Skip to content

FIX: Add scikit-learn >= 1.6.0 compatibility for _validate_data #41

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
J4nvg wants to merge 1 commit into
base: main
Choose a base branch
from
Open

FIX: Add scikit-learn >= 1.6.0 compatibility for _validate_data #41

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
35 changes: 30 additions & 5 deletions imbens/ensemble/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,8 +42,13 @@
check_random_state,
column_or_1d,
has_fit_parameter,
validate_data,
)
try:
from sklearn.utils.validation import validate_data
HAS_VALIDATE_DATA = True
except ImportError:
HAS_VALIDATE_DATA = False


TRAINING_LOG_HEAD_TITLES = {
"iter": "#Estimators",
Expand Down Expand Up @@ -516,6 +521,27 @@ def _validate_y(self, y):
self.n_classes_ = len(self.classes_)
return y


def _validate_data(self, X="no_validation", y="no_validation", reset=True, validate_separately=False, **check_params):
"""Cross-compatible _validate_data for scikit-learn < 1.6.0 and >= 1.6.0"""
if HAS_VALIDATE_DATA:
return validate_data(
self,
X=X,
y=y,
reset=reset,
validate_separately=validate_separately,
**check_params
)
else:
return super()._validate_data(
X=X,
y=y,
reset=reset,
validate_separately=validate_separately,
**check_params
)

def _validate_estimator(self, default):
"""Check the estimator, sampler and the n_estimator attribute.

Expand Down Expand Up @@ -572,7 +598,7 @@ def fit(self, X, y, *, sample_weight=None, **kwargs):
self.random_state = check_random_state(self.random_state)

# Convert data (X is required to be 2d and indexable)
X, y = validate_data(self, X, y, **self.check_x_y_args)
X, y = self._validate_data(X=X, y=y, **self.check_x_y_args)
if sample_weight is not None:
sample_weight = _check_sample_weight(sample_weight, X, dtype=np.float64)
sample_weight /= sample_weight.sum()
Expand Down Expand Up @@ -704,9 +730,8 @@ def decision_function(self, X):
check_is_fitted(self)

# Check data
X = validate_data(
self,
X,
X = self._validate_data(
X=X,
accept_sparse=["csr", "csc"],
dtype=None,
ensure_all_finite=False,
Expand Down