catboost / catboost/catboost

How to speed up pred_prob

Open
#1,758 0 comments 0 reactions 0 assignees View on GitHub
performance
Dominant language
C++
Stars
9.1k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

I need to predict scores (labels) on 800M unlabeled samples.
the running time on colab default setting is as following

```
# 300,000 : 649.1985890865326
# 200,000 : 428.93789553642273
# 100,000 : 221.7507927417755
# 10,000 : 19.62497639656067
# 1,000 : 1.960167646408081
```

with this calculation 800M would take 20 days

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.