Stream Data Mining Library for Spark Streaming
Second release for StreamDM.
It contains the first iteration of the StreamDM API, and implements the following methods:
Classification: SGD Learner, Perceptron, Naive Bayes, and Hoeffding Decision Trees; Clustering: CluStream and StreamKM++; Ensembles: Bagging. It uses weka's arff format as the default data description and contains following data generators:
HyperplaneGenerator RandomTreeGenerator RandomRBFGenerator RandomRBFEventsGenerator
First release candidate for StreamDM.
It contains the first iteration of the StreamDM API, and implements the following methods: