Develop Reference

Exception in thread "main" java.lang.NoSuchMethodException

This is my program for word count in Mapreduce and I have created jar file successfully but when I am executing on Hadoop I am facing the following error.
package com.niit;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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 WordCount {
public static class Map extends Mapper<LongWritable,Text,Text,IntWritable> {
public void map(LongWritable key, Text value,Context context) throws IOException,InterruptedException{
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
value.set(tokenizer.nextToken());
context.write(value, new IntWritable(1));
}
}
}
public static class Reduce extends Reducer<Text,IntWritable,Text,IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException,InterruptedException {
int sum=0;
for(IntWritable x: values) {
sum+=x.get();
}
context.write(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
Configuration conf= new Configuration();
Job job = new Job(conf,"My Word Count Program");
job.setJarByClass(WordCount.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 outputPath = new Path(args[1]);
//Configuring the input/output path from the filesystem into the job
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//deleting the output path automatically from hdfs so that we don't have to delete it explicitly
outputPath.getFileSystem(conf).delete(outputPath);
//exiting the job only if the flag value becomes false
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
and this is the error message I'm getting:
Command: yarn jar WordCount-1.0.jar com.niit.WordCount /usr/lib/hadoop-2.2.0/workspace/input/simple.txt /usr/lib/hadoop-2.2.0/workspace/output
Exception in thread "main" java.lang.NoSuchMethodException: com.niit.WordCount.main([Ljava.lang.String;)
at java.lang.Class.getMethod(Class.java:1665)
at org.apache.hadoop.util.RunJar.main(RunJar.java:206)

How can I compile Java source code?

I try to build a project that find the maximum of Average temperature of each month. Here is my code:
File Map.java
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class Map extends Mapper<LongWritable, Text, Text, FloatWritable> {
private FloatWritable average = new FloatWritable();
private float maxFloat, minFloat, averageFloat;
private Text word = new Text();
#Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
StringTokenizer line = new StringTokenizer(value.toString(), ",");
if (line.countTokens() > 0) {
word.set(line.nextToken().substring(2,8));
if (line.hasMoreTokens()) {
maxFloat = Float.parseFloat(line.nextToken());
}
if (line.hasMoreTokens()) {
minFloat = Float.parseFloat(line.nextToken());
}
averageFloat = (minFloat + maxFloat) / 2;
average.set(averageFloat);
context.write(word, average);
}
}
}
File Reduce.java
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
import java.util.Iterator;
public class Reduce extends Reducer<Text, FloatWritable, Text, FloatWritable> {
private float max_temp = Float.MIN_VALUE;
private float temp = 0;
#Override
protected void reduce(Text key, Iterable<FloatWritable> values, Context context)
throws IOException, InterruptedException {
Iterator<FloatWritable> itr = values.iterator();
while (itr.hasNext()) {
temp = itr.next().get();
if (temp > max_temp) {
max_temp = temp;
}
}
context.write(key, new FloatWritable(max_temp));
}
}
File MaxTempDriver.java
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class MaxTempDriver {
public static void main(String[] args) throws Exception {
// Create a new job
Job job = new Job();
// Set job name to locate it in the distributed environment
job.setJarByClass(MaxTempDriver.class);
job.setJobName("Max Temperature");
// Set input and output Path, note that we use the default input format
// which is TextInputFormat (each record is a line of input)
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// Set Mapper and Reducer class
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
// Set Output key and value
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FloatWritable.class);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
And now I don't know how to compile these 3 files. I have read from the some tutorials from internet but it seems that they only had 1 file with map.class and reduce.class at the same file. How to compile these file?

javac do not generate any Error or jar file in hadoop

I study hdfs, so I test simple MapReduce code that gets average of overall in JSON file.
Json form's sample is in here(click me)
GetAverage.java
package some.package.path.here.bigdata;
import java.io.IOException;
import java.util.Arrays;
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.LongWritable;
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 org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.json.*;
public class GetAverage extends Configured implements Tool {
public static void main(String[] args) throws Exception {
System.out.println(Arrays.toString(args));
int res = ToolRunner.run(new Configuration(), new GetAverage(), args);
System.exit(res);
}
#Override
public int run(String[] args) throws Exception {
System.out.println(Arrays.toString(args));
Job job = Job.getInstance(getConf());
job.setJarByClass(GetAverage.class);
job.setOutputKeyClass(Text.class);
//Overall value type is float.
job.setOutputValueClass(FloatWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
return 0;
}
public static class Map extends Mapper<LongWritable, Text, Text, FloatWritable> {
private Text asin_value = new Text();
private FloatWritable overall_value = new FloatWritable();
#Override
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String asin;
float overall;
String line = value.toString();
String[] tuple = line.split("\\n");
try{
for(int i=0; i<tuple.length; i++){
JSONObject obj = new JSONObject(tuple[i]);
System.out.println(obj);
asin = obj.getString("asin");
overall = Float.parseFloat(obj.getString("overall"));
asin_value.set(asin);
overall_value.set(overall);
context.write(asin_value, overall_value);
}
}catch(JSONException e){
e.printStackTrace();
}
}
}
public static class Reduce extends Reducer<Text, FloatWritable, Text, FloatWritable> {
#Override
public void reduce(Text key, Iterable<FloatWritable> values, Context context)
throws IOException, InterruptedException {
float sum = 0;
int length = 0;
for (FloatWritable val : values) {
sum += val.get();
length++;
}
float average = sum / length;
context.write(key, new FloatWritable(average));
}
}
}
When I compile this, Code do not showing any message and generate any jar file.
I compile this java file with under command.
cat ./complie command
javac -classpath /usr/local/hadoop/share/hadoop/common/hadoop-common-2.8.0.jar:/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.8.0.jar:../org.json.jar -d getaverage_classes/ GetAverage.java
And my directory structure is...
~/test |- GetAverage.java
|- compile_command
|- getaverage_classes - some/package/path/here/bigdata |-GetAverage$Map.class
|- GetAverage$Reduce.class
|- GetAverage.class
Please answer my question anyone knows this problem. :)

Can't access hashmap in mapper, MapReduce

I'd like to replace values of input data in my mapper, using dictionalies(csv) defined in another file. So I tried to put the csv data to HashMap and refer it in the mapper.
The java code and csv below are simplified version of my program. This code works in my local environment(Mac OS X, pseudo-distributed mode), but doesn't in my EC2 instance(ubuntu, pseudo-distributed mode).
In detail, I got this stdout in process:
cat:4
human:2
flamingo:1
this means the filereader successfully put csv data into HashMap.
However the mapper mapped nothing and therefore I got empty output in the EC2 environment, although it mapped 3 * (the number of lines of the input file) elements and generated the following in the local:
test,cat
test,flamingo
test,human
Does anyone have answers or hints?
Test.java
import java.io.IOException;
import java.util.StringTokenizer;
import java.io.FileReader;
import java.io.BufferedReader;
import java.io.DataInput;
import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
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 org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.io.WritableUtils;
public class Test {
public static HashMap<String, Integer> map = new HashMap<String, Integer>();
public static class Mapper1 extends Mapper<LongWritable, Text, Text, Text> {
#Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
for(Map.Entry<String, Integer> e : map.entrySet()) {
context.write(new Text(e.getKey()), new Text("test"));
}
}
}
public static class Reducer1 extends Reducer<Text, Text, Text, Text> {
#Override
protected void reduce(Text key, Iterable<Text> vals, Context context) throws IOException, InterruptedException {
context.write(new Text("test"), key);
}
}
public static class CommaTextOutputFormat extends TextOutputFormat<Text, Text> {
#Override
public RecordWriter<Text, Text> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
Configuration conf = job.getConfiguration();
String extension = ".txt";
Path file = getDefaultWorkFile(job, extension);
FileSystem fs = file.getFileSystem(conf);
FSDataOutputStream fileOut = fs.create(file, false);
return new LineRecordWriter<Text, Text>(fileOut, ",");
}
}
public static void get_list(String list_path){
try {
FileReader fr = new FileReader(list_path);
BufferedReader br = new BufferedReader(fr);
String line = null, name = null;
int leg = 0;
while ((line = br.readLine()) != null) {
if (!line.startsWith("name") && !line.trim().isEmpty()) {
String[] name_leg = line.split(",", 0);
name = name_leg[0];
leg = Integer.parseInt(name_leg[1]);
map.put(name, leg);
}
}
br.close();
}
catch(IOException ex) {
System.err.println(ex.getMessage());
ex.printStackTrace();
}
for(Map.Entry<String, Integer> e : map.entrySet()) {
System.out.println(e.getKey() + ":" + e.getValue());
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
if (args.length != 3) {
System.err.println(
"Need 3 arguments: <input dir> <output base dir> <list path>");
System.exit(1);
}
get_list(args[2]);
Job job = Job.getInstance(conf, "test");
job.setJarByClass(Test.class);
job.setMapperClass(Mapper1.class);
job.setReducerClass(Reducer1.class);
job.setNumReduceTasks(1);
job.setInputFormatClass(TextInputFormat.class);
// mapper output
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
// reducer output
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// formtter
job.setOutputFormatClass(CommaTextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
if(!job.waitForCompletion(true)){
System.exit(1);
}
System.out.println("All Finished");
System.exit(0);
}
}
list.csv (args[2])
name,legs
cat,4
human,2
flamingo,1
=================================
I refer to #Rahul Sharma 's answer and modifiy my code as below. Then my code works in the both environments.
Thank you very much #Rahul Sharma and #Serhiy for your precise answer and useful comments.
Test.java
import java.io.IOException;
import java.util.StringTokenizer;
import java.io.FileReader;
import java.io.BufferedReader;
import java.io.DataInput;
import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;
import java.net.URI;
import java.io.InputStreamReader;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
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 org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.io.WritableUtils;
public class Test {
public static HashMap<String, Integer> map = new HashMap<String, Integer>();
public static class Mapper1 extends Mapper<LongWritable, Text, Text, Text> {
#Override
protected void setup(Context context) throws IOException, InterruptedException {
URI[] files = context.getCacheFiles();
Path list_path = new Path(files[0]);
try {
FileSystem fs = list_path.getFileSystem(context.getConfiguration());
BufferedReader br = new BufferedReader(new InputStreamReader(fs.open(list_path)));
String line = null, name = null;
int leg = 0;
while ((line = br.readLine()) != null) {
if (!line.startsWith("name") && !line.trim().isEmpty()) {
String[] name_leg = line.split(",", 0);
name = name_leg[0];
leg = Integer.parseInt(name_leg[1]);
map.put(name, leg);
}
}
br.close();
}
catch(IOException ex) {
System.err.println(ex.getMessage());
ex.printStackTrace();
}
for(Map.Entry<String, Integer> e : map.entrySet()) {
System.out.println(e.getKey() + ":" + e.getValue());
}
}
#Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
for(Map.Entry<String, Integer> e : map.entrySet()) {
context.write(new Text(e.getKey()), new Text("test"));
}
}
}
public static class Reducer1 extends Reducer<Text, Text, Text, Text> {
#Override
protected void reduce(Text key, Iterable<Text> vals, Context context) throws IOException, InterruptedException {
context.write(new Text("test"), key);
}
}
// Writer
public static class CommaTextOutputFormat extends TextOutputFormat<Text, Text> {
#Override
public RecordWriter<Text, Text> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
Configuration conf = job.getConfiguration();
String extension = ".txt";
Path file = getDefaultWorkFile(job, extension);
FileSystem fs = file.getFileSystem(conf);
FSDataOutputStream fileOut = fs.create(file, false);
return new LineRecordWriter<Text, Text>(fileOut, ",");
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
if (args.length != 3) {
System.err.println(
"Need 3 arguments: <input dir> <output base dir> <list path>");
System.exit(1);
}
Job job = Job.getInstance(conf, "test");
job.addCacheFile(new Path(args[2]).toUri());
job.setJarByClass(Test.class);
job.setMapperClass(Mapper1.class);
job.setReducerClass(Reducer1.class);
job.setNumReduceTasks(1);
job.setInputFormatClass(TextInputFormat.class);
// mapper output
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
// reducer output
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// formtter
job.setOutputFormatClass(CommaTextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
if(!job.waitForCompletion(true)){
System.exit(1);
}
System.out.println("All Finished");
System.exit(0);
}
}

First you need to learn more about mapreduce framework.
Your program behave as expected in local mode because Mapper, reducer and Job are launched on same JVM. In case, of pseudo-distributed mode or distributed modes there will be separate jvms allocated for each component. The values you put into hashMap using get_list are not visible to mapper and reducer as they are in separate jvms
Use distributed cache to make it work in cluster mode.
Job Main class add file to distributed cache:
JobConf job = new JobConf();<br>
DistributedCache.addCacheArchive(new URI(args[2]), job);
Access file in mapper or reducer:
public void setup(Context context) throws IOException, InterruptedException {
Configuration conf = context.getConfiguration();
FileSystem fs = FileSystem.getLocal(conf);
Path[] dataFile = DistributedCache.getLocalCacheFiles(conf);
BufferedReader cacheReader = new BufferedReader(new InputStreamReader(fs.open(dataFile[0])));
// Implement here get_list method functionality
}

Error:(63, 40) java: incompatible types: org.apache.hadoop.mapreduce.Job cannot be converted to org.apache.hadoop.mapred.JobConf

I was just running a simple hadooop programm in intellj IDE. but there is an error mentioned when I try to compile
$Error:(63, 40) java: incompatible types:
org.apache.hadoop.mapreduce.Job cannot be converted to
org.apache.hadoop.mapred.JobConf
Here is my code for this small program:
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileOutputFormat;
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 java.io.IOException;
import java.util.StringTokenizer;
public class WordCount {
public static class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class IntSumReducer
extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}

Root cause:
you have used old API' FileOutputFormat(mapred) in your job which takes JobConf object as first parameter not Job, but FileInputFormat method you used from new API(maprecude) which takes Job object as first parameter.
(Job is also from new API, JobConf is from old API)
Solution:
Change this line in your code:
import org.apache.hadoop.mapred.FileOutputFormat;
to
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;