This is a simple project about LDA model on Spark.
It will use Spark MLlib to train a LDA model on a training set. Then it will print the document-topic and topic-word distribution and forecast the topic distribution of new documents. You also can use it to query the most relevant documents in training set of a given topic. Besides, there is a parameter file that you can config for your own application.
---Contact me: [email protected]
---Any suggestion and question is welcome---
---Thanks---