Distributed model fitted by LDA.
This type of model is currently only produced by Expectation-Maximization (EM).
This model stores the inferred topics, the full training dataset, and the topic distribution
for each training document.
Load a model from the given path.
The model should have been saved by Saveable.save.
Spark context used for loading model files.
Path specifying the directory to which the model was saved.