Created
August 8, 2022 00:37
-
-
Save rubykv/86fb3e0089767417daad7ad73135b0a7 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
public static void generateModel() throws IOException { | |
File file = ResourceUtils.getFile("src/main/resources/training-data.txt"); | |
InputStreamFactory inputStreamFactory = new MarkableFileInputStreamFactory(file); | |
ObjectStream<String> lineStream = new PlainTextByLineStream(inputStreamFactory, "UTF-8"); | |
ObjectStream<DocumentSample> sampleStream = new DocumentSampleStream(lineStream); | |
int minNgramSize = 1; | |
int maxNgramSize = 6; | |
DoccatFactory customFactory = new DoccatFactory(new FeatureGenerator[] { new BagOfWordsFeatureGenerator(), | |
new NGramFeatureGenerator(minNgramSize, maxNgramSize) }); | |
TrainingParameters mlParams = new TrainingParameters(); | |
mlParams.put(TrainingParameters.ALGORITHM_PARAM, "MAXENT"); | |
mlParams.put(TrainingParameters.TRAINER_TYPE_PARAM, EventTrainer.EVENT_VALUE); | |
mlParams.put(TrainingParameters.ITERATIONS_PARAM, 10); | |
mlParams.put(TrainingParameters.CUTOFF_PARAM, 3); | |
DoccatModel model = DocumentCategorizerME.train("en", sampleStream, mlParams, customFactory); | |
try (OutputStream modelOut = new BufferedOutputStream( | |
new FileOutputStream("src/main/resources/nlp-model/en-trained-model.bin"))) { | |
model.serialize(modelOut); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment