public void add(CNGramsStats nGramsFreqStats) {
String label = nGramsFreqStats.getLabel();
if (label.split(" ").length > 1) {
_validationNGramRankList.add(Integer.valueOf(nGramsFreqStats.getNGramRank()));
_validationNGramNNPList.add(Boolean.valueOf(nGramsFreqStats.isNNP()));
} else {
_validation1GramRankList.add(Integer.valueOf(nGramsFreqStats.getNGramRank()));
_validation1GramNNPList.add(Boolean.valueOf(nGramsFreqStats.isNNP()));
}
}
public void add(CNGramsStats nGramsFreqStats) {
String label = nGramsFreqStats.getLabel();
float tagEstimator = CNGramsModel.getInstance().getTagEstimator();
float maxTermFreqEstimator = CNGramsModel.getInstance().getMaxTermFreqEstimator();
double[] allDataset = new double[5];
double isNNPValue = nGramsFreqStats.isNNP() ? 1.0 : 0.0;
allDataset[0] = nGramsFreqStats.getNGramRank();
allDataset[1] = tagEstimator;
allDataset[2] = maxTermFreqEstimator;
allDataset[3] = isNNPValue;
allDataset[4] = (label.split(" ").length > 1) ? 1.0 : 0.0;
if (label.split(" ").length > 1) {
allDataset[4] = 1.0;
double[] nGramDataset = new double[4];
nGramDataset[0] = nGramsFreqStats.getNGramRank();
nGramDataset[1] = tagEstimator;
nGramDataset[2] = maxTermFreqEstimator;
nGramDataset[3] = isNNPValue;
_nGramDatasetsList.add(nGramDataset);
} else {
allDataset[4] = 0.0;
double[] oneGramDataset = new double[4];
oneGramDataset[0] = nGramsFreqStats.getNGramRank();
oneGramDataset[1] = tagEstimator;
oneGramDataset[2] = maxTermFreqEstimator;
oneGramDataset[3] = isNNPValue;
_oneGramDatasetsList.add(oneGramDataset);
}
_allDatasetsList.add(allDataset);
}
/** Compute the key parameters of the NGramsOrder model. */
private void compute() {
int oneGramsCounter = 0;
int nGramsCounter = 0;
/*
* initialize the statistics for NGram
*/
NLabeledNGramsStats[] nGramsStat = new NLabeledNGramsStats[MAX_ORDER_NGRAM_STATS];
NLabeled1GramsStats[] oneGramsStat = new NLabeled1GramsStats[MAX_ORDER_NGRAM_STATS];
for (int k = 0; k < MAX_ORDER_NGRAM_STATS; k++) {
nGramsStat[k] = new NLabeledNGramsStats(k);
oneGramsStat[k] = new NLabeled1GramsStats(k);
}
int nGramRank = 0;
for (CNGramsStats nGramsFrequencyStat : _nGramsFrequencyStatsList) {
nGramRank = nGramsFrequencyStat.getNGramRank();
/*
* Collect only lower order NGram labels
*/
if (nGramRank < MAX_ORDER_NGRAM_STATS) {
if (nGramsFrequencyStat.isCompound()) {
nGramsStat[nGramRank].add(
nGramsFrequencyStat.getNumNGramOccurrences(),
nGramsFrequencyStat.isNNP(),
nGramsFrequencyStat.getMaxNumTermOccurrences());
nGramsCounter++;
} else {
oneGramsStat[nGramRank].add(
nGramsFrequencyStat.getNumNGramOccurrences(), nGramsFrequencyStat.isNNP(), -1);
oneGramsCounter++;
}
}
}
CNGramsModel instance = CNGramsModel.getInstance();
/*
* Normalize to compute the average values..
*/
StringBuilder buf = new StringBuilder();
buf.append(CFileUtil.COMMENTS_FIRST_CHAR);
buf.append(" nnpFudge:");
buf.append(instance.getTagEstimator());
buf.append(" compoundFudge:");
buf.append(instance.getMaxTermFreqEstimator());
buf.append("\n");
buf.append(CFileUtil.COMMENTS_FIRST_CHAR);
buf.append("1-Gram frequency model parameters\n");
for (int k = 0; k < MAX_ORDER_NGRAM_STATS; k++) {
if (oneGramsStat[k].compute(oneGramsCounter)) {
buf.append(oneGramsStat[k].toString());
buf.append("\n");
}
}
buf.append(CEnv.ENTRIES_DELIM);
buf.append("\n");
buf.append(CFileUtil.COMMENTS_FIRST_CHAR);
buf.append("N-Gram frequency model parameters\n");
for (int k = 0; k < MAX_ORDER_NGRAM_STATS; k++) {
if (nGramsStat[k].compute(nGramsCounter)) {
buf.append(nGramsStat[k].toString());
buf.append("\n");
}
}
buf.append(CEnv.ENTRIES_DELIM);
try {
final String fileName = TRAINING_FILES + "_" + _fileIndex;
CFileUtil.write(fileName, buf.toString());
} catch (IOException e) {
CLogger.error(e.toString());
}
}