py-why / py-why/EconML

effect interval for multi-treatment

Open
#359 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
4.8k
Forks
827
PR merge metrics
No merged PRs in 30d

Description

Seems like I can't get effect interval for multi-treatment. I think I used to be able to with older version of econml.
Is the way to get the interval for multi-treatment changed by updates?
This is the code I used. and the result is returned at the end, I can't interpret what that means.

dml = BootstrapEstimator(DMLCateEstimator(model_y=RandomForestRegressor(),
model_t=RandomForestRegressor(),
model_final=LinearRegression(fit_intercept=False),
random_state=123), n_bootstrap_samples=4, n_jobs=-1)
dml.fit(Y, np.concatenate((T1.reshape(-1,1), (T2.reshape(-1,1)) ), axis=1),
X=np.stack([np.hstack([np.ones(n), np.zeros(n)]), np.hstack([np.zeros(n), np.ones(n)])]).T, W= W[:, selected] )
dml.effect_interval(X=np.array([[1 ],[ 1]]))

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the supplied BootstrapEstimator, DMLCateEstimator, and effect_interval call with the multi-treatment inputs. Check the current effect_interval API and its handling of the provided X shape, then determine whether the returned result is expected or indicates a regression; document the interpretation or the supported usage.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.