Package org.jpmml.sparkml.testing

Class SparkMLEncoderBatch

java.lang.Object

org.jpmml.evaluator.testing.ArchiveBatch

org.jpmml.converter.testing.ModelEncoderBatch

org.jpmml.sparkml.testing.SparkMLEncoderBatch

All Implemented Interfaces:

AutoCloseable, org.jpmml.evaluator.testing.Batch

public abstract class SparkMLEncoderBatch
extends org.jpmml.converter.testing.ModelEncoderBatch

Constructor Summary

Constructors

Constructor	Description
SparkMLEncoderBatch(String algorithm, String dataset, Predicate<org.jpmml.evaluator.ResultField> columnFilter, com.google.common.base.Equivalence<Object> equivalence)

Method Summary

Modifier and Type	Method	Description
abstract SparkMLEncoderBatchTest	getArchiveBatchTest()
List<Map<String,Object>>	getOptionsMatrix()
String	getPipelineModelZipPath()
org.dmg.pmml.PMML	getPMML()
String	getSchemaJsonPath()
org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	getVerificationDataset(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> inputDataset)
protected org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	loadInput(org.apache.spark.sql.SparkSession sparkSession, List<File> tmpResources)
protected org.apache.spark.ml.PipelineModel	loadPipelineModel(org.apache.spark.sql.SparkSession sparkSession, List<File> tmpResources)
protected org.apache.spark.sql.types.StructType	loadSchema(org.apache.spark.sql.SparkSession sparkSession, List<File> tmpResources)
protected static File	toTmpFile(InputStream is, String prefix, String suffix)
protected org.apache.spark.sql.types.StructType	updateSchema(org.apache.spark.sql.types.StructType schema, org.apache.spark.ml.PipelineModel pipelineModel)

Methods inherited from class org.jpmml.converter.testing.ModelEncoderBatch

getEvaluator, getEvaluatorBuilder, getOptions, getValidators, open, setOptions, truncate, validatePMML

Methods inherited from class org.jpmml.evaluator.testing.ArchiveBatch

close, createTableReader, getAlgorithm, getColumnFilter, getDataset, getEquivalence, getInput, getInputCsvPath, getOutput, getOutputCsvPath, getSeparator, loadRecords

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

SparkMLEncoderBatch

public SparkMLEncoderBatch(String algorithm,
                           String dataset,
                           Predicate<org.jpmml.evaluator.ResultField> columnFilter,
                           com.google.common.base.Equivalence<Object> equivalence)

Method Detail

getArchiveBatchTest

public abstract SparkMLEncoderBatchTest getArchiveBatchTest()

Specified by:

getArchiveBatchTest in class org.jpmml.converter.testing.ModelEncoderBatch

getOptionsMatrix

public List<Map<String,Object>> getOptionsMatrix()

Overrides:

getOptionsMatrix in class org.jpmml.converter.testing.ModelEncoderBatch

getPipelineModelZipPath

public String getPipelineModelZipPath()

getSchemaJsonPath

public String getSchemaJsonPath()

getVerificationDataset

public org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> getVerificationDataset(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> inputDataset)

getPMML

public org.dmg.pmml.PMML getPMML()
                          throws Exception

Specified by:

getPMML in class org.jpmml.converter.testing.ModelEncoderBatch

Throws:

Exception

loadSchema

protected org.apache.spark.sql.types.StructType loadSchema(org.apache.spark.sql.SparkSession sparkSession,
                                                           List<File> tmpResources)
                                                    throws IOException

Throws:

IOException

loadPipelineModel

protected org.apache.spark.ml.PipelineModel loadPipelineModel(org.apache.spark.sql.SparkSession sparkSession,
                                                              List<File> tmpResources)
                                                       throws IOException

Throws:

IOException

updateSchema

protected org.apache.spark.sql.types.StructType updateSchema(org.apache.spark.sql.types.StructType schema,
                                                             org.apache.spark.ml.PipelineModel pipelineModel)

loadInput

protected org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> loadInput(org.apache.spark.sql.SparkSession sparkSession,
                                                                           List<File> tmpResources)
                                                                    throws IOException

Throws:

IOException

toTmpFile

protected static File toTmpFile(InputStream is,
                                String prefix,
                                String suffix)
                         throws IOException

Throws:

IOException