-
-
Save NicoHinderling/2946f63e057a811a8c34 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package wordcount; | |
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.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 org.apache.hadoop.util.GenericOptionsParser; | |
public class fourB { | |
public static class TokenizerMapper | |
extends Mapper<Object, Text, IntWritable, IntWritable>{ | |
private final static IntWritable zero = new IntWritable(0); | |
private final static IntWritable one = new IntWritable(1); | |
private Text missing = new Text(); | |
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()) { | |
String wordy = itr.nextToken(); | |
for (int m = 0; m < 15; m++){ | |
if(m == wordy.length()){ | |
int counter = 0; | |
for(int x = 0; x < wordy.length(); x++){ | |
if(wordy.charAt(x)== 'a' || wordy.charAt(x)== 'e' || wordy.charAt(x)== 'i' || wordy.charAt(x)== 'o' || wordy.charAt(x)== 'u' || wordy.charAt(x)== 'y' || wordy.charAt(x)== 'A' || wordy.charAt(x)== 'E' || wordy.charAt(x)== 'I' || wordy.charAt(x)== 'O' || wordy.charAt(x)== 'U' || wordy.charAt(x)== 'Y'){ | |
counter++; | |
} | |
} | |
System.out.println(wordy + " of length " + m + " contains " + counter + " values!"); | |
context.write(new IntWriteable (m), new IntWriteable(counter)); | |
} | |
context.write(new IntWritable (m), zero); | |
} | |
} | |
} | |
} | |
public static class IntSumReducer | |
extends Reducer<IntWritable,IntWritable,Text,DoubleWritable> { | |
public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { | |
double sum = 0; | |
double denom = 0; | |
int[] arr = new int[key.get ()+1] | |
for (IntWritable val : values) { | |
denom++; | |
arr[val.get ()]++; | |
} | |
Text fin = new Text (); | |
for (int i = 0; i < arr.length (); i++) { | |
fin.set(key.toString () + " " + i) | |
context.write ( fin, new DoubleWritable(arr[i] / denom) ); | |
} | |
} | |
} | |
public static void main(String[] args) throws Exception { | |
Configuration conf = new Configuration(); | |
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); | |
if (otherArgs.length != 2) { | |
System.err.println("Usage: wordcount <in> <out>"); | |
System.exit(2); | |
} | |
Job job = new Job(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(otherArgs[0])); | |
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); | |
System.exit(job.waitForCompletion(true) ? 0 : 1); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment