5、CosineSimilarity(相似率具体实现工具类) importcom.jincou.algorithm.tokenizer.Tokenizer;importcom.jincou.algorithm.tokenizer.Word; importorg.apache.commons.lang3.StringUtils;importorg.slf4j.Logger;importorg.slf4j.LoggerFactory;importorg.springframework.util.CollectionUtils;importjava.math.BigDecimal;importja...
5、CosineSimilarity(相似率具体实现工具类) import com.jincou.algorithm.tokenizer.Tokenizer;import com.jincou.algorithm.tokenizer.Word; import org.apache.commons.lang3.StringUtils;import org.slf4j.Logger;import org.slf4j.LoggerFactory;import org.springframework.util.CollectionUtils;import java.math.BigDecim...
5、CosineSimilarity(相似率具体实现工具类) import com.jincou.algorithm.tokenizer.Tokenizer; import com.jincou.algorithm.tokenizer.Word; import org.apache.commons.lang3.StringUtils; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import org.springframework.util.CollectionUtils; import java.math...
public static double getSimilarity(String doc1, String doc2) { if (doc1 != null && doc1.trim().length() > 0 && doc2 != null && doc2.trim().length() > 0) { Map AlgorithmMap = new HashMap(); //将两个字符串中的中文字符以及出现的总数封装到,AlgorithmMap中 for (int i = 0;...
public class CosineSimilarAlgorithm { /** * * @Title: cosSimilarityByFile * @Description: 获取两个文件相似性 * @param @param firstFile * @param @param secondFile * @param @return * @return Double * @throws */ public static Double cosSimilarityByFile(String firstFile,String secondFile){ ...
5、CosineSimilarity(相似率具体实现工具类) import com.jincou.algorithm.tokenizer.Tokenizer; import com.jincou.algorithm.tokenizer.Word; import org.apache.commons.lang3.StringUtils; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import org.springframework.util.CollectionUtils; ...
5、CosineSimilarity(相似率具体实现工具类) importcom.jincou.algorithm.tokenizer.Tokenizer;importcom.jincou.algorithm.tokenizer.Word;importorg.apache.commons.lang3.StringUtils;importorg.slf4j.Logger;importorg.slf4j.LoggerFactory;importorg.springframework.util.CollectionUtils;importjava.math.BigDecimal;importjava...
publicclassCosine {publicstaticdoublegetSimilarity(String doc1, String doc2) {if(doc1 !=null&& doc1.trim().length() > 0 && doc2 !=null&& doc2.trim().length() > 0) { Map<Integer,int[]> AlgorithmMap =newHashMap<Integer,int[]>();//将两个字符串中的中文字符以及出现的总数封装到,...
I think the "i am a book" is taken as a single feature. To do the comparison you have to split your compared strings first using a whitespace as a separator. Next you have to populate hashmaps with corresponding words extracted from a book title. You can then test your algorithm if ...