Skip to content

Pass optional column names to parallel tree function in using the self.feature_names_in attribute. #26208

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
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Pass optional column names to parallel tree function in using the self.feature_names_in attribute. #26208

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
77fc5d6
pass column names to parallel fucntion in creating trees, adding the …
Apr 18, 2023
da6555a
remove pandas import from code and use hasattr instead
Apr 18, 2023
c7ca397
improve code with suggestion from PR thread
Apr 18, 2023
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
13 changes: 12 additions & 1 deletion sklearn/ensemble/_forest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,12 +156,16 @@ def _parallel_build_trees(
verbose=0,
class_weight=None,
n_samples_bootstrap=None,
feature_names_in_=None,
):
"""
Private function used to fit a single tree in parallel."""
if verbose > 1:
print("building tree %d of %d" % (tree_idx + 1, n_trees))

if feature_names_in_ is not None:
tree.feature_names_in_ = feature_names_in_

if bootstrap:
n_samples = X.shape[0]
if sample_weight is None:
Expand Down Expand Up @@ -343,9 +347,15 @@ def fit(self, X, y, sample_weight=None):
# Validate or convert input data
if issparse(y):
raise ValueError("sparse multilabel-indicator for y is not supported.")

X, y = self._validate_data(
X, y, multi_output=True, accept_sparse="csc", dtype=DTYPE
X,
y,
multi_output=True,
accept_sparse="csc",
dtype=DTYPE,
)

if sample_weight is not None:
sample_weight = _check_sample_weight(sample_weight, X)

Expand Down Expand Up @@ -467,6 +477,7 @@ def fit(self, X, y, sample_weight=None):
verbose=self.verbose,
class_weight=self.class_weight,
n_samples_bootstrap=n_samples_bootstrap,
feature_names_in_=getattr(self, "feature_names_in_", None),
)
for i, t in enumerate(trees)
)
Expand Down
1 change: 0 additions & 1 deletion sklearn/tree/_classes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -885,7 +885,6 @@ def fit(self, X, y, sample_weight=None, check_input=True):
self : DecisionTreeClassifier
Fitted estimator.
"""

super().fit(
X,
y,
Expand Down