在 HPC（分布式计算）上运行 Python

Question

How to make my python code run on High Performance Computing (HPC) cluster in a distributed fashion?

(Note: I am looking for an alternative way to simplify the Pyspark job, as python code is running smooth with smaller dataset. I don't want to use Pyspark in this case, since library dependencies are there in my code.)

Please suggest some useful ways of exploiting parallel computing paradigm on the distributed HPC.

Answer 1

This is not a question.

This is a solution.

plotly.offline.plot(fig, filename='filepath.html')