标签：ted exit err tostring orm col get table oca
实验内容：
现有某电商网站用户对商品的收藏数据，记录了用户收藏的商品id以及收藏日期，名为buyer_favorite1。
buyer_favorite1包含：买家id，商品id，收藏日期这三个字段，数据以“\t”分割，样本数据及格式如下：
要求编写MapReduce程序，统计每个买家收藏商品数量。
统计结果数据如下：
代码：
1 package mapreduce; 2 import java.io.IOException; 3 4 import java.util.StringTokenizer; 5 import org.apache.hadoop.fs.Path; 6 import org.apache.hadoop.io.IntWritable; 7 import org.apache.hadoop.io.Text; 8 import org.apache.hadoop.mapreduce.Job; 9 import org.apache.hadoop.mapreduce.Mapper; 10 import org.apache.hadoop.mapreduce.Reducer; 11 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 12 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 13 14 public class WordCount { 15 public static class doMapper extends Mapper<Object, Text, Text, IntWritable>{ 16 //第一个Object表示输入key的类型；第二个Text表示输入value的类型；第三个Text表示表示输出键的类型；第四个IntWritable表示输出值的类型 17 public static final IntWritable one = new IntWritable(1); 18 public static Text word = new Text(); 19 @Override 20 protected void map(Object key, Text value, Context context) throws IOException, InterruptedException //抛出异常 21 { 22 StringTokenizer tokenizer = new StringTokenizer(value.toString(),"\t"); 23 //StringTokenizer是Java工具包中的一个类，用于将字符串进行拆分 24 word.set(tokenizer.nextToken()); 25 //返回当前位置到下一个分隔符之间的字符串 26 context.write(word, one); 27 //将word存到容器中，记一个数 28 } 29 } 30 public static class doReducer extends Reducer<Text, IntWritable, Text, IntWritable>{ 31 //参数同Map一样，依次表示是输入键类型，输入值类型，输出键类型，输出值类型 32 private IntWritable result = new IntWritable(); 33 @Override 34 protected void reduce(Text key, Iterable<IntWritable> values, Context context) 35 throws IOException, InterruptedException { 36 int sum = 0; 37 for (IntWritable value : values) { 38 sum += value.get(); 39 } 40 //for循环遍历，将得到的values值累加 41 result.set(sum); 42 context.write(key, result); 43 } 44 } 45 public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { 46 Job job = Job.getInstance(); 47 job.setJobName("WordCount"); 48 job.setJarByClass(WordCount.class); 49 job.setMapperClass(doMapper.class); 50 job.setReducerClass(doReducer.class); 51 job.setOutputKeyClass(Text.class); 52 job.setOutputValueClass(IntWritable.class); 53 Path in = new Path("hdfs://localhost:9000/mymapreduce1/in"); 54 Path out = new Path("hdfs://localhost:9000/mymapreduce1/out"); 55 FileInputFormat.addInputPath(job, in); 56 FileOutputFormat.setOutputPath(job, out); 57 System.exit(job.waitForCompletion(true) ? 0 : 1); 58 } 59 }
最终结果截图：
标签：ted exit err tostring orm col get table oca
原文地址：https://www.cnblogs.com/liyuchao/p/11767262.html
