org.jpmml.sparkml.feature.IndexToStringConverter Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of pmml-sparkml Show documentation

JPMML Apache Spark ML to PMML converter

The newest version!

/*
 * Copyright (c) 2016 Villu Ruusmann
 *
 * This file is part of JPMML-SparkML
 *
 * JPMML-SparkML is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * JPMML-SparkML is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with JPMML-SparkML.  If not, see .
 */
package org.jpmml.sparkml.feature;

import java.util.Arrays;
import java.util.Collections;
import java.util.List;

import org.apache.spark.ml.feature.IndexToString;
import org.dmg.pmml.DataField;
import org.dmg.pmml.DataType;
import org.dmg.pmml.OpType;
import org.jpmml.converter.CategoricalFeature;
import org.jpmml.converter.Feature;
import org.jpmml.sparkml.FeatureConverter;
import org.jpmml.sparkml.SparkMLEncoder;

public class IndexToStringConverter extends FeatureConverter {

	public IndexToStringConverter(IndexToString transformer){
		super(transformer);
	}

	@Override
	public List encodeFeatures(SparkMLEncoder encoder){
		IndexToString transformer = getTransformer();

		DataField dataField = encoder.createDataField(formatName(transformer), OpType.CATEGORICAL, DataType.STRING, Arrays.asList(transformer.getLabels()));

		return Collections.singletonList(new CategoricalFeature(encoder, dataField));
	}
}