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 reduce(
DoubleWritable key,
Iterator<DoubleWritable> values,
OutputCollector<DoubleWritable, Text> output,
Reporter reporter)
throws IOException {
output.collect(key, new Text(values.next().toString() + " - "));
}
@Override
public void reduce(
IntWritable key,
Iterator<DoubleWritable> values,
OutputCollector<IntWritable, DoubleWritable> output,
Reporter reporter)
throws IOException {
output.collect(key, values.next());
}
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(
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(
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);
}
/** Implements the map-method of the Mapper-interface */
@Override
public void map(
LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
String token = tokenizer.nextToken();
if (token.length() > 3) {
word.set(token);
output.collect(word, one);
}
}
}
public void map(
LongWritable key,
Text value,
OutputCollector<IntWritable, DoubleWritable> output,
Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
int rowIdx = 0;
double xValue = 0;
if (tokenizer.hasMoreTokens()) {
rowIdx = Integer.parseInt(tokenizer.nextToken());
xValue = Double.parseDouble(tokenizer.nextToken());
}
double xResult = (resVec[rowIdx] - (sumVec[rowIdx] * xValue)) / diaVec[rowIdx];
output.collect(new IntWritable(rowIdx), new DoubleWritable(xResult));
}
public void map(
LongWritable key, Point value, OutputCollector<LongWritable, Point> output, Reporter reporter)
throws IOException {
double min = value.sumOfSquares(centers.get(0));
int best = 0;
for (int index = 1; index < numberOfCenters; ++index) {
double current = value.sumOfSquares(centers.get(index));
if (current < min) {
min = current;
best = index;
}
}
reporter.incrCounter("NUMBER", "NODES", 1);
reporter.incrCounter("CENTER", "" + best, 1);
output.collect(new LongWritable(best), value);
}
public void reduce(
IntWritable key,
Iterator<Text> values,
OutputCollector<IntWritable, Text> output,
Reporter reporter)
throws IOException {
HashMap<String, Integer> countries_map = new HashMap<String, Integer>();
ArrayList<Integer> counties = new ArrayList<>();
String cp = new String();
while (values.hasNext()) {
cp = values.next().toString();
if (countries_map.containsKey(cp)) {
countries_map.put(cp, countries_map.get(cp) + 1);
} else {
countries_map.put(cp, 1);
}
}
for (java.util.Map.Entry<String, Integer> entry : countries_map.entrySet()) {
counties.add(entry.getValue());
}
output.collect(
key,
new Text(
""
+ countries_map.entrySet().size()
+ " "
+ Collections.min(counties)
+ " "
+ median(counties)
+ " "
+ Collections.max(counties)
+ " "
+ mean(counties)
+ " "
+ standard_deviation(counties)));
}
public void map(
WritableComparable<?> key,
Text value,
OutputCollector<Text, CrawlDatum> output,
Reporter reporter)
throws IOException {
String url = value.toString(); // value is line of text
if (url != null && url.trim().startsWith("#")) {
/* Ignore line that start with # */
return;
}
// if tabs : metadata that could be stored
// must be name=value and separated by \t
float customScore = -1f;
int customInterval = interval;
int fixedInterval = -1;
Map<String, String> metadata = new TreeMap<String, String>();
if (url.indexOf("\t") != -1) {
String[] splits = url.split("\t");
url = splits[0];
for (int s = 1; s < splits.length; s++) {
// find separation between name and value
int indexEquals = splits[s].indexOf("=");
if (indexEquals == -1) {
// skip anything without a =
continue;
}
String metaname = splits[s].substring(0, indexEquals);
String metavalue = splits[s].substring(indexEquals + 1);
if (metaname.equals(nutchScoreMDName)) {
try {
customScore = Float.parseFloat(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFetchIntervalMDName)) {
try {
customInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFixedFetchIntervalMDName)) {
try {
fixedInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else metadata.put(metaname, metavalue);
}
}
try {
url = urlNormalizers.normalize(url, URLNormalizers.SCOPE_INJECT);
url = filters.filter(url); // filter the url
} catch (Exception e) {
if (LOG.isWarnEnabled()) {
LOG.warn("Skipping " + url + ":" + e);
}
url = null;
}
if (url == null) {
reporter.getCounter("injector", "urls_filtered").increment(1);
} else { // if it passes
value.set(url); // collect it
CrawlDatum datum = new CrawlDatum();
datum.setStatus(CrawlDatum.STATUS_INJECTED);
// Is interval custom? Then set as meta data
if (fixedInterval > -1) {
// Set writable using float. Flaot is used by AdaptiveFetchSchedule
datum
.getMetaData()
.put(Nutch.WRITABLE_FIXED_INTERVAL_KEY, new FloatWritable(fixedInterval));
datum.setFetchInterval(fixedInterval);
} else {
datum.setFetchInterval(customInterval);
}
datum.setFetchTime(curTime);
// now add the metadata
Iterator<String> keysIter = metadata.keySet().iterator();
while (keysIter.hasNext()) {
String keymd = keysIter.next();
String valuemd = metadata.get(keymd);
datum.getMetaData().put(new Text(keymd), new Text(valuemd));
}
if (customScore != -1) datum.setScore(customScore);
else datum.setScore(scoreInjected);
try {
scfilters.injectedScore(value, datum);
} catch (ScoringFilterException e) {
if (LOG.isWarnEnabled()) {
LOG.warn(
"Cannot filter injected score for url "
+ url
+ ", using default ("
+ e.getMessage()
+ ")");
}
}
reporter.getCounter("injector", "urls_injected").increment(1);
output.collect(value, datum);
}
}