public void run(String format, String[] args) {
super.run(format, args);
mlParams = CmdLineUtil.loadTrainingParameters(params.getParams(), false);
if (mlParams == null) {
mlParams = ModelUtil.createTrainingParameters(params.getIterations(), params.getCutoff());
}
File modelOutFile = params.getModel();
CmdLineUtil.checkOutputFile("sentence detector model", modelOutFile);
ChunkerModel model;
try {
ChunkerFactory chunkerFactory = ChunkerFactory.create(params.getFactory());
model = ChunkerME.train(params.getLang(), sampleStream, mlParams, chunkerFactory);
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while reading training data or indexing data: " + e.getMessage(), e);
} finally {
try {
sampleStream.close();
} catch (IOException e) {
// sorry that this can fail
}
}
CmdLineUtil.writeModel("chunker", modelOutFile, model);
}
public void run(String[] args) {
Parameters params = validateAndParseParams(args, Parameters.class);
File testData = new File(params.getCensusData());
File dictOutFile = new File(params.getDict());
CmdLineUtil.checkInputFile("Name data", testData);
CmdLineUtil.checkOutputFile("Dictionary file", dictOutFile);
FileInputStream sampleDataIn = CmdLineUtil.openInFile(testData);
ObjectStream<StringList> sampleStream =
new NameFinderCensus90NameStream(sampleDataIn, Charset.forName(params.getEncoding()));
Dictionary mDictionary;
try {
System.out.println("Creating Dictionary...");
mDictionary = createDictionary(sampleStream);
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while reading training data or indexing data: " + e.getMessage(), e);
} finally {
try {
sampleStream.close();
} catch (IOException e) {
// sorry this can fail..
}
}
System.out.println("Saving Dictionary...");
OutputStream out = null;
try {
out = new FileOutputStream(dictOutFile);
mDictionary.serialize(out);
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while writing dictionary file: " + e.getMessage(), e);
} finally {
if (out != null)
try {
out.close();
} catch (IOException e) {
// file might be damaged
throw new TerminateToolException(
-1, "Attention: Failed to correctly write dictionary:" + e.getMessage(), e);
}
}
}
public void run(String[] args) {
if (0 == args.length) {
System.out.println(getHelp());
} else {
DoccatModel model = new DoccatModelLoader().load(new File(args[0]));
DocumentCategorizerME doccat = new DocumentCategorizerME(model);
ObjectStream<String> documentStream =
new ParagraphStream(new PlainTextByLineStream(new InputStreamReader(System.in)));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "doc");
perfMon.start();
try {
String document;
while ((document = documentStream.read()) != null) {
double prob[] = doccat.categorize(WhitespaceTokenizer.INSTANCE.tokenize(document));
String category = doccat.getBestCategory(prob);
DocumentSample sample = new DocumentSample(category, document);
System.out.println(sample.toString());
perfMon.incrementCounter();
}
} catch (IOException e) {
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
public ObjectStream<ChunkSample> create(String[] args) {
Parameters params = ArgumentParser.parse(args, Parameters.class);
language = params.getLang();
FileInputStream sampleDataIn = CmdLineUtil.openInFile(params.getData());
ObjectStream<String> lineStream =
new PlainTextByLineStream(sampleDataIn.getChannel(), params.getEncoding());
ADChunkBasedShallowParserSampleStream sampleStream =
new ADChunkBasedShallowParserSampleStream(
lineStream,
params.getFunctTags(),
params.getIsIncludePOSTags(),
params.getUseCGTags(),
params.getExpandME());
if (params.getStart() != null && params.getStart() > -1) {
sampleStream.setStart(params.getStart());
}
if (params.getEnd() != null && params.getEnd() > -1) {
sampleStream.setEnd(params.getEnd());
}
return sampleStream;
}
/**
* Read the file into an {@code ObjectStream}.
*
* @param infile the string pointing to the file
* @return the object stream
*/
public static ObjectStream<String> readFileIntoMarkableStreamFactory(final String infile) {
InputStreamFactory inputStreamFactory = null;
try {
inputStreamFactory = new MarkableFileInputStreamFactory(new File(infile));
} catch (FileNotFoundException e) {
e.printStackTrace();
}
ObjectStream<String> lineStream = null;
try {
lineStream = new PlainTextByLineStream((inputStreamFactory), "UTF-8");
} catch (IOException e) {
CmdLineUtil.handleCreateObjectStreamError(e);
}
return lineStream;
}
public void run(String[] args) {
Params params = validateAndParseParams(args, Params.class);
String lang = params.getLang();
CmdLineUtil.checkLanguageCode(lang);
String country = params.getCountry();
if (StringsUtil.isNullOrEmpty(country)) {
throw new TerminateToolException(1, "Country cannot be empty. Example country: BR");
}
long start = System.nanoTime();
ComponentFactory factory;
try {
factory = ComponentFactory.create(new Locale(lang, country));
} catch (InitializationException e) {
e.printStackTrace();
throw new TerminateToolException(
1,
"Could not find configuration for "
+ lang
+ ". Only "
+ new Locale("pt", "BR")
+ " might be supported for now.");
}
Analyzer cogroo = factory.createPipe();
System.out.println("Loading time [" + ((System.nanoTime() - start) / 1000000) + "ms]");
Scanner kb = new Scanner(System.in);
System.out.print("Enter the sentence or 'q' to quit: ");
String input = kb.nextLine();
while (!input.equals("q")) {
CheckDocument document = new CheckDocument();
document.setText(input);
cogroo.analyze(document);
System.out.println(TextUtils.nicePrint(document));
System.out.print("Enter the sentence or 'q' to quit: ");
input = kb.nextLine();
}
}
public ObjectStream<NameSample> create(String[] args) {
Parameters params = ArgumentParser.parse(args, Parameters.class);
int typesToGenerate = 0;
if (params.getTypes().contains("DNA")) {
typesToGenerate = typesToGenerate | BioNLP2004NameSampleStream.GENERATE_DNA_ENTITIES;
} else if (params.getTypes().contains("protein")) {
typesToGenerate = typesToGenerate | BioNLP2004NameSampleStream.GENERATE_PROTEIN_ENTITIES;
} else if (params.getTypes().contains("cell_type")) {
typesToGenerate = typesToGenerate | BioNLP2004NameSampleStream.GENERATE_CELLTYPE_ENTITIES;
} else if (params.getTypes().contains("cell_line")) {
typesToGenerate = typesToGenerate | BioNLP2004NameSampleStream.GENERATE_CELLLINE_ENTITIES;
} else if (params.getTypes().contains("RNA")) {
typesToGenerate = typesToGenerate | BioNLP2004NameSampleStream.GENERATE_RNA_ENTITIES;
}
return new BioNLP2004NameSampleStream(
CmdLineUtil.openInFile(new File(params.getData())), typesToGenerate);
}
public void run(String format, String[] args) {
super.run(format, args);
mlParams = CmdLineUtil.loadTrainingParameters(params.getParams(), true);
if (mlParams != null && !TrainerFactory.isValid(mlParams.getSettings())) {
throw new TerminateToolException(
1, "Training parameters file '" + params.getParams() + "' is invalid!");
}
if (mlParams == null) {
mlParams = ModelUtil.createDefaultTrainingParameters();
mlParams.put(TrainingParameters.ALGORITHM_PARAM, getModelType(params.getType()).toString());
}
File modelOutFile = params.getModel();
CmdLineUtil.checkOutputFile("pos tagger model", modelOutFile);
Dictionary ngramDict = null;
Integer ngramCutoff = params.getNgram();
if (ngramCutoff != null) {
System.err.print("Building ngram dictionary ... ");
try {
ngramDict = POSTaggerME.buildNGramDictionary(sampleStream, ngramCutoff);
sampleStream.reset();
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while building NGram Dictionary: " + e.getMessage(), e);
}
System.err.println("done");
}
POSTaggerFactory postaggerFactory = null;
try {
postaggerFactory = POSTaggerFactory.create(params.getFactory(), ngramDict, null);
} catch (InvalidFormatException e) {
throw new TerminateToolException(-1, e.getMessage(), e);
}
if (params.getDict() != null) {
try {
postaggerFactory.setTagDictionary(postaggerFactory.createTagDictionary(params.getDict()));
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while loading POS Dictionary: " + e.getMessage(), e);
}
}
if (params.getTagDictCutoff() != null) {
try {
TagDictionary dict = postaggerFactory.getTagDictionary();
if (dict == null) {
dict = postaggerFactory.createEmptyTagDictionary();
postaggerFactory.setTagDictionary(dict);
}
if (dict instanceof MutableTagDictionary) {
POSTaggerME.populatePOSDictionary(
sampleStream, (MutableTagDictionary) dict, params.getTagDictCutoff());
} else {
throw new IllegalArgumentException(
"Can't extend a POSDictionary that does not implement MutableTagDictionary.");
}
sampleStream.reset();
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while creating/extending POS Dictionary: " + e.getMessage(), e);
}
}
POSModel model;
try {
model =
opennlp.tools.postag.POSTaggerME.train(
params.getLang(), sampleStream, mlParams, postaggerFactory);
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while reading training data or indexing data: " + e.getMessage(), e);
} finally {
try {
sampleStream.close();
} catch (IOException e) {
// sorry that this can fail
}
}
CmdLineUtil.writeModel("pos tagger", modelOutFile, model);
}
