crimesbyweekdayyear.CrimesByWeekDayYear.java Source code

Introduction

Here is the source code for crimesbyweekdayyear.CrimesByWeekDayYear.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
package crimesbyweekdayyear;

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 *
 * @author Sattya
 */
public class CrimesByWeekDayYear extends Configured implements Tool {

    public static class MapClass extends MapReduceBase implements Mapper<Text, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Text key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            String line = key.toString();
            if (line != null) {
                String[] cols = line.split(",");
                try {
                    String date[] = cols[2].split(" ");
                    String firstDate = date[0];
                    SimpleDateFormat myFormat = new SimpleDateFormat("MM/dd/yy");
                    Date fdate = myFormat.parse(firstDate);
                    String day[] = fdate.toString().split(" ");
                    word.set(day[0] + "_" + cols[17]);
                    output.collect(word, one);
                } catch (Exception e) {
                    System.out.println("Bad row: " + e);
                }
            }
        }
    }

    public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {

        public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output,
                Reporter reporter) throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += ((IntWritable) values.next()).get();
            }
            output.collect(key, new IntWritable(sum));

        }

    }

    public int run(String[] args) throws Exception {
        Configuration conf = getConf();

        JobConf job = new JobConf(conf, CrimesByWeekDayYear.class);

        Path in = new Path(args[0]);
        Path out = new Path(args[1]);
        FileInputFormat.setInputPaths(job, in);
        FileOutputFormat.setOutputPath(job, out);

        job.setJobName("CrimesByWeekDayYear");
        job.setMapperClass(MapClass.class);
        job.setReducerClass(Reduce.class);

        job.setInputFormat(KeyValueTextInputFormat.class);
        job.setOutputFormat(TextOutputFormat.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //   job.set("key.value.separator.in.input.line", "");

        JobClient.runJob(job);

        return 0;
    }

    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(), new CrimesByWeekDayYear(), args);
        System.exit(res);
    }
}