使用libsvm实现文本分类

缺乏、安全感 2022-09-22 13:55 337阅读 0赞

文本分类，首先它是分类问题，应该对应着分类过程的两个重要的步骤，一个是使用训练数据集训练分类器，另一个就是使用测试数据集来评价分类器的分类精度。然而，作为文本分类，它还具有文本这样的约束，所以对于文本来说，需要额外的处理过程，我们结合使用libsvm从宏观上总结一下，基于libsvm实现文本分类实现的基本过程，如下所示：

1.  选择文本训练数据集和测试数据集：训练集和测试集都是类标签已知的；
2.  训练集文本预处理：这里主要包括分词、去停用词、建立词袋模型（倒排表）；
3.  选择文本分类使用的特征向量（词向量）：最终的目标是使得最终选出的特征向量在多个类别之间具有一定的类别区分度，可以使用相关有效的技术去实现特征向量的选择，由于分词后得到大量的词，通过选择降维技术能很好地减少计算量，还能维持分类的精度；
4.  输出libsvm支持的量化的训练样本集文件：类别名称、特征向量中每个词元素分别到数字编号的映射转换，以及基于类别和特征向量来量化文本训练集，能够满足使用libsvm训练所需要的数据格式；
5.  测试数据集预处理：同样包括分词（需要和训练过程中使用的分词器一致）、去停用词、建立词袋模型（倒排表），但是这时需要加载训练过程中生成的特征向量，用特征向量去排除多余的不在特征向量中的词（也称为降维）；
6.  输出libsvm支持的量化的测试样本集文件：格式和训练数据集的预处理阶段的输出相同。
7.  使用libsvm训练文本分类器：使用训练集预处理阶段输出的量化的数据集文件，这个阶段也需要做很多工作（后面会详细说明），最终输出分类模型文件
8.  使用libsvm验证分类模型的精度：使用测试集预处理阶段输出的量化的数据集文件，和分类模型文件来验证分类的精度。
9.  分类模型参数寻优：如果经过libsvm训练出来的分类模型精度很差，可以通过libsvm自带的交叉验证（Cross Validation）功能来实现参数的寻优，通过搜索参数取值空间来获取最佳的参数值，使分类模型的精度满足实际分类需要。

基于上面的分析，分别对上面每个步骤进行实现，最终完成一个分类任务。

数据集选择

我们选择了搜狗的语料库，可以参考后面的链接下载语料库文件。这里，需要注意的是，分别准备一个训练数据集和一个测试数据集，不要让两个数据集有交叉。例如，假设有C个类别，选择每个分类的下的N篇文档作为训练集，总共的训练集文档数量为C\*N，剩下的每一类下M篇作为测试数据集使用，测试数据集总共文档数等于C\*M。

数据集文本预处理

我们选择使用ICTCLAS分词器，使用该分词器可以不需要预先建立自己的词典，而且分词后已经标注了词性，可以根据词性对词进行一定程度过滤（如保留名词，删除量词、叹词等等对分类没有意义的词汇）。  
下载ICTCLAS软件包，如果是在Win7 64位系统上使用Java实现分词，选择如下两个软件包：

*  20131115123549\_nlpir\_ictclas2013\_u20131115\_release.zip
 *  20130416090323\_Win-64bit-JNI-lib.zip

将第二个软件包中的NLPIR\_JNI.dll文件拷贝到C:\\Windows\\System32目录下面，将第一个软件包中的Data目录和NLPIR.dll、NLPIR.lib、NLPIR.h、NLPIR.lib文件拷贝到Java工程根目录下面。  
对于其他操作系统，可以到ICTCLAS网站（[http://ictclas.nlpir.org/downloads][http_ictclas.nlpir.org_downloads]）下载对应版本的软件包。  
下面，我们使用Java实现分词，定义分词器接口，以便切换其他分词器实现时，容易扩展，如下所示：

增加一个外部的停用词表，这个我们直接封装到抽象类AbstractDocumentAnalyzer中去了，该抽象类就是从一个指定的文件或目录读取停用词文件，将停用词加载到内存中，在分词的过程中对词进行进一步的过滤。然后基于上面的实现，给出包裹ICTCLAS分词器的实现，代码如下所示：

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">19</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">public</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">class</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">IctclasAnalyzer&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">extends</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">AbstractDocumentAnalyzer&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">implements</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">DocumentAnalyzer { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">21</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">static</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">final</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">Log LOG = LogFactory.getLog(IctclasAnalyzer.</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">class</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">28</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">boolean</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">initialized = NLPIR.NLPIR_Init(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">"."</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">.getBytes(charSet),&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">1</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">30</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">throw</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">RuntimeException(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">"Fail to initialize!"</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">33</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">throw</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">RuntimeException(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">""</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">, e);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">41</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">Map&lt;String, Term&gt; terms =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">HashMap&lt;String, Term&gt;(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">44</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">br =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">BufferedReader(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">InputStreamReader(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">FileInputStream(file), charSet));</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">46</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">while</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">((line = br.readLine()) !=&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">null</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">) { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">49</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">byte</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">nativeBytes[] = analyzer.NLPIR_ParagraphProcess(line.getBytes(charSet),&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">1</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">50</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">String content =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">String(nativeBytes,&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">, nativeBytes.length, charSet);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">51</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">String[] rawWords = content.split(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">"\\s+"</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">53</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">String[] words = rawWord.split(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">"/"</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">54</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">if</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">(words.length ==&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">2</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">) { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">55</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">String word = words[</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">];</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">56</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">String lexicalCategory = words[</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">1</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">];</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">65</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">LOG.debug(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">"Got word: word="</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">+ rawWord);</code></td> 
  </tr> 
 </tbody> 
</table>

它是对一个文件进行读取，然后进行分词，去停用词，最后返回的Map包含了的集合，此属性包括词性（Lexical Category）、词频、TF等信息。  
这样，遍历数据集目录和文件，就能去将全部的文档分词，最终构建词袋模型。我们使用Java中集合来存储文档、词、类别之间的关系，如下所示：

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">02</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">final</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">List&lt;String&gt; labels =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">ArrayList&lt;String&gt;();</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">04</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">final</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">Map&lt;String, Integer&gt; labelledTotalDocCountMap =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">HashMap&lt;String, Integer&gt;();</code></td> 
  </tr> 
 </tbody> 
</table>

基于训练数据集选择特征向量

上面已经构建好词袋模型，包括相关的文档和词等的关系信息。现在我们来选择用来建立分类模型的特征词向量，首先要选择一种度量，来有效地选择出特征词向量。基于论文《A comparative study on feature selection in text categorization》，我们选择基于卡方统计量（chi-square statistic， CHI）技术来实现选择，这里根据计算公式：![Center][]  
其中，公式中各个参数的含义，说明如下：

*  N：训练数据集文档总数
 *  A：在一个类别中，包含某个词的文档的数量
 *  B：在一个类别中，排除该类别，其他类别包含某个词的文档的数量
 *  C：在一个类别中，不包含某个词的文档的数量
 *  D：在一个类别中，不包含某个词也不在该类别中的文档的数量

要想进一步了解，可以参考这篇论文。  
使用卡方统计量，为每个类别下的每个词都进行计算得到一个CHI值，然后对这个类别下的所有的词基于CHI值进行排序，选择出最大的topN个词（很显然使用堆排序算法更合适）；最后将多个类别下选择的多组topN个词进行合并，得到最终的特征向量。  
其实，这里可以进行一下优化，每个类别下对应着topN个词，在合并的时候可以根据一定的标准，将各个类别都出现的词给出一个比例，超过指定比例的可以删除掉，这样可以使特征向量在多个类别分类过程中更具有区分度。这里，我们只是做了个简单的合并。  
我们看一下，用到的存储结构，使用Java的集合来存储：

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">2</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">final</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">Map&lt;String, Map&lt;String, Term&gt;&gt; chiLabelToWordsVectorsMap =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">HashMap&lt;String, Map&lt;String, Term&gt;&gt;(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">4</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">final</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">Map&lt;String, Term&gt; chiMergedTermVectorMap =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">new</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">HashMap&lt;String, Term&gt;(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

下面，实现特征向量选择计算的实现，代码如下所示：

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">015</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">public</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">class</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">FeatureTermVectorSelector&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">extends</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">AbstractComponent { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">017</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">static</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">final</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">Log LOG = LogFactory.getLog(FeatureTermVectorSelector.</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">class</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">018</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">final</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">int</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">keptTermCountEachLabel;</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">022</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">keptTermCountEachLabel = context.getConfiguration().getInt(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">"processor.each.label.kept.term.count"</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">,&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">3000</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">041</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">LOG.info(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">"Sort CHI terms for: label="</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">+ label +&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">", termCount="</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">+ entry.getValue().size());</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">043</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">for</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">int</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">i =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">; i &lt; Math.min(a.length, keptTermCountEachLabel); i++) { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">051</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(128,128,128)!important; background:none!important">@SuppressWarnings</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">(</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:blue!important; background:none!important">"unchecked"</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">)</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">059</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">void</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">processOneLabel(String label) { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">068</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">int</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">docCountContainingWordInLabel =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">;</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">069</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">if</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">(labelledDocs.get(label) !=&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">null</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">) { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">074</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">int</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">docCountContainingWordNotInLabel =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">;</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">100</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">double</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">chi = (</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">double</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">) N*temp*temp / (A+C)*(A+B)*(B+D)*(C+D);</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">107</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">int</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">getDocCountNotContainingWordInLabel(String word, String label) { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">108</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">int</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">count =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">;</code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">129</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">private</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">int</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">getDocCountNotContainingWordNotInLabel(String word, String label) { </code></td> 
  </tr> 
 </tbody> 
</table>

<table style="border-spacing:0px; margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; border-collapse:collapse!important; width:auto!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
 <tbody style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
  <tr style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; background:none!important"> 
   <td style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:3em!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; color:rgb(175,175,175)!important; background:none!important"> <code style="margin:0px!important; padding:0px 0.3em 0px 0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; text-align:right!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:2.7em!important; line-height:1.1em!important; direction:ltr!important; display:block!important; background:none!important">130</code></td> 
   <td style="margin:0px!important; padding:0px 0px 0px 0.5em!important; border-width:0px 0px 0px 3px!important; border-left-style:solid!important; border-left-color:rgb(108,226,108)!important; outline:0px!important; font-size:1em!important; vertical-align:top!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; direction:ltr!important; background:none!important"> <code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; font-weight:bold!important; direction:ltr!important; display:inline!important; color:rgb(0,102,153)!important; background:none!important">int</code>&nbsp;<code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">count =&nbsp;</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; color:rgb(0,153,0)!important; background:none!important">0</code><code style="margin:0px!important; padding:0px!important; border:0px!important; outline:0px!important; font-size:1em!important; vertical-align:baseline!important; font-family:Consolas,'Bitstream Vera Sans Mono','Courier New',Courier,monospace!important; float:none!important; position:static!important; left:auto!important; top:auto!important; right:auto!important; bottom:auto!important; height:auto!important; width:auto!important; line-height:1.1em!important; direction:ltr!important; display:inline!important; background:none!important">;</code></td> 
  </tr> 
 </tbody> 
</table>

输出量化数据文件

特征向量已经从训练数据集中计算出来，接下来需要对每个词给出一个唯一的编号，从1开始，这个比较容易，输出特征向量文件，为测试验证的数据集所使用，文件格式如下所示：

由于libsvm使用的训练数据格式都是数字类型的，所以需要对训练集中的文档进行量化处理，我们使用TF-IDF度量，表示词与文档的相关性指标。  
然后，需要遍历已经构建好的词袋模型，并使用已经编号的类别和特征向量，对每个文档计算TF-IDF值，每个文档对应一条记录，取出其中一条记录，输出格式如下所示：

第一列的8表示类别编号，其余的每一列是词及其权重，使用冒号分隔，例如“9219:0.24673737883635047”表示编号为9219的词，对应的TF-IDF值为0.24673737883635047。如果特征向量有个N个，那么每条记录就对应着一个N维向量。  
对于测试数据集中的文档，也使用类似的方法，不过首先需要加载已经输出的特征向量文件，从而构建一个支持libsvm格式的输出测试集文件。

使用libsvm训练文本分类器

前面的准备工作已经完成，现在可以使用libsvm工具包训练文本分类器。在使用libsvm的开始，需要做一个尺度变换操作（有时也称为归一化），有利于libsvm训练出更好的模型。我们已经知道前面输出的数据中，每一维向量都使用了TF-IDF的值，但是TF-IDF的值可能在一个不规范的范围之内（因为它依赖于TF和IDF的值），例如0.19872~8.3233，所以可以使用libsvm将所有的值都变换到同一个范围之内，如0~1.0，或者-1.0~1.0，可以根据实际需要选择。我们看一下命令：

尺度变换后输出到文件train-scale.txt中，它可以直接作为libsvm训练的数据文件，我使用Java版本的libsvm代码，输入参数如下所示：

这里面，-t 0表示使用线性核函数，我发现在进行文本分类时，线性核函数比libsvm默认的-t 2非线性核函数的效果要要好一些。最后输出的是模型文件model.txt，内容示例如下所示：

上面，我们只是选择了非默认的核函数，还有其他参数可以选择，比如代价系数c，默认是1，表示在计算线性分类面时，可以容许一个点被分错。这时候，可以使用交叉验证来逐步优化计算，选择最合适的参数。  
使用libsvm，指定交叉验证选项的时候，只输出经过交叉验证得到的分类器的精度，而不会输出模型文件，例如使用交叉验证模型运行时的参数示例如下：

用-v启用交叉验证模式，参数-v 5表示将每一类下面的数据分成5份，按顺序1对2，2对3，3对4，4对5，5对1分别进行验证，从而得出交叉验证的精度。例如，下面是我们的10个类别的交叉验证运行结果：

在选好各个参数以后，就可以使用最优的参数来计算输出模型文件。

使用libsvm验证文本分类器精度

前面已经训练出来分类模型，就是最后输出的模型文件。现在可以使用测试数据集了，通过使用测试数据集来做对基于文本分类模型文件预测分类精度进行验证。同样，需要做尺度变换，例如：

注意，这里必须和训练集使用相同的尺度变换参数值。  
我还是使用Java版本的libsvm进行预测，验证分类器精度，svm\_predict类的输入参数：

这样，预测结果就在predict.txt文件中，同时输出分类精度结果，例如：

如果觉得分类器精度不够，可以使用交叉验证去获取更优的参数，来训练并输出模型文件，例如，下面是几组结果：

第一组是默认情况下c=1时的精度为 67.10000000000001%；  
第二组使用了交叉验证模型，交叉验证精度为71.10428571428571%，获得参数c=32，使用该参数训练输出模型文件，基于该模型文件进行预测，最终的精度为66.81%，可见没有使用默认c参数值的精度高；  
第三组使用交叉验证，精度比第二组高一些，输出模型后并进行预测，最终精度为67.88%，略有提高。  
可以基于这种方式不断地去寻找最优的参数，从而使分类器具有更好的精度。

总结

文本分类有其特殊性，在使用libsvm分类，或者其他的工具，都不要忘记，有如下几点需要考虑到：

1.  其实文本在预处理过程进行的很多过程对最后使用工具进行分类都会有影响。
2.  最重要的就是文本特征向量的选择方法，如果文本特征向量选择的很差，即使再好的分类工具，可能训练得到的分类器都未必能达到更好。
3.  文本特征向量选择的不好，在训练调优分类器的过程中，虽然找到了更好的参数，但是这本身可能会是一个不好的分类器，在实际预测中可以出现误分类的情况。
4.  选择训练集和测试集，对整个文本预处理过程，以及使用分类工具进行训练，都有影响。