001/*
002 * Copyright (c) 2015-2020, Oracle and/or its affiliates. All rights reserved.
003 *
004 * Licensed under the Apache License, Version 2.0 (the "License");
005 * you may not use this file except in compliance with the License.
006 * You may obtain a copy of the License at
007 *
008 *     http://www.apache.org/licenses/LICENSE-2.0
009 *
010 * Unless required by applicable law or agreed to in writing, software
011 * distributed under the License is distributed on an "AS IS" BASIS,
012 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express implied.
013 * See the License for the specific language governing permissions and
014 * limitations under the License.
015 */
016
017package org.tribuo.data.text.impl;
018
019import com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance;
020import com.oracle.labs.mlrg.olcut.provenance.impl.ConfiguredObjectProvenanceImpl;
021import org.tribuo.Feature;
022import org.tribuo.data.text.FeatureAggregator;
023
024import java.util.ArrayList;
025import java.util.HashMap;
026import java.util.List;
027import java.util.Map;
028
029/**
030 * A feature aggregator that averages feature values across a feature list.
031 */
032public class AverageAggregator implements FeatureAggregator {
033
034    private final ThreadLocal<Map<String,Double>> map = ThreadLocal.withInitial(HashMap::new);
035    private final ThreadLocal<Map<String,Integer>> countMap = ThreadLocal.withInitial(HashMap::new);
036
037    @Override
038    public List<Feature> aggregate(List<Feature> input) {
039        Map<String,Double> curMap = map.get();
040        Map<String,Integer> curCountMap = countMap.get();
041        curMap.clear();
042        curCountMap.clear();
043
044        for (Feature f : input) {
045            double curValue = f.getValue();
046            curMap.merge(f.getName(),curValue,Double::sum);
047            curCountMap.merge(f.getName(),1,Integer::sum);
048        }
049
050        List<Feature> features = new ArrayList<>();
051
052        for (Map.Entry<String,Double> e : curMap.entrySet()) {
053            int count = curCountMap.get(e.getKey());
054            features.add(new Feature(e.getKey(),e.getValue()/count));
055        }
056
057        return features;
058    }
059
060    @Override
061    public ConfiguredObjectProvenance getProvenance() {
062        return new ConfiguredObjectProvenanceImpl(this,"FeatureAggregator");
063    }
064}