-1
하나의 단일 디렉토리에 포함 된 25,000 개의 개별 텍스트 영화 리뷰에 대한 감정 분석을 수행하기 위해 Stanford CoreNLP를 사용하고 있습니다. 이렇게하기 위해서는 스탠포드 코드를 하나의 텍스트 파일 내에서 개별 문장 만 분석하기 때문에 약간 수정해야합니다.Java - 디렉토리 내의 각 파일 내용 처리
다음이 수행에서 내 시도이다 : 나는 다음과 같은 오류가 나타날 수있는
이import java.io.File;
import java.io.IOException;
import java.nio.charset.Charset;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import org.apache.commons.io.FileUtils;
import com.google.common.io.Files;
import edu.stanford.nlp.dcoref.CorefChain;
import edu.stanford.nlp.dcoref.CorefCoreAnnotations.CorefChainAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.NamedEntityTagAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.PartOfSpeechAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.SentencesAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.TextAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.TokensAnnotation;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
import edu.stanford.nlp.semgraph.SemanticGraph;
import edu.stanford.nlp.semgraph.SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.trees.TreeCoreAnnotations.TreeAnnotation;
import edu.stanford.nlp.util.CoreMap;
import java.io.File;
import java.util.Iterator;
import org.apache.commons.io.*;
/** A simple corenlp example ripped directly from the Stanford CoreNLP website using text from wikinews. */
public class sentimentMain {
public static void main(String[] args) throws IOException {
// creates a StanfordCoreNLP object, with POS tagging, lemmatization, NER, parsing, and coreference resolution
Properties props = new Properties();
props.put("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref");
StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// read some text from the file..
Iterator it = FileUtils.iterateFiles(new File("C:\\stanford-corenlp-full-2016-10-31\\train\\neg"), null, false);
Iterator it1 = FileUtils.iterateFiles(new File("C:\\stanford-corenlp-full-2016-10-31\\train\\pos"), null, false);
Iterator it2 = FileUtils.iterateFiles(new File("C:\\stanford-corenlp-full-2016-10-31\\train\\unsup"), null, false);
File inputFile = new File ((String) (it.next()));
String text = Files.toString(inputFile, Charset.forName("UTF-8"));
System.out.println(text);
//File inputFile = new File("C:/stanford-corenlp-full-2016-10-31/input.txt");
//String text = Files.toString(inputFile, Charset.forName("UTF-8"));
// create an empty Annotation just with the given text
Annotation document = new Annotation(text);
// run all Annotators on this text
pipeline.annotate(document);
// these are all the sentences in this document
// a CoreMap is essentially a Map that uses class objects as keys and has values with custom types
List<CoreMap> sentences = document.get(SentencesAnnotation.class);
for(CoreMap sentence: sentences) {
// traversing the words in the current sentence
// a CoreLabel is a CoreMap with additional token-specific methods
for (CoreLabel token: sentence.get(TokensAnnotation.class)) {
// this is the text of the token
String word = token.get(TextAnnotation.class);
// this is the POS tag of the token
String pos = token.get(PartOfSpeechAnnotation.class);
// this is the NER label of the token
String ne = token.get(NamedEntityTagAnnotation.class);
System.out.println("word: " + word + " pos: " + pos + " ne:" + ne);
}
// this is the parse tree of the current sentence
Tree tree = sentence.get(TreeAnnotation.class);
System.out.println("parse tree:\n" + tree);
// this is the Stanford dependency graph of the current sentence
SemanticGraph dependencies = sentence.get(CollapsedCCProcessedDependenciesAnnotation.class);
System.out.println("dependency graph:\n" + dependencies);
}
// This is the coreference link graph
// Each chain stores a set of mentions that link to each other,
// along with a method for getting the most representative mention
// Both sentence and token offsets start at 1!
Map<Integer, CorefChain> graph =
document.get(CorefChainAnnotation.class);
}
}
:
Exception in thread "main" java.lang.ClassCastException: java.io.File cannot be cast to java.lang.String
at sentimentMain.main(sentimentMain.java:46)
나는 "it.next는()"변환 할 수없는 것을 이해 문자열로하지만, 다른 사람이 파일의 내용이 처리를위한 문자열로 입력되고 있는지 확인할 수있는 다른 방법을 알고 있습니까? 사전에
감사합니다 :)
'Annotation document = new Annotation (text);'범위에없는'text' 변수에 접근하려고합니다. 'while (it.hasNext()) {'loop 안에 정의했다. –