How can I read a csv file using panda dataframe from GPU?

Question

I am reading a file using file=pd.read_csv('file_1.csv')

which is taking a long time on CPU.

Is there any method to read this using GPU.

https://blog.dask.org/2019/01/13/dask-cudf-first-steps This might be helpful — Ege Aydın, May 08 '19 at 20:17

score 3 · Accepted Answer · answered Jun 07 '18 at 10:53

3

No. The biggest bottleneck is IO and that’s handled by the CPU.

answered Jun 07 '18 at 10:53

Mateusz Dymczyk

What is the maximum data size that a panda dataframe can read ? – Anshul Gupta Jun 07 '18 at 17:23
@AnshulGupta That should be a new question, but don't do that, as it is easy to google for. (The answer appears to be: as much as you have RAM for, assuming it is 64-bit python.) – Darren Cook Jun 07 '18 at 17:38

1 Answers1