本文整理了Java中zemberek.core.logging.Log.info()
方法的一些代码示例,展示了Log.info()
的具体用法。这些代码示例主要来源于Github
/Stackoverflow
/Maven
等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。Log.info()
方法的具体详情如下:
包路径:zemberek.core.logging.Log
类名称:Log
方法名:info
暂无
代码示例来源:origin: ahmetaa/zemberek-nlp
public static void simpleSentenceBoundaryDetector() {
String input =
"Prof. Dr. Veli Davul açıklama yaptı. Kimse %6.5 lik enflasyon oranını beğenmemiş!" +
" Oysa maçta ikinci olmuştuk... Değil mi?";
Log.info("Paragraph = " + input);
TurkishSentenceExtractor extractor = TurkishSentenceExtractor.DEFAULT;
List<String> sentences = extractor.fromParagraph(input);
Log.info("Sentences:");
for (String sentence : sentences) {
Log.info(sentence);
}
}
代码示例来源:origin: ahmetaa/zemberek-nlp
public static void simpleTokenization() {
Log.info("Simple tokenization returns a list of token strings.");
TurkishTokenizer tokenizer = TurkishTokenizer.DEFAULT;
String input = "İstanbul'a, merhaba!";
Log.info("Input = " + input);
Log.info("Tokenization list = " +
Joiner.on("|").join(tokenizer.tokenizeToStrings("İstanbul'a, merhaba!")));
}
代码示例来源:origin: ahmetaa/zemberek-nlp
void info() {
Log.info("There are %d sentences and %d tokens.",
sentences.size(),
sentences.stream().mapToInt(SentenceAnalysis::size).sum());
}
代码示例来源:origin: ahmetaa/zemberek-nlp
static void convertTweetData() throws IOException {
Path in = Paths.get("/home/aaa/Downloads/20milyontweet/all_tweets.txt");
Path out = Paths.get("/home/aaa/Downloads/20milyontweet/all_tweets-utf8");
List<String> lines = Files.readAllLines(in, Charset.forName("iso-8859-9"));
Log.info("Writing.");
Files.write(out, lines, StandardCharsets.UTF_8);
}
代码示例来源:origin: ahmetaa/zemberek-nlp
void createGraph(BlockTextLoader corpusProvider, Path graphPath) throws Exception {
Stopwatch sw = Stopwatch.createStarted();
ContextualSimilarityGraph graph = buildGraph(corpusProvider, 1);
Log.info("Serializing graph for random walk structure.");
graph.serializeForRandomWalk(graphPath);
Log.info("Serialized to %s", graphPath);
Log.info("Graph created in %.3f seconds.",
sw.elapsed(TimeUnit.MILLISECONDS) / 1000d);
}
代码示例来源:origin: ahmetaa/zemberek-nlp
public static void tokenIterator() {
Log.info("Low level tokenization iterator using Ant-lr Lexer.");
String input = "İstanbul'a, merhaba!";
Log.info("Input = " + input);
Iterator<Token> tokenIterator = tokenizer.getTokenIterator(input);
while (tokenIterator.hasNext()) {
Token token = tokenIterator.next();
Log.info("Token = " + token.getText() +
", Type = " + TurkishLexer.VOCABULARY.getDisplayName(token.getType()));
}
}
代码示例来源:origin: ahmetaa/zemberek-nlp
void dataInfo(List<String> lines) {
Log.info("Total lines = " + lines.size());
Histogram<String> hist = new Histogram<>();
lines.stream()
.map(s -> s.substring(0, s.indexOf(' ')))
.forEach(hist::add);
Log.info("Categories :");
for (String s : hist.getSortedList()) {
Log.info(s + " " + hist.getCount(s));
}
}
代码示例来源:origin: ahmetaa/zemberek-nlp
void dataInfo(List<String> lines) {
Log.info("Total lines = " + lines.size());
Histogram<String> hist = new Histogram<>();
lines.stream()
.map(s -> s.substring(0, s.indexOf(' ')))
.forEach(hist::add);
Log.info("Categories :");
for (String s : hist.getSortedList()) {
Log.info(s + " " + hist.getCount(s));
}
}
代码示例来源:origin: ahmetaa/zemberek-nlp
public static void main(String[] args) {
TurkishMorphology morphology = TurkishMorphology.createWithDefaults();
String word = "kutucuğumuz";
Log.info("Word = " + word);
Log.info("Results: ");
WordAnalysis results = morphology.analyze(word);
for (SingleAnalysis result : results) {
Log.info(result.formatLong());
Log.info("\tStems = " + result.getStems());
Log.info("\tLemmas = " + result.getLemmas());
}
}
代码示例来源:origin: ahmetaa/zemberek-nlp
static void testModel(Path root, Path test, String name) {
Log.info("Testing...");
Path modelPath = root.resolve(name + ".model");
Path predictions = root.resolve(name + ".predictions");
new EvaluateClassifier().execute(
"-i", test.toString(),
"-m", modelPath.toString(),
"-o", predictions.toString(),
"-k", "1"
);
}
代码示例来源:origin: ahmetaa/zemberek-nlp
public CorpusDb(Path dbRoot) throws IOException, SQLException {
if (dbRoot.toFile().exists() && !dbRoot.toFile().isDirectory()) {
throw new IllegalArgumentException("Database root path is not a directory :" + dbRoot);
}
if (!dbRoot.toFile().exists()) {
Log.info("Creating database root folder %s", dbRoot);
Files.createDirectories(dbRoot);
}
this.dbPath = dbRoot.resolve("data");
connectionPool = JdbcConnectionPool.create(getJdbcConnectionString(), "sa", "sa");
createTablesIfNotExist();
}
代码示例来源:origin: ahmetaa/zemberek-nlp
public static void main(String[] args) throws IOException {
DistanceList experiment = DistanceList.readFromBinary(
Paths.get("/media/depo/data/aaa/corpora/distance-large-min10.bin"),
Paths.get("/media/depo/data/aaa/corpora/vocab-large-min10.bin"));
Log.info("Writing");
experiment.saveReduced(Paths.get("/media/depo/data/aaa/corpora/distance-10.bin"), 10);
}
代码示例来源:origin: ahmetaa/zemberek-nlp
private WebCorpus getWebCorpus(Path input) throws IOException {
Log.info("Loading %s", input);
WebCorpus wc = new WebCorpus(input.toFile().getName(), input.toFile().getName());
wc.addDocuments(WebCorpus.loadDocuments(input));
return wc;
}
代码示例来源:origin: ahmetaa/zemberek-nlp
public Builder addTextDictionaryResources(Collection<String> resources) throws IOException {
Log.info("Dictionaries :%s", String.join(", ", resources));
List<String> lines = new ArrayList<>();
for (String resource : resources) {
lines.addAll(TextIO.loadLinesFromResource(resource));
}
lexicon.addAll(TurkishDictionaryLoader.load(lines));
return this;
}
代码示例来源:origin: ahmetaa/zemberek-nlp
Vocabulary collectVocabularyHistogram(BlockTextLoader corpora, int threadCount)
throws Exception {
ExecutorService executorService = new BlockingExecutor(threadCount);
Vocabulary result = new Vocabulary();
for (TextChunk chunk : corpora) {
Log.info("Processing %s", chunk);
executorService.submit(new WordCollectorTask(chunk, result));
}
executorService.shutdown();
executorService.awaitTermination(1, TimeUnit.DAYS);
return result;
}
代码示例来源:origin: ahmetaa/zemberek-nlp
public RuleBasedDisambiguator(TurkishMorphology analyzer, Rules rules)
throws IOException {
this.analyzer = analyzer;
Log.info("Loading 100k word frequencies.");
List<String> freqLines = TextIO.loadLinesFromCompressedResource("/ambiguity/freq-100k.txt.gz");
wordFreq = Histogram.loadFromLines(freqLines, ' ');
this.rules = rules;
}
代码示例来源:origin: ahmetaa/zemberek-nlp
@Override
public void run() throws Exception {
ZemberekGrpcConfiguration configuration = null;
if (dataRoot != null) {
IOUtil.checkDirectoryArgument(dataRoot, "Zemberek External Data Root");
Log.info("Zemberek external data root is : %s", dataRoot.toFile().getAbsolutePath());
configuration = ZemberekGrpcConfiguration.fromDataRoot(dataRoot);
}
ZemberekGrpcServer server = new ZemberekGrpcServer(port, configuration);
server.start();
}
代码示例来源:origin: ahmetaa/zemberek-nlp
@Override
public void analyzeSentence(SentenceAnalysisRequest request,
StreamObserver<SentenceAnalysisProto> responseObserver) {
String sentence = request.getInput();
SentenceAnalysis a = morphology.analyzeAndDisambiguate(sentence);
Log.info("Sentence = %s", sentence);
responseObserver.onNext(toSentenceAnalysis(a, request.getContainAllAnalyses()));
responseObserver.onCompleted();
}
代码示例来源:origin: ahmetaa/zemberek-nlp
public static TurkishMorphology createWithDefaults() {
Stopwatch sw = Stopwatch.createStarted();
TurkishMorphology instance = new Builder().setLexicon(RootLexicon.getDefault()).build();
Log.info("Initialized in %d ms.", sw.elapsed(TimeUnit.MILLISECONDS));
return instance;
}
代码示例来源:origin: ahmetaa/zemberek-nlp
static Model loadFromTextFile(Path file) throws IOException {
FloatValueMap<String> data = new FloatValueMap<>(10000);
List<String> all = TextIO.loadLines(file);
for (String s : all) {
float weight = Float.parseFloat(Strings.subStringUntilFirst(s, " "));
String key = Strings.subStringAfterFirst(s, " ");
data.set(key, weight);
}
Log.info("Model Loaded.");
return new Model(data);
}
内容来源于网络,如有侵权,请联系作者删除!