package org.apache.mahout.classifier.bayes;

import java.io.File;
import java.io.FilenameFilter;
import java.io.IOException;
import java.nio.charset.Charset;
import java.util.Arrays;
import java.util.List;
import java.util.Map;

import org.apache.commons.cli2.CommandLine;
import org.apache.commons.cli2.Group;
import org.apache.commons.cli2.Option;
import org.apache.commons.cli2.OptionException;
import org.apache.commons.cli2.builder.ArgumentBuilder;
import org.apache.commons.cli2.builder.DefaultOptionBuilder;
import org.apache.commons.cli2.builder.GroupBuilder;
import org.apache.commons.cli2.commandline.Parser;
import org.apache.mahout.classifier.ClassifierResult;
import org.apache.mahout.classifier.ResultAnalyzer;
import org.apache.mahout.classifier.bayes.algorithm.BayesAlgorithm;
import org.apache.mahout.classifier.bayes.algorithm.CBayesAlgorithm;
import org.apache.mahout.classifier.bayes.common.BayesParameters;
import org.apache.mahout.classifier.bayes.datastore.HBaseBayesDatastore;
import org.apache.mahout.classifier.bayes.datastore.InMemoryBayesDatastore;
import org.apache.mahout.classifier.bayes.exceptions.InvalidDatastoreException;
import org.apache.mahout.classifier.bayes.interfaces.Algorithm;
import org.apache.mahout.classifier.bayes.interfaces.Datastore;
import org.apache.mahout.classifier.bayes.mapreduce.bayes.BayesClassifierDriver;
import org.apache.mahout.classifier.bayes.model.ClassifierContext;
import org.apache.mahout.common.CommandLineUtil;
import org.apache.mahout.common.FileLineIterable;
import org.apache.mahout.common.HadoopUtil;
import org.apache.mahout.common.TimingStatistics;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
import org.apache.mahout.common.nlp.NGrams;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
* Test the Naive Bayes classifier with improved weighting
* <p/>
* To run the twenty newsgroups example: refer
http://cwiki.apache.org/MAHOUT/twentynewsgroups.html
*/
public final class SinglyClassifier2 {
    private static ClassifierContext classifier;
    private static final Logger log =
        LoggerFactory.getLogger(SinglyClassifier2.class);
    Algorithm algorithm;
    Datastore datastore;

    /**
     * main method
     */
    public static void main(String[] args) throws Exception {
        String[] doc = {"mspublisher", "parallax", "polaroid", "corel", "illustrator", "coreldraw"};
        SinglyClassifier2 sc = new SinglyClassifier2();

        List<ClassifierResult> results = sc.classifyDocument(doc, "comp.graphics", 47);
        System.out.println(results);

//        System.err.println("keys: "+sc.datastore.getKeys("weight"));
//        double weight = sc.datastore.getWeight("weight", "味噌_名詞", "愛知県");
//        System.err.println("weight: "+weight);
    }

    /**
     * constructor
     */
    public SinglyClassifier2() throws Exception {

        BayesParameters params = new BayesParameters();
        params.setGramSize(1);
        params.set("basePath", "/user/toracluster/scope/run_24/model");
        params.set("classifierType", "cbayes");
        params.set("dataSource", "hdfs");
        params.set("defaultCat", "comp.graphics");
        params.set("encoding", "UTF-8");
        params.set("alpha_i", "1.0");
        params.setMinDF(1);
        params.set("verbose", "true");

        log.info("Loading model from: {}", params.print());
        boolean verbose = Boolean.valueOf(params.get("verbose"));

        if (params.get("dataSource").equals("hdfs")) {
            if (params.get("classifierType").equalsIgnoreCase("bayes")) {
                log.info("Testing Bayes Classifier");
                algorithm = new BayesAlgorithm();
                datastore = new InMemoryBayesDatastore(params);
            } else if (params.get("classifierType").equalsIgnoreCase("cbayes")) {
                log.info("Testing Complementary Bayes Classifier");
                algorithm = new CBayesAlgorithm();
                datastore = new InMemoryBayesDatastore(params);
            } else {
                throw new IllegalArgumentException("Unrecognized classifier type: " + params.get("classifierType"));
            }

        } else if (params.get("dataSource").equals("hbase")) {
            if (params.get("classifierType").equalsIgnoreCase("bayes")) {
                log.info("Testing Bayes Classifier");
                algorithm = new BayesAlgorithm();
                datastore = new HBaseBayesDatastore(params.get("basePath"), params);
            } else if (params.get("classifierType").equalsIgnoreCase("cbayes")) {
                log.info("Testing Complementary Bayes Classifier");
                algorithm = new CBayesAlgorithm();
                datastore = new HBaseBayesDatastore(params.get("basePath"), params);
            } else {
                throw new IllegalArgumentException("Unrecognized classifier type: " + params.get("classifierType"));
            }

        } else {
            throw new IllegalArgumentException("Unrecognized dataSource type: " + params.get("dataSource"));
        }
        classifier = new ClassifierContext(algorithm, datastore);
        //classifier.initialize();
        datastore.initialize();
    }

    /**
     *
     */
    public List<ClassifierResult> classifyDocument(String[] doc, String defaultCategory, int numResults) throws InvalidDatastoreException {
        algorithm.initialize(datastore);
        ClassifierResult[] results = classifier.classifyDocument(doc, defaultCategory, numResults);
        return Arrays.asList(results);
    }
}