WikipediaPageviewTopicsAnnotator.java
/*******************************************************************************
* Copyright (C) 2020 Ram Sadasiv
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
******************************************************************************/
package io.outofprintmagazine.nlp.pipeline.annotators;
import java.io.IOException;
import java.math.BigDecimal;
import java.net.URISyntaxException;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;
import java.util.Set;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import edu.stanford.nlp.ling.CoreAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.Annotator;
import edu.stanford.nlp.pipeline.CoreDocument;
import edu.stanford.nlp.util.ArraySet;
import io.outofprintmagazine.nlp.pipeline.scorers.MapSum;
import io.outofprintmagazine.nlp.pipeline.scorers.IScorer;
import io.outofprintmagazine.nlp.pipeline.serializers.MapSerializer;
import io.outofprintmagazine.nlp.pipeline.serializers.ISerializer;
import io.outofprintmagazine.nlp.utils.WikipediaUtils;
public class WikipediaPageviewTopicsAnnotator extends AbstractPosAnnotator implements Annotator, IOOPAnnotator{
@SuppressWarnings("unused")
private static final Logger logger = LogManager.getLogger(WikipediaPageviewTopicsAnnotator.class);
@SuppressWarnings("unused")
private Logger getLogger() {
return logger;
}
public WikipediaPageviewTopicsAnnotator() {
super();
this.setScorer((IScorer)new MapSum(this.getAnnotationClass()));
this.setSerializer((ISerializer)new MapSerializer(this.getAnnotationClass()));
}
@Override
public Set<Class<? extends CoreAnnotation>> requires() {
return Collections.unmodifiableSet(
new ArraySet<>(
Arrays.asList(
CoreAnnotations.TextAnnotation.class,
CoreAnnotations.TokensAnnotation.class,
CoreAnnotations.SentencesAnnotation.class,
io.outofprintmagazine.nlp.pipeline.OOPAnnotations.OOPTopicsAnnotation.class
)
)
);
}
@Override
public Class getAnnotationClass() {
return io.outofprintmagazine.nlp.pipeline.OOPAnnotations.OOPWikipediaPageviewTopicsAnnotation.class;
}
protected Class getTopicsAnnotationClass() {
return io.outofprintmagazine.nlp.pipeline.OOPAnnotations.OOPTopicsAnnotation.class;
}
@Override
public void annotate(Annotation annotation) {
CoreDocument document = new CoreDocument(annotation);
if (!annotation.containsKey(io.outofprintmagazine.nlp.pipeline.OOPAnnotations.OOPTopicsAnnotation.class)) {
logger.error("requires() not satisfied");
}
Map<String,BigDecimal> topics = (Map<String, BigDecimal>) document.annotation().get(getTopicsAnnotationClass());
Map<String,BigDecimal> scoreMap = new HashMap<String,BigDecimal>();
for (String topic : topics.keySet()) {
try {
addToScoreMap(scoreMap, topic, WikipediaUtils.getInstance(getParameterStore()).getWikipediaPageviewsForTopic(topic).multiply(topics.get(topic)));
}
catch (IOException | URISyntaxException e) {
logger.error(e);
}
}
document.annotation().set(getAnnotationClass(), scoreMap);
}
@Override
public String getDescription() {
return "Wikipedia pageviews for the past month "
+ "(https://wikimedia.org/api/rest_v1/metrics/pageviews/per-article/en.wikipedia.org/all-access/all-agents/Shakespeare) "
+ "for Topics (NNP,NNPS).";
}
}