本文整理汇总了Java中cc.mallet.classify.MaxEnt类的典型用法代码示例。如果您正苦于以下问题：Java MaxEnt类的具体用法？Java MaxEnt怎么用？Java MaxEnt使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
MaxEnt类属于cc.mallet.classify包，在下文中一共展示了MaxEnt类的11个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Java代码示例。
示例1: createTrainer
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
public ClassifierTrainer<MaxEnt> createTrainer(String... args) {
MaxEntTrainer trainer = new MaxEntTrainer();
if (args != null) {
if (args.length % 2 != 0) {
throw new IllegalArgumentException("each argument must be supplied with a value: "
+ getUsageMessage());
}
for (int i = 0; i < args.length; i += 2) {
String optionName = args[i];
String optionValue = args[i + 1];
if (optionName.equals("--numIterations")) {
int numIterations = Integer.parseInt(optionValue);
if (numIterations > 0)
trainer.setNumIterations(numIterations);
else
throw new IllegalArgumentException("numIterations must be positive. "
+ getUsageMessage());
}
else if (optionName.equals("--gaussianPriorVariance"))
trainer.setGaussianPriorVariance(Double.parseDouble(optionValue));
else
throw new IllegalArgumentException(String.format(
"the argument %1$s is invalid. ",
optionName) + getUsageMessage());
}
}
return trainer;
}
开发者ID:ClearTK，项目名称:cleartk，代码行数:30，代码来源:MaxEntTrainerFactory.java
示例2: DMRInferencer
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
public DMRInferencer (int[][] typeTopicCounts, int[] tokensPerTopic, MaxEnt dmrParameters, Alphabet alphabet,
double beta, double betaSum) {
this.dmrParameters = dmrParameters;
this.numFeatures = dmrParameters.getAlphabet().size();
this.defaultFeatureIndex = dmrParameters.getDefaultFeatureIndex();
this.tokensPerTopic = tokensPerTopic;
this.typeTopicCounts = typeTopicCounts;
this.alphabet = alphabet;
numTopics = tokensPerTopic.length;
numTypes = typeTopicCounts.length;
if (Integer.bitCount(numTopics) == 1) {
// exact power of 2
topicMask = numTopics - 1;
topicBits = Integer.bitCount(topicMask);
}
else {
// otherwise add an extra bit
topicMask = Integer.highestOneBit(numTopics) * 2 - 1;
topicBits = Integer.bitCount(topicMask);
}
this.beta = beta;
this.betaSum = betaSum;
cachedCoefficients = new double[numTopics];
alpha = new double[numTopics];
for (int topic=0; topic < numTopics; topic++) {
smoothingOnlyMass += alpha[topic] * beta / (tokensPerTopic[topic] + betaSum);
cachedCoefficients[topic] = alpha[topic] / (tokensPerTopic[topic] + betaSum);
}
random = new Randoms();
}
开发者ID:mimno，项目名称:Mallet，代码行数:41，代码来源:DMRInferencer.java
示例3: printModel
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
public void printModel(PrintWriter out, int numOfExtremeFeatures) {
if (classifier instanceof MaxEnt) {
out.println("Num of features: " + classifier.getAlphabet().size());
((MaxEnt) classifier).printExtremeFeatures(out, Math.min(numOfExtremeFeatures, classifier.getAlphabet().size()));
out.flush();
} else {
classifier.print(out);
}
}
开发者ID:begab，项目名称:kpe，代码行数:10，代码来源:MalletClassifier.java
示例4: DMROptimizable
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
public DMROptimizable (InstanceList instances, MaxEnt initialClassifier) {
this.trainingList = instances;
Alphabet alphabet = instances.getDataAlphabet();
Alphabet labelAlphabet = instances.getTargetAlphabet();
this.numLabels = labelAlphabet.size();
// Add one feature for the "default feature".
this.numFeatures = alphabet.size() + 1; // add a spot for the intercept term
//System.out.println("num features: " + numFeatures + " numLabels: " + numLabels);
this.defaultFeatureIndex = numFeatures - 1;
this.parameters = new double [numLabels * numFeatures];
//this.constraints = new double [numLabels * numFeatures];
this.cachedGradient = new double [numLabels * numFeatures];
if (initialClassifier != null) {
this.classifier = initialClassifier;
this.parameters = classifier.getParameters();
this.defaultFeatureIndex = classifier.getDefaultFeatureIndex();
assert (initialClassifier.getInstancePipe() == instances.getPipe());
}
else if (this.classifier == null) {
this.classifier =
new MaxEnt (instances.getPipe(), parameters);
}
formatter = new DecimalFormat("0.###E0");
cachedValueStale = true;
cachedGradientStale = true;
// Initialize the constraints
logger.fine("Number of instances in training list = " + trainingList.size());
for (Instance instance : trainingList) {
FeatureVector multinomialValues = (FeatureVector) instance.getTarget();
if (multinomialValues == null)
continue;
FeatureVector features = (FeatureVector) instance.getData();
assert (features.getAlphabet() == alphabet);
boolean hasNaN = false;
for (int i = 0; i < features.numLocations(); i++) {
if (Double.isNaN(features.valueAtLocation(i))) {
logger.info("NaN for feature " + alphabet.lookupObject(features.indexAtLocation(i)).toString());
hasNaN = true;
}
}
if (hasNaN) {
logger.info("NaN in instance: " + instance.getName());
}
}
//TestMaximizable.testValueAndGradientCurrentParameters (this);
}
开发者ID:kostagiolasn，项目名称:NucleosomePatternClassifier，代码行数:67，代码来源:DMROptimizable.java
示例5: getClassifier
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
@Override
public MaxEnt getClassifier() {
return p;
}
开发者ID:kostagiolasn，项目名称:NucleosomePatternClassifier，代码行数:5，代码来源:MaxEntPRTrainer.java
示例6: train
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
@Override
public MaxEnt train(InstanceList trainingSet) {
return train(trainingSet,maxIterations);
}
开发者ID:kostagiolasn，项目名称:NucleosomePatternClassifier，代码行数:5，代码来源:MaxEntPRTrainer.java
示例7: addInstances
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
public void addInstances (InstanceList training) {
alphabet = training.getDataAlphabet();
numTypes = alphabet.size();
betaSum = beta * numTypes;
Randoms random = null;
if (randomSeed == -1) {
random = new Randoms();
}
else {
random = new Randoms(randomSeed);
}
alphaCache = new double[ training.size() ][numTopics];
alphaSumCache = new double[ training.size() ];
int index = 0;
for (Instance instance : training) {
FeatureSequence tokens = (FeatureSequence) instance.getData();
LabelSequence topicSequence =
new LabelSequence(topicAlphabet, new int[ tokens.size() ]);
int[] topics = topicSequence.getFeatures();
for (int position = 0; position < topics.length; position++) {
int topic = random.nextInt(numTopics);
topics[position] = topic;
}
TopicAssignment t = new TopicAssignment(instance, topicSequence);
data.add(t);
Arrays.fill(alphaCache[index], initialAlpha);
alphaSumCache[index] = numTopics * initialAlpha;
index++;
}
alphaCache = new double[ data.size() ][numTopics];
alphaSumCache = new double[ data.size() ];
buildInitialTypeTopicCounts();
// Create a "fake" pipe with the features in the data and
// an int-int hashmap of topic counts in the target.
parameterPipe = new Noop();
Alphabet featureAlphabet = training.getTargetAlphabet();
numFeatures = featureAlphabet.size() + 1;
parameterPipe.setDataAlphabet(featureAlphabet);
parameterPipe.setTargetAlphabet(topicAlphabet);
dmrParameters = new MaxEnt(parameterPipe, new double[numFeatures * numTopics]);
defaultFeatureIndex = dmrParameters.getDefaultFeatureIndex();
double logInitialAlpha = Math.log(initialAlpha);
for (int topic=0; topic < numTopics; topic++) {
dmrParameters.setParameter(topic, defaultFeatureIndex, logInitialAlpha);
}
for (int doc=0; doc < data.size(); doc++) {
cacheAlphas(data.get(doc).instance, doc);
}
totalTokens = 0;
for (int doc = 0; doc < data.size(); doc++) {
FeatureSequence fs = (FeatureSequence) data.get(doc).instance.getData();
totalTokens += fs.getLength();
}
}
开发者ID:mimno，项目名称:Mallet，代码行数:74，代码来源:DMRTopicModel.java
示例8: readObject
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
private void readObject (ObjectInputStream in) throws IOException, ClassNotFoundException {
int version = in.readInt ();
dmrParameters = (MaxEnt) in.readObject();
numFeatures = dmrParameters.getAlphabet().size();
defaultFeatureIndex = dmrParameters.getDefaultFeatureIndex();
data = (ArrayList<TopicAssignment>) in.readObject ();
alphabet = (Alphabet) in.readObject();
topicAlphabet = (LabelAlphabet) in.readObject();
numTopics = in.readInt();
topicMask = in.readInt();
topicBits = in.readInt();
numTypes = in.readInt();
alpha = (double[]) in.readObject();
alphaSum = in.readDouble();
beta = in.readDouble();
betaSum = in.readDouble();
typeTopicCounts = (int[][]) in.readObject();
tokensPerTopic = (int[]) in.readObject();
docLengthCounts = (int[]) in.readObject();
topicDocCounts = (int[][]) in.readObject();
numIterations = in.readInt();
burninPeriod = in.readInt();
saveSampleInterval = in.readInt();
optimizeInterval = in.readInt();
showTopicsInterval = in.readInt();
wordsPerTopic = in.readInt();
saveStateInterval = in.readInt();
stateFilename = (String) in.readObject();
saveModelInterval = in.readInt();
modelFilename = (String) in.readObject();
randomSeed = in.readInt();
formatter = (NumberFormat) in.readObject();
printLogLikelihood = in.readBoolean();
numThreads = in.readInt();
}
开发者ID:mimno，项目名称:Mallet，代码行数:50，代码来源:DMRTopicModel.java
示例9: DMROptimizable
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
public DMROptimizable (InstanceList instances, MaxEnt initialClassifier) {
this.trainingList = instances;
Alphabet alphabet = instances.getDataAlphabet();
Alphabet labelAlphabet = instances.getTargetAlphabet();
this.numLabels = labelAlphabet.size();
// Add one feature for the "default feature".
this.numFeatures = alphabet.size() + 1; // add a spot for the intercept term
//System.out.println("num features: " + numFeatures + " numLabels: " + numLabels);
this.defaultFeatureIndex = numFeatures - 1;
this.parameters = new double [numLabels * numFeatures];
//this.constraints = new double [numLabels * numFeatures];
this.cachedGradient = new double [numLabels * numFeatures];
if (initialClassifier != null) {
this.classifier = initialClassifier;
this.parameters = classifier.getParameters();
this.defaultFeatureIndex = classifier.getDefaultFeatureIndex();
assert (initialClassifier.getInstancePipe() == instances.getPipe());
}
else if (this.classifier == null) {
this.classifier =
new MaxEnt (instances.getPipe(), parameters);
}
formatter = new DecimalFormat("0.###E0");
cachedValueStale = true;
cachedGradientStale = true;
// Initialize the constraints
logger.fine("Number of instances in training list = " + trainingList.size());
for (Instance instance : trainingList) {
FeatureVector multinomialValues = (FeatureVector) instance.getTarget();
if (multinomialValues == null)
continue;
FeatureVector features = (FeatureVector) instance.getData();
assert (features.getAlphabet() == alphabet);
boolean hasNaN = false;
for (int i = 0; i < features.numLocations(); i++) {
if (Double.isNaN(features.valueAtLocation(i))) {
logger.info("NaN for feature " + alphabet.lookupObject(features.indexAtLocation(i)).toString());
hasNaN = true;
}
}
if (hasNaN) {
logger.info("NaN in instance: " + instance.getName());
}
}
//TestMaximizable.testValueAndGradientCurrentParameters (this);
}
开发者ID:mimno，项目名称:Mallet，代码行数:67，代码来源:DMROptimizable.java
示例10: readObject
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
private void readObject (ObjectInputStream in) throws IOException, ClassNotFoundException {
int version = in.readInt ();
dmrParameters = (MaxEnt) in.readObject();
numFeatures = dmrParameters.getAlphabet().size();
defaultFeatureIndex = dmrParameters.getDefaultFeatureIndex();
alphabet = (Alphabet) in.readObject();
numTopics = in.readInt();
topicMask = in.readInt();
topicBits = in.readInt();
numTypes = in.readInt();
alpha = (double[]) in.readObject();
beta = in.readDouble();
betaSum = in.readDouble();
typeTopicCounts = (int[][]) in.readObject();
tokensPerTopic = (int[]) in.readObject();
random = (Randoms) in.readObject();
smoothingOnlyMass = in.readDouble();
cachedCoefficients = (double[]) in.readObject();
}
开发者ID:mimno，项目名称:Mallet，代码行数:30，代码来源:DMRInferencer.java
示例11: getClassifier
import cc.mallet.classify.MaxEnt; //导入依赖的package包/类
public MaxEnt getClassifier () { return classifier; }
开发者ID:kostagiolasn，项目名称:NucleosomePatternClassifier，代码行数:2，代码来源:DMROptimizable.java
注：本文中的cc.mallet.classify.MaxEnt类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。 |
客服电话
APP下载
官方微信
请发表评论