List of usage examples for org.apache.hadoop.io IntWritable toString
@Override
public String toString()
From source file:org.plista.kornakapi.core.training.SemanticModel.java
License:Apache License
/** * method to load model from squence file * @throws IOException//from w w w .ja v a 2 s. com */ public void read() throws IOException { Path indexPath = path.suffix("/indexItem.model"); if (fs.exists(indexPath)) { indexItem = new HashMap<Integer, String>(); Reader reader = new SequenceFile.Reader(fs, indexPath, lconf); IntWritable key = new IntWritable(); Text val = new Text(); while (reader.next(key, val)) { indexItem.put(key.get(), val.toString()); } Closeables.close(reader, false); } Path itemIndexPath = path.suffix("/itemIndex.model"); if (fs.exists(itemIndexPath)) { itemIndex = new HashMap<String, Integer>(); Reader reader = new SequenceFile.Reader(fs, itemIndexPath, lconf); IntWritable val = new IntWritable(); Text key = new Text(); while (reader.next(key, val)) { itemIndex.put(key.toString(), val.get()); } Closeables.close(reader, false); } Path featurePath = path.suffix("/itemFeature.model"); if (fs.exists(featurePath)) { Reader reader = new SequenceFile.Reader(fs, featurePath, lconf); itemFeatures = new HashMap<String, Vector>(); Text key = new Text(); VectorWritable val = new VectorWritable(); while (reader.next(key, val)) { itemFeatures.put(key.toString(), val.get()); } Closeables.close(reader, false); } if (log.isInfoEnabled()) { log.info("LDA Model Read"); } }
From source file:org.rad.pnf.reduce.PrimeNumberReducer.java
License:Open Source License
@Override public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { List<BigInteger> primeNumbers = new ArrayList<BigInteger>(); for (IntWritable value : values) { primeNumbers.add(new BigInteger(value.toString())); }//from ww w .j ava2 s . co m context.write(key, primeNumbers); }
From source file:sigis.kmeansmultiplek.AnotherKmeans.java
private void readAndPrintOutputValues(final Configuration configuration) throws IOException { final Path input = new Path(OUTPUT_PATH + "/" + Cluster.CLUSTERED_POINTS_DIR + "/part-m-00000"); //final Path input = new Path(OUTPUT_PATH + "/" + Cluster.FINAL_ITERATION_SUFFIX + "/part-r-00000"); System.out.println(Cluster.FINAL_ITERATION_SUFFIX); System.out.println(Cluster.CLUSTERED_POINTS_DIR); final SequenceFile.Reader reader = new SequenceFile.Reader(configuration, SequenceFile.Reader.file(input)); final IntWritable key = new IntWritable(); final WeightedPropertyVectorWritable value = new WeightedPropertyVectorWritable(); while (reader.next(key, value)) { LOG.info("{} belongs to cluster {}", value.toString(), key.toString()); System.out.println(value.toString().substring(18, 28)); LOG.info("belongs to cluster {}", key.toString()); }/* w w w.ja va 2 s . c om*/ reader.close(); }
From source file:uk.bl.wa.hadoop.indexer.WARCIndexerReducer.java
License:Open Source License
@Override public void reduce(IntWritable key, Iterator<WritableSolrRecord> values, OutputCollector<Text, Text> output, Reporter reporter) throws IOException { WctEnricher wct;/*ww w . jav a 2 s . co m*/ WritableSolrRecord wsr; SolrRecord solr; // Get the slice number, but counting from 1 instead of 0: int slice = key.get() + 1; // Go through the documents for this shard: long noValues = 0; while (values.hasNext()) { wsr = values.next(); solr = wsr.getSolrRecord(); noValues++; // Add additional metadata for WCT Instances. if (solr.containsKey(WctFields.WCT_INSTANCE_ID)) { wct = new WctEnricher(key.toString()); wct.addWctMetadata(solr); } if (!dummyRun) { docs.add(solr.getSolrDocument()); // Have we exceeded the batchSize? checkSubmission(docs, batchSize, reporter); } else { log.info("DUMMY_RUN: Skipping addition of doc: " + solr.getField("id").getFirstValue()); } // Occasionally update application-level status: if ((noValues % 1000) == 0) { reporter.setStatus(this.shardPrefix + slice + ": processed " + noValues + ", dropped " + reporter.getCounter(MyCounters.NUM_DROPPED_RECORDS).getValue()); } if (this.exportXml && solr.getSolrDocument().getFieldValue(SolrFields.SOLR_URL_TYPE) != null && solr.getSolrDocument().getFieldValue(SolrFields.SOLR_URL_TYPE) .equals(SolrFields.SOLR_URL_TYPE_SLASHPAGE)) { output.collect(new Text(""), new Text(MetadataBuilder.SolrDocumentToElement(solr.getSolrDocument()))); } } try { /** * If we have at least one document unsubmitted, make sure we submit * it. */ checkSubmission(docs, 1, reporter); // If we are indexing to HDFS, shut the shard down: if (useEmbeddedServer) { // Commit, and block until the changes have been flushed. solrServer.commit(true, false); // And shut it down. solrServer.shutdown(); } } catch (Exception e) { log.error("ERROR on commit: " + e); e.printStackTrace(); } }