文件列表:

AdaGraphMiner\MOA-AdaGraphMiner-src.zip (96068, 2011-11-12)
AdaGraphMiner\MOA-AdaGraphMiner.jar (148945, 2011-11-12)
AdaGraphMiner\src\moa\core\Example.java (974, 2011-08-15)
AdaGraphMiner\src\moa\core\GraphExample.java (1418, 2011-08-15)
AdaGraphMiner\src\moa\evaluation\LearningEvaluation.java (3829, 2011-08-15)
AdaGraphMiner\src\moa\learners\AbstractLearner.java (9261, 2011-08-15)
AdaGraphMiner\src\moa\learners\AdaGraphMiner.java (28356, 2011-11-12)
AdaGraphMiner\src\moa\learners\Learner.java (1763, 2011-08-15)
AdaGraphMiner\src\moa\streams\ConceptDriftStream.java (4787, 2011-11-12)
AdaGraphMiner\src\moa\streams\GraphFileStream.java (5061, 2011-08-15)
AdaGraphMiner\src\moa\streams\InstanceStream.java (1279, 2011-08-15)
AdaGraphMiner\src\moa\tasks\LearnEvaluateModel.java (8716, 2011-08-15)
AdaGraphMiner\src\moa\tasks\LearnModel.java (4998, 2011-08-15)
AdaGraphMiner\src\moss\Fragment.java (100459, 2011-08-15)
AdaGraphMiner\src\moss\Graph.java (81175, 2011-08-15)
AdaGraphMiner\src\moss\MossGraphMiner.java (134735, 2011-08-15)
AdaGraphMiner\src\moss\NamedGraph.java (18916, 2011-08-15)
AdaGraphMiner\src\moss\outputGraph.java (1984, 2011-08-15)
AdaGraphMiner\src\moss\Recoder.java (19211, 2011-08-15)
AdaGraphMiner\src\moa\core (0, 2011-08-15)
AdaGraphMiner\src\moa\evaluation (0, 2011-08-15)
AdaGraphMiner\src\moa\learners (0, 2011-08-15)
AdaGraphMiner\src\moa\streams (0, 2011-08-15)
AdaGraphMiner\src\moa\tasks (0, 2011-08-15)
AdaGraphMiner\src\moa (0, 2011-08-15)
AdaGraphMiner\src\moss (0, 2011-08-15)
AdaGraphMiner\src (0, 2011-08-15)
AdaGraphMiner (0, 2014-02-13)

README ======================= MOA-AdaGraphMiner is a extension to MOA that allows to mine frequent closed graphs from a large stream of small graphs. INSTALL ========= To install MOA-ADAGraphMiner, you will need the moss.jar library in your java classpath. You can download it from: http://www.borgelt.net/moss.html Also you need to have the following jar files: MOA-ADAGraphMiner.jar moa.jar sizeofag.jar USAGE ========== You may run the task "LearnEvaluateModel" and use the learner AdaGraphMiner with the following options: - w: Size of the sliding window. - b: Size of a batch of examples. - s: Minimum support. - a: Alpha Minimum support. - d: Delta Closed support. - g: Rightmost path extensions as gspan - v: Verbose mode - m: Mode of Learning: INC, WIN, ADAWIN, ADAADWIN REFERENCES ================== Albert Bifet, Geoff Holmes, Bernhard Pfahringer, Ricard Gavald: Mining frequent closed graphs on evolving data streams. KDD 2011: 591-599

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：