#mapreduce #空值填充

package MapSort;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

import java.io.IOException;
import java.util.ArrayList;

public class MobileImpressionAnalysis {
    public static String inPath = "hdfs://node1:8020/in123";
    public static String outPath = "hdfs://node1:8020/out123";
    public static void main(String[] args) throws IOException,InterruptedException,ClassNotFoundException
    {
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://node1:8020/");
        Job job = Job.getInstance(configuration,MobileImpressionAnalysis.class.getSimpleName());

        job.setJarByClass(MobileImpressionAnalysis.class);
        job.setMapperClass(AvgMap.class);
        job.setReducerClass(AvgReduce.class);

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

        job.setNumReduceTasks(1);
        FileInputFormat.setInputPaths(job,new Path(inPath));
        FileSystem fs = FileSystem.get(configuration);
        Path output = new Path(outPath);
        if (fs.exists(output)){
            fs.delete(output);
        }
        FileOutputFormat.setOutputPath(job,output);
//        job.setInputFormatClass(TextInputFormat.class);
//        job.setOutputFormatClass(TextOutputFormat.class);

        job.waitForCompletion(true);
    }

}
class AvgMap extends Mapper<LongWritable,Text,Text,Text>
{
    @Override
    protected void map(LongWritable key,Text values,Context context) throws IOException,InterruptedException
    {
        String [] line = values.toString().split(",");
        String id = line[0];
        context.write(new Text(id),values);
    }
}
class AvgReduce extends Reducer<Text,Text,Text,NullWritable>
{
    private ArrayList<Text> records = new ArrayList<>();
    @Override
    protected void reduce(Text key, Iterable<Text> values,Context context)
            throws IOException,InterruptedException
    {
        for (Text value:values){
            records.add(new Text(value));
        }
    }
    @Override
    protected void cleanup(Context context) throws IOException,InterruptedException
    {
        double sum = 0;
        int count = 0;
        for (Text record:records){
            String [] line = record.toString().split(",");
            if(!line[2].isEmpty()){
                double voltage = Double.parseDouble(line[2]);
                sum += voltage;
                count++;
            }
        }
        double avg = count>0?sum/count:0;
        int printed=0;
        for (Text record:records){
            String [] line = record.toString().split(",");
            String volt = line[2].trim();
            if (volt.isEmpty()){
                line[2] = String.format("%.2f",avg);
            }
            String newrecord = String.join(",",line);
            if (printed<10){
                context.write(new Text(newrecord),NullWritable.get());
                printed++;
            } else {
                break;
            }

        }
    }
}