The Anaconda env is in the environment.yml.
To train the model run
$ python train.py
The necessary data is specified in the Config classes on the top of the file.
The output is in data/models.
It needs the files to be in 'data/main/TrainData//'. The file in the folder are just a splitted version of the original test_data_students.txt - so that multiple threads can operate.
$ python test.py
$ ./launch_pyro.sh <int>
easy way to prepare the cluster for distributed model training