[SPARK-1406] Mllib pmml model export #3062
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,74 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package org.apache.spark.mllib.pmml | ||
|
|
||
| import java.io.{File, OutputStream, StringWriter} | ||
| import javax.xml.transform.stream.StreamResult | ||
|
|
||
| import org.jpmml.model.JAXBUtil | ||
|
|
||
| import org.apache.spark.SparkContext | ||
| import org.apache.spark.mllib.pmml.export.PMMLModelExportFactory | ||
|
|
||
| /** | ||
| * Export model to the PMML format | ||
| * Predictive Model Markup Language (PMML) is an XML-based file format | ||
| * developed by the Data Mining Group (www.dmg.org). | ||
| */ | ||
| trait PMMLExportable { | ||
|
|
||
| /** | ||
| * Export the model to the stream result in PMML format | ||
| */ | ||
| private def toPMML(streamResult: StreamResult): Unit = { | ||
| val pmmlModelExport = PMMLModelExportFactory.createPMMLModelExport(this) | ||
| JAXBUtil.marshalPMML(pmmlModelExport.getPmml, streamResult) | ||
| } | ||
|
|
||
| /** | ||
| * Export the model to a local file in PMML format | ||
| */ | ||
| def toPMML(localPath: String): Unit = { | ||
| toPMML(new StreamResult(new File(localPath))) | ||
| } | ||
|
|
||
| /** | ||
| * Export the model to a directory on a distributed file system in PMML format | ||
| */ | ||
| def toPMML(sc: SparkContext, path: String): Unit = { | ||
| val pmml = toPMML() | ||
| sc.parallelize(Array(pmml), 1).saveAsTextFile(path) | ||
| } | ||
|
|
||
| /** | ||
| * Export the model to the OutputStream in PMML format | ||
| */ | ||
| def toPMML(outputStream: OutputStream): Unit = { | ||
| toPMML(new StreamResult(outputStream)) | ||
| } | ||
|
|
||
| /** | ||
| * Export the model to a String in PMML format | ||
| */ | ||
| def toPMML(): String = { | ||
| val writer = new StringWriter | ||
| toPMML(new StreamResult(writer)) | ||
| writer.toString | ||
| } | ||
|
|
||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,89 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package org.apache.spark.mllib.pmml.export | ||
|
|
||
| import scala.{Array => SArray} | ||
|
|
||
| import org.dmg.pmml._ | ||
|
|
||
| import org.apache.spark.mllib.regression.GeneralizedLinearModel | ||
|
|
||
| /** | ||
| * PMML Model Export for GeneralizedLinearModel class with binary ClassificationModel | ||
| */ | ||
| private[mllib] class BinaryClassificationPMMLModelExport( | ||
| model : GeneralizedLinearModel, | ||
| description : String, | ||
| normalizationMethod : RegressionNormalizationMethodType, | ||
| threshold: Double) | ||
| extends PMMLModelExport { | ||
|
|
||
| populateBinaryClassificationPMML() | ||
|
|
||
| /** | ||
| * Export the input LogisticRegressionModel or SVMModel to PMML format. | ||
| */ | ||
| private def populateBinaryClassificationPMML(): Unit = { | ||
| pmml.getHeader.setDescription(description) | ||
|
|
||
| if (model.weights.size > 0) { | ||
| val fields = new SArray[FieldName](model.weights.size) | ||
| val dataDictionary = new DataDictionary | ||
| val miningSchema = new MiningSchema | ||
| val regressionTableYES = new RegressionTable(model.intercept).withTargetCategory("1") | ||
| var interceptNO = threshold | ||
| if (RegressionNormalizationMethodType.LOGIT == normalizationMethod) { | ||
| if (threshold <= 0) | ||
| interceptNO = -1000 | ||
| else if (threshold >= 1) | ||
| interceptNO = 1000 | ||
|
|
||
| else | ||
| interceptNO = -math.log(1/threshold -1) | ||
|
There was a problem hiding this comment. space around |
||
| } | ||
| val regressionTableNO = new RegressionTable(interceptNO).withTargetCategory("0") | ||
| val regressionModel = new RegressionModel() | ||
| .withFunctionName(MiningFunctionType.CLASSIFICATION) | ||
| .withMiningSchema(miningSchema) | ||
| .withModelName(description) | ||
| .withNormalizationMethod(normalizationMethod) | ||
| .withRegressionTables(regressionTableYES, regressionTableNO) | ||
|
|
||
| for (i <- 0 until model.weights.size) { | ||
| fields(i) = FieldName.create("field_" + i) | ||
| dataDictionary.withDataFields(new DataField(fields(i), OpType.CONTINUOUS, DataType.DOUBLE)) | ||
| miningSchema | ||
| .withMiningFields(new MiningField(fields(i)) | ||
| .withUsageType(FieldUsageType.ACTIVE)) | ||
| regressionTableYES.withNumericPredictors(new NumericPredictor(fields(i), model.weights(i))) | ||
| } | ||
|
|
||
| // add target field | ||
| val targetField = FieldName.create("target") | ||
| dataDictionary | ||
| .withDataFields(new DataField(targetField, OpType.CATEGORICAL, DataType.STRING)) | ||
| miningSchema | ||
| .withMiningFields(new MiningField(targetField) | ||
| .withUsageType(FieldUsageType.TARGET)) | ||
|
|
||
| dataDictionary.withNumberOfFields(dataDictionary.getDataFields.size) | ||
|
|
||
| pmml.setDataDictionary(dataDictionary) | ||
| pmml.withModels(regressionModel) | ||
| } | ||
| } | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,75 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package org.apache.spark.mllib.pmml.export | ||
|
|
||
| import scala.{Array => SArray} | ||
|
|
||
| import org.dmg.pmml._ | ||
|
|
||
| import org.apache.spark.mllib.regression.GeneralizedLinearModel | ||
|
|
||
| /** | ||
| * PMML Model Export for GeneralizedLinearModel abstract class | ||
| */ | ||
| private[mllib] class GeneralizedLinearPMMLModelExport( | ||
| model: GeneralizedLinearModel, | ||
| description: String) | ||
| extends PMMLModelExport { | ||
|
|
||
| populateGeneralizedLinearPMML(model) | ||
|
|
||
| /** | ||
| * Export the input GeneralizedLinearModel model to PMML format. | ||
| */ | ||
| private def populateGeneralizedLinearPMML(model: GeneralizedLinearModel): Unit = { | ||
| pmml.getHeader.setDescription(description) | ||
|
|
||
| if (model.weights.size > 0) { | ||
| val fields = new SArray[FieldName](model.weights.size) | ||
| val dataDictionary = new DataDictionary | ||
| val miningSchema = new MiningSchema | ||
| val regressionTable = new RegressionTable(model.intercept) | ||
| val regressionModel = new RegressionModel() | ||
| .withFunctionName(MiningFunctionType.REGRESSION) | ||
| .withMiningSchema(miningSchema) | ||
| .withModelName(description) | ||
| .withRegressionTables(regressionTable) | ||
|
|
||
| for (i <- 0 until model.weights.size) { | ||
| fields(i) = FieldName.create("field_" + i) | ||
| dataDictionary.withDataFields(new DataField(fields(i), OpType.CONTINUOUS, DataType.DOUBLE)) | ||
| miningSchema | ||
| .withMiningFields(new MiningField(fields(i)) | ||
| .withUsageType(FieldUsageType.ACTIVE)) | ||
| regressionTable.withNumericPredictors(new NumericPredictor(fields(i), model.weights(i))) | ||
| } | ||
|
|
||
| // for completeness add target field | ||
| val targetField = FieldName.create("target") | ||
| dataDictionary.withDataFields(new DataField(targetField, OpType.CONTINUOUS, DataType.DOUBLE)) | ||
| miningSchema | ||
| .withMiningFields(new MiningField(targetField) | ||
| .withUsageType(FieldUsageType.TARGET)) | ||
|
|
||
| dataDictionary.withNumberOfFields(dataDictionary.getDataFields.size) | ||
|
|
||
| pmml.setDataDictionary(dataDictionary) | ||
| pmml.withModels(regressionModel) | ||
| } | ||
| } | ||
| } |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should be
Double.MinValue.