public void printDocumentTopics(PrintWriter pw, double threshold, int max) {
pw.println("#doc source topic proportion ...");
int docLen;
double topicDist[] = new double[topics.length];
for (int di = 0; di < topics.length; di++) {
pw.print(di);
pw.print(' ');
if (ilist.get(di).getSource() != null) {
pw.print(ilist.get(di).getSource().toString());
} else {
pw.print("null-source");
}
pw.print(' ');
docLen = topics[di].length;
for (int ti = 0; ti < numTopics; ti++)
topicDist[ti] = (((float) docTopicCounts[di][ti]) / docLen);
if (max < 0) max = numTopics;
for (int tp = 0; tp < max; tp++) {
double maxvalue = 0;
int maxindex = -1;
for (int ti = 0; ti < numTopics; ti++)
if (topicDist[ti] > maxvalue) {
maxvalue = topicDist[ti];
maxindex = ti;
}
if (maxindex == -1 || topicDist[maxindex] < threshold) break;
pw.print(maxindex + " " + topicDist[maxindex] + " ");
topicDist[maxindex] = 0;
}
pw.println(' ');
}
}
public void count() {
TIntIntHashMap docCounts = new TIntIntHashMap();
int index = 0;
if (instances.size() == 0) {
logger.info("Instance list is empty");
return;
}
if (instances.get(0).getData() instanceof FeatureSequence) {
for (Instance instance : instances) {
FeatureSequence features = (FeatureSequence) instance.getData();
for (int i = 0; i < features.getLength(); i++) {
docCounts.adjustOrPutValue(features.getIndexAtPosition(i), 1, 1);
}
int[] keys = docCounts.keys();
for (int i = 0; i < keys.length - 1; i++) {
int feature = keys[i];
featureCounts[feature] += docCounts.get(feature);
documentFrequencies[feature]++;
}
docCounts = new TIntIntHashMap();
index++;
if (index % 1000 == 0) {
System.err.println(index);
}
}
} else if (instances.get(0).getData() instanceof FeatureVector) {
for (Instance instance : instances) {
FeatureVector features = (FeatureVector) instance.getData();
for (int location = 0; location < features.numLocations(); location++) {
int feature = features.indexAtLocation(location);
double value = features.valueAtLocation(location);
documentFrequencies[feature]++;
featureCounts[feature] += value;
}
index++;
if (index % 1000 == 0) {
System.err.println(index);
}
}
} else {
logger.info("Unsupported data class: " + instances.get(0).getData().getClass().getName());
}
}
/**
* Initialize this separate model using a complete list.
*
* @param documents
* @param testStartIndex
*/
public void divideDocuments(InstanceList documents, int testStartIndex) {
Alphabet dataAlpha = documents.getDataAlphabet();
Alphabet targetAlpha = documents.getTargetAlphabet();
this.training = new InstanceList(dataAlpha, targetAlpha);
this.test = new InstanceList(dataAlpha, targetAlpha);
int di = 0;
for (di = 0; di < testStartIndex; di++) {
training.add(documents.get(di));
}
for (di = testStartIndex; di < documents.size(); di++) {
test.add(documents.get(di));
}
}
private void readObject(ObjectInputStream in) throws IOException, ClassNotFoundException {
int featuresLength;
int version = in.readInt();
ilist = (InstanceList) in.readObject();
numTopics = in.readInt();
alpha = in.readDouble();
beta = in.readDouble();
tAlpha = in.readDouble();
vBeta = in.readDouble();
int numDocs = ilist.size();
topics = new int[numDocs][];
for (int di = 0; di < ilist.size(); di++) {
int docLen = ((FeatureSequence) ilist.get(di).getData()).getLength();
topics[di] = new int[docLen];
for (int si = 0; si < docLen; si++) topics[di][si] = in.readInt();
}
docTopicCounts = new int[numDocs][numTopics];
for (int di = 0; di < ilist.size(); di++)
for (int ti = 0; ti < numTopics; ti++) docTopicCounts[di][ti] = in.readInt();
int numTypes = ilist.getDataAlphabet().size();
typeTopicCounts = new int[numTypes][numTopics];
for (int fi = 0; fi < numTypes; fi++)
for (int ti = 0; ti < numTopics; ti++) typeTopicCounts[fi][ti] = in.readInt();
tokensPerTopic = new int[numTopics];
for (int ti = 0; ti < numTopics; ti++) tokensPerTopic[ti] = in.readInt();
}
public static ElementInMove_c resolveInstance(
ModelRoot modelRoot,
java.util.UUID p_m_elementid,
java.util.UUID p_m_diagramid,
float p_m_startingx,
float p_m_startingy) {
InstanceList instances = modelRoot.getInstanceList(ElementInMove_c.class);
ElementInMove_c source = null;
synchronized (instances) {
Object[] key = {p_m_elementid, p_m_diagramid};
source = (ElementInMove_c) instances.get(key);
if (source != null && !modelRoot.isCompareRoot()) {
source.convertFromProxy();
source.batchUnrelate();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_elementid = IdAssigner.preprocessUUID(p_m_elementid);
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_diagramid = IdAssigner.preprocessUUID(p_m_diagramid);
source.m_startingx = p_m_startingx;
source.m_startingy = p_m_startingy;
return source;
}
}
// there is no instance matching the id
ElementInMove_c new_inst =
new ElementInMove_c(modelRoot, p_m_elementid, p_m_diagramid, p_m_startingx, p_m_startingy);
return new_inst;
}
public static void clearInstances(ModelRoot modelRoot) {
InstanceList instances = modelRoot.getInstanceList(InformalArgument_c.class);
synchronized (instances) {
for (int i = instances.size() - 1; i >= 0; i--) {
((NonRootModelElement) instances.get(i)).delete_unchecked();
}
}
}
public static BridgeInvocation_c createProxy(
ModelRoot modelRoot,
java.util.UUID p_m_statement_id,
java.util.UUID p_m_brg_id,
int p_m_bridgenamelinenumber,
int p_m_bridgenamecolumn,
int p_m_externalentitykeyletterslinenumber,
int p_m_externalentitykeyletterscolumn,
String p_contentPath,
IPath p_localPath) {
ModelRoot resolvedModelRoot = ModelRoot.findModelRoot(modelRoot, p_contentPath, p_localPath);
// if a model root was not resolved it is most likely
// due to a missing file of the proxy, defualt back to
// the original model root
if (resolvedModelRoot != null) modelRoot = resolvedModelRoot;
InstanceList instances = modelRoot.getInstanceList(BridgeInvocation_c.class);
BridgeInvocation_c new_inst = null;
synchronized (instances) {
Object[] key = {p_m_statement_id};
new_inst = (BridgeInvocation_c) instances.get(key);
}
String contentPath = PersistenceUtil.resolveRelativePath(p_localPath, new Path(p_contentPath));
if (modelRoot.isNewCompareRoot()) {
// for comparisons we do not want to change
// the content path
contentPath = p_contentPath;
}
if (new_inst != null && !modelRoot.isCompareRoot()) {
PersistableModelComponent pmc = new_inst.getPersistableComponent();
if (pmc == null) {
// dangling reference, redo this instance
new_inst.batchUnrelate();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
new_inst.m_statement_id = IdAssigner.preprocessUUID(p_m_statement_id);
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
new_inst.m_brg_id = IdAssigner.preprocessUUID(p_m_brg_id);
new_inst.m_bridgenamelinenumber = p_m_bridgenamelinenumber;
new_inst.m_bridgenamecolumn = p_m_bridgenamecolumn;
new_inst.m_externalentitykeyletterslinenumber = p_m_externalentitykeyletterslinenumber;
new_inst.m_externalentitykeyletterscolumn = p_m_externalentitykeyletterscolumn;
}
}
if (new_inst == null) {
// there is no instance matching the id, create a proxy
// if the resource doesn't exist then this will be a dangling reference
new_inst =
new BridgeInvocation_c(
modelRoot,
p_m_statement_id,
p_m_brg_id,
p_m_bridgenamelinenumber,
p_m_bridgenamecolumn,
p_m_externalentitykeyletterslinenumber,
p_m_externalentitykeyletterscolumn);
new_inst.m_contentPath = contentPath;
}
return new_inst;
}
public void estimate(
InstanceList documents,
int numIterations,
int showTopicsInterval,
int outputModelInterval,
String outputModelFilename,
Randoms r) {
ilist = documents.shallowClone();
numTypes = ilist.getDataAlphabet().size();
int numDocs = ilist.size();
topics = new int[numDocs][];
docTopicCounts = new int[numDocs][numTopics];
typeTopicCounts = new int[numTypes][numTopics];
tokensPerTopic = new int[numTopics];
tAlpha = alpha * numTopics;
vBeta = beta * numTypes;
long startTime = System.currentTimeMillis();
// Initialize with random assignments of tokens to topics
// and finish allocating this.topics and this.tokens
int topic, seqLen;
FeatureSequence fs;
for (int di = 0; di < numDocs; di++) {
try {
fs = (FeatureSequence) ilist.get(di).getData();
} catch (ClassCastException e) {
System.err.println(
"LDA and other topic models expect FeatureSequence data, not FeatureVector data. "
+ "With text2vectors, you can obtain such data with --keep-sequence or --keep-bisequence.");
throw e;
}
seqLen = fs.getLength();
numTokens += seqLen;
topics[di] = new int[seqLen];
// Randomly assign tokens to topics
for (int si = 0; si < seqLen; si++) {
topic = r.nextInt(numTopics);
topics[di][si] = topic;
docTopicCounts[di][topic]++;
typeTopicCounts[fs.getIndexAtPosition(si)][topic]++;
tokensPerTopic[topic]++;
}
}
this.estimate(
0, numDocs, numIterations, showTopicsInterval, outputModelInterval, outputModelFilename, r);
// 124.5 seconds
// 144.8 seconds after using FeatureSequence instead of tokens[][] array
// 121.6 seconds after putting "final" on FeatureSequence.getIndexAtPosition()
// 106.3 seconds after avoiding array lookup in inner loop with a temporary variable
}
/* One iteration of Gibbs sampling, across all documents. */
public void sampleTopicsForAllDocs(Randoms r) {
double[] topicWeights = new double[numTopics];
// Loop over every word in the corpus
for (int di = 0; di < topics.length; di++) {
sampleTopicsForOneDoc(
(FeatureSequence) ilist.get(di).getData(),
topics[di],
docTopicCounts[di],
topicWeights,
r);
}
}
/* One iteration of Gibbs sampling, across all documents. */
public void sampleTopicsForDocs(int start, int length, Randoms r) {
assert (start + length <= docTopicCounts.length);
double[] topicWeights = new double[numTopics];
// Loop over every word in the corpus
for (int di = start; di < start + length; di++) {
sampleTopicsForOneDoc(
(FeatureSequence) ilist.get(di).getData(),
topics[di],
docTopicCounts[di],
topicWeights,
r);
}
}
private static Graphnode_c findGraphnodeInstance(
ModelRoot modelRoot, ClassQueryInterface_c test, boolean loadComponent) {
InstanceList instances = modelRoot.getInstanceList(Graphnode_c.class);
synchronized (instances) {
for (int i = 0; i < instances.size(); ++i) {
Graphnode_c x = (Graphnode_c) instances.get(i);
if (test == null || test.evaluate(x)) {
return x;
}
}
}
return null;
}
private static InformalArgument_c findInformalArgumentInstance(
ModelRoot modelRoot, ClassQueryInterface_c test, boolean loadComponent) {
InstanceList instances = modelRoot.getInstanceList(InformalArgument_c.class);
synchronized (instances) {
for (int i = 0; i < instances.size(); ++i) {
InformalArgument_c x = (InformalArgument_c) instances.get(i);
if (test == null || test.evaluate(x)) {
if (x.ensureLoaded(loadComponent)) return x;
}
}
}
return null;
}
public void addDocuments(
InstanceList additionalDocuments,
int numIterations,
int showTopicsInterval,
int outputModelInterval,
String outputModelFilename,
Randoms r) {
if (ilist == null) throw new IllegalStateException("Must already have some documents first.");
for (Instance inst : additionalDocuments) ilist.add(inst);
assert (ilist.getDataAlphabet() == additionalDocuments.getDataAlphabet());
assert (additionalDocuments.getDataAlphabet().size() >= numTypes);
numTypes = additionalDocuments.getDataAlphabet().size();
int numNewDocs = additionalDocuments.size();
int numOldDocs = topics.length;
int numDocs = numOldDocs + numNewDocs;
// Expand various arrays to make space for the new data.
int[][] newTopics = new int[numDocs][];
for (int i = 0; i < topics.length; i++) newTopics[i] = topics[i];
topics = newTopics; // The rest of this array will be initialized below.
int[][] newDocTopicCounts = new int[numDocs][numTopics];
for (int i = 0; i < docTopicCounts.length; i++) newDocTopicCounts[i] = docTopicCounts[i];
docTopicCounts = newDocTopicCounts; // The rest of this array will be initialized below.
int[][] newTypeTopicCounts = new int[numTypes][numTopics];
for (int i = 0; i < typeTopicCounts.length; i++)
for (int j = 0; j < numTopics; j++)
newTypeTopicCounts[i][j] = typeTopicCounts[i][j]; // This array further populated below
FeatureSequence fs;
for (int di = numOldDocs; di < numDocs; di++) {
try {
fs = (FeatureSequence) additionalDocuments.get(di - numOldDocs).getData();
} catch (ClassCastException e) {
System.err.println(
"LDA and other topic models expect FeatureSequence data, not FeatureVector data. "
+ "With text2vectors, you can obtain such data with --keep-sequence or --keep-bisequence.");
throw e;
}
int seqLen = fs.getLength();
numTokens += seqLen;
topics[di] = new int[seqLen];
// Randomly assign tokens to topics
for (int si = 0; si < seqLen; si++) {
int topic = r.nextInt(numTopics);
topics[di][si] = topic;
docTopicCounts[di][topic]++;
typeTopicCounts[fs.getIndexAtPosition(si)][topic]++;
tokensPerTopic[topic]++;
}
}
}
/* One iteration of Gibbs sampling, across all documents. */
private void sampleTopicsForAllDocs(Randoms r) {
double[] uniTopicWeights = new double[numTopics];
double[] biTopicWeights = new double[numTopics * 2];
// Loop over every word in the corpus
for (int di = 0; di < topics.length; di++) {
sampleTopicsForOneDoc(
(FeatureSequenceWithBigrams) ilist.get(di).getData(),
topics[di],
grams[di],
docTopicCounts[di],
uniTopicWeights,
biTopicWeights,
r);
}
}
public void generateTestInference() {
if (lda == null) {
System.out.println("Should run lda estimation first.");
System.exit(1);
return;
}
if (testTopicDistribution == null) testTopicDistribution = new double[test.size()][];
TopicInferencer infer = lda.getInferencer();
int iterations = 800;
int thinning = 5;
int burnIn = 100;
for (int ti = 0; ti < test.size(); ti++) {
testTopicDistribution[ti] =
infer.getSampledDistribution(test.get(ti), iterations, thinning, burnIn);
}
}
public static ComponentInComponent_c createProxy(
ModelRoot modelRoot,
java.util.UUID p_m_id,
java.util.UUID p_m_parent_id,
String p_contentPath,
IPath p_localPath) {
ModelRoot resolvedModelRoot = ModelRoot.findModelRoot(modelRoot, p_contentPath, p_localPath);
// if a model root was not resolved it is most likely
// due to a missing file of the proxy, defualt back to
// the original model root
if (resolvedModelRoot != null) modelRoot = resolvedModelRoot;
InstanceList instances = modelRoot.getInstanceList(ComponentInComponent_c.class);
ComponentInComponent_c new_inst = null;
synchronized (instances) {
Object[] key = {p_m_id};
new_inst = (ComponentInComponent_c) instances.get(key);
}
String contentPath = PersistenceUtil.resolveRelativePath(p_localPath, new Path(p_contentPath));
if (modelRoot.isNewCompareRoot()) {
// for comparisons we do not want to change
// the content path
contentPath = p_contentPath;
}
if (new_inst != null && !modelRoot.isCompareRoot()) {
PersistableModelComponent pmc = new_inst.getPersistableComponent();
if (pmc == null) {
// dangling reference, redo this instance
new_inst.batchUnrelate();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
new_inst.m_id = IdAssigner.preprocessUUID(p_m_id);
// extract 28 bit value only
new_inst.m_idLongBased = 0xfffffff & p_m_id.getLeastSignificantBits();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
new_inst.m_parent_id = IdAssigner.preprocessUUID(p_m_parent_id);
}
}
if (new_inst == null) {
// there is no instance matching the id, create a proxy
// if the resource doesn't exist then this will be a dangling reference
new_inst = new ComponentInComponent_c(modelRoot, p_m_id, p_m_parent_id);
new_inst.m_contentPath = contentPath;
}
return new_inst;
}
public void doInference() {
try {
ParallelTopicModel model = ParallelTopicModel.read(new File(inferencerFile));
TopicInferencer inferencer = model.getInferencer();
// TopicInferencer inferencer =
// TopicInferencer.read(new File(inferencerFile));
// InstanceList testing = readFile();
readFile();
InstanceList testing = generateInstanceList(); // readFile();
for (int i = 0; i < testing.size(); i++) {
StringBuilder probabilities = new StringBuilder();
double[] testProbabilities = inferencer.getSampledDistribution(testing.get(i), 10, 1, 5);
ArrayList probabilityList = new ArrayList();
for (int j = 0; j < testProbabilities.length; j++) {
probabilityList.add(new Pair<Integer, Double>(j, testProbabilities[j]));
}
Collections.sort(probabilityList, new CustomComparator());
for (int j = 0; j < testProbabilities.length && j < topN; j++) {
if (j > 0) probabilities.append(" ");
probabilities.append(
((Pair<Integer, Double>) probabilityList.get(j)).getFirst().toString()
+ ","
+ ((Pair<Integer, Double>) probabilityList.get(j)).getSecond().toString());
}
System.out.println(docIds.get(i) + "," + probabilities.toString());
}
} catch (Exception e) {
e.printStackTrace();
System.err.println(e.getMessage());
}
}
public static InformalArgument_c resolveInstance(ModelRoot modelRoot, java.util.UUID p_m_arg_id) {
InstanceList instances = modelRoot.getInstanceList(InformalArgument_c.class);
InformalArgument_c source = null;
synchronized (instances) {
Object[] key = {p_m_arg_id};
source = (InformalArgument_c) instances.get(key);
if (source != null && !modelRoot.isCompareRoot()) {
source.convertFromProxy();
source.batchUnrelate();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_arg_id = IdAssigner.preprocessUUID(p_m_arg_id);
return source;
}
}
// there is no instance matching the id
InformalArgument_c new_inst = new InformalArgument_c(modelRoot, p_m_arg_id);
return new_inst;
}
public void printState(PrintWriter pw) {
Alphabet a = ilist.getDataAlphabet();
pw.println("#doc pos typeindex type topic");
for (int di = 0; di < topics.length; di++) {
FeatureSequence fs = (FeatureSequence) ilist.get(di).getData();
for (int si = 0; si < topics[di].length; si++) {
int type = fs.getIndexAtPosition(si);
pw.print(di);
pw.print(' ');
pw.print(si);
pw.print(' ');
pw.print(type);
pw.print(' ');
pw.print(a.lookupObject(type));
pw.print(' ');
pw.print(topics[di][si]);
pw.println();
}
}
}
public static Graphnode_c[] GraphnodeInstances(
ModelRoot modelRoot, ClassQueryInterface_c test, boolean loadComponent) {
InstanceList instances = modelRoot.getInstanceList(Graphnode_c.class);
Vector matches = new Vector();
synchronized (instances) {
for (int i = 0; i < instances.size(); ++i) {
Graphnode_c x = (Graphnode_c) instances.get(i);
if (test == null || test.evaluate(x)) {
matches.add(x);
}
}
if (matches.size() > 0) {
Graphnode_c[] ret_set = new Graphnode_c[matches.size()];
matches.copyInto(ret_set);
return ret_set;
} else {
return new Graphnode_c[0];
}
}
}
public void test() throws Exception {
ParallelTopicModel model = ParallelTopicModel.read(new File(inferencerFile));
TopicInferencer inferencer = model.getInferencer();
ArrayList<Pipe> pipeList = new ArrayList<Pipe>();
pipeList.add(new CharSequence2TokenSequence(Pattern.compile("\\p{L}\\p{L}+")));
pipeList.add(new TokenSequence2FeatureSequence());
InstanceList instances = new InstanceList(new SerialPipes(pipeList));
Reader fileReader = new InputStreamReader(new FileInputStream(new File(fileName)), "UTF-8");
instances.addThruPipe(
new CsvIterator(
fileReader,
Pattern.compile("^(\\S*)[\\s,]*(\\S*)[\\s,]*(.*)$"),
3,
2,
1)); // data, label, name fields
double[] testProbabilities = inferencer.getSampledDistribution(instances.get(1), 10, 1, 5);
for (int i = 0; i < 1000; i++) System.out.println(i + ": " + testProbabilities[i]);
}
public static BridgeInvocation_c resolveInstance(
ModelRoot modelRoot,
java.util.UUID p_m_statement_id,
java.util.UUID p_m_brg_id,
int p_m_bridgenamelinenumber,
int p_m_bridgenamecolumn,
int p_m_externalentitykeyletterslinenumber,
int p_m_externalentitykeyletterscolumn) {
InstanceList instances = modelRoot.getInstanceList(BridgeInvocation_c.class);
BridgeInvocation_c source = null;
synchronized (instances) {
Object[] key = {p_m_statement_id};
source = (BridgeInvocation_c) instances.get(key);
if (source != null && !modelRoot.isCompareRoot()) {
source.convertFromProxy();
source.batchUnrelate();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_statement_id = IdAssigner.preprocessUUID(p_m_statement_id);
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_brg_id = IdAssigner.preprocessUUID(p_m_brg_id);
source.m_bridgenamelinenumber = p_m_bridgenamelinenumber;
source.m_bridgenamecolumn = p_m_bridgenamecolumn;
source.m_externalentitykeyletterslinenumber = p_m_externalentitykeyletterslinenumber;
source.m_externalentitykeyletterscolumn = p_m_externalentitykeyletterscolumn;
return source;
}
}
// there is no instance matching the id
BridgeInvocation_c new_inst =
new BridgeInvocation_c(
modelRoot,
p_m_statement_id,
p_m_brg_id,
p_m_bridgenamelinenumber,
p_m_bridgenamecolumn,
p_m_externalentitykeyletterslinenumber,
p_m_externalentitykeyletterscolumn);
return new_inst;
}
public static Graphnode_c resolveInstance(
ModelRoot modelRoot, float p_m_width, float p_m_height, java.util.UUID p_m_elementid) {
InstanceList instances = modelRoot.getInstanceList(Graphnode_c.class);
Graphnode_c source = null;
synchronized (instances) {
Object[] key = {p_m_elementid};
source = (Graphnode_c) instances.get(key);
if (source != null && !modelRoot.isCompareRoot()) {
source.convertFromProxy();
source.batchUnrelate();
source.m_width = p_m_width;
source.m_height = p_m_height;
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_elementid = IdAssigner.preprocessUUID(p_m_elementid);
return source;
}
}
// there is no instance matching the id
Graphnode_c new_inst = new Graphnode_c(modelRoot, p_m_width, p_m_height, p_m_elementid);
return new_inst;
}
public static ComponentResultSet_c resolveInstance(
ModelRoot modelRoot, java.util.UUID p_m_id, String p_m_name, int p_m_type) {
InstanceList instances = modelRoot.getInstanceList(ComponentResultSet_c.class);
ComponentResultSet_c source = null;
synchronized (instances) {
Object[] key = {p_m_name, new UUID(0, new Long(p_m_type)), p_m_id};
source = (ComponentResultSet_c) instances.get(key);
if (source != null && !modelRoot.isCompareRoot()) {
source.convertFromProxy();
source.batchUnrelate();
source.m_name = p_m_name;
source.m_type = p_m_type;
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_id = IdAssigner.preprocessUUID(p_m_id);
return source;
}
}
// there is no instance matching the id
ComponentResultSet_c new_inst = new ComponentResultSet_c(modelRoot, p_m_id, p_m_name, p_m_type);
return new_inst;
}
public static AssignToMember_c resolveInstance(
ModelRoot modelRoot,
java.util.UUID p_m_statement_id,
java.util.UUID p_m_r_value_id,
java.util.UUID p_m_l_value_id,
int p_m_attributelinenumber,
int p_m_attributecolumn) {
InstanceList instances = modelRoot.getInstanceList(AssignToMember_c.class);
AssignToMember_c source = null;
synchronized (instances) {
Object[] key = {p_m_statement_id};
source = (AssignToMember_c) instances.get(key);
if (source != null && !modelRoot.isCompareRoot()) {
source.convertFromProxy();
source.batchUnrelate();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_statement_id = IdAssigner.preprocessUUID(p_m_statement_id);
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_r_value_id = IdAssigner.preprocessUUID(p_m_r_value_id);
source.m_attributelinenumber = p_m_attributelinenumber;
source.m_attributecolumn = p_m_attributecolumn;
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_l_value_id = IdAssigner.preprocessUUID(p_m_l_value_id);
return source;
}
}
// there is no instance matching the id
AssignToMember_c new_inst =
new AssignToMember_c(
modelRoot,
p_m_statement_id,
p_m_r_value_id,
p_m_l_value_id,
p_m_attributelinenumber,
p_m_attributecolumn);
return new_inst;
}
public static InformalArgument_c[] InformalArgumentInstances(
ModelRoot modelRoot, ClassQueryInterface_c test, boolean loadComponent) {
if (loadComponent) {
PersistenceManager.ensureAllInstancesLoaded(modelRoot, InformalArgument_c.class);
}
InstanceList instances = modelRoot.getInstanceList(InformalArgument_c.class);
Vector matches = new Vector();
synchronized (instances) {
for (int i = 0; i < instances.size(); ++i) {
InformalArgument_c x = (InformalArgument_c) instances.get(i);
if (test == null || test.evaluate(x)) {
if (x.ensureLoaded(loadComponent)) matches.add(x);
}
}
if (matches.size() > 0) {
InformalArgument_c[] ret_set = new InformalArgument_c[matches.size()];
matches.copyInto(ret_set);
return ret_set;
} else {
return new InformalArgument_c[0];
}
}
}
public double dataLogLikelihood(InstanceList ilist) {
double logLikelihood = 0;
for (int ii = 0; ii < ilist.size(); ii++) {
double instanceWeight = ilist.getInstanceWeight(ii);
Instance inst = ilist.get(ii);
Labeling labeling = inst.getLabeling();
if (labeling != null)
logLikelihood += instanceWeight * dataLogProbability(inst, labeling.getBestIndex());
else {
Labeling predicted = this.classify(inst).getLabeling();
// System.err.println ("label = \n"+labeling);
// System.err.println ("predicted = \n"+predicted);
for (int lpos = 0; lpos < predicted.numLocations(); lpos++) {
int li = predicted.indexAtLocation(lpos);
double labelWeight = predicted.valueAtLocation(lpos);
// System.err.print (", "+labelWeight);
if (labelWeight == 0) continue;
logLikelihood += instanceWeight * labelWeight * dataLogProbability(inst, li);
}
}
}
return logLikelihood;
}
public void printState(PrintWriter pw) {
pw.println("#doc pos typeindex type bigrampossible? topic bigram");
for (int di = 0; di < topics.length; di++) {
FeatureSequenceWithBigrams fs = (FeatureSequenceWithBigrams) ilist.get(di).getData();
for (int si = 0; si < topics[di].length; si++) {
int type = fs.getIndexAtPosition(si);
pw.print(di);
pw.print(' ');
pw.print(si);
pw.print(' ');
pw.print(type);
pw.print(' ');
pw.print(uniAlphabet.lookupObject(type));
pw.print(' ');
pw.print(fs.getBiIndexAtPosition(si) == -1 ? 0 : 1);
pw.print(' ');
pw.print(topics[di][si]);
pw.print(' ');
pw.print(grams[di][si]);
pw.println();
}
}
}
public double labelLogLikelihood(InstanceList ilist) {
double logLikelihood = 0;
for (int ii = 0; ii < ilist.size(); ii++) {
double instanceWeight = ilist.getInstanceWeight(ii);
Instance inst = ilist.get(ii);
Labeling labeling = inst.getLabeling();
if (labeling == null) continue;
Labeling predicted = this.classify(inst).getLabeling();
// System.err.println ("label = \n"+labeling);
// System.err.println ("predicted = \n"+predicted);
if (labeling.numLocations() == 1) {
logLikelihood += instanceWeight * Math.log(predicted.value(labeling.getBestIndex()));
} else {
for (int lpos = 0; lpos < labeling.numLocations(); lpos++) {
int li = labeling.indexAtLocation(lpos);
double labelWeight = labeling.valueAtLocation(lpos);
// System.err.print (", "+labelWeight);
if (labelWeight == 0) continue;
logLikelihood += instanceWeight * labelWeight * Math.log(predicted.value(li));
}
}
}
return logLikelihood;
}
public static ComponentInComponent_c resolveInstance(
ModelRoot modelRoot, java.util.UUID p_m_id, java.util.UUID p_m_parent_id) {
InstanceList instances = modelRoot.getInstanceList(ComponentInComponent_c.class);
ComponentInComponent_c source = null;
synchronized (instances) {
Object[] key = {p_m_id};
source = (ComponentInComponent_c) instances.get(key);
if (source != null && !modelRoot.isCompareRoot()) {
source.convertFromProxy();
source.batchUnrelate();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_id = IdAssigner.preprocessUUID(p_m_id);
// extract 28 bit value only
source.m_idLongBased = 0xfffffff & p_m_id.getLeastSignificantBits();
// pre-process the uuid so that we re-use null uuid instance rather then creating a new one.
source.m_parent_id = IdAssigner.preprocessUUID(p_m_parent_id);
return source;
}
}
// there is no instance matching the id
ComponentInComponent_c new_inst = new ComponentInComponent_c(modelRoot, p_m_id, p_m_parent_id);
return new_inst;
}
