Results differ between versions '0.8.1' and '0.9.0b1'
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.8k
- Forks
- 827
- PR merge metrics
- No merged PRs in 30d
Description
I have upgraded econml from '0.8.1' to '0.9.0b1' (pip install -e git+https://github.com/microsoft/EconML.git@master#egg=econml) and I changed nothing to my code.
The results I obtain are however very different when fitting the following estimator:
est_forest_gb = ForestDML(
model_y = GradientBoostingRegressor(n_estimators = 200, random_state = 42),
model_t = GradientBoostingRegressor(n_estimators = 200, random_state = 42),
n_estimators = 200,
n_crossfit_splits = [(fold0, fold1), (fold1, fold0)],
random_state = 123)
Do you have an idea of what could explain the difference?
Thanks.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the ForestDML estimator with the supplied GradientBoostingRegressor settings and compare behavior between econml 0.8.1 and 0.9.0b1. Read the 26-comment thread and review changes between those versions; done means the cause of the differing results is reproduced and clearly identified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, scikit-learn
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100