DenseFeatureUDF.java

DenseFeatureUDF.java

/*
 * Hivemall: Hive scalable Machine Learning Library
 *
 * Copyright (C) 2015 Makoto YUI
 *
 * Licensed 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 hivemall.ftvec;

import hivemall.io.FeatureValue;

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

import javax.annotation.Nonnegative;

import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.hive.ql.udf.UDFType;
import org.apache.hadoop.io.FloatWritable;

@Description(name = "dense_feature", value = "_FUNC_(array<string> feature_vector, int dimensions)"
        + " - Returns a dense feature in array<float>")
@UDFType(deterministic = true, stateful = false)
public final class DenseFeatureUDF extends UDF {

    public List<FloatWritable> evaluate(List<String> features, @Nonnegative int dimensions) {
        if(features == null) {
            return null;
        }
        final FloatWritable[] fv = new FloatWritable[dimensions + 1];
        final FeatureValue probe = new FeatureValue();
        for(String ft : features) {
            FeatureValue.parseFeatureAsString(ft, probe);
            String f = probe.getFeature();
            int i = Integer.parseInt(f);
            float v = probe.getValue();
            fv[i] = new FloatWritable(v);
        }
        return Arrays.asList(fv);

    }

}