverterUtil.java:142)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
	at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
	at py4j.Gateway.invoke(Gateway.java:280)
	at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
	at py4j.commands.CallCommand.execute(CallCommand.java:79)
	at py4j.GatewayConnection.run(GatewayConnection.java:214)
	at java.lang.Thread.run(Thread.java:748)

  def testPMML(sc: SparkContext) = {
    val rdd = sc.makeRDD(Seq((1.0, 2.0, 3.0, 0.0), (0.0, 2.0, 0.0, 3.0) , (1.0, 0.0, 0.0, 2.0)))
      .map(a => Row(a._1, Vectors.dense(Array(a._2, a._3, a._4)).toSparse))
    val schema = StructType(List(StructField("label", DoubleType), StructField("features", new VectorUDT)))
    val sqlContext = new SQLContext(sc)
    val irisData = sqlContext.createDataFrame(rdd, schema)

    val classifier = new LogisticRegression()
      .setLabelCol("label")
      .setFeaturesCol("features")

    // the first way
    val pipeline = new Pipeline()
      .setStages(Array(classifier))
    val pipelineModel = pipeline.fit(irisData)
    var pmml = ConverterUtil.toPMML(schema, pipelineModel)
    JAXBUtil.marshalPMML(pmml, new StreamResult(System.out))

    // the second way
    val lrModel = classifier.fit(irisData)
    pmml = ConverterUtil.toPMML(schema, lrModel)
    JAXBUtil.marshalPMML(pmml, new StreamResult(System.out))
  }

Caused by: org.jpmml.evaluator.InvalidResultException (at or around line 23)
	at org.jpmml.evaluator.FieldValueUtil.performInvalidValueTreatment(FieldValueUtil.java:178)
	at org.jpmml.evaluator.FieldValueUtil.prepareInputValue(FieldValueUtil.java:90)
	at org.jpmml.evaluator.InputField.prepare(InputField.java:64)

    <dependency>
  		<groupId>org.jpmml</groupId>
  		<artifactId>jpmml-sparkml</artifactId>
  		<version>1.3.3</version>
  		<scope>compile</scope>
  </dependency>

  <build>
  	<resources>
  		<resource>
  			<directory>src/main/resources</directory>
  			<excludes>
  				<exclude>**/*.xml</exclude>
  			</excludes>
  			<filtering>true</filtering>
  		</resource>
  	</resources>
  	<plugins>
  		<plugin>
  			<groupId>net.alchim31.maven</groupId>
  			<artifactId>scala-maven-plugin</artifactId>
  			<version>3.2.1</version>
  			<executions>
  				<execution>
  					<id>compile</id>
  					<goals>
  						<goal>compile</goal>
  					</goals>
  					<phase>process-resources</phase>
  				</execution>
  			</executions>
  			<configuration>
  				<scalaVersion>${scala.version}</scalaVersion>
  			</configuration>
  		</plugin>
  		<plugin>
  			<groupId>org.apache.maven.plugins</groupId>
  			<artifactId>maven-shade-plugin</artifactId>
  			<version>${maven.shade.version}</version>
  			<executions>
  				<execution>
  					<phase>package</phase>
  					<goals>
  						<goal>shade</goal>
  					</goals>
  					<configuration>
  						<relocations>
  							<relocation>
  								<pattern>org.dmg.pmml</pattern>
  								<shadedPattern>org.shaded.dmg.pmml</shadedPattern>
  							</relocation>
  							<relocation>
  								<pattern>org.jpmml</pattern>
  								<shadedPattern>org.shaded.jpmml</shadedPattern>
  							</relocation>
  						</relocations>
  					</configuration>
  				</execution>
  			</executions>
  		</plugin>
  	</plugins>
  </build>

18/03/06 21:40:01 WARN sparkml.ConverterUtil: Failed to load transformer converter class
java.lang.ClassNotFoundException: org.jpmml.sparkml.feature.NGramConverter
	at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
	at org.shaded.jpmml.sparkml.ConverterUtil.init(ConverterUtil.java:351)
	at org.shaded.jpmml.sparkml.ConverterUtil.init(ConverterUtil.java:318)
	at org.shaded.jpmml.sparkml.ConverterUtil.<clinit>(ConverterUtil.java:369)
	at com.nubia.train.Ad_ctr_train_PMML$.main(Ad_ctr_train_PMML.scala:157)
	at com.nubia.train.Ad_ctr_train_PMML.main(Ad_ctr_train_PMML.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
18/03/06 21:40:01 WARN sparkml.ConverterUtil: Failed to load transformer class
java.lang.ClassNotFoundException: org.apache.spark.ml.feature.MaxAbsScalerModel
	at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
	at org.shaded.jpmml.sparkml.ConverterUtil.init(ConverterUtil.java:341)
	at org.shaded.jpmml.sparkml.ConverterUtil.init(ConverterUtil.java:318)
	at org.shaded.jpmml.sparkml.ConverterUtil.<clinit>(ConverterUtil.java:369)
	at com.nubia.train.Ad_ctr_train_PMML$.main(Ad_ctr_train_PMML.scala:157)
	at com.nubia.train.Ad_ctr_train_PMML.main(Ad_ctr_train_PMML.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
......

val formula = new org.apache.spark.ml.feature.RFormula().setFormula("ResultConverted ~ distancevaluefromcentrallocation + availabilitynext3days")

root
|-- ResultConverted: boolean (nullable = true)
|-- distancevaluefromcentrallocation: double (nullable = true)
|-- availabilitynext3days: long (nullable = true)

Exception in thread "main" java.lang.IllegalArgumentException: Expected 2 target categories, got 0 target categories
      at org.jpmml.sparkml.ModelConverter.encodeSchema(ModelConverter.java:134)
      at org.jpmml.sparkml.ModelConverter.registerModel(ModelConverter.java:161)

java.lang.NoSuchMethodError: org.dmg.pmml.DataField.setOpType(Lorg/dmg/pmml/OpType;)Lorg/dmg/pmml/DataField;
        at org.jpmml.sparkml.FeatureMapper.toContinuous(FeatureMapper.java:185)
        at org.jpmml.sparkml.FeatureMapper.createSchema(FeatureMapper.java:135)
        at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:123)
        at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
        at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:37)
        at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
        at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:41)
        at $iwC$$iwC$$iwC$$iwC.<init>(<console>:43)
        at $iwC$$iwC$$iwC.<init>(<console>:45)
        at $iwC$$iwC.<init>(<console>:47)
        at $iwC.<init>(<console>:49)
        at <init>(<console>:51)
        at .<init>(<console>:55)
        at .<clinit>(<console>)
        at .<init>(<console>:7)
        at .<clinit>(<console>)
        at $print(<console>)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:497)
        at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
        at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
        at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
        at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
        at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
        at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
        at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
        at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
        at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
        at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
        at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
        at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
        at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
        at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
        at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
        at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
        at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
        at org.apache.spark.repl.Main$.main(Main.scala:31)
        at org.apache.spark.repl.Main.main(Main.scala)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:497)
        at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
        at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
        at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
        at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
        at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

scala> val pmml = ConverterUtil.toPMML(df.schema, model)
java.lang.NoSuchMethodError: org.dmg.pmml.MiningField.setUsageType(Lorg/dmg/pmml/MiningField$UsageType;)Lorg/dmg/pmml/MiningField;
  at org.jpmml.converter.ModelUtil.createMiningField(ModelUtil.java:73)
  at org.jpmml.converter.ModelUtil.createMiningSchema(ModelUtil.java:57)
  at org.jpmml.converter.ModelUtil.createMiningSchema(ModelUtil.java:46)
  at org.jpmml.sparkml.model.RandomForestClassificationModelConverter.encodeModel(RandomForestClassificationModelConverter.java:45)
  at org.jpmml.sparkml.model.RandomForestClassificationModelConverter.encodeModel(RandomForestClassificationModelConverter.java:33)
  at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:131)
  ... 52 elided

Exception in thread "main" java.lang.IllegalArgumentException: skip
	at org.jpmml.sparkml.feature.StringIndexerModelConverter.encodeFeatures(StringIndexerModelConverter.java:65)
	at org.jpmml.sparkml.FeatureConverter.registerFeatures(FeatureConverter.java:47)
	at org.jpmml.sparkml.PMMLBuilder.build(PMMLBuilder.java:114)
	at com.nubia.train.Ad_ctr_train$.main(Ad_ctr_train.scala:182)
	at com.nubia.train.Ad_ctr_train.main(Ad_ctr_train.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:745)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:187)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:212)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:126)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

PipelineModel model = pipeline.fit(trainingData);

TrainValidationSplitModel tvsm = (TrainValidationSplitModel) model.stages()[0];
RandomForestRegressionModel rfrm = (RandomForestRegressionModel) tvsm.bestModel();

List<Transformer> stages = new ArrayList<>();
stages.add(rfrm);

final PipelineModel pipelineModel = new PipelineModel(
    UUID.randomUUID().toString(),
    stages);

StructType schema = testData.schema();

PMML pmml = ConverterUtil.toPMML(schema, pipelineModel);

Exception in thread "main" java.lang.IllegalArgumentException: Field "label" does not exist.
	at org.apache.spark.sql.types.StructType$$anonfun$apply$1.apply(StructType.scala:264)
	at org.apache.spark.sql.types.StructType$$anonfun$apply$1.apply(StructType.scala:264)
	at scala.collection.MapLike$class.getOrElse(MapLike.scala:128)
	at scala.collection.AbstractMap.getOrElse(Map.scala:59)
	at org.apache.spark.sql.types.StructType.apply(StructType.scala:263)
	at org.jpmml.sparkml.SparkMLEncoder.createDataField(SparkMLEncoder.java:139)
	at org.jpmml.sparkml.SparkMLEncoder.getFeatures(SparkMLEncoder.java:73)
	at org.jpmml.sparkml.SparkMLEncoder.getOnlyFeature(SparkMLEncoder.java:60)
	at org.jpmml.sparkml.ModelConverter.encodeSchema(ModelConverter.java:66)
	at org.jpmml.sparkml.ModelConverter.registerModel(ModelConverter.java:161)
	at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:76)
	at org.loesoft.playground.datascience.mllib.Foo.main(Foo.java:144)

Exception in thread "main" java.lang.IllegalArgumentException: Expected string, integral, double or boolean type, got vector type
	at org.jpmml.sparkml.SparkMLEncoder.createDataField(SparkMLEncoder.java:160)
	at org.jpmml.sparkml.SparkMLEncoder.getFeatures(SparkMLEncoder.java:73)
	at org.jpmml.sparkml.ModelConverter.encodeSchema(ModelConverter.java:140)
	at org.jpmml.sparkml.ModelConverter.registerModel(ModelConverter.java:161)
	at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:76)
	at org.loesoft.playground.datascience.mllib.Foo.main(Foo.java:146)

IllegalArgumentExceptionTraceback (most recent call last)
<ipython-input-46-d8430332ffa6> in <module>()
      1 from jpmml_sparkml import toPMMLBytes
----> 2 pmmlBytes = toPMMLBytes(spark, DF, pipelineModel)
      3 print(pmmlBytes)

/home/hadoop/pyenv/eggs/jpmml_sparkml-1.1rc0-py2.7.egg/jpmml_sparkml/__init__.pyc in toPMMLBytes(sc, df, pipelineModel)
     17         if(not isinstance(javaConverter, JavaClass)):
     18                 raise RuntimeError("JPMML-SparkML not found on classpath")
---> 19         return javaConverter.toPMMLByteArray(javaSchema, javaPipelineModel)

/usr/lib/spark/python/lib/py4j-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1131         answer = self.gateway_client.send_command(command)
   1132         return_value = get_return_value(
-> 1133             answer, self.gateway_client, self.target_id, self.name)
   1134 
   1135         for temp_arg in temp_args:

/usr/lib/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
     77                 raise QueryExecutionException(s.split(': ', 1)[1], stackTrace)
     78             if s.startswith('java.lang.IllegalArgumentException: '):
---> 79                 raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace)
     80             raise
     81     return deco

IllegalArgumentException: u'Expected string, integral, double or boolean type, got decimal(18,0) type'

Caused by: java.lang.IllegalArgumentException: Expected string, integral, double or boolean type, got float type
	at org.jpmml.sparkml.SparkMLEncoder.createDataField(SparkMLEncoder.java:303)
	at org.jpmml.sparkml.SparkMLEncoder.getFeatures(SparkMLEncoder.java:232)
	at org.jpmml.sparkml.feature.VectorAssemblerConverter.encodeFeatures(VectorAssemblerConverter.java:43)
	at org.jpmml.sparkml.SparkMLEncoder.append(SparkMLEncoder.java:74)
	at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:123)

(training, test) = data.toDF("label","degree","tcNum","pageRank","commVertexNum","normQ","gtRate","eqRate","ltRate").randomSplit(Array(1.0 - fracTest, fracTest), 1234)
// Set up Pipeline
    val stages = new mutable.ArrayBuffer[PipelineStage]()
    // (1) For classification, re-index classes.
    val labelColName = if (algo == "classification") "indexedLabel" else "label"
    if (algo == "classification") {
      val labelIndexer = new StringIndexer()
        .setInputCol("label")
        .setOutputCol(labelColName)
      stages += labelIndexer
    }

    val vectorAssember = new VectorAssembler()
    vectorAssember.setInputCols(Array("degree","tcNum","pageRank","commVertexNum","normQ","gtRate","eqRate","ltRate"))
    vectorAssember.setOutputCol("features")
    val vectorData = vectorAssember.transform(training)

//    val vectorData = vectorAssember.transform(training)

    stages += vectorAssember
    // (3) Learn GBT.
    val dt = algo match {
      case "classification" =>
        new GBTClassifier()
          .setLabelCol(labelColName)
          .setFeaturesCol("features")
          .setMaxDepth(params.maxDepth)
          .setMaxBins(params.maxBins)
          .setMinInstancesPerNode(params.minInstancesPerNode)
          .setMinInfoGain(params.minInfoGain)
          .setCacheNodeIds(params.cacheNodeIds)
          .setCheckpointInterval(params.checkpointInterval)
          .setMaxIter(params.maxIter)
      case "regression" =>
        new GBTRegressor()
          .setFeaturesCol("features")
          .setLabelCol(labelColName)
          .setMaxDepth(params.maxDepth)
          .setMaxBins(params.maxBins)
          .setMinInstancesPerNode(params.minInstancesPerNode)
          .setMinInfoGain(params.minInfoGain)
          .setCacheNodeIds(params.cacheNodeIds)
          .setCheckpointInterval(params.checkpointInterval)
          .setMaxIter(params.maxIter)
      case _ => throw new IllegalArgumentException("Algo ${params.algo} not supported.")
    }
    stages += dt
    val pipeline = new Pipeline().setStages(stages.toArray)

    // Fit the Pipeline.
    val startTime = System.nanoTime()
    val pipelineModel = pipeline.fit(training)
    val elapsedTime = (System.nanoTime() - startTime) / 1e9
    println(s"Training time: $elapsedTime seconds")

    /**
      * write model pmml format to hdfs
      */
    val modelPmmlPath = "sjmei/pmmlmodel"
    val pmml = ConverterUtil.toPMML(training.schema, pipelineModel);
//    val conf = new Configuration();
//    HadoopFileUtil.deleteFile(modelPmmlPath)
//    val path = new Path(modelPmmlPath);
//    val fs = path.getFileSystem(conf);
//    val out = fs.create(path);
    MetroJAXBUtil.marshalPMML(pmml, new FileOutputStream(modelPmmlPath));

acc count:4537
error count:5553
acc rate:0.44965312190287415

public class ScoreTest {

    public static void main(String[] args) throws Exception {
        PMML pmml = readPMML(new File("sjmei/pmmlmodel/rf.pmml"));
        ModelEvaluatorFactory modelEvaluatorFactory = ModelEvaluatorFactory.newInstance();
//        System.out.println(pmml.getModels().get(0));
//        Evaluator evaluator = modelEvaluatorFactory.newModelEvaluator(pmml);
        ModelEvaluator evaluator = new MiningModelEvaluator(pmml);

        List<InputField> inputFields = evaluator.getInputFields();

        InputStream is = new FileInputStream(new File("jrdm-dm/data/graph.result.final.vertices.wide.tbl/part-00000"));
        BufferedReader br = new BufferedReader(new InputStreamReader(is));
        String line;

        int diffDelta = 0;
        int sameDelta = 0;
        while((line = br.readLine()) != null) {
            String[] splits = line.split("\t",-1);

            String label = splits[14];

            Map<FieldName, FieldValue> arguments = readArgumentsFromLine(splits, inputFields);

            Map<FieldName, ?> results = evaluator.evaluate(arguments);
//            System.out.println(results);
            List<TargetField> targetFields = evaluator.getTargetFields();
            for(TargetField targetField : targetFields){
                FieldName targetFieldName = targetField.getName();
                Object targetFieldValue = results.get(targetFieldName);

                ProbabilityDistribution nodeMap = (ProbabilityDistribution)targetFieldValue;
                Object result = nodeMap.getResult();
                if(String.valueOf(transToDouble(label)).equalsIgnoreCase(result.toString())){
                    sameDelta +=1;
                }else{
                    diffDelta +=1;
                }
            }
        }

        System.out.println("acc count:"+sameDelta);
        System.out.println("error count:"+diffDelta);
        System.out.println("acc rate:"+(sameDelta*1.0d/(sameDelta+diffDelta)));

    }

    /**
     * 从文件中读取pmml模型文件
     * @param file
     * @return
     * @throws Exception
     */
    public static PMML readPMML(File file) throws Exception {


        String pmmlString = new Scanner(file).useDelimiter("\\Z").next();
        InputStream is = new ByteArrayInputStream(pmmlString.getBytes());
        InputSource source = new InputSource(is);
        SAXSource transformedSource = ImportFilter.apply(source);

        return JAXBUtil.unmarshalPMML(transformedSource);
    }

    /**
     * 构造模型输入特征字段
     * @param splits
     * @param inputFields
     * @return
     */
    public static Map<FieldName, FieldValue> readArgumentsFromLine(String[] splits, List<InputField> inputFields) {

        List<Double> lists = new ArrayList<Double>();
        lists.add(Double.valueOf(splits[3]));
        lists.add(Double.valueOf(splits[4]));
        lists.add(Double.valueOf(splits[5]));
        lists.add(Double.valueOf(splits[7]));
        lists.add(Double.valueOf(splits[8]));
        lists.add(Double.valueOf(splits[9]));
        lists.add(Double.valueOf(splits[10]));
        lists.add(Double.valueOf(splits[11]));

        Map<FieldName, FieldValue> arguments = new LinkedHashMap<FieldName, FieldValue>();

        int i = 0;
        for(InputField inputField : inputFields){
            FieldName inputFieldName = inputField.getName();
            Object rawValue = lists.get(i);
            FieldValue inputFieldValue = inputField.prepare(rawValue);

            arguments.put(inputFieldName, inputFieldValue);
            i+=1;
        }

        return arguments;
    }

    public static Double transToDouble(String label) {
        try {
            return Double.valueOf(label);
        }catch (Exception e){
            return Double.valueOf(0);
        }
    }
}

  val training = spark.read.format("libsvm").load(libsvmDataPath).toDF("label", "features")

  val vi = new VectorIndexer()
      .setInputCol("features")
      .setOutputCol("indexed")
      .setMaxCategories(693)

   val pca = new PCA()
      .setInputCol("features")
      .setOutputCol("pcaFeatures")
      .setK(3)

   val lr = new LogisticRegression()
      .setMaxIter(10)
      .setRegParam(0.3)
      .setElasticNetParam(0.8)
      .setProbabilityCol("myProbability")

    val pipeline = new Pipeline().setStages(Array(vi, pca, lr))

    val model = pipeline.fit(training)

    model.write.overwrite().save(modelSavePath)

    training.show(10)
    println("==========================")
    println("traing dataframe's schema is:  " + training.schema.mkString)
    println("==========================")
    val schema = training.schema
    val pmml = ConverterUtil.toPMML(schema, model)
    JAXBUtil.marshalPMML(pmml, new StreamResult(System.out))

+-----+--------------------+
|label|            features|
+-----+--------------------+
|  0.0|(692,[127,128,129...|
|  1.0|(692,[158,159,160...|
|  1.0|(692,[124,125,126...|
|  1.0|(692,[152,153,154...|
|  1.0|(692,[151,152,153...|
|  0.0|(692,[129,130,131...|
|  1.0|(692,[158,159,160...|
|  1.0|(692,[99,100,101,...|
|  0.0|(692,[154,155,156...|
|  0.0|(692,[127,128,129...|
+-----+--------------------+
only showing top 10 rows

==========================
traing dataframe's schema is: 	
StructField(label,DoubleType,true)StructField(features,org.apache.spark.ml.linalg.VectorUDT@3bfc3ba7,true)
==========================
Exception in thread "main" java.lang.IllegalArgumentException: Expected string, integral, double or boolean type, got vector type
	at org.jpmml.sparkml.SparkMLEncoder.createDataField(SparkMLEncoder.java:160)
	at org.jpmml.sparkml.SparkMLEncoder.getFeatures(SparkMLEncoder.java:73)
	at org.jpmml.sparkml.feature.VectorIndexerModelConverter.encodeFeatures(VectorIndexerModelConverter.java:56)
	at org.jpmml.sparkml.FeatureConverter.registerFeatures(FeatureConverter.java:47)
	at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:75)
	at com.myhexin.oryx.batchlayer.TestPMML$.trainModel(TestPMML.scala:138)
	at com.myhexin.oryx.batchlayer.TestPMML$.main(TestPMML.scala:29)
	at com.myhexin.oryx.batchlayer.TestPMML.main(TestPMML.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:743)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:187)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:212)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:126)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

Traceback (most recent call last):
  File "setup.py", line 3, in <module>
    from jpmml_sparkml import __license__, __version__
  File "/home/bluedata/jpmml-sparkml-package/target/egg-sources/jpmml_sparkml/__init__.py", line 4, in <module>
    from pyspark.ml.common import _py2java
  File "/usr/lib/spark/spark-2.1.1-bin-hadoop2.7/python/pyspark/ml/__init__.py", line 22, in <module>
    from pyspark.ml.base import Estimator, Model, Transformer
  File "/usr/lib/spark/spark-2.1.1-bin-hadoop2.7/python/pyspark/ml/base.py", line 21, in <module>
    from pyspark.ml.param import Params
  File "/usr/lib/spark/spark-2.1.1-bin-hadoop2.7/python/pyspark/ml/param/__init__.py", line 26, in <module>
    import numpy as np
  File "/usr/lib64/python3.4/site-packages/numpy/__init__.py", line 142, in <module>
    from . import add_newdocs
  File "/usr/lib64/python3.4/site-packages/numpy/add_newdocs.py", line 13, in <module>
    from numpy.lib import add_newdoc
  File "/usr/lib64/python3.4/site-packages/numpy/lib/__init__.py", line 8, in <module>
    from .type_check import *
  File "/usr/lib64/python3.4/site-packages/numpy/lib/type_check.py", line 11, in <module>
    import numpy.core.numeric as _nx
  File "/usr/lib64/python3.4/site-packages/numpy/core/__init__.py", line 26, in <module>
    raise ImportError(msg)
ImportError:
Importing the multiarray numpy extension module failed.  Most
likely you are trying to import a failed build of numpy.
If you're working with a numpy git repo, try `git clean -xdf` (removes all
files not under version control).  Otherwise reinstall numpy.

Original error was: **cannot import name multiarray**

[ERROR] Command execution failed.
org.apache.commons.exec.ExecuteException: Process exited with an error: 1 (Exit value: 1)
        at org.apache.commons.exec.DefaultExecutor.executeInternal(DefaultExecutor.java:404)
        at org.apache.commons.exec.DefaultExecutor.execute(DefaultExecutor.java:166)
        at org.codehaus.mojo.exec.ExecMojo.executeCommandLine(ExecMojo.java:764)
        at org.codehaus.mojo.exec.ExecMojo.executeCommandLine(ExecMojo.java:711)
        at org.codehaus.mojo.exec.ExecMojo.execute(ExecMojo.java:289)
        at org.apache.maven.plugin.DefaultBuildPluginManager.executeMojo(DefaultBuildPluginManager.java:134)
        at org.apache.maven.lifecycle.internal.MojoExecutor.execute(MojoExecutor.java:208)
        at org.apache.maven.lifecycle.internal.MojoExecutor.execute(MojoExecutor.java:154)
        at org.apache.maven.lifecycle.internal.MojoExecutor.execute(MojoExecutor.java:146)
        at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject(LifecycleModuleBuilder.java:117)
        at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject(LifecycleModuleBuilder.java:81)
        at org.apache.maven.lifecycle.internal.builder.singlethreaded.SingleThreadedBuilder.build(SingleThreadedBuilder.jav
        at org.apache.maven.lifecycle.internal.LifecycleStarter.execute(LifecycleStarter.java:128)
        at org.apache.maven.DefaultMaven.doExecute(DefaultMaven.java:309)
        at org.apache.maven.DefaultMaven.doExecute(DefaultMaven.java:194)
        at org.apache.maven.DefaultMaven.execute(DefaultMaven.java:107)
        at org.apache.maven.cli.MavenCli.execute(MavenCli.java:993)
        at org.apache.maven.cli.MavenCli.doMain(MavenCli.java:345)
        at org.apache.maven.cli.MavenCli.main(MavenCli.java:191)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:497)
        at org.codehaus.plexus.classworlds.launcher.Launcher.launchEnhanced(Launcher.java:289)
        at org.codehaus.plexus.classworlds.launcher.Launcher.launch(Launcher.java:229)
        at org.codehaus.plexus.classworlds.launcher.Launcher.mainWithExitCode(Launcher.java:415)
        at org.codehaus.plexus.classworlds.launcher.Launcher.main(Launcher.java:356)

from jpmml_sparkml import toPMMLBytes
pmmlBytes = toPMMLBytes(sc, vectorized_CV_data, CV_model)
print(pmmlBytes.decode("UTF-8"))

import org.jpmml.sparkml.ConverterUtil

.... all of  the code to create the pipeline

val sparkPipelinePMMLEstimator = new Pipeline().setStages( categoricalFeatureIndexers.union(categoricalFeatureOneHotEncoders.union(Seq(featureAssemblerLr, featureAssemblerRf) )) :+ randomForest)

val sparkPipelinePMML = sparkPipelinePMMLEstimator.fit(df)
val pmmlBytes = org.jpmml.sparkml.ConverterUtil.toPMMLByteArray(df.schema, sparkPipelinePMML)

scala> val pmmlBytes = org.jpmml.sparkml.ConverterUtil.toPMMLByteArray(df.schema, sparkPipelinePMML)
java.lang.NoClassDefFoundError: org/dmg/pmml/mining/MiningModel
  ... 48 elided
Caused by: java.lang.ClassNotFoundException: org.dmg.pmml.mining.MiningModel
  at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
  at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
  at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
  ... 48 more

[INFO] Error stacktraces are turned on.
[INFO] Scanning for projects...
[INFO] 
[INFO] ------------------------------------------------------------------------
[INFO] Building JPMML-SparkML 1.2.7
[INFO] ------------------------------------------------------------------------
[INFO] 
[INFO] --- maven-clean-plugin:2.5:clean (default-clean) @ jpmml-sparkml ---
[INFO] Deleting /home/delhivery/dev/jpmml-sparkml/target
[INFO] 
[INFO] --- maven-enforcer-plugin:1.4.1:enforce (enforce-maven) @ jpmml-sparkml ---
[INFO] 
[INFO] --- maven-enforcer-plugin:1.4.1:enforce (default) @ jpmml-sparkml ---
[INFO] 
[INFO] --- jacoco-maven-plugin:0.7.9:prepare-agent (pre-unit-test) @ jpmml-sparkml ---
[INFO] jacoco.agent set to -javaagent:/home/delhivery/.m2/repository/org/jacoco/org.jacoco.agent/0.7.9/org.jacoco.agent-0.7.9-runtime.jar=destfile=/home/delhivery/dev/jpmml-sparkml/target/jacoco.exec
[INFO] 
[INFO] --- maven-resources-plugin:2.6:resources (default-resources) @ jpmml-sparkml ---
[INFO] Using 'UTF-8' encoding to copy filtered resources.
[INFO] Copying 1 resource
[INFO] 
[INFO] --- maven-compiler-plugin:3.5.1:compile (default-compile) @ jpmml-sparkml ---
[INFO] Changes detected - recompiling the module!
[INFO] Compiling 53 source files to /home/delhivery/dev/jpmml-sparkml/target/classes
[INFO] /home/delhivery/dev/jpmml-sparkml/src/main/java/org/jpmml/sparkml/WeightedTermFeature.java: Some input files use or override a deprecated API.
[INFO] /home/delhivery/dev/jpmml-sparkml/src/main/java/org/jpmml/sparkml/WeightedTermFeature.java: Recompile with -Xlint:deprecation for details.
[INFO] /home/delhivery/dev/jpmml-sparkml/src/main/java/org/jpmml/sparkml/ConverterUtil.java: /home/delhivery/dev/jpmml-sparkml/src/main/java/org/jpmml/sparkml/ConverterUtil.java uses unchecked or unsafe operations.
[INFO] /home/delhivery/dev/jpmml-sparkml/src/main/java/org/jpmml/sparkml/ConverterUtil.java: Recompile with -Xlint:unchecked for details.
[INFO] 
[INFO] --- maven-resources-plugin:2.6:testResources (default-testResources) @ jpmml-sparkml ---
[INFO] Using 'UTF-8' encoding to copy filtered resources.
[INFO] Copying 62 resources
[INFO] 
[INFO] --- maven-compiler-plugin:3.5.1:testCompile (default-testCompile) @ jpmml-sparkml ---
[INFO] Changes detected - recompiling the module!
[INFO] Compiling 5 source files to /home/delhivery/dev/jpmml-sparkml/target/test-classes
[INFO] 
[INFO] --- maven-surefire-plugin:2.19.1:test (default-test) @ jpmml-sparkml ---
[INFO] Surefire report directory: /home/delhivery/dev/jpmml-sparkml/target/surefire-reports

-------------------------------------------------------
 T E S T S
-------------------------------------------------------
Exception in thread "main" java.lang.reflect.InvocationTargetException
	at java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.base/java.lang.reflect.Method.invoke(Method.java:564)
	at java.instrument/sun.instrument.InstrumentationImpl.loadClassAndStartAgent(InstrumentationImpl.java:510)
	at java.instrument/sun.instrument.InstrumentationImpl.loadClassAndCallPremain(InstrumentationImpl.java:522)
Caused by: java.lang.RuntimeException: Class java/util/UUID could not be instrumented.
	at org.jacoco.agent.rt.internal_8ff85ea.core.runtime.ModifiedSystemClassRuntime.createFor(ModifiedSystemClassRuntime.java:140)
	at org.jacoco.agent.rt.internal_8ff85ea.core.runtime.ModifiedSystemClassRuntime.createFor(ModifiedSystemClassRuntime.java:101)
FATAL ERROR in native method: processing of -javaagent failed
	at org.jacoco.agent.rt.internal_8ff85ea.PreMain.createRuntime(PreMain.java:55)
	at org.jacoco.agent.rt.internal_8ff85ea.PreMain.premain(PreMain.java:47)
	... 6 more
Caused by: java.lang.NoSuchFieldException: $jacocoAccess
	at java.base/java.lang.Class.getField(Class.java:1958)
	at org.jacoco.agent.rt.internal_8ff85ea.core.runtime.ModifiedSystemClassRuntime.createFor(ModifiedSystemClassRuntime.java:138)
	... 9 more
Aborted (core dumped)

Results :

Tests run: 0, Failures: 0, Errors: 0, Skipped: 0

[INFO] ------------------------------------------------------------------------
[INFO] BUILD FAILURE
[INFO] ------------------------------------------------------------------------
[INFO] Total time: 8.266 s
[INFO] Finished at: 2018-05-23T16:26:03+05:30
[INFO] Final Memory: 79M/270M
[INFO] ------------------------------------------------------------------------
[ERROR] Failed to execute goal org.apache.maven.plugins:maven-surefire-plugin:2.19.1:test (default-test) on project jpmml-sparkml: Execution default-test of goal org.apache.maven.plugins:maven-surefire-plugin:2.19.1:test failed: The forked VM terminated without properly saying goodbye. VM crash or System.exit called?
[ERROR] Command was /bin/sh -c cd /home/delhivery/dev/jpmml-sparkml && /usr/lib/jvm/java-11-openjdk-amd64/bin/java -javaagent:/home/delhivery/.m2/repository/org/jacoco/org.jacoco.agent/0.7.9/org.jacoco.agent-0.7.9-runtime.jar=destfile=/home/delhivery/dev/jpmml-sparkml/target/jacoco.exec -jar /home/delhivery/dev/jpmml-sparkml/target/surefire/surefirebooter236796039577445911.jar /home/delhivery/dev/jpmml-sparkml/target/surefire/surefire9119811316382229884tmp /home/delhivery/dev/jpmml-sparkml/target/surefire/surefire_010927105446816610308tmp
[ERROR] -> [Help 1]
org.apache.maven.lifecycle.LifecycleExecutionException: Failed to execute goal org.apache.maven.plugins:maven-surefire-plugin:2.19.1:test (default-test) on project jpmml-sparkml: Execution default-test of goal org.apache.maven.plugins:maven-surefire-plugin:2.19.1:test failed: The forked VM terminated without properly saying goodbye. VM crash or System.exit called?
Command was /bin/sh -c cd /home/delhivery/dev/jpmml-sparkml && /usr/lib/jvm/java-11-openjdk-amd64/bin/java -javaagent:/home/delhivery/.m2/repository/org/jacoco/org.jacoco.agent/0.7.9/org.jacoco.agent-0.7.9-runtime.jar=destfile=/home/delhivery/dev/jpmml-sparkml/target/jacoco.exec -jar /home/delhivery/dev/jpmml-sparkml/target/surefire/surefirebooter236796039577445911.jar /home/delhivery/dev/jpmml-sparkml/target/surefire/surefire9119811316382229884tmp /home/delhivery/dev/jpmml-sparkml/target/surefire/surefire_010927105446816610308tmp
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:213)
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:154)
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:146)
    at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject (LifecycleModuleBuilder.java:117)
    at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject (LifecycleModuleBuilder.java:81)
    at org.apache.maven.lifecycle.internal.builder.singlethreaded.SingleThreadedBuilder.build (SingleThreadedBuilder.java:51)
    at org.apache.maven.lifecycle.internal.LifecycleStarter.execute (LifecycleStarter.java:128)
    at org.apache.maven.DefaultMaven.doExecute (DefaultMaven.java:309)
    at org.apache.maven.DefaultMaven.doExecute (DefaultMaven.java:194)
    at org.apache.maven.DefaultMaven.execute (DefaultMaven.java:107)
    at org.apache.maven.cli.MavenCli.execute (MavenCli.java:955)
    at org.apache.maven.cli.MavenCli.doMain (MavenCli.java:290)
    at org.apache.maven.cli.MavenCli.main (MavenCli.java:194)
    at jdk.internal.reflect.NativeMethodAccessorImpl.invoke0 (Native Method)
    at jdk.internal.reflect.NativeMethodAccessorImpl.invoke (NativeMethodAccessorImpl.java:62)
    at jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke (DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke (Method.java:564)
    at org.codehaus.plexus.classworlds.launcher.Launcher.launchEnhanced (Launcher.java:289)
    at org.codehaus.plexus.classworlds.launcher.Launcher.launch (Launcher.java:229)
    at org.codehaus.plexus.classworlds.launcher.Launcher.mainWithExitCode (Launcher.java:415)
    at org.codehaus.plexus.classworlds.launcher.Launcher.main (Launcher.java:356)
Caused by: org.apache.maven.plugin.PluginExecutionException: Execution default-test of goal org.apache.maven.plugins:maven-surefire-plugin:2.19.1:test failed: The forked VM terminated without properly saying goodbye. VM crash or System.exit called?
Command was /bin/sh -c cd /home/delhivery/dev/jpmml-sparkml && /usr/lib/jvm/java-11-openjdk-amd64/bin/java -javaagent:/home/delhivery/.m2/repository/org/jacoco/org.jacoco.agent/0.7.9/org.jacoco.agent-0.7.9-runtime.jar=destfile=/home/delhivery/dev/jpmml-sparkml/target/jacoco.exec -jar /home/delhivery/dev/jpmml-sparkml/target/surefire/surefirebooter236796039577445911.jar /home/delhivery/dev/jpmml-sparkml/target/surefire/surefire9119811316382229884tmp /home/delhivery/dev/jpmml-sparkml/target/surefire/surefire_010927105446816610308tmp
    at org.apache.maven.plugin.DefaultBuildPluginManager.executeMojo (DefaultBuildPluginManager.java:145)
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:208)
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:154)
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:146)
    at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject (LifecycleModuleBuilder.java:117)
    at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject (LifecycleModuleBuilder.java:81)
    at org.apache.maven.lifecycle.internal.builder.singlethreaded.SingleThreadedBuilder.build (SingleThreadedBuilder.java:51)
    at org.apache.maven.lifecycle.internal.LifecycleStarter.execute (LifecycleStarter.java:128)
    at org.apache.maven.DefaultMaven.doExecute (DefaultMaven.java:309)
    at org.apache.maven.DefaultMaven.doExecute (DefaultMaven.java:194)
    at org.apache.maven.DefaultMaven.execute (DefaultMaven.java:107)
    at org.apache.maven.cli.MavenCli.execute (MavenCli.java:955)
    at org.apache.maven.cli.MavenCli.doMain (MavenCli.java:290)
    at org.apache.maven.cli.MavenCli.main (MavenCli.java:194)
    at jdk.internal.reflect.NativeMethodAccessorImpl.invoke0 (Native Method)
    at jdk.internal.reflect.NativeMethodAccessorImpl.invoke (NativeMethodAccessorImpl.java:62)
    at jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke (DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke (Method.java:564)
    at org.codehaus.plexus.classworlds.launcher.Launcher.launchEnhanced (Launcher.java:289)
    at org.codehaus.plexus.classworlds.launcher.Launcher.launch (Launcher.java:229)
    at org.codehaus.plexus.classworlds.launcher.Launcher.mainWithExitCode (Launcher.java:415)
    at org.codehaus.plexus.classworlds.launcher.Launcher.main (Launcher.java:356)
Caused by: java.lang.RuntimeException: The forked VM terminated without properly saying goodbye. VM crash or System.exit called?
Command was /bin/sh -c cd /home/delhivery/dev/jpmml-sparkml && /usr/lib/jvm/java-11-openjdk-amd64/bin/java -javaagent:/home/delhivery/.m2/repository/org/jacoco/org.jacoco.agent/0.7.9/org.jacoco.agent-0.7.9-runtime.jar=destfile=/home/delhivery/dev/jpmml-sparkml/target/jacoco.exec -jar /home/delhivery/dev/jpmml-sparkml/target/surefire/surefirebooter236796039577445911.jar /home/delhivery/dev/jpmml-sparkml/target/surefire/surefire9119811316382229884tmp /home/delhivery/dev/jpmml-sparkml/target/surefire/surefire_010927105446816610308tmp
    at org.apache.maven.plugin.surefire.booterclient.ForkStarter.fork (ForkStarter.java:590)
    at org.apache.maven.plugin.surefire.booterclient.ForkStarter.fork (ForkStarter.java:460)
    at org.apache.maven.plugin.surefire.booterclient.ForkStarter.run (ForkStarter.java:229)
    at org.apache.maven.plugin.surefire.booterclient.ForkStarter.run (ForkStarter.java:201)
    at org.apache.maven.plugin.surefire.AbstractSurefireMojo.executeProvider (AbstractSurefireMojo.java:1026)
    at org.apache.maven.plugin.surefire.AbstractSurefireMojo.executeAfterPreconditionsChecked (AbstractSurefireMojo.java:862)
    at org.apache.maven.plugin.surefire.AbstractSurefireMojo.execute (AbstractSurefireMojo.java:755)
    at org.apache.maven.plugin.DefaultBuildPluginManager.executeMojo (DefaultBuildPluginManager.java:134)
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:208)
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:154)
    at org.apache.maven.lifecycle.internal.MojoExecutor.execute (MojoExecutor.java:146)
    at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject (LifecycleModuleBuilder.java:117)
    at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject (LifecycleModuleBuilder.java:81)
    at org.apache.maven.lifecycle.internal.builder.singlethreaded.SingleThreadedBuilder.build (SingleThreadedBuilder.java:51)
    at org.apache.maven.lifecycle.internal.LifecycleStarter.execute (LifecycleStarter.java:128)
    at org.apache.maven.DefaultMaven.doExecute (DefaultMaven.java:309)
    at org.apache.maven.DefaultMaven.doExecute (DefaultMaven.java:194)
    at org.apache.maven.DefaultMaven.execute (DefaultMaven.java:107)
    at org.apache.maven.cli.MavenCli.execute (MavenCli.java:955)
    at org.apache.maven.cli.MavenCli.doMain (MavenCli.java:290)
    at org.apache.maven.cli.MavenCli.main (MavenCli.java:194)
    at jdk.internal.reflect.NativeMethodAccessorImpl.invoke0 (Native Method)
    at jdk.internal.reflect.NativeMethodAccessorImpl.invoke (NativeMethodAccessorImpl.java:62)
    at jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke (DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke (Method.java:564)
    at org.codehaus.plexus.classworlds.launcher.Launcher.launchEnhanced (Launcher.java:289)
    at org.codehaus.plexus.classworlds.launcher.Launcher.launch (Launcher.java:229)
    at org.codehaus.plexus.classworlds.launcher.Launcher.mainWithExitCode (Launcher.java:415)
    at org.codehaus.plexus.classworlds.launcher.Launcher.main (Launcher.java:356)
[ERROR] 
[ERROR] Re-run Maven using the -X switch to enable full debug logging.
[ERROR] 
[ERROR] For more information about the errors and possible solutions, please read the following articles:
[ERROR] [Help 1] http://cwiki.apache.org/confluence/display/MAVEN/PluginExecutionException

Exception in thread "main" java.lang.IllegalArgumentException: Expected a pipeline with one or more models, got a pipeline with zero models
	at com.netease.mail.yanxuan.rms.utils.ConverterUtil.toPMML(ConverterUtil.java:118)
	at com.netease.mail.yanxuan.rms.scala.nn.feature.FeatureModelExport$.main(FeatureModelExport.scala:29)
	at com.netease.mail.yanxuan.rms.scala.nn.feature.FeatureModelExport.main(FeatureModelExport.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:755)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

val sourceData = session.read.format("myformat").
  load(DataFileURL)

val assembler = new VectorAssembler()
  .setInputCols(Array("X1", "X2", "X3"))
  .setOutputCol("features")

val dt = new DecisionTreeRegressor()
  .setLabelCol("Y")
  .setFeaturesCol("features")
  .setImpurity("variance")
  .setMaxDepth(30)
  .setMaxBins(32)

val pipeline = new Pipeline().setStages(Array(assembler, dt))

val model = pipeline.fit(sourceData)

val pmml = ConverterUtil.toPMML(sourceData.schema, model)

DecisionTreeRegressionModel (uid=dtr_8e66c6f292fc) of depth 7 with 57 nodes
  If (feature 2 <= 20.0)
   If (feature 1 in {0.0,1.0})
    If (feature 1 in {1.0})
     If (feature 0 in {0.0})
      Predict: 309.38
     Else (feature 0 not in {0.0})
      Predict: 569.6666666666669
    Else (feature 1 not in {1.0})
     If (feature 0 in {0.0})
      Predict: 583.5585714285714
     Else (feature 0 not in {0.0})
      Predict: 591.8775
   Else (feature 1 not in {0.0,1.0})
    If (feature 0 in {1.0})
     Predict: 1882.7800000000002
    Else (feature 0 not in {1.0})
     Predict: 2435.3799999999997
  Else (feature 2 > 20.0)
   If (feature 1 in {0.0})
    If (feature 2 <= 22.0)
     If (feature 0 in {0.0})
      If (feature 2 <= 21.0)
       Predict: 160.80599999999998
      Else (feature 2 > 21.0)
       Predict: 418.02833333333336
     Else (feature 0 not in {0.0})
      If (feature 2 <= 21.0)
       Predict: 636.2533333333334
      Else (feature 2 > 21.0)
       Predict: 273.82000000000005
    Else (feature 2 > 22.0)
     If (feature 2 <= 24.0)
      If (feature 0 in {0.0})
       If (feature 2 <= 23.0)
        Predict: 196.11
       Else (feature 2 > 23.0)
        Predict: 214.44
      Else (feature 0 not in {0.0})
       Predict: 303.5300000000001
     Else (feature 2 > 24.0)
      Predict: 152.13000000000002
   Else (feature 1 not in {0.0})
    If (feature 2 <= 22.0)
     If (feature 1 in {2.0})
      If (feature 2 <= 21.0)
       If (feature 0 in {1.0})
        Predict: 238.91666666666666
       Else (feature 0 not in {1.0})
        Predict: 244.89999999999998
      Else (feature 2 > 21.0)
       Predict: 333.3599999999999
     Else (feature 1 not in {2.0})
      If (feature 2 <= 21.0)
       If (feature 0 in {0.0})
        Predict: 387.8825
       Else (feature 0 not in {0.0})
        Predict: 446.2525
      Else (feature 2 > 21.0)
       If (feature 0 in {1.0})
        Predict: 316.75
       Else (feature 0 not in {1.0})
        Predict: 402.85714285714283
    Else (feature 2 > 22.0)
     If (feature 2 <= 24.0)
      If (feature 0 in {0.0})
       If (feature 2 <= 23.0)
        Predict: 239.59000000000003
       Else (feature 2 > 23.0)
        If (feature 1 in {2.0})
         Predict: 541.51
        Else (feature 1 not in {2.0})
         Predict: 1087.8500000000001
      Else (feature 0 not in {0.0})
       If (feature 2 <= 23.0)
        If (feature 1 in {1.0})
         Predict: 842.3125000000001
        Else (feature 1 not in {1.0})
         Predict: 1059.3700000000003
       Else (feature 2 > 23.0)
        Predict: 384.6300000000001
     Else (feature 2 > 24.0)
      If (feature 1 in {1.0})
       Predict: 350.58000000000004
      Else (feature 1 not in {1.0})
       Predict: 477.96000000000004

+-----+-------+---+----+-------------+--------------+--------------------+--------------------+----------+
|label|country|  a|   b|country_index|      features|       rawPrediction|         probability|prediction|
+-----+-------+---+----+-------------+--------------+--------------------+--------------------+----------+
|  0.0|     FR|1.0|-0.2|          0.0|[0.0,1.0,-0.2]|[0.43756144584300...|[0.60767781895595...|       0.0|
|  1.0|     DE|0.9| 0.5|          1.0| [1.0,0.9,0.5]|[-0.7827870058785...|[0.31371953355157...|       1.0|
+-----+-------+---+----+-------------+--------------+--------------------+--------------------+----------+

Exception in thread "main" java.lang.UnsupportedOperationException
	at org.jpmml.converter.CategoricalFeature.toContinuousFeature(CategoricalFeature.java:63)
	at org.jpmml.converter.regression.RegressionModelUtil.createRegressionTable(RegressionModelUtil.java:232)
	at org.jpmml.converter.regression.RegressionModelUtil.createBinaryLogisticClassification(RegressionModelUtil.java:113)
	at org.jpmml.converter.regression.RegressionModelUtil.createBinaryLogisticClassification(RegressionModelUtil.java:87)
	at org.jpmml.sparkml.model.LogisticRegressionModelConverter.encodeModel(LogisticRegressionModelConverter.java:52)
	at org.jpmml.sparkml.model.LogisticRegressionModelConverter.encodeModel(LogisticRegressionModelConverter.java:39)
	at org.jpmml.sparkml.ModelConverter.registerModel(ModelConverter.java:165)
	at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:81)
	at com.vika.pmml.PmmlExample.run(PmmlExample.java:99)
	at com.vika.pmml.PmmlExample.main(PmmlExample.java:40)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at com.intellij.rt.execution.application.AppMain.main(AppMain.java:144)

Exception in thread "main" org.jpmml.evaluator.TypeCheckException: Expected DOUBLE, but got STRING (FR)
	at org.jpmml.evaluator.TypeUtil.toDouble(TypeUtil.java:617)
	at org.jpmml.evaluator.TypeUtil.cast(TypeUtil.java:424)
	at org.jpmml.evaluator.FieldValue.getValue(FieldValue.java:320)
	at org.jpmml.evaluator.FieldValue.asNumber(FieldValue.java:269)
	at org.jpmml.evaluator.RegressionModelEvaluator.evaluateRegressionTable(RegressionModelEvaluator.java:194)
	at org.jpmml.evaluator.RegressionModelEvaluator.evaluateClassification(RegressionModelEvaluator.java:146)
	at org.jpmml.evaluator.RegressionModelEvaluator.evaluate(RegressionModelEvaluator.java:70)
	at org.jpmml.evaluator.ModelEvaluator.evaluate(ModelEvaluator.java:346)

<PMML xmlns="http://www.dmg.org/PMML-4_2" version="4.2">
    <Header>
        <Application/>
        <Timestamp>2017-02-20T03:17:32Z</Timestamp>
    </Header>
    <DataDictionary>
        <DataField name="a3" optype="categorical" dataType="double">
            <Value value="-1.0"/>
            <Value value="1.0"/>
        </DataField>
        <DataField name="a1" optype="continuous" dataType="double"/>
        <DataField name="a2" optype="continuous" dataType="double"/>
        <DataField name="prediction" optype="categorical" dataType="double"/>
    </DataDictionary>
    <TreeModel functionName="classification" splitCharacteristic="binarySplit">
        <MiningSchema>
            <MiningField name="a3" usageType="target"/>
        </MiningSchema>
        <Output>
            <OutputField name="probability_-1.0" feature="probability" value="-1.0"/>
            <OutputField name="probability_1.0" feature="probability" value="1.0"/>
        </Output>
        <Node score="-1.0" recordCount="5300.0">
            <True/>
            <ScoreDistribution value="-1.0" recordCount="2924.0"/>
            <ScoreDistribution value="1.0" recordCount="2376.0"/>
        </Node>
    </TreeModel>
</PMML>

Exception in thread "main" java.lang.IllegalArgumentException: skip
	at org.jpmml.sparkml.feature.StringIndexerModelConverter.encodeFeatures(StringIndexerModelConverter.java:65)
	at org.jpmml.sparkml.FeatureConverter.registerFeatures(FeatureConverter.java:47)
	at org.jpmml.sparkml.PMMLBuilder.build(PMMLBuilder.java:114)
	at com.nubia.train.Ad_ctr_train$.main(Ad_ctr_train.scala:182)
	at com.nubia.train.Ad_ctr_train.main(Ad_ctr_train.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:745)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:187)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:212)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:126)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

scalaVersion := "2.10.6"

libraryDependencies ++= Seq(
  "org.apache.spark" % "spark-core_2.11" % "2.1.0" % "provided",
  "org.apache.spark" % "spark-sql_2.11" % "2.1.0",
  "org.apache.hbase" % "hbase-common" % "1.2.2",
  "org.apache.spark" % "spark-mllib_2.11" % "2.1.0",
  "org.jpmml" % "jpmml-sparkml" % "1.2.6"
)

excludeDependencies += "org.jpmml" % "pmml-model"

Exception in thread "main" java.lang.IllegalArgumentException: Field a1 has valid values [b, a]
	at org.jpmml.converter.PMMLEncoder.toCategorical(PMMLEncoder.java:189)
	at org.jpmml.sparkml.feature.VectorIndexerModelConverter.encodeFeatures(VectorIndexerModelConverter.java:98)
	at org.jpmml.sparkml.FeatureConverter.registerFeatures(FeatureConverter.java:48)
	at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:96)
	at org.jpmml.sparkml.ConverterUtil.toPMML(ConverterUtil.java:68)