MarkovStateTransitionModel.java

/*
 * avenir: Predictive analytic based on Hadoop Map Reduce
 * Author: Pranab Ghosh
 * 
 * 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 storm.applications.model.fraud.prepare;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import storm.applications.util.data.Tuple;
import storm.applications.util.hadoop.Utility;

/**
 * Markov state transition probability matrix
 * @author pranab
 */
public class MarkovStateTransitionModel extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        Job job = new Job(getConf());
        String jobName = "Markov tate transition model";
        job.setJobName(jobName);

        job.setJarByClass(MarkovStateTransitionModel.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        Utility.setConfiguration(job.getConfiguration(), "avenir");
        job.setMapperClass(StateTransitionMapper.class);
        job.setReducerClass(StateTransitionReducer.class);
        job.setCombinerClass(StateTransitionCombiner.class);

        job.setMapOutputKeyClass(Tuple.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Text.class);

        job.setNumReduceTasks(job.getConfiguration().getInt("num.reducer", 1));

        int status =  job.waitForCompletion(true) ? 0 : 1;
        return status;
    }
    
    public static void main(String[] args) throws Exception {
        int exitCode = ToolRunner.run(new MarkovStateTransitionModel(), args);
        System.exit(exitCode);
    }
}