[marf-cvs] marf/src/marf/Stats Ngram.java, 1.15, 1.15.6.1 Observation.java, 1.12, 1.12.6.1 Probabi
Brought to you by:
mokhov
From: Serguei A. M. <mo...@us...> - 2008-04-09 00:32:50
|
Update of /cvsroot/marf/marf/src/marf/Stats In directory sc8-pr-cvs16.sourceforge.net:/tmp/cvs-serv9497/src/marf/Stats Modified Files: Tag: DISTRIBUTED_MARF_0_3_0_INTEGRATION Ngram.java Observation.java ProbabilityTable.java StatisticalObject.java WordStats.java Log Message: Consolidate most of the differences between the MAIN and Distributed MARF branches. This primarily includes the copyright year update to 2008, SpeakerIdentApp with the new options of loaders and the BandStopFilter, ZipfLaw, CosineSimilarityMeasure, and HammingDistance. Include stats per config along with stats per subject. Add timing measurements. A lot of comment spell checks and other corrections. Generalize some of the code, fix naming conventions in places. Fix some bugs that popped up in the main branch down to DMARF. Add some new implementation developments, such as nlp.Storage and Classification.Similarity. Refactor Configuration and some other classes. Make WAVLoader more customizable, in particular being able to load 16000 Hz samples. Many other fixes that will be summarized in the MAIN's ChangeLog. Index: Observation.java =================================================================== RCS file: /cvsroot/marf/marf/src/marf/Stats/Observation.java,v retrieving revision 1.12 retrieving revision 1.12.6.1 diff -C2 -d -r1.12 -r1.12.6.1 *** Observation.java 2 Jan 2006 22:24:00 -0000 1.12 --- Observation.java 9 Apr 2008 00:32:15 -0000 1.12.6.1 *************** *** 3,7 **** /** ! * <p>Generic Observation of an occurce of something (like a word or an n-gram).</p> * * $Id$ --- 3,7 ---- /** ! * <p>Generic Observation of an occurrence of something (like a word or an n-gram).</p> * * $Id$ Index: ProbabilityTable.java =================================================================== RCS file: /cvsroot/marf/marf/src/marf/Stats/ProbabilityTable.java,v retrieving revision 1.40 retrieving revision 1.40.6.1 diff -C2 -d -r1.40 -r1.40.6.1 *** ProbabilityTable.java 13 Feb 2006 00:35:22 -0000 1.40 --- ProbabilityTable.java 9 Apr 2008 00:32:15 -0000 1.40.6.1 *************** *** 85,89 **** /** * Retrieves the probability of a list of observations ! * as a number of occurences. * @param poObservationList a collection of observations * @return the probability --- 85,89 ---- /** * Retrieves the probability of a list of observations ! * as a number of occurrences. * @param poObservationList a collection of observations * @return the probability *************** *** 91,95 **** public final synchronized double p(final Vector poObservationList) { ! double dProbability = getOccurence(poObservationList); Debug.debug --- 91,95 ---- public final synchronized double p(final Vector poObservationList) { ! double dProbability = getOccurrence(poObservationList); Debug.debug *************** *** 114,124 **** /** ! * Allows setting an occurence given the <i>x</i> coordinate. * An unigram model is assumed. * @param piX the <i>x</i> index ! * @param pdOccurence the occurence * @throws ArrayIndexOutOfBoundsException if the coordinate is out of range */ ! public final synchronized void setOccurence(final int piX, final double pdOccurence) { if --- 114,124 ---- /** ! * Allows setting an occurrence given the <i>x</i> coordinate. * An unigram model is assumed. * @param piX the <i>x</i> index ! * @param pdOccurence the occurrence * @throws ArrayIndexOutOfBoundsException if the coordinate is out of range */ ! public final synchronized void setOccurrence(final int piX, final double pdOccurence) { if *************** *** 137,152 **** oObservationList.add(this.oColumnIndex.elementAt(piX)); ! setOccurence(oObservationList, pdOccurence); } /** ! * Allows setting an occurence given the <i>x</i> and <i>y</i> coordinates. * A bigram model is assumed. * @param piX the <i>x</i> index * @param piY the <i>y</i> index ! * @param pdOccurence the occurence * @throws ArrayIndexOutOfBoundsException if either of the coordinates is out of range */ ! public final synchronized void setOccurence(final int piX, final int piY, final double pdOccurence) { if --- 137,152 ---- oObservationList.add(this.oColumnIndex.elementAt(piX)); ! setOccurrence(oObservationList, pdOccurence); } /** ! * Allows setting an occurrence given the <i>x</i> and <i>y</i> coordinates. * A bigram model is assumed. * @param piX the <i>x</i> index * @param piY the <i>y</i> index ! * @param pdOccurrence the occurrence * @throws ArrayIndexOutOfBoundsException if either of the coordinates is out of range */ ! public final synchronized void setOccurrence(final int piX, final int piY, final double pdOccurrence) { if *************** *** 170,186 **** oObservationList.add(this.oColumnIndex.elementAt(piX)); ! setOccurence(oObservationList, pdOccurence); } /** ! * Allows setting an occurence given the <i>x</i>, <i>y</i>, and <i>z</i> coordinates. * A trigram model is assumed. * @param piX the <i>x</i> index * @param piY the <i>y</i> index * @param piZ the <i>z</i> index ! * @param pdOccurence the occurence * @throws ArrayIndexOutOfBoundsException if either of the coordinates is out of range */ ! public final synchronized void setOccurence(final int piX, final int piY, final int piZ, final double pdOccurence) { if --- 170,186 ---- oObservationList.add(this.oColumnIndex.elementAt(piX)); ! setOccurrence(oObservationList, pdOccurrence); } /** ! * Allows setting an occurrence given the <i>x</i>, <i>y</i>, and <i>z</i> coordinates. * A trigram model is assumed. * @param piX the <i>x</i> index * @param piY the <i>y</i> index * @param piZ the <i>z</i> index ! * @param pdOccurrence the occurrence * @throws ArrayIndexOutOfBoundsException if either of the coordinates is out of range */ ! public final synchronized void setOccurrence(final int piX, final int piY, final int piZ, final double pdOccurrence) { if *************** *** 209,223 **** oObservationList.add(this.oColumnIndex.elementAt(piX)); ! setOccurence(oObservationList, pdOccurence); } /** ! * Allows getting an occurence given the <i>x</i> coordinate. * An unigram model is assumed. * @param piX the <i>x</i> index ! * @return the number of occurences of the item at the coordinates. * @throws ArrayIndexOutOfBoundsException if the coordinate is out of range */ ! public final synchronized double getOccurence(final int piX) { if --- 209,223 ---- oObservationList.add(this.oColumnIndex.elementAt(piX)); ! setOccurrence(oObservationList, pdOccurrence); } /** ! * Allows getting an occurrence given the <i>x</i> coordinate. * An unigram model is assumed. * @param piX the <i>x</i> index ! * @return the number of occurrences of the item at the coordinates. * @throws ArrayIndexOutOfBoundsException if the coordinate is out of range */ ! public final synchronized double getOccurrence(final int piX) { if *************** *** 236,251 **** oObservationList.add(this.oColumnIndex.elementAt(piX)); ! return getOccurence(oObservationList); } /** ! * Allows getting an occurence given <i>x</i> and <i>y</i> coordinates. * A bigram model is assumed. * @param piX the <i>x</i> index * @param piY the <i>y</i> index ! * @return the number of occurences of the item at the coordinates. * @throws ArrayIndexOutOfBoundsException if either of the coordinates is out of range */ ! public final synchronized double getOccurence(final int piX, final int piY) { Debug.debug("getOccurence("+piX+","+piY+")"); --- 236,251 ---- oObservationList.add(this.oColumnIndex.elementAt(piX)); ! return getOccurrence(oObservationList); } /** ! * Allows getting an occurrence given <i>x</i> and <i>y</i> coordinates. * A bigram model is assumed. * @param piX the <i>x</i> index * @param piY the <i>y</i> index ! * @return the number of occurrences of the item at the coordinates. * @throws ArrayIndexOutOfBoundsException if either of the coordinates is out of range */ ! public final synchronized double getOccurrence(final int piX, final int piY) { Debug.debug("getOccurence("+piX+","+piY+")"); *************** *** 271,287 **** oObservationList.add(this.oColumnIndex.elementAt(piX)); ! return getOccurence(oObservationList); } /** ! * Allows getting an occurence given <i>x</i>, <i>y</i>, and <i>z</i> coordinates. * A trigram model is assumed. * @param piX the <i>x</i> index * @param piY the <i>y</i> index * @param piZ the <i>z</i> index ! * @return the number of occurences of the item at the coordinates. * @throws ArrayIndexOutOfBoundsException if either of the coordinates is out of range */ ! public final double getOccurence(final int piX, final int piY, final int piZ) { if --- 271,287 ---- oObservationList.add(this.oColumnIndex.elementAt(piX)); ! return getOccurrence(oObservationList); } /** ! * Allows getting an occurrence given <i>x</i>, <i>y</i>, and <i>z</i> coordinates. * A trigram model is assumed. * @param piX the <i>x</i> index * @param piY the <i>y</i> index * @param piZ the <i>z</i> index ! * @return the number of occurrences of the item at the coordinates. * @throws ArrayIndexOutOfBoundsException if either of the coordinates is out of range */ ! public final double getOccurrence(final int piX, final int piY, final int piZ) { if *************** *** 310,323 **** oObservationList.add(this.oColumnIndex.elementAt(piX)); ! return getOccurence(oObservationList); } /** ! * Allows setting an occurence of a list of observations. * Works with uni-, bi-, and trigram models. * @param poObservationList the list ! * @param pdOccurence the desired occurence */ ! public final synchronized void setOccurence(final Vector poObservationList, final double pdOccurence) { int iUniIndex; --- 310,323 ---- oObservationList.add(this.oColumnIndex.elementAt(piX)); ! return getOccurrence(oObservationList); } /** ! * Allows setting an occurrence of a list of observations. * Works with uni-, bi-, and trigram models. * @param poObservationList the list ! * @param pdOccurrence the desired occurrence */ ! public final synchronized void setOccurrence(final Vector poObservationList, final double pdOccurrence) { int iUniIndex; *************** *** 325,329 **** int iTriIndex; ! // Debug.debug("setOccurence(poObservationList["+poObservationList+"])"); switch(poObservationList.size()) --- 325,329 ---- int iTriIndex; ! // Debug.debug("setOccurrence(poObservationList["+poObservationList+"])"); switch(poObservationList.size()) *************** *** 336,344 **** { this.oColumnIndex.add(poObservationList.elementAt(0)); ! this.oNMatrix.add(new Double(pdOccurence)); } else { ! this.oNMatrix.setElementAt(new Double(pdOccurence), iUniIndex); } --- 336,344 ---- { this.oColumnIndex.add(poObservationList.elementAt(0)); ! this.oNMatrix.add(new Double(pdOccurrence)); } else { ! this.oNMatrix.setElementAt(new Double(pdOccurrence), iUniIndex); } *************** *** 384,388 **** oRow.setSize(iBiIndex + 1); ! oRow.setElementAt(new Double(pdOccurence), iBiIndex); break; --- 384,388 ---- oRow.setSize(iBiIndex + 1); ! oRow.setElementAt(new Double(pdOccurrence), iBiIndex); break; *************** *** 484,488 **** oRow.setSize(iTriIndex + 1); ! oRow.setElementAt(new Double(pdOccurence), iTriIndex); break; --- 484,488 ---- oRow.setSize(iTriIndex + 1); ! oRow.setElementAt(new Double(pdOccurrence), iTriIndex); break; *************** *** 492,503 **** /** ! * Allows getting the occurence of a list of observations. * Works with uni-, bi-, and trigram models. * @param poObservationList the list ! * @return the number of occurences */ ! public final synchronized double getOccurence(final Vector poObservationList) { ! double dOccurence = 0.0; int iUniIndex; --- 492,503 ---- /** ! * Allows getting the occurrence of a list of observations. * Works with uni-, bi-, and trigram models. * @param poObservationList the list ! * @return the number of occurrences */ ! public final synchronized double getOccurrence(final Vector poObservationList) { ! double dOccurrence = 0.0; int iUniIndex; *************** *** 518,529 **** } ! Double oOccurence = (Double)this.oNMatrix.elementAt(iUniIndex); ! if(oOccurence == null) { return 0.0; } ! dOccurence = oOccurence.doubleValue(); break; --- 518,529 ---- } ! Double oOccurrence = (Double)this.oNMatrix.elementAt(iUniIndex); ! if(oOccurrence == null) { return 0.0; } ! dOccurrence = oOccurrence.doubleValue(); break; *************** *** 547,558 **** } ! Double oOccurence = (Double)oRow.elementAt(iBiIndex); ! if(oOccurence == null) { return 0.0; } ! dOccurence = oOccurence.doubleValue(); break; --- 547,558 ---- } ! Double oOccurrence = (Double)oRow.elementAt(iBiIndex); ! if(oOccurrence == null) { return 0.0; } ! dOccurrence = oOccurrence.doubleValue(); break; *************** *** 584,595 **** } ! Double oOccurence = (Double)oRow.elementAt(iTriIndex); ! if(oOccurence == null) { return 0.0; } ! dOccurence = oOccurence.doubleValue(); break; --- 584,595 ---- } ! Double oOccurrence = (Double)oRow.elementAt(iTriIndex); ! if(oOccurrence == null) { return 0.0; } ! dOccurrence = oOccurrence.doubleValue(); break; *************** *** 599,607 **** //Debug.debug("dOccurence = " + dOccurence); ! return dOccurence; } /** ! * Increments the frequency of occurences of a list of observations. * @param poObservationList the list to work with * @return the new frequency --- 599,607 ---- //Debug.debug("dOccurence = " + dOccurence); ! return dOccurrence; } /** ! * Increments the frequency of occurrences of a list of observations. * @param poObservationList the list to work with * @return the new frequency *************** *** 609,614 **** public final synchronized int incFrequency(final Vector poObservationList) { ! int iFrequency = (int)getOccurence(poObservationList) + 1; ! setOccurence(poObservationList, iFrequency); return iFrequency; } --- 609,614 ---- public final synchronized int incFrequency(final Vector poObservationList) { ! int iFrequency = (int)getOccurrence(poObservationList) + 1; ! setOccurrence(poObservationList, iFrequency); return iFrequency; } *************** *** 642,646 **** for(int j = 0; j < this.oColumnIndex.size(); j++) { ! System.out.print(getOccurence(j) + ","); } --- 642,646 ---- for(int j = 0; j < this.oColumnIndex.size(); j++) { ! System.out.print(getOccurrence(j) + ","); } *************** *** 663,667 **** for(int j = 0; j < this.oColumnIndex.size(); j++) { ! System.out.print("," + getOccurence(j, i)); } --- 663,667 ---- for(int j = 0; j < this.oColumnIndex.size(); j++) { ! System.out.print("," + getOccurrence(j, i)); } *************** *** 689,693 **** for(int k = 0; k < this.oColumnIndex.size(); k++) { ! System.out.print("," + getOccurence(k, j, i)); } --- 689,693 ---- for(int k = 0; k < this.oColumnIndex.size(); k++) { ! System.out.print("," + getOccurrence(k, j, i)); } Index: WordStats.java =================================================================== RCS file: /cvsroot/marf/marf/src/marf/Stats/WordStats.java,v retrieving revision 1.20 retrieving revision 1.20.6.1 diff -C2 -d -r1.20 -r1.20.6.1 *** WordStats.java 17 Jan 2006 22:41:14 -0000 1.20 --- WordStats.java 9 Apr 2008 00:32:15 -0000 1.20.6.1 *************** *** 76,80 **** /** ! * Reports lexeme, frequency, and rank of an occurence of a word. * @see java.lang.Object#toString() * @since 0.3.0.5 --- 76,80 ---- /** ! * Reports lexeme, frequency, and rank of an occurrence of a word. * @see java.lang.Object#toString() * @since 0.3.0.5 Index: StatisticalObject.java =================================================================== RCS file: /cvsroot/marf/marf/src/marf/Stats/StatisticalObject.java,v retrieving revision 1.16 retrieving revision 1.16.4.1 diff -C2 -d -r1.16 -r1.16.4.1 *** StatisticalObject.java 3 Sep 2006 20:56:02 -0000 1.16 --- StatisticalObject.java 9 Apr 2008 00:32:15 -0000 1.16.4.1 *************** *** 17,21 **** { /** ! * Number of occurences of this object basic data in a given document * (for example a corpus or a WAVE file). * Default <code>0</code>. --- 17,21 ---- { /** ! * Number of occurrences of this object basic data in a given document * (for example a corpus or a WAVE file). * Default <code>0</code>. *************** *** 85,89 **** /** ! * Restrieves the object's rank. * @return current rank */ --- 85,89 ---- /** ! * Retrieves the object's rank. * @return current rank */ *************** *** 151,155 **** /** ! * Reports frequency and rank of an occurence of a statistical object. * @see java.lang.Object#toString() * @since 0.3.0.5 --- 151,155 ---- /** ! * Reports frequency and rank of an occurrence of a statistical object. * @see java.lang.Object#toString() * @since 0.3.0.5 Index: Ngram.java =================================================================== RCS file: /cvsroot/marf/marf/src/marf/Stats/Ngram.java,v retrieving revision 1.15 retrieving revision 1.15.6.1 diff -C2 -d -r1.15 -r1.15.6.1 *** Ngram.java 2 Jan 2006 22:24:00 -0000 1.15 --- Ngram.java 9 Apr 2008 00:32:15 -0000 1.15.6.1 *************** *** 108,112 **** /** ! * Retrievs the size of the N-gram. * @return N */ --- 108,112 ---- /** ! * Retrieves the size of the N-gram. * @return N */ |