TDC
TDC copied to clipboard
mims-harvard
ValueError with Oracles
Describe the bug Running the example code for the GSK3B oracle produces a ValueError.
To Reproduce
Using this code from: https://tdcommons.ai/functions/oracles/#glycogen-synthase-kinase-3-beta-gsk3β
from tdc import Oracle
oracle = Oracle(name = 'GSK3B')
oracle(['CC(C)(C)[C@H]1CCc2c(sc(NC(=O)COc3ccc(Cl)cc3)c2C(N)=O)C1', \ 'CCNC(=O)c1ccc(NC(=O)N2CC[C@H](C)[C@H](O)C2)c(C)c1', \ 'C[C@@H]1CCN(C(=O)CCCc2ccccc2)C[C@@H]1O'])
Expected behavior
The above code should produce [0.03, 0.0, 0.0], but instead I'm getting:
ValueError: node array from the pickle has an incompatible dtype:, etc.
Environment:
- OS: mac
- Python version: 3.11.3
- TDC version: 0.4.0
- Any other relevant information: sklearn version 1.3.0
Additional context I think there is some incompatibility with a recent version of sklearn.tree.
Hi, thanks for your interest, I used python 3.7 and sklearn 0.23.2, it works on both mac and linux. What is your version sklearn?
I'm using sklearn 1.3.0. I tried downgrading to sklearn 0.23.2 as you suggest, but had errors during pip install, maybe due to an incompatibility with my python version.
