de.tudarmstadt.ukp.experiments.argumentation.sequence.evaluation.EvalHelper.java Source code

Introduction

Here is the source code for de.tudarmstadt.ukp.experiments.argumentation.sequence.evaluation.EvalHelper.java

Source

/*
 * Copyright 2016
 * Ubiquitous Knowledge Processing (UKP) Lab
 * Technische Universitt Darmstadt
 *
 * 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 de.tudarmstadt.ukp.experiments.argumentation.sequence.evaluation;

import de.tudarmstadt.ukp.dkpro.tc.svmhmm.util.ConfusionMatrix;
import org.apache.commons.csv.CSVFormat;
import org.apache.commons.csv.CSVParser;
import org.apache.commons.csv.CSVRecord;

import java.io.File;
import java.io.FileFilter;
import java.io.FileReader;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

/**
 * @author Ivan Habernal
 */
public class EvalHelper {
    public static final FileFilter DIRECTORY_FILTER = new FileFilter() {
        @Override
        public boolean accept(File pathname) {
            return pathname.isDirectory();
        }
    };

    public static File[] listSubFolders(File folder) {
        File[] subFolders = folder.listFiles(new FileFilter() {
            @Override
            public boolean accept(File pathname) {
                return pathname.isDirectory();
            }
        });

        if (subFolders.length == 0) {
            throw new IllegalStateException("No sub-folders found in " + folder.getAbsolutePath());
        }

        return subFolders;
    }

    public static Map<String, File> listSubFoldersAndRemoveUUID(File methodFolder) {
        File[] subFolders = listSubFolders(methodFolder);

        Map<String, File> result = new HashMap<>();

        for (File subFolder : subFolders) {
            String name = removeUUID(subFolder.getName());

            result.put(name, subFolder);
        }

        return result;
    }

    public static String removeUUID(String name) {
        return name.replaceAll("-(\\w{8}(-\\w{4}){3}-\\w{12}?)", "");
    }

    /**
     * Reads predicted and gold data from predictions CSV file and fills&returns the confusion matrix
     *
     * @param csvPredictions predictions (gold; predicted)
     * @return matrix
     */
    public static ConfusionMatrix createConfusionMatrixFromCSVPredictions(File csvPredictions) throws IOException {
        CSVParser csvParser = new CSVParser(new FileReader(csvPredictions),
                CSVFormat.DEFAULT.withCommentMarker('#'));

        ConfusionMatrix result = new ConfusionMatrix();

        for (CSVRecord csvRecord : csvParser) {
            // copy record
            // update confusion matrix
            result.increaseValue(csvRecord.get(0), csvRecord.get(1));
        }

        return result;
    }

    /**
     * Reads predicted and gold data from predictions CSV file and fills&returns the confusion matrix
     *
     * @param csvPredictions predictions (gold; predicted)
     * @return matrix
     */
    // needs to be updated to the new implementation
    /*
    public static ConfusionMatrix createProbabilisticConfusionMatrixFromCSVPredictions(
        File csvPredictions)
        throws IOException
    {
    CSVParser csvParser = new CSVParser(new FileReader(csvPredictions),
            CSVFormat.DEFAULT.withCommentMarker('#'));
        
    ConfusionMatrix result = new ConfusionMatrix();
        
    Set<String> categories = new TreeSet<>();
        
    for (CSVRecord csvRecord : csvParser) {
        categories.add(csvRecord.get(0));
        categories.add(csvRecord.get(1));
    }
        
    ConfusionMatrix pcm = new ConfusionMatrix(
            categories.toArray(new String[categories.size()]));
        
    csvParser = new CSVParser(new FileReader(csvPredictions),
            CSVFormat.DEFAULT.withCommentMarker('#'));
        
    for (CSVRecord csvRecord : csvParser) {
        pcm.inc(csvRecord.get(0), csvRecord.get(1));
    }
        
    return pcm;
    }
    */

}