数据
10181 1000481 2010-04-04 16:54:31
20001 1001597 2010-04-07 15:07:52
20001 1001560 2010-04-07 15:08:27
20042 1001368 2010-04-08 08:20:30
20067 1002061 2010-04-08 16:45:33
20056 1003289 2010-04-12 10:50:55
20056 1003290 2010-04-12 11:57:35
20056 1003292 2010-04-12 12:05:29
20054 1002420 2010-04-14 15:24:12
20055 1001679 2010-04-14 19:46:04
20054 1010675 2010-04-14 15:23:53
20054 1002429 2010-04-14 17:52:45
20076 1002427 2010-04-14 19:35:39
20054 1003326 2010-04-20 12:54:44
20056 1002420 2010-04-15 11:24:49
20064 1002422 2010-04-15 11:35:54
20056 1003066 2010-04-15 11:43:01
20056 1003055 2010-04-15 11:43:06
20056 1010183 2010-04-15 11:45:24
20056 1002422 2010-04-15 11:45:49
20056 1003100 2010-04-15 11:45:54
20056 1003094 2010-04-15 11:45:57
20056 1003064 2010-04-15 11:46:04
20056 1010178 2010-04-15 16:15:20
20076 1003101 2010-04-15 16:37:27
20076 1003103 2010-04-15 16:37:05
20076 1003100 2010-04-15 16:37:18
20076 1003066 2010-04-15 16:37:31
20054 1003103 2010-04-15 16:40:14
20054 1003100 2010-04-15 16:40:16
package mapreduce;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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;
public class WordCount {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Job job = Job.getInstance();//设置环境参数
job.setJobName("WordCount");//设置环境参数名
job.setJarByClass(WordCount.class);//设置整个程序类名
job.setMapperClass(doMapper.class);//添加doMapper类
job.setReducerClass(doReducer.class);//添加doReducer类
job.setOutputKeyClass(Text.class);//设置输出类型
job.setOutputValueClass(IntWritable.class);//设置输出类型
Path in = new Path("hdfs://localhost:9000/mymapreduce1/in/buyer_favorite1");
Path out = new Path("hdfs://localhost:9000/mymapreduce1/out");
FileInputFormat.addInputPath(job, in);//设置输入文件
FileOutputFormat.setOutputPath(job, out);//设置输出文件
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
public static class doMapper extends Mapper<Object, Text, Text, IntWritable>{
//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表示输出键的类型;第四个IntWritable表示输出值的类型
public static final IntWritable one = new IntWritable(1);
public static Text word = new Text();
@Override
protected void map(Object key, Text value, Context context)
throws IOException, InterruptedException{
//抛出异常
StringTokenizer tokenizer = new StringTokenizer(value.toString(),"\t");
//StringTokenizer是Java工具包中的一个类,用于将字符串进行拆分
word.set(tokenizer.nextToken());
//返回当前位置到下一个分隔符之间的字符串
context.write(word, one);
//将word存到容器中,记一个数
}
}
public static class doReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
//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
private IntWritable result = new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (IntWritable value : values) {
sum += value.get();
}
//for循环遍历,将得到的values值累加
result.set(sum);
context.write(key, result);
}
}
}
//
商品分类 商品点击次数
52127 5
52120 93
52092 93
52132 38
52006 462
52109 28
52109 43
52132 0
52132 34
52132 9
52132 30
52132 45
52132 24
52009 2615
52132 25
52090 13
52132 6
52136 0
52090 10
52024 347
package mapreduce;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
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.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;
public class MyAverage{
public static class Map extends Mapper<Object , Text , Text , IntWritable>{
private static Text newKey=new Text();
//实现map函数
public void map(Object key,Text value,Context context) throws IOException, InterruptedException{
// 将输入的纯文本文件的数据转化成String
String line=value.toString();
System.out.println(line);
String arr[]=line.split("\t");
newKey.set(arr[0]);
int click=Integer.parseInt(arr[1]);
context.write(newKey, new IntWritable(click));
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable>{
//实现reduce函数
public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException{
int num=0;
int count=0;
for(IntWritable val:values){
num+=val.get(); //每个元素求和num
count++; //统计元素的次数count
}
int avg=num/count; //计算平均数
context.write(key,new IntWritable(avg));
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{
Configuration conf=new Configuration();
System.out.println("start");
Job job =new Job(conf,"MyAverage");
job.setJarByClass(MyAverage.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
Path in=new Path("hdfs://localhost:9000/mymapreduce4/in/goods_click");
Path out=new Path("hdfs://localhost:9000/mymapreduce4/out");
FileInputFormat.addInputPath(job,in);
FileOutputFormat.setOutputPath(job,out);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
/
用户id 商品id 收藏日期
10181 1000481 2010-04-04 16:54:31
20001 1001597 2010-04-07 15:07:52
20001 1001560 2010-04-07 15:08:27
20042 1001368 2010-04-08 08:20:30
20067 1002061 2010-04-08 16:45:33
20056 1003289 2010-04-12 10:50:55
20056 1003290 2010-04-12 11:57:35
20056 1003292 2010-04-12 12:05:29
20054 1002420 2010-04-14 15:24:12
20055 1001679 2010-04-14 19:46:04
20054 1010675 2010-04-14 15:23:53
20054 1002429 2010-04-14 17:52:45
20076 1002427 2010-04-14 19:35:39
20054 1003326 2010-04-20 12:54:44
20056 1002420 2010-04-15 11:24:49
20064 1002422 2010-04-15 11:35:54
20056 1003066 2010-04-15 11:43:01
20056 1003055 2010-04-15 11:43:06
20056 1010183 2010-04-15 11:45:24
20056 1002422 2010-04-15 11:45:49
20056 1003100 2010-04-15 11:45:54
20056 1003094 2010-04-15 11:45:57
20056 1003064 2010-04-15 11:46:04
20056 1010178 2010-04-15 16:15:20
20076 1003101 2010-04-15 16:37:27
20076 1003103 2010-04-15 16:37:05
20076 1003100 2010-04-15 16:37:18
20076 1003066 2010-04-15 16:37:31
20054 1003103 2010-04-15 16:40:14
20054 1003100 2010-04-15 16:40:16
package mapreduce;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
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.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;
public class Filter{
public static class Map extends Mapper<Object , Text , Text , NullWritable>
//map将输入中的value复制到输出数据的key上,并直接输出
{
private static Text newKey=new Text(); //从输入中得到的每行的数据的类型
public void map(Object key,Text value,Context context) throws IOException, InterruptedException
//实现map函数
{ //获取并输出每一次的处理过程
String line=value.toString();
System.out.println(line);
String arr[]=line.split("\t");
newKey.set(arr[1]);
context.write(newKey, NullWritable.get());
System.out.println(newKey);
}
}
public static class Reduce extends Reducer<Text, NullWritable, Text, NullWritable>{
public void reduce(Text key,Iterable<NullWritable> values,Context context) throws IOException, InterruptedException
//实现reduce函数
{
context.write(key,NullWritable.get()); //获取并输出每一次的处理过程
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{
Configuration conf=new Configuration();
System.out.println("start");
Job job =new Job(conf,"filter");
job.setJarByClass(Filter.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
Path in=new Path("hdfs://localhost:9000/mymapreduce2/in/buyer_favorite1");
Path out=new Path("hdfs://localhost:9000/mymapreduce2/out");
FileInputFormat.addInputPath(job,in);
FileOutputFormat.setOutputPath(job,out);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}