搜索资源列表
Classifier4J
- Classifier4J这个Java类库为文本自动分类提供了一个API。缺省（目前）实现的API是一个贝叶斯分类器。这个类库可以用于多个目的－可能作为一个垃圾邮件过滤器或一个blog-Classifier4J Java class library for the automatic text classification provided an API. Default (current) to achieve the API is a Bayesian classifier. This lib
EmailTool
- java邮件分析器，可以从文本文件中分析出各种邮件地址，并且根据输入的域名后缀将邮件地址分类为相应的文件输出文件-java message parser, you can analyze a text file from a variety of e-mail address, and the input of the domain name suffix will e-mail address is classified as the corresponding file output fil
src
- java实现的博客.完成了博客的编辑,分类,评论等.其中运用了ckeditor插件完成博客的文本编辑。-java achieve blog. complete blog editing, classification, comments, etc. which use a text editor to complete the plug ckeditor the blog.
KNN
- 实现了KNN文本的分类，KNN最近邻基于欧几里德距离的JAVA算法实现适用于初级学习KNN的初学者。-Realization of KNN text classification, KNN nearest neighbor JAVA algorithm for Euclidean distance implementation is applied to the primary learning KNN beginners based on.
java_KNN
- 实现了KNN文本的分类，KNN最近邻基于欧几里德距离的JAVA算法实现适用于初级学习KNN的初学者。-Realization of KNN text classification, KNN nearest neighbor JAVA algorithm for Euclidean distance implementation is applied to the primary learning KNN beginners based on.
TestStopWords
- 这一个关于中文件文本分类测试例子中关于停用词测试的JAVA程序源代码。-test text stop word
JGibbLDA-v.1.0
- 基于LDA（Latent Dirichlet Allocation）的文本分类处理，开始学习和接触了LDA，因为代码采用的是Java，LDA开源工具是JGibbLDA，这个是LDA的Java版本实现-Based on the LDA (Latent Dirichlet Allocation) of the text classification process, started learning and exposure to LDA, because the code uses Java, L
MiniEditDistance
- java语言实现的文本分类的第一步，替换一个词语的最小代价，即为最小编辑距离-java implement the minimum edit distance
AutoModel
- 对已知类别投诉文本进行建模，用以对后面未知类别文本进行分类(Modeling a known class of complaint texts to classify text in the later unknown category)
CNN
- 卷积神经网络的源代码，用于微博博文文本情感分析的三分类。(Convolutional neural network source code for micro-blog Bowen text sentiment analysis of the three categories.)
learning-spark-master
- 将逻辑回归应用于二元分类的情况。这里以垃圾邮件分类为例，即是否为垃圾邮件两种情况。然后，根据词频把每个文件中的文本转换为特征向量，训练出一个可以把两类消息分开的逻辑回归模型，判断输入测试语句是否为垃圾邮件。(Spark MLlib (Java): Input: spam.txt; normal.txt; text sentence. Output:1.0(spam), 0.0(normal email))