@Override
protected void setup(Context ctx) throws IOException, InterruptedException {
try {
Configuration conf = ctx.getConfiguration();
Path[] localFiles = DistributedCache.getLocalCacheFiles(conf);
Preconditions.checkArgument(
localFiles != null && localFiles.length >= 1,
"missing paths from the DistributedCache");
Path inputVectorPath = HadoopUtil.getSingleCachedFile(conf);
SequenceFileValueIterator<VectorWritable> iterator =
new SequenceFileValueIterator<VectorWritable>(inputVectorPath, true, conf);
try {
inputVector = iterator.next().get();
} finally {
Closeables.close(iterator, true);
}
int outDim = conf.getInt(OUTPUT_VECTOR_DIMENSION, Integer.MAX_VALUE);
outputVector =
conf.getBoolean(IS_SPARSE_OUTPUT, false)
? new RandomAccessSparseVector(outDim, 10)
: new DenseVector(outDim);
} catch (IOException ioe) {
throw new IllegalStateException(ioe);
}
}
public static Vector retrieveTimesSquaredOutputVector(
Path outputVectorTmpPath, Configuration conf) throws IOException {
Path outputFile = new Path(outputVectorTmpPath, OUTPUT_VECTOR_FILENAME + "/part-r-00000");
SequenceFileValueIterator<VectorWritable> iterator =
new SequenceFileValueIterator<VectorWritable>(outputFile, true, conf);
try {
return iterator.next().get();
} finally {
Closeables.close(iterator, true);
}
}