广告数据集mapreduce实验（词频统计）

本实验是使用广告数据集，通过mapreduce获取购买者年龄人数分布

数据列分别为

//ad_id,xyz_campaign_id,age,gender,Impressions,Clicks,Total_Conversion,Approved_Conversion

//广告编号，广告类型，用户年龄，用户性别，出现次数，点击次数，询问人数，购买人数。

这里Approved_Conversion为购买产品个数，代码中首先判断是否了购买产品，然后对购买产品的人年龄进行词频统计。

数据集为：

（共一千余条，仅展示部分）

代码为

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.output.FileOutputFormat;

import java.io.IOException;

//购买人的年龄进行词频统计
public class AdAgeMapReduce {
    private static class MyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            //ad_id,age,gender,Impressions,Clicks,Total_Conversion,Approved_Conversion
            //708746,30-34,M,7350,1,2,
            if (key.get() != 0L) {
                String[] arr = value.toString().split(",");
                int length = arr.length - 1;
                if (arr[length].equals("1")) {
                    context.write(new Text(arr[2]), new IntWritable(1));
                }
            }
        }
    }

    private static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable intWritable : values) {
                sum += intWritable.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "ad");
        job.setJarByClass(AdAgeMapReduce.class);
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileSystem fileSystem = FileSystem.get(conf);
        if (args.length == 0) {
            args = new String[]{"D:\\input", "D:\\output"};#数据集储存在了D盘下的input中
        }
        Path outPath = new Path(args[1]);
        if (fileSystem.exists(outPath)) fileSystem.delete(outPath, true);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

结果为：