Skip to content

Fix drtester dataframe #1025

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
michaelellis003 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix drtester dataframe #1025

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3728b5a
Fix DRTester to accept pandas DataFrames
michaelellis003 Mar 26, 2026
fdcc2f5
Use check_input_arrays for input conversion
michaelellis003 Mar 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 31 additions & 0 deletions econml/tests/test_drtester.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -286,3 +286,34 @@ def test_exceptions(self):

autoc_res = my_dr_tester.evaluate_uplift(Xval, Xtrain, metric='toc')
self.assertLess(autoc_res.pvals[0], 0.05)

def test_dataframe_input(self):
Xtrain, Dtrain, Ytrain, Xval, Dval, Yval = self._get_data(num_treatments=1)

reg_t = RandomForestClassifier(random_state=0)
reg_y = GradientBoostingRegressor(random_state=0)

cate = DML(
model_y=reg_y,
model_t=reg_t,
model_final=reg_y,
discrete_treatment=True
).fit(Y=Ytrain, T=Dtrain, X=Xtrain)

# Fit with numpy arrays as baseline
dr_numpy = DRTester(
model_regression=reg_y,
model_propensity=reg_t,
cate=cate
).fit_nuisance(Xval, Dval, Yval, Xtrain, Dtrain, Ytrain)

# Fit with DataFrames/Series
dr_pandas = DRTester(
model_regression=reg_y,
model_propensity=reg_t,
cate=cate
).fit_nuisance(
pd.DataFrame(Xval), pd.Series(Dval), pd.Series(Yval),
pd.DataFrame(Xtrain), pd.Series(Dtrain), pd.Series(Ytrain)
)
np.testing.assert_array_equal(dr_pandas.dr_val_, dr_numpy.dr_val_)
5 changes: 4 additions & 1 deletion econml/validate/drtester.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
from statsmodels.api import OLS
from statsmodels.tools import add_constant

from econml.utilities import deprecated
from econml.utilities import check_input_arrays, deprecated

from .results import CalibrationEvaluationResults, BLPEvaluationResults, UpliftEvaluationResults, EvaluationResults
from .utils import calculate_dr_outcomes, calc_uplift
Expand Down Expand Up @@ -221,6 +221,9 @@ def fit_nuisance(
If training data is provided, also adds attributes for the doubly robust outcomes for the training
set (dr_train) and the training treatments (Dtrain)
"""
Xval, Dval, yval = check_input_arrays(Xval, Dval, yval)
Xtrain, Dtrain, ytrain = check_input_arrays(Xtrain, Dtrain, ytrain)

self.Dval = Dval

# Unique treatments (ordered, includes control)
Expand Down
Loading