@Override
public int run(String[] args) throws Exception {
addInputOption();
addOutputOption();
addOption(DefaultOptionCreator.distanceMeasureOption().create());
addOption(DefaultOptionCreator.t1Option().create());
addOption(DefaultOptionCreator.t2Option().create());
addOption(DefaultOptionCreator.overwriteOption().create());
Map<String, List<String>> argMap = parseArguments(args);
if (argMap == null) {
return -1;
}
Path input = getInputPath();
Path output = getOutputPath();
if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
HadoopUtil.delete(new Configuration(), output);
}
String measureClass = getOption(DefaultOptionCreator.DISTANCE_MEASURE_OPTION);
double t1 = Double.parseDouble(getOption(DefaultOptionCreator.T1_OPTION));
double t2 = Double.parseDouble(getOption(DefaultOptionCreator.T2_OPTION));
DistanceMeasure measure = ClassUtils.instantiateAs(measureClass, DistanceMeasure.class);
run(input, output, measure, t1, t2);
return 0;
}
@Override
public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
addInputOption();
addOutputOption();
addOption(MinhashOptionCreator.minClusterSizeOption().create());
addOption(MinhashOptionCreator.minVectorSizeOption().create());
addOption(MinhashOptionCreator.hashTypeOption().create());
addOption(MinhashOptionCreator.numHashFunctionsOption().create());
addOption(MinhashOptionCreator.keyGroupsOption().create());
addOption(MinhashOptionCreator.numReducersOption().create());
addOption(MinhashOptionCreator.debugOutputOption().create());
addOption(DefaultOptionCreator.overwriteOption().create());
if (parseArguments(args) == null) {
return -1;
}
Path input = getInputPath();
Path output = getOutputPath();
if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
HadoopUtil.delete(getConf(), output);
}
int minClusterSize = Integer.valueOf(getOption(MinhashOptionCreator.MIN_CLUSTER_SIZE));
int minVectorSize = Integer.valueOf(getOption(MinhashOptionCreator.MIN_VECTOR_SIZE));
String hashType = getOption(MinhashOptionCreator.HASH_TYPE);
int numHashFunctions = Integer.valueOf(getOption(MinhashOptionCreator.NUM_HASH_FUNCTIONS));
int keyGroups = Integer.valueOf(getOption(MinhashOptionCreator.KEY_GROUPS));
int numReduceTasks = Integer.parseInt(getOption(MinhashOptionCreator.NUM_REDUCERS));
boolean debugOutput = hasOption(MinhashOptionCreator.DEBUG_OUTPUT);
runJob(
input,
output,
minClusterSize,
minVectorSize,
hashType,
numHashFunctions,
keyGroups,
numReduceTasks,
debugOutput);
return 0;
}
@Override
public int run(String[] args) throws Exception {
String path = System.getProperty("user.dir");
addInputOption();
addOutputOption();
addOption(ALPHA_I, "a", "smoothing parameter", String.valueOf(1.0f));
addOption(
buildOption(
TRAIN_COMPLEMENTARY, "c", "train complementary?", false, false, String.valueOf(false)));
addOption(LABEL_INDEX, "li", "The path to store the label index in", false);
addOption(DefaultOptionCreator.overwriteOption().create());
Path labPath = new Path(path + "/../out/labelindex/");
long labelSize = createLabelIndex(labPath);
float alphaI = 1.0F;
boolean trainComplementary = true;
HadoopUtil.setSerializations(getConf());
HadoopUtil.cacheFiles(labPath, getConf());
HadoopUtil.delete(getConf(), new Path("/tmp/summedObservations"));
HadoopUtil.delete(getConf(), new Path("/tmp/weights"));
HadoopUtil.delete(getConf(), new Path("/tmp/thetas"));
// Add up all the vectors with the same labels, while mapping the labels into our index
Job indexInstances =
prepareJob(
new Path(path + "/../out/training"),
new Path("/tmp/summedObservations"),
SequenceFileInputFormat.class,
IndexInstancesMapper.class,
IntWritable.class,
VectorWritable.class,
VectorSumReducer.class,
IntWritable.class,
VectorWritable.class,
SequenceFileOutputFormat.class);
indexInstances.setCombinerClass(VectorSumReducer.class);
boolean succeeded = indexInstances.waitForCompletion(true);
if (!succeeded) {
return -1;
}
// Sum up all the weights from the previous step, per label and per feature
Job weightSummer =
prepareJob(
new Path("/tmp/summedObservations"),
new Path("/tmp/weights"),
SequenceFileInputFormat.class,
WeightsMapper.class,
Text.class,
VectorWritable.class,
VectorSumReducer.class,
Text.class,
VectorWritable.class,
SequenceFileOutputFormat.class);
weightSummer.getConfiguration().set(WeightsMapper.NUM_LABELS, String.valueOf(labelSize));
weightSummer.setCombinerClass(VectorSumReducer.class);
succeeded = weightSummer.waitForCompletion(true);
if (!succeeded) {
return -1;
}
// Put the per label and per feature vectors into the cache
HadoopUtil.cacheFiles(new Path("/tmp/weights"), getConf());
if (trainComplementary) {
// Calculate the per label theta normalizers, write out to LABEL_THETA_NORMALIZER vector
// see http://people.csail.mit.edu/jrennie/papers/icml03-nb.pdf - Section 3.2, Weight
// Magnitude Errors
Job thetaSummer =
prepareJob(
new Path("/tmp/summedObservations"),
new Path("/tmp/thetas"),
SequenceFileInputFormat.class,
ThetaMapper.class,
Text.class,
VectorWritable.class,
VectorSumReducer.class,
Text.class,
VectorWritable.class,
SequenceFileOutputFormat.class);
thetaSummer.setCombinerClass(VectorSumReducer.class);
thetaSummer.getConfiguration().setFloat(ThetaMapper.ALPHA_I, alphaI);
thetaSummer
.getConfiguration()
.setBoolean(ThetaMapper.TRAIN_COMPLEMENTARY, trainComplementary);
succeeded = thetaSummer.waitForCompletion(true);
if (!succeeded) {
return -1;
}
}
// Put the per label theta normalizers into the cache
HadoopUtil.cacheFiles(new Path("/tmp/thetas"), getConf());
// Validate our model and then write it out to the official output
getConf().setFloat(ThetaMapper.ALPHA_I, alphaI);
getConf().setBoolean(NaiveBayesModel.COMPLEMENTARY_MODEL, trainComplementary);
NaiveBayesModel naiveBayesModel = BayesUtils.readModelFromDir(new Path("/tmp/"), getConf());
naiveBayesModel.validate();
naiveBayesModel.serialize(new Path(path + "/../out/model"), getConf());
return 0;
}
@Override
public int run(String[] args) throws Exception {
addInputOption();
addOutputOption();
addOption("numberOfColumns", "r", "Number of columns in the input matrix", false);
addOption(
"similarityClassname",
"s",
"Name of distributed similarity class to instantiate, alternatively use "
+ "one of the predefined similarities ("
+ VectorSimilarityMeasures.list()
+ ')');
addOption(
"maxSimilaritiesPerRow",
"m",
"Number of maximum similarities per row (default: "
+ DEFAULT_MAX_SIMILARITIES_PER_ROW
+ ')',
String.valueOf(DEFAULT_MAX_SIMILARITIES_PER_ROW));
addOption(
"excludeSelfSimilarity",
"ess",
"compute similarity of rows to themselves?",
String.valueOf(false));
addOption("threshold", "tr", "discard row pairs with a similarity value below this", false);
addOption(DefaultOptionCreator.overwriteOption().create());
Map<String, List<String>> parsedArgs = parseArguments(args);
if (parsedArgs == null) {
return -1;
}
int numberOfColumns;
if (hasOption("numberOfColumns")) {
// Number of columns explicitly specified via CLI
numberOfColumns = Integer.parseInt(getOption("numberOfColumns"));
} else {
// else get the number of columns by determining the cardinality of a vector in the input
// matrix
numberOfColumns = getDimensions(getInputPath());
}
String similarityClassnameArg = getOption("similarityClassname");
String similarityClassname;
try {
similarityClassname = VectorSimilarityMeasures.valueOf(similarityClassnameArg).getClassname();
} catch (IllegalArgumentException iae) {
similarityClassname = similarityClassnameArg;
}
// Clear the output and temp paths if the overwrite option has been set
if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
// Clear the temp path
HadoopUtil.delete(getConf(), getTempPath());
// Clear the output path
HadoopUtil.delete(getConf(), getOutputPath());
}
int maxSimilaritiesPerRow = Integer.parseInt(getOption("maxSimilaritiesPerRow"));
boolean excludeSelfSimilarity = Boolean.parseBoolean(getOption("excludeSelfSimilarity"));
double threshold =
hasOption("threshold") ? Double.parseDouble(getOption("threshold")) : NO_THRESHOLD;
Path weightsPath = getTempPath("weights");
Path normsPath = getTempPath("norms.bin");
Path numNonZeroEntriesPath = getTempPath("numNonZeroEntries.bin");
Path maxValuesPath = getTempPath("maxValues.bin");
Path pairwiseSimilarityPath = getTempPath("pairwiseSimilarity");
AtomicInteger currentPhase = new AtomicInteger();
if (shouldRunNextPhase(parsedArgs, currentPhase)) {
Job normsAndTranspose =
prepareJob(
getInputPath(),
weightsPath,
VectorNormMapper.class,
IntWritable.class,
VectorWritable.class,
MergeVectorsReducer.class,
IntWritable.class,
VectorWritable.class);
normsAndTranspose.setCombinerClass(MergeVectorsCombiner.class);
Configuration normsAndTransposeConf = normsAndTranspose.getConfiguration();
normsAndTransposeConf.set(THRESHOLD, String.valueOf(threshold));
normsAndTransposeConf.set(NORMS_PATH, normsPath.toString());
normsAndTransposeConf.set(NUM_NON_ZERO_ENTRIES_PATH, numNonZeroEntriesPath.toString());
normsAndTransposeConf.set(MAXVALUES_PATH, maxValuesPath.toString());
normsAndTransposeConf.set(SIMILARITY_CLASSNAME, similarityClassname);
boolean succeeded = normsAndTranspose.waitForCompletion(true);
if (!succeeded) {
return -1;
}
}
if (shouldRunNextPhase(parsedArgs, currentPhase)) {
Job pairwiseSimilarity =
prepareJob(
weightsPath,
pairwiseSimilarityPath,
CooccurrencesMapper.class,
IntWritable.class,
VectorWritable.class,
SimilarityReducer.class,
IntWritable.class,
VectorWritable.class);
pairwiseSimilarity.setCombinerClass(VectorSumReducer.class);
Configuration pairwiseConf = pairwiseSimilarity.getConfiguration();
pairwiseConf.set(THRESHOLD, String.valueOf(threshold));
pairwiseConf.set(NORMS_PATH, normsPath.toString());
pairwiseConf.set(NUM_NON_ZERO_ENTRIES_PATH, numNonZeroEntriesPath.toString());
pairwiseConf.set(MAXVALUES_PATH, maxValuesPath.toString());
pairwiseConf.set(SIMILARITY_CLASSNAME, similarityClassname);
pairwiseConf.setInt(NUMBER_OF_COLUMNS, numberOfColumns);
pairwiseConf.setBoolean(EXCLUDE_SELF_SIMILARITY, excludeSelfSimilarity);
boolean succeeded = pairwiseSimilarity.waitForCompletion(true);
if (!succeeded) {
return -1;
}
}
if (shouldRunNextPhase(parsedArgs, currentPhase)) {
Job asMatrix =
prepareJob(
pairwiseSimilarityPath,
getOutputPath(),
UnsymmetrifyMapper.class,
IntWritable.class,
VectorWritable.class,
MergeToTopKSimilaritiesReducer.class,
IntWritable.class,
VectorWritable.class);
asMatrix.setCombinerClass(MergeToTopKSimilaritiesReducer.class);
asMatrix.getConfiguration().setInt(MAX_SIMILARITIES_PER_ROW, maxSimilaritiesPerRow);
boolean succeeded = asMatrix.waitForCompletion(true);
if (!succeeded) {
return -1;
}
}
return 0;
}