Parallel matrix calculation

8080labs / ppscore

Predictive Power Score (PPS) in Python

MIT License

1.12k stars 168 forks source link

Parallel matrix calculation #47

Open timothyxp opened 4 years ago

timothyxp commented 4 years ago

Add paralleling compurations for pps.matrix. In my sample test data with 20 columns on 8CPU machine boost from 21 second to 5.7. But for data with a lot of columns(>60) still too slow. I have idea to add parameter for selection only interesting columns from data(maybe interesting for specific column) and optimize calculations for data with a large number of columns. Also it will be usefull for better matrix understanding.

FlorianWetschoreck commented 4 years ago

Thank you for opening the PR - I will have to take some time to look over this but currently I am quite busy, so I am not sure yet when I will find the time

FlorianWetschoreck commented 3 years ago

Thank you for the PR - I would love to have a quick chat with you about it. You can reach me via florian@8080labs.com