text-classification

代码说明：

  matlab编写的文本分类的程序，可以对已经分好词的文本进行分类，先自己导入数据，用libsvm中的svm进行分类和预测，特征用tfidf算法，还利用卡方检验进行了特征选择，可自行设定阈值。(matlab prepared text classification program, you can have a good word of text classification, classification and prediction using libsvm in svm, characterized by tfidf algorithm, also used the chi-square test was used for feature selection, you can set thresholds on their own.)

文件列表：

text classification
...................\datatest.txt,281,2013-10-24
...................\datatrain.txt,337,2013-10-24
...................\extractwords.m,404,2013-10-24
...................\inputchinese1.txt,70,2013-10-23
...................\porterStemmer.m,9904,2013-10-23
...................\stopwordchinese.txt,6364,2009-11-23
...................\test.mat,239,2013-10-23
...................\tfidf.m,2723,2013-10-23
...................\worddictionary.m,1547,2013-10-23
...................\wordpredict.asv,525,2013-10-24
...................\wordpredict.m,525,2013-10-24
...................\wordtest.txt,358,2013-10-24
...................\wordtrain.txt,441,2013-10-24
...................\wordtrain_label.mat,195,2013-10-24
...................\文本特征词提取步骤.docx,26967,2013-10-24
...................\新建 文本文档.txt,717,2013-10-23