Introduction - If you have any usage issues, please Google them yourself
利用knn算法实现了一个中文网页自动分类器, 包括网页预处理,ictclas中文分词,基于tf-idf的文本特征表示,基于df的特征选取和基于knn的分类算法,最后通过struts2框架web发布
Packet : text_category.rar filelist
src\alternate.properties
src\edu\udo\cs\wvtool\config\package.html
src\edu\udo\cs\wvtool\config\WVTConfigException.java
src\edu\udo\cs\wvtool\config\WVTConfiguration.java
src\edu\udo\cs\wvtool\config\WVTConfigurationFact.java
src\edu\udo\cs\wvtool\config\WVTConfigurationRule.java
src\edu\udo\cs\wvtool\crawler\CrawledInputList.java
src\edu\udo\cs\wvtool\crawler\package.html
src\edu\udo\cs\wvtool\crawler\WVToolCrawler.java
src\edu\udo\cs\wvtool\external\GermanStemmer.java
src\edu\udo\cs\wvtool\external\LovinsStemmer.java
src\edu\udo\cs\wvtool\external\package.html
src\edu\udo\cs\wvtool\external\Stemmer.java
src\edu\udo\cs\wvtool\external\Stopwords.java
src\edu\udo\cs\wvtool\external\StopwordsCzech.java
src\edu\udo\cs\wvtool\external\StopwordsFrench.java
src\edu\udo\cs\wvtool\external\StopWordsGerman.java
src\edu\udo\cs\wvtool\external\XmlReader.java
src\edu\udo\cs\wvtool\generic\charmapper\DummyCharConverter.java
src\edu\udo\cs\wvtool\generic\charmapper\package.html
src\edu\udo\cs\wvtool\generic\charmapper\WVTCharConverter.java
src\edu\udo\cs\wvtool\generic\inputfilter\package.html
src\edu\udo\cs\wvtool\generic\inputfilter\PDFInputFilter.java
src\edu\udo\cs\wvtool\generic\inputfilter\SelectingInputFilter.java
src\edu\udo\cs\wvtool\generic\inputfilter\SimpleTagIgnoringReader.java
src\edu\udo\cs\wvtool\generic\inputfilter\TagIgnoringReader.java
src\edu\udo\cs\wvtool\generic\inputfilter\TextInputFilter.java
src\edu\udo\cs\wvtool\generic\inputfilter\WVTInputFilter.java
src\edu\udo\cs\wvtool\generic\inputfilter\XMLInputFilter.java
src\edu\udo\cs\wvtool\generic\loader\package.html
src\edu\udo\cs\wvtool\generic\loader\SourceAsTextLoader.java
src\edu\udo\cs\wvtool\generic\loader\UniversalLoader.java
src\edu\udo\cs\wvtool\generic\loader\WVTDocumentLoader.java
src\edu\udo\cs\wvtool\generic\output\package.html
src\edu\udo\cs\wvtool\generic\output\WordVectorWriter.java
src\edu\udo\cs\wvtool\generic\output\WVTOutputFilter.java
src\edu\udo\cs\wvtool\generic\stemmer\AbstractStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\AbstractWordNetStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\DictionaryStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\DummyStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\FastGermanStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\LovinsStemmerWrapper.java
src\edu\udo\cs\wvtool\generic\stemmer\package.html
src\edu\udo\cs\wvtool\generic\stemmer\PorterStemmerWrapper.java
src\edu\udo\cs\wvtool\generic\stemmer\SimpleStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\SnowballLovinsStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\SnowballStemmerWrapper.java
src\edu\udo\cs\wvtool\generic\stemmer\ToLowerCaseConverter.java
src\edu\udo\cs\wvtool\generic\stemmer\WordNetHypernymStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\WordNetSynonymStemmer.java
src\edu\udo\cs\wvtool\generic\stemmer\WVTStemmer.java
src\edu\udo\cs\wvtool\generic\tokenizer\NGramTokenizer.java
src\edu\udo\cs\wvtool\generic\tokenizer\package.html
src\edu\udo\cs\wvtool\generic\tokenizer\SimpleTokenizer.java
src\edu\udo\cs\wvtool\generic\tokenizer\WVTTokenizer.java
src\edu\udo\cs\wvtool\generic\vectorcreation\BinaryOccurrences.java
src\edu\udo\cs\wvtool\generic\vectorcreation\package.html
src\edu\udo\cs\wvtool\generic\vectorcreation\TermFrequency.java
src\edu\udo\cs\wvtool\generic\vectorcreation\TermOccurrences.java
src\edu\udo\cs\wvtool\generic\vectorcreation\TFIDF.java
src\edu\udo\cs\wvtool\generic\vectorcreation\WVTVectorCreator.java
src\edu\udo\cs\wvtool\generic\wordfilter\AbstractStopWordFilter.java
src\edu\udo\cs\wvtool\generic\wordfilter\CombinedWordFilter.java
src\edu\udo\cs\wvtool\generic\wordfilter\DummyWordFilter.java
src\edu\udo\cs\wvtool\generic\wordfilter\package.html
src\edu\udo\cs\wvtool\generic\wordfilter\SelectingWordFilter.java
src\edu\udo\cs\wvtool\generic\wordfilter\StopWordFilterFile.java
src\edu\udo\cs\wvtool\generic\wordfilter\StopWordsWrapper.java
src\edu\udo\cs\wvtool\generic\wordfilter\StopWordsWrapperGerman.java
src\edu\udo\cs\wvtool\generic\wordfilter\WVTWordFilter.java
src\edu\udo\cs\wvtool\main\package.html
src\edu\udo\cs\wvtool\main\WVTDocumentInfo.java
src\edu\udo\cs\wvtool\main\WVTFileInputList.java
src\edu\udo\cs\wvtool\main\WVTInputList.java
src\edu\udo\cs\wvtool\main\WVTool.java
src\edu\udo\cs\wvtool\main\WVToolWordListener.java
src\edu\udo\cs\wvtool\main\WVTWordVector.java
src\edu\udo\cs\wvtool\util\package.html
src\edu\udo\cs\wvtool\util\StdOutLogger.java
src\edu\udo\cs\wvtool\util\TokenEnumeration.java
src\edu\udo\cs\wvtool\util\WordList2AMLFile.java
src\edu\udo\cs\wvtool\util\WVToolException.java
src\edu\udo\cs\wvtool\util\WVToolIOException.java
src\edu\udo\cs\wvtool\util\WVToolLogger.java
src\edu\udo\cs\wvtool\wordlist\package.html
src\edu\udo\cs\wvtool\wordlist\WVTWord.java
src\edu\udo\cs\wvtool\wordlist\WVTWordList.java
src\first-default.xml
src\org\tartarus\snowball\Among.java
src\org\tartarus\snowball\ext\danishStemmer.java
src\org\tartarus\snowball\ext\dutchStemmer.java
src\org\tartarus\snowball\ext\englishStemmer.java
src\org\tartarus\snowball\ext\finnishStemmer.java
src\org\tartarus\snowball\ext\frenc