Closed KGAE-CUP closed 2 years ago
@KGAE-CUP check my PR to your fork : https://github.com/KGAE-CUP/srbench/pull/2
need to rebase again to resolve conflicts/ updates to CI
@KGAE-CUP check my PR to your fork : KGAE-CUP#2
need to rebase again to resolve conflicts/ updates to CI
@lacava OK, Thank you for your reply! The above test code is in numpy format and there is no variable name, so it reported an error when I added the code of variable name replacement. If I delete the variable name replacement code, will it affect the later real competition?
@KGAE-CUP I think the mapping should be like this
for k, v in reversed(mapping.items()):
because x_1 replace x_10 to someName0 and x_11 to someName1
The above test code is in numpy format and there is no variable name, so it reported an error when I added the code of variable name replacement. If I delete the variable name replacement code, will it affect the later real competition?
yes, the function returned needs to use the correct variable names. see @janoPig 's comment. to add detail it should be something like
def model(est, X):
mapping = {'x_'+str(i):k for i,k in enumerate(X.columns)}
new_model = est.model_
for k,v in reversed(mapping.items()):
new_model = new_model.replace(k,v)
Competition Checklist:
submission/
with a meaningful name corresponding to your method name.The added folder includes these elements:
[ ]
metadata.yml
(required): A file describing your submission, following the descriptions inexample/metadata.yml
.[ ]
regressor.py
(required): a Python file that defines your method, named appropriately. See submission/feat-example/regressor.py for complete documentation. It contains:est
: a sklearn-compatibleRegressor
object.model(est, X=None)
: a function that returns a sympy-compatible string specifying the final model. It can optionally take the training data as an input argument. See guidance below.eval_kwargs
(optional): a dictionary that can specify method-specific arguments toevaluate_model.py
.[ ]
LICENSE
(optional) A license file[ ]
environment.yml
(optional): a conda environment file that specifies dependencies for your submission.[ ]
install.sh
(optional): a bash script that installs your method.[ ] additional files (optional): you may include a folder containing the code for your method in the submission.
I have verified that:
install.sh
shouldn't pulll a different version of the code when run multiple times.)Refer to the competition guide if you are unsure about any steps. If you don't find an answer, ping us!