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.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.util.GenericOptionsParser;
public class MinTemp{
public static class NcdcParser {
private static final int MISSING_TEMPERATURE = 9999;
private String year;
private int airTemperature;
private String quality;
public void parse(String record){
year = record.substring(15,19);
String airTemperatureString;
if(record.charAt(87)== '+'){
airTemperatureString = record.substring(88,92);
}else{
airTemperatureString = record.substring(87,92);
}
airTemperature = Integer.parseInt(airTemperatureString);
quality = record.substring(92,93);
}
public void parse(Text record){
parse(record.toString());
}
public boolean isValidTemperature(){
return airTemperature !=MISSING_TEMPERATURE && quality.matches("[01459]");
}
public String getYear(){
return year;
}
public int getAirTemperature(){
return airTemperature;
}
}
public static class MinTemperatureMapper extends
Mapper<LongWritable, Text, Text, IntWritable> {
private NcdcParser parser = new NcdcParser();
public void map(LongWritable key,Text value,Context context){
parser.parse(value);
if(parser.isValidTemperature()){
try {
context.write(new Text(parser.getYear()), new IntWritable(parser.getAirTemperature()));
} catch (IOException e) {
e.printStackTrace();
} catch (InterruptedException e) {
e.printStackTrace();
}
}
}
}
public static class MinTemperatureReducer 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 minValue = Integer.MAX_VALUE;
for(IntWritable value : values){
minValue = Math.min(minValue, value.get());
}
result.set(minValue);
context.write(key,result);
}
}
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: MinTemperature <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "Min temperature");
job.setJarByClass(MinTemp.class);
job.setMapperClass(MinTemperatureMapper.class);
job.setCombinerClass(MinTemperatureReducer.class);
job.setReducerClass(MinTemperatureReducer.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.util.GenericOptionsParser;
public class MinTemp{
public static class NcdcParser {
private static final int MISSING_TEMPERATURE = 9999;
private String year;
private int airTemperature;
private String quality;
public void parse(String record){
year = record.substring(15,19);
String airTemperatureString;
if(record.charAt(87)== '+'){
airTemperatureString = record.substring(88,92);
}else{
airTemperatureString = record.substring(87,92);
}
airTemperature = Integer.parseInt(airTemperatureString);
quality = record.substring(92,93);
}
public void parse(Text record){
parse(record.toString());
}
public boolean isValidTemperature(){
return airTemperature !=MISSING_TEMPERATURE && quality.matches("[01459]");
}
public String getYear(){
return year;
}
public int getAirTemperature(){
return airTemperature;
}
}
public static class MinTemperatureMapper extends
Mapper<LongWritable, Text, Text, IntWritable> {
private NcdcParser parser = new NcdcParser();
public void map(LongWritable key,Text value,Context context){
parser.parse(value);
if(parser.isValidTemperature()){
try {
context.write(new Text(parser.getYear()), new IntWritable(parser.getAirTemperature()));
} catch (IOException e) {
e.printStackTrace();
} catch (InterruptedException e) {
e.printStackTrace();
}
}
}
}
public static class MinTemperatureReducer 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 minValue = Integer.MAX_VALUE;
for(IntWritable value : values){
minValue = Math.min(minValue, value.get());
}
result.set(minValue);
context.write(key,result);
}
}
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: MinTemperature <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "Min temperature");
job.setJarByClass(MinTemp.class);
job.setMapperClass(MinTemperatureMapper.class);
job.setCombinerClass(MinTemperatureReducer.class);
job.setReducerClass(MinTemperatureReducer.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}