org.apache.mahout.utils.clustering

Class ClusterDumper

java.lang.Object

org.apache.hadoop.conf.Configured

org.apache.mahout.common.AbstractJob

org.apache.mahout.utils.clustering.ClusterDumper

All Implemented Interfaces:

org.apache.hadoop.conf.Configurable, org.apache.hadoop.util.Tool

public final class ClusterDumper
extends AbstractJob

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ClusterDumper.OUTPUT_FORMAT

Field Summary

Fields

Modifier and Type	Field and Description
static String	DICTIONARY_OPTION
static String	DICTIONARY_TYPE_OPTION
static String	EVALUATE_CLUSTERS
static String	NUM_WORDS_OPTION
static String	OUTPUT_FORMAT_OPT
static String	POINTS_DIR_OPTION
static String	SAMPLE_POINTS
static String	SUBSTRING_OPTION

Fields inherited from class org.apache.mahout.common.AbstractJob

argMap, inputFile, inputPath, outputFile, outputPath, tempPath

Constructor Summary

Constructors

Constructor and Description
ClusterDumper()
ClusterDumper(org.apache.hadoop.fs.Path seqFileDir, org.apache.hadoop.fs.Path pointsDir)

Method Summary

Methods

Modifier and Type	Method and Description
Map<Integer,List<WeightedVectorWritable>>	getClusterIdToPoints()
long	getMaxPointsPerCluster()
int	getNumTopFeatures()
int	getSubString()
String	getTermDictionary()
static void	main(String[] args)
void	printClusters(String[] dictionary)
static Map<Integer,List<WeightedVectorWritable>>	readPoints(org.apache.hadoop.fs.Path pointsPathDir, long maxPointsPerCluster, org.apache.hadoop.conf.Configuration conf)
int	run(String[] args)
void	setMaxPointsPerCluster(long maxPointsPerCluster)
void	setNumTopFeatures(int num)
void	setSubString(int subString)
void	setTermDictionary(String termDictionary, String dictionaryType)

Methods inherited from class org.apache.mahout.common.AbstractJob

addFlag, addInputOption, addOption, addOption, addOption, addOption, addOutputOption, buildOption, buildOption, getAnalyzerClassFromOption, getCLIOption, getConf, getDimensions, getFloat, getFloat, getGroup, getInputFile, getInputPath, getInt, getInt, getOption, getOption, getOption, getOptions, getOutputFile, getOutputPath, getOutputPath, getTempPath, getTempPath, hasOption, keyFor, maybePut, parseArguments, parseArguments, parseDirectories, prepareJob, prepareJob, prepareJob, prepareJob, setConf, setS3SafeCombinedInputPath, shouldRunNextPhase

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

SAMPLE_POINTS

public static final String SAMPLE_POINTS

See Also:

Constant Field Values

DICTIONARY_TYPE_OPTION

public static final String DICTIONARY_TYPE_OPTION

See Also:

Constant Field Values

DICTIONARY_OPTION

public static final String DICTIONARY_OPTION

See Also:

Constant Field Values

POINTS_DIR_OPTION

public static final String POINTS_DIR_OPTION

See Also:

Constant Field Values

NUM_WORDS_OPTION

public static final String NUM_WORDS_OPTION

See Also:

Constant Field Values

SUBSTRING_OPTION

public static final String SUBSTRING_OPTION

See Also:

Constant Field Values

EVALUATE_CLUSTERS

public static final String EVALUATE_CLUSTERS

See Also:

Constant Field Values

OUTPUT_FORMAT_OPT

public static final String OUTPUT_FORMAT_OPT

See Also:

Constant Field Values

Constructor Detail

ClusterDumper

public ClusterDumper(org.apache.hadoop.fs.Path seqFileDir,
             org.apache.hadoop.fs.Path pointsDir)

ClusterDumper

public ClusterDumper()

Method Detail

main

public static void main(String[] args)
                 throws Exception

Throws:

Exception

run

public int run(String[] args)
        throws Exception

Throws:

Exception

printClusters

public void printClusters(String[] dictionary)
                   throws Exception

Throws:

Exception

getSubString

public int getSubString()

setSubString

public void setSubString(int subString)

getClusterIdToPoints

public Map<Integer,List<WeightedVectorWritable>> getClusterIdToPoints()

getTermDictionary

public String getTermDictionary()

setTermDictionary

public void setTermDictionary(String termDictionary,
                     String dictionaryType)

setNumTopFeatures

public void setNumTopFeatures(int num)

getNumTopFeatures

public int getNumTopFeatures()

getMaxPointsPerCluster

public long getMaxPointsPerCluster()

setMaxPointsPerCluster

public void setMaxPointsPerCluster(long maxPointsPerCluster)

readPoints

public static Map<Integer,List<WeightedVectorWritable>> readPoints(org.apache.hadoop.fs.Path pointsPathDir,
                                                   long maxPointsPerCluster,
                                                   org.apache.hadoop.conf.Configuration conf)