@Override
public void reduce(
Text key, Iterator<Text> values, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
String line = "";
String header = "";
TreeMap<String, String> ciudades = new TreeMap<String, String>();
// Obtenemos los datos y los metemos a un treemap para que los ordene por ciudad
while (values.hasNext()) {
String[] tmp = values.next().toString().split(",");
String ciudad = tmp[0];
String mes = tmp[1];
String temperatura = tmp[2];
String fecha = tmp[3];
ciudades.put(ciudad, tmp[1] + "," + tmp[2] + "," + tmp[3]);
}
// Recorremos las ciudades y vamos imprimiendo
for (String ciudad : ciudades.keySet()) {
header += ciudad + ",,";
String[] temporal = ciudades.get(ciudad).split(",");
line += temporal[2] + "," + temporal[1] + ",";
}
if (c == 0) { // Imprimimos cabezera
output.collect(new Text("Año,"), new Text(header));
c++;
}
output.collect(new Text(key.toString() + ","), new Text(line));
}
void search(
Vector<Star> v1,
Vector<Star> v2,
BlockIDWritable key,
OutputCollector<BlockIDWritable, PairWritable> output)
throws IOException {
for (int i = 0; i < v1.size(); i++) {
for (int j = 0; j < v2.size(); j++) {
Star star1 = v1.get(i);
Star star2 = v2.get(j);
// what is this margin about
if (star1.margin && star2.margin) continue;
double dist = star1.x * star2.x + star1.y * star2.y + star1.z * star2.z;
if (dist > costheta) {
p.set(star1, star2, dist);
output.collect(key, p);
p.set(star2, star1, dist);
output.collect(key, p);
// num += 2;
}
}
} // end for i,j
}
public void map(
LongWritable key, Text value, OutputCollector<LongWritable, Text> output, Reporter reporter)
throws IOException {
String line = value.toString();
if (validate(line, reporter)) output.collect(key, value);
}
public void map(
LongWritable key,
Text value,
OutputCollector<IntWritable, DoubleWritable> output,
Reporter reporter)
throws IOException {
/*
* It implements the mapper. It outputs the numbers of weight and updated weights.
*
* Note that the format of intermediate output is <IntWritable, DoubleWritable>,
* because the key is the number of weight (an integer), and the value is the weight's value (double)
*/
inputData = value.toString();
// go through the process
initialize();
getposphase();
getnegphase();
update();
// output the intermediate data
// The <key, value> pairs are <weightID, weightUpdate>
double[][] vishidinc_array = vishidinc.getArray();
for (int i = 0; i < numdims; i++) {
for (int j = 0; j < numhid; j++) {
weightPos.set(i * numhid + j);
weightValue.set(vishidinc_array[i][j]);
output.collect(weightPos, weightValue);
}
}
}
// specify input and out keys
public void map(
LongWritable key, Text value, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
String line = value.toString(); // define new variable to be string
ArrayList<Integer> range = new ArrayList<Integer>();
for (int i = 2000; i <= 2010; i++) {
range.add(i);
}
// String[] inputs = line.split(",(?=([^\"]*\"[^\"]*\")*[^\"]*$)");
String[] inputs = line.split(",");
try {
int year = Integer.parseInt(inputs[165]);
if (range.contains(year)) {
String dur = inputs[3];
String artist_name = inputs[2];
String song_title = inputs[1];
String final_input = artist_name + ',' + dur + ',' + song_title;
Final_Value.set(final_input);
output.collect(Final_Value, dummy);
}
} catch (NumberFormatException e) {
// do nothing
}
}
public void map(
LongWritable key, Text value, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
parser.parse(value);
output.collect(new Text(parser.getStationId()), value);
}
protected void emit(K key, V val, OutputCollector<K, V> out) throws IOException {
++total;
while ((float) kept / total < keep) {
++kept;
out.collect(key, val);
}
}
/**
* Takes in (id, node) pairs and emits them right back out
*
* @param key The Node ID
* @param Node The Node object
* @param output An Output Collector that collects (id, node) pairs
* @param reporter Default reporter object
*/
public void map(
IntWritable key,
WikiPage value,
OutputCollector<IntWritable, WikiPage> output,
Reporter reporter)
throws IOException {
output.collect(key, value);
}
public void reduce(
DoubleWritable key,
Iterator<DoubleWritable> values,
OutputCollector<DoubleWritable, Text> output,
Reporter reporter)
throws IOException {
output.collect(key, new Text(values.next().toString() + " - "));
}
public void map(LongWritable key, Text value, OutputCollector output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
public void reduce(
IntPair key,
Iterator<NullWritable> values,
OutputCollector<IntPair, NullWritable> output,
Reporter reporter)
throws IOException {
/*[*/ output.collect(key, NullWritable.get()); /*]*/
}
@Override
public void reduce(
IntWritable key,
Iterator<DoubleWritable> values,
OutputCollector<IntWritable, DoubleWritable> output,
Reporter reporter)
throws IOException {
output.collect(key, values.next());
}
public void reduce(
Text key,
Iterator<CrawlDatum> values,
OutputCollector<Text, CrawlDatum> output,
Reporter reporter)
throws IOException {
boolean oldSet = false;
boolean injectedSet = false;
while (values.hasNext()) {
CrawlDatum val = values.next();
if (val.getStatus() == CrawlDatum.STATUS_INJECTED) {
injected.set(val);
injected.setStatus(CrawlDatum.STATUS_DB_UNFETCHED);
injectedSet = true;
} else {
old.set(val);
oldSet = true;
}
}
CrawlDatum res = null;
/**
* Whether to overwrite, ignore or update existing records
*
* @see https://issues.apache.org/jira/browse/NUTCH-1405
*/
// Injected record already exists and overwrite but not update
if (injectedSet && oldSet && overwrite) {
res = injected;
if (update) {
LOG.info(key.toString() + " overwritten with injected record but update was specified.");
}
}
// Injected record already exists and update but not overwrite
if (injectedSet && oldSet && update && !overwrite) {
res = old;
old.putAllMetaData(injected);
old.setScore(injected.getScore() != scoreInjected ? injected.getScore() : old.getScore());
old.setFetchInterval(
injected.getFetchInterval() != interval
? injected.getFetchInterval()
: old.getFetchInterval());
}
// Old default behaviour
if (injectedSet && !oldSet) {
res = injected;
} else {
res = old;
}
output.collect(key, res);
}
public void map(Object key, Text value, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
String[] _allCols = StringUtils.splitPreserveAllTokens(value.toString(), splitChar);
StringBuffer stringBuffer = new StringBuffer();
for (int i = 0; i < _allCols.length; i++) {
stringBuffer.append(i).append('=').append(_allCols[i]).append("\t");
}
output.collect(new Text(_allCols[0]), new Text(stringBuffer.toString()));
}
@Override
public void map(
LongWritable longWritable,
Text value,
OutputCollector<Text, Text> output,
Reporter reporter)
throws IOException {
String ip = value.toString();
output.collect(new Text(ip), new Text("1"));
}
@Override
public void reduce(
Text key, Iterator<Text> iterator, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
long sum = 0;
while (iterator.hasNext()) {
sum = sum + Long.parseLong(iterator.next().toString());
}
output.collect(key, new Text(String.valueOf(sum)));
}
public void map(
BytesWritable key,
BytesWritable value,
OutputCollector<BytesWritable, IntWritable> output,
Reporter reporter)
throws IOException {
// newKey = (key, value)
BytesWritable keyValue = new BytesWritable(pair(key, value));
// output (newKey, value)
output.collect(keyValue, this.value);
}
public void map(
LongWritable key, Text value, OutputCollector<IntWritable, Text> output, Reporter reporter)
throws IOException {
String arr[] = value.toString().split("\\r?\\n");
for (String row : arr) {
if (row.startsWith("\"")) {
continue;
}
String parts[] = row.split(",");
output.collect(new IntWritable(new Integer(parts[1])), new Text(parts[4]));
}
}
public void reduce(
Text key,
Iterator<IntWritable> values,
OutputCollector<Text, IntWritable> output,
Reporter reporter)
throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
public void map(
LongWritable key,
Text value,
OutputCollector<DoubleWritable, DoubleWritable> output,
Reporter reporter)
throws IOException {
String line = value.toString();
DoubleWritable clave = new DoubleWritable();
DoubleWritable valor = new DoubleWritable();
clave.set(Double.parseDouble(line));
valor.set(Math.sqrt(Double.parseDouble(line)));
output.collect(clave, valor);
}
public void map(
LongWritable key,
Text value,
OutputCollector<IntWritable, IntWritable> output,
Reporter reporter)
throws IOException {
String line = value.toString();
IntWritable clave = new IntWritable();
IntWritable valor = new IntWritable();
clave.set(Integer.parseInt(line));
valor.set(Integer.parseInt(line) + 1);
output.collect(clave, valor);
}
@SuppressWarnings("unchecked")
public void reduce(
Text key,
Iterator<Text> values,
OutputCollector<NullWritable, Text> output,
Reporter reporter)
throws IOException {
OutputCollector collector =
multipleOutputs.getCollector("station", key.toString().replace("-", ""), reporter);
while (values.hasNext()) {
collector.collect(NullWritable.get(), values.next());
}
}
void collectStats(OutputCollector<Text, Text> output, String name, long execTime, Long objSize)
throws IOException {
long totalSize = objSize.longValue();
float ioRateMbSec = (float) totalSize * 1000 / (execTime * MEGA);
LOG.info("Number of bytes processed = " + totalSize);
LOG.info("Exec time = " + execTime);
LOG.info("IO rate = " + ioRateMbSec);
output.collect(
new Text(AccumulatingReducer.VALUE_TYPE_LONG + "tasks"), new Text(String.valueOf(1)));
output.collect(
new Text(AccumulatingReducer.VALUE_TYPE_LONG + "size"),
new Text(String.valueOf(totalSize)));
output.collect(
new Text(AccumulatingReducer.VALUE_TYPE_LONG + "time"),
new Text(String.valueOf(execTime)));
output.collect(
new Text(AccumulatingReducer.VALUE_TYPE_FLOAT + "rate"),
new Text(String.valueOf(ioRateMbSec * 1000)));
output.collect(
new Text(AccumulatingReducer.VALUE_TYPE_FLOAT + "sqrate"),
new Text(String.valueOf(ioRateMbSec * ioRateMbSec * 1000)));
}
public void reduce(
Text key, Iterator<Text> values, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
ColumnFamily columnFamily;
String keyspace = "Keyspace1";
String cfName = "Super1";
Message message;
List<ColumnFamily> columnFamilies;
columnFamilies = new LinkedList<ColumnFamily>();
String line;
/* Create a column family */
columnFamily = ColumnFamily.create(keyspace, cfName);
while (values.hasNext()) {
// Split the value (line based on your own delimiter)
line = values.next().toString();
String[] fields = line.split("\1");
String SuperColumnName = fields[1];
String ColumnName = fields[2];
String ColumnValue = fields[3];
int timestamp = 0;
columnFamily.addColumn(
new QueryPath(
cfName, ByteBufferUtil.bytes(SuperColumnName), ByteBufferUtil.bytes(ColumnName)),
ByteBufferUtil.bytes(ColumnValue),
timestamp);
}
columnFamilies.add(columnFamily);
/* Get serialized message to send to cluster */
message = createMessage(keyspace, key.getBytes(), cfName, columnFamilies);
List<IAsyncResult> results = new ArrayList<IAsyncResult>();
for (InetAddress endpoint :
StorageService.instance.getNaturalEndpoints(keyspace, ByteBufferUtil.bytes(key))) {
/* Send message to end point */
results.add(MessagingService.instance().sendRR(message, endpoint));
}
/* wait for acks */
for (IAsyncResult result : results) {
try {
result.get(DatabaseDescriptor.getRpcTimeout(), TimeUnit.MILLISECONDS);
} catch (TimeoutException e) {
// you should probably add retry logic here
throw new RuntimeException(e);
}
}
output.collect(key, new Text(" inserted into Cassandra node(s)"));
}
// reduce method accepts the Key Value pairs from mappers, do the aggregation based on keys and
// produce the final out put
public void reduce(
Text key,
Iterator<IntWritable> values,
OutputCollector<Text, IntWritable> output,
Reporter reporter)
throws IOException {
int sum = 0;
/*iterates through all the values available with a key and add them together and give the
final result as the key and sum of its values*/
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
public void map(
LongWritable key,
Text value,
OutputCollector<IntPair, NullWritable> output,
Reporter reporter)
throws IOException {
parser.parse(value);
if (parser.isValidTemperature()) {
/*[*/ output.collect(
new IntPair(parser.getYearInt(), +parser.getAirTemperature()),
NullWritable.get()); /*]*/
}
}
@Override
public void reduce(
Text key, /*[*/
Iterator /*]*/<IntWritable> values,
/*[*/ OutputCollector<Text, IntWritable> output,
Reporter reporter /*]*/)
throws IOException {
int maxValue = Integer.MIN_VALUE;
while (
/*[*/ values.hasNext() /*]*/) {
maxValue = Math.max(maxValue, /*[*/ values.next().get() /*]*/);
}
/*[*/ output.collect /*]*/(key, new IntWritable(maxValue));
}
public void map(
LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
String line = value.toString();
String lastToken = null;
StringTokenizer s = new StringTokenizer(line, "\t");
String year = s.nextToken();
while (s.hasMoreTokens()) {
lastToken = s.nextToken();
}
int averagePrice = Integer.parseInt(lastToken);
output.collect(new Text(year), new IntWritable(averagePrice));
}
public void reduce(
Text key,
Iterator<IntWritable> value,
OutputCollector<Text, IntWritable> output,
Reporter reporter)
throws IOException {
// TODO Auto-generated method stub
int maxAvg = 30;
int val = Integer.MIN_VALUE;
while (value.hasNext()) {
if ((val = value.next().get()) > maxAvg) {
output.collect(key, new IntWritable(val));
}
}
}
@Override
public void map(
LongWritable key, Text value, OutputCollector<Text, Text> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokens = new StringTokenizer(line);
String[] keys = tokens.nextToken().toString().split("-");
String date_temp = tokens.nextToken();
String country = keys[0];
String year = keys[1];
// Mandamos año y un iterable de [ciudad,mes,temperatura,fecha]
output.collect(new Text(year), new Text(country + "," + date_temp));
}
