marf.Classification.Stochastic
Class ZipfLaw

java.lang.Object
  marf.Storage.StorageManager
      marf.Classification.Classification
          marf.Classification.Stochastic.Stochastic
              marf.Classification.Stochastic.ZipfLaw

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, IClassification, IStorageManager

public class ZipfLaw
extends Stochastic

Module exercising Zipf's Law.

$Id: ZipfLaw.java,v 1.32 2007/12/31 00:17:05 mokhov Exp $

Since:

0.3.0.2

Version:

$Revision: 1.32 $

Author:

Serguei Mokhov

See Also:

Serialized Form

Field Summary

static int

DEFAULT_OUTPUT_PAGE_SIZE Default number of entries display/output per page.

Fields inherited from class marf.Classification.Classification

adFeatureVector, oFeatureExtraction, oResultSet, oTrainingSet

Fields inherited from class marf.Storage.StorageManager

bDumpOnNotFound, iCurrentDumpMode, oObjectToSerialize, strFilename

Fields inherited from interface marf.Classification.IClassification

MARF_INTERFACE_CODE_REVISION

Fields inherited from interface marf.Storage.IStorageManager

DUMP_BINARY, DUMP_CSV_TEXT, DUMP_GZIP_BINARY, DUMP_HTML, DUMP_SQL, DUMP_XML, MARF_INTERFACE_CODE_REVISION, STORAGE_FILE_EXTENSIONS

Constructor Summary

ZipfLaw(IFeatureExtraction poFeatureExtraction)
Classification API.

ZipfLaw(java.lang.String pstrStatsFilename)
Takes a filename argument.

Method Summary

void	backSynchronizeObject() Must to be overridden by the modules that use object serialization with the generic implementation of restore().
boolean	classify(double[] padFeatureVector) Not Implemented.
void	collectStatistics(double[] padFeatures) Collects result statistics.
void	collectStatistics(java.io.StreamTokenizer poStreamTokenizer) Collects result statistics.
void	dump() An object must know how dump itself or its data structures to a file.
void	dumpAll() Dumps results to STDOUT.
void	dumpCSV() Implements CSV dump through the dumpGraphValues() method.
void	dumpGraphValues() Dumps CVS values of the rank and frequency into a file.
static java.lang.String	getMARFSourceCodeRevision() Retrieves class' revision.
int	getMaxWordLength() Allows getting the length of the longest word found (in characters).
int	getMinWordLength() Allows getting the length of the smallest word found (in characters).
Result	getResult() Retrieves the maximum-probability classification result.
StatisticalObject[]	getSortedStatRefs() Allows getting an array of sorted references to WordStats objects.
java.util.Hashtable	getStats() Allows getting raw Hashtable of the WordStats objects.
WordStats	getWordStats(java.lang.String pstrLexeme) Allows getting a particular WordStats object by its lexeme.
boolean	isDumpLogariphmOn() Allows examining the value of the log-log flag.
void	restore() An object must know how restore itself or its data structures from a file.
void	setDumpLogariphm(boolean pbDumpLogariphm) Allows setting the dump log-log flag to indicate the module to dump graphs in the log-log scale.
java.lang.String	toString() Reports minimum and maximum word lengths and the dictionary itself in a form of a String.
boolean	train(double[] padFeatureVector) Not Implemented.

Methods inherited from class marf.Classification.Classification

classify, clone, getFeatureExtraction, getResultSet, getTrainingSetFilename, loadTrainingSet, setFeatureExtraction, train

Methods inherited from class marf.Storage.StorageManager

dumpBinary, dumpGzipBinary, dumpHTML, dumpSQL, dumpXML, enableDumpOnNotFound, equals, getDefaultExtension, getDefaultExtension, getDumpMode, getFilename, getObjectToSerialize, hashCode, restoreBinary, restoreCSV, restoreGzipBinary, restoreHTML, restoreSQL, restoreXML, setDumpMode, setFilename

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Field Detail

DEFAULT_OUTPUT_PAGE_SIZE

public static final int DEFAULT_OUTPUT_PAGE_SIZE

Default number of entries display/output per page.

Since:

0.3.0.5

See Also:

Constant Field Values

Constructor Detail

ZipfLaw

public ZipfLaw(java.lang.String pstrStatsFilename)

Takes a filename argument.

Parameters:

pstrStatsFilename - the desired file to process

ZipfLaw

public ZipfLaw(IFeatureExtraction poFeatureExtraction)

Classification API.

Parameters:

poFeatureExtraction - preprocessing module to get the data from

Method Detail

classify

public boolean classify(double[] padFeatureVector)
                 throws ClassificationException

Description copied from class: Stochastic

Not Implemented.

Specified by:

classify in interface IClassification

Overrides:

classify in class Stochastic

Parameters:

padFeatureVector - vector of features to compare with the stored ones

Returns:

nothing

Throws:

ClassificationException - never thrown

Since:

0.3.0.6

See Also:

IClassification.classify(double[])

train

public boolean train(double[] padFeatureVector)
              throws ClassificationException

Description copied from class: Stochastic

Not Implemented.

Specified by:

train in interface IClassification

Overrides:

train in class Stochastic

Parameters:

padFeatureVector - feature vector to train on

Returns:

nothing

Throws:

ClassificationException - never thrown

Since:

0.3.0.6

See Also:

IClassification.train(double[])

getResult

public Result getResult()

Description copied from class: Stochastic

Retrieves the maximum-probability classification result.

Specified by:

getResult in interface IClassification

Overrides:

getResult in class Stochastic

Returns:

Result object

Since:

0.3.0.6

See Also:

IClassification.getResult()

collectStatistics

public final void collectStatistics(double[] padFeatures)
                             throws ClassificationException

Collects result statistics. TODO: employ StatsCollector.

Parameters:

padFeatures - desired stream tokenizer

Throws:

ClassificationException - in case of inner exceptions

collectStatistics

public final void collectStatistics(java.io.StreamTokenizer poStreamTokenizer)
                             throws ClassificationException

Collects result statistics. TODO: employ StatsCollector.

Parameters:

poStreamTokenizer - desired stream tokenizer

Throws:

ClassificationException - in case of inner exceptions

dumpAll

public final void dumpAll()

Dumps results to STDOUT.

dumpGraphValues

public final void dumpGraphValues()
                           throws java.io.IOException

Dumps CVS values of the rank and frequency into a file. Filename is composed from the original corpus name plus the .csv extension. By default the dump is in the log() scale.

Throws:

java.io.IOException

backSynchronizeObject

public void backSynchronizeObject()

Description copied from class: StorageManager

Must to be overridden by the modules that use object serialization with the generic implementation of restore(). By default this method is unimplemented.

Overrides:

backSynchronizeObject in class StorageManager

Since:

0.3.0.5

See Also:

restore(), StorageManager.backSynchronizeObject()

dump

public void dump()
          throws StorageException

An object must know how dump itself or its data structures to a file. Options are: Object serialization and CSV. Internally, the method calls all the dump*() methods based on the current dump mode. This derivative uses only DUMP_GZIP_BINARY, DUMP_BINARY and DUMP_CSV_TEXT modes.

Specified by:

dump in interface IStorageManager

Overrides:

dump in class Classification

Throws:

StorageException - if saving to a file for some reason fails or the dump mode set to an unsupported value

Since:

0.3.0.5

See Also:

StorageManager.dumpGzipBinary(), dumpCSV(), StorageManager.dumpBinary(), backSynchronizeObject()

restore

public void restore()
             throws StorageException

An object must know how restore itself or its data structures from a file. Options are: Object serialization and CSV. Internally, the method calls all the restore*() methods based on the current dump mode.

Specified by:

restore in interface IStorageManager

Overrides:

restore in class Classification

Throws:

StorageException - if loading from a file for some reason fails or the dump mode set to an unsupported value

Since:

0.3.0.5

See Also:

IStorageManager.DUMP_GZIP_BINARY, IStorageManager.DUMP_BINARY, IStorageManager.DUMP_CSV_TEXT, StorageManager.dumpGzipBinary(), StorageManager.dumpBinary(), dumpCSV(), backSynchronizeObject(), StorageManager.iCurrentDumpMode

dumpCSV

public void dumpCSV()
             throws StorageException

Implements CSV dump through the dumpGraphValues() method.

Specified by:

dumpCSV in interface IStorageManager

Overrides:

dumpCSV in class StorageManager

Throws:

StorageException - in case of any I/O error

Since:

0.3.0.5

See Also:

dumpGraphValues()

isDumpLogariphmOn

public boolean isDumpLogariphmOn()

Allows examining the value of the log-log flag.

Returns:

the current value of the flag

Since:

0.3.0.5

See Also:

setDumpLogariphm(boolean)

setDumpLogariphm

public void setDumpLogariphm(boolean pbDumpLogariphm)

Allows setting the dump log-log flag to indicate the module to dump graphs in the log-log scale.

Parameters:

pbDumpLogariphm - new value of the log-log flag

Since:

0.3.0.5

getSortedStatRefs

public final StatisticalObject[] getSortedStatRefs()

Allows getting an array of sorted references to WordStats objects.

Returns:

the sorted WordStats array

Since:

0.3.0.5

getStats

public final java.util.Hashtable getStats()

Allows getting raw Hashtable of the WordStats objects.

Returns:

the stats hashtable

Since:

0.3.0.5

getWordStats

public final WordStats getWordStats(java.lang.String pstrLexeme)

Allows getting a particular WordStats object by its lexeme.

Parameters:

pstrLexeme - lexeme to look up the WordStats entry

Returns:

the corresponding WordStats entry or null if not found

Since:

0.3.0.5

getMaxWordLength

public final int getMaxWordLength()

Allows getting the length of the longest word found (in characters).

Returns:

the length of the longest word in the dictionary

Since:

0.3.0.5

getMinWordLength

public final int getMinWordLength()

Allows getting the length of the smallest word found (in characters).

Returns:

the length of the smallest word in the dictionary

Since:

0.3.0.5

toString

public java.lang.String toString()

Reports minimum and maximum word lengths and the dictionary itself in a form of a String.

Overrides:

toString in class StorageManager

Since:

0.3.0.5

See Also:

Object.toString()

getMARFSourceCodeRevision

public static java.lang.String getMARFSourceCodeRevision()

Retrieves class' revision.

Returns:

revision string