Created
September 30, 2020 09:54
-
-
Save Dysta/ca429711ef23e84b2e62c9ba30df7a1f to your computer and use it in GitHub Desktop.
Correction TP4 PLE
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 bigdata; | |
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.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.mapreduce.lib.input.TextInputFormat; | |
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; | |
import org.apache.hadoop.fs.FileSystem; | |
public class TP4 { | |
public static class TP4Mapper extends Mapper<Object, Text, Text, IntWritable> { | |
public void map(Object key, Text value, Context context) throws IOException, InterruptedException { | |
String tok[] = value.toString().split(","); | |
if (!tok[4].equals("") && !tok[4].equals("Population")) { | |
double pop = Math.floor(Math.log10(Double.parseDouble(tok[4]))); | |
pop = Math.pow(10., pop); | |
int pop_class = (int) pop; | |
context.write(new Text(String.valueOf(pop_class)), new IntWritable(Integer.parseInt(tok[4]))); | |
} | |
} | |
} | |
public static class TP4Reducer extends Reducer<Text, IntWritable, Text, IntWritable> { | |
public void setup(Context context) throws IOException, InterruptedException { | |
context.write(new Text("classe\tcount\tavg\tmax\tmin"), null); | |
} | |
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { | |
int sum = 0; | |
int count = 0; | |
int min = Integer.MAX_VALUE, max = Integer.MIN_VALUE; | |
for (IntWritable i : values) { | |
int current = i.get(); | |
if (current < min) | |
min = current; | |
if (current > max) | |
max = current; | |
count += current; | |
sum++; | |
} | |
StringBuilder b = new StringBuilder(); | |
b.append(key.toString()).append("\t"); | |
b.append(String.valueOf(sum)).append("\t"); | |
b.append(String.valueOf(count/sum)).append("\t"); | |
b.append(String.valueOf(max)).append("\t"); | |
b.append(String.valueOf(min)).append("\t"); | |
context.write(new Text(b.toString()), null); | |
} | |
} | |
public static void main(String[] args) throws Exception { | |
Configuration conf = new Configuration(); | |
Job job = Job.getInstance(conf, "TP4-xgerardin"); | |
job.setNumReduceTasks(1); | |
job.setJarByClass(TP4.class); | |
job.setMapperClass(TP4Mapper.class); | |
job.setMapOutputKeyClass(Text.class); | |
job.setMapOutputValueClass(IntWritable.class); | |
job.setReducerClass(TP4Reducer.class); | |
job.setOutputKeyClass(Text.class); | |
job.setOutputValueClass(IntWritable.class); | |
job.setOutputFormatClass(TextOutputFormat.class); | |
job.setInputFormatClass(TextInputFormat.class); | |
FileInputFormat.addInputPath(job, new Path(args[0])); | |
if (FileSystem.get(conf).resolvePath(new Path(args[1])) != null) | |
FileSystem.get(conf).delete(new Path(args[1]), true); | |
FileOutputFormat.setOutputPath(job, new Path(args[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