文本的词条化和向量化

Posted 2020-06-18 杨鑫newlfe

<strong><span style="font-size:18px;">/***
 * @author YangXin
 * @info 此代码展示了如何对文本中的所有单词进行编码， 然后产生每个单词编码的线性权重之和，
 * 从而将文本编码为向量。这是用StaticWordValueEncoder实现的，并且还要有办法将文本分解
 * 或分析称单词。Mahout提供了编辑器，Lucene提供了分析器。
 */
package unitFourteen;

import java.io.IOException;
import java.io.StringReader;

import org.apache.commons.collections.bag.SynchronizedSortedBag;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.util.Version;
import org.apache.mahout.math.RandomAccessSparseVector;
import org.apache.mahout.math.SequentialAccessSparseVector;
import org.apache.mahout.math.Vector;
import org.apache.mahout.vectorizer.encoders.FeatureVectorEncoder;
import org.apache.mahout.vectorizer.encoders.StaticWordValueEncoder;

public class TokenizingAndVectorizingText {
	public static void main(String[] args) throws IOException {
		FeatureVectorEncoder encoder = new StaticWordValueEncoder("text");
		Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31);     

		StringReader in = new StringReader("text to magically vectorize");
		TokenStream ts = analyzer.tokenStream("body", in);
		TermAttribute termAtt = ts.addAttribute(TermAttribute.class);

		Vector v1 = new RandomAccessSparseVector(100);                   
		while (ts.incrementToken()) {
		  char[] termBuffer = termAtt.termBuffer();
		  int termLen = termAtt.termLength();
		  String w = new String(termBuffer, 0, termLen);                 
		  encoder.addToVector(w, 1, v1);                                 
		}
		System.out.printf("%s\n", new SequentialAccessSparseVector(v1));
	}
}
</span></strong>