[go: up one dir, main page]
Skip to content
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

Jump to bottom

FIX Target encoder const y #28233

Merged
merged 10 commits into from
Feb 2, 2024
Merged

FIX Target encoder const y #28233

Show file tree
Hide file tree
Changes from 9 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
7d9fafb
Quick fix.
s-banach Jan 23, 2024
14f4255
fix test
Jan 23, 2024
31bfdc8
Change pandas config in context manager
s-banach Jan 26, 2024
8b91110
Merge branch 'main' into TargetEncoder-const-Y
s-banach Jan 31, 2024
056b767
Black format test (Whoops!)
s-banach Feb 1, 2024
ef73bd9
Rename test, add pandas minversion to importorskip
s-banach Feb 2, 2024
3dbc6af
Update v1.4.rst
s-banach Feb 2, 2024
82fa733
fix: use suggested test name
s-banach Feb 2, 2024
79ccd8f
Waste more compute money for a spelling error
s-banach Feb 2, 2024
abca02b
Update doc/whats_new/v1.4.rst
s-banach Feb 2, 2024
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
8 changes: 8 additions & 0 deletions doc/whats_new/v1.4.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,14 @@ Changelog
and `axis=1`, as documented in the docstring.
:pr:`28222` by :user:`Guillaume Lemaitre <glemaitre>`.


:mod:`sklearn.preprocessing`
............................

- |Fix| :class:`preprocessing.TargetEncoder` no longer fails when `target_type="continuous"` and the input is read-only.
In particular, it now works with pandas copy-on-write mode enabled.
:pr:`28233` by :user:`John Hopfensperger <s-banach>`.
s-banach marked this conversation as resolved.
Show resolved Hide resolved

.. _changes_1_4:

Version 1.4.0
Expand Down
4 changes: 2 additions & 2 deletions sklearn/preprocessing/_target_encoder_fast.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ ctypedef fused Y_DTYPE:

def _fit_encoding_fast(
INT_DTYPE[:, ::1] X_int,
Y_DTYPE[:] y,
const Y_DTYPE[:] y,
cnp.int64_t[::1] n_categories,
double smooth,
double y_mean,
Expand Down Expand Up @@ -79,7 +79,7 @@ def _fit_encoding_fast(

def _fit_encoding_fast_auto_smooth(
INT_DTYPE[:, ::1] X_int,
Y_DTYPE[:] y,
const Y_DTYPE[:] y,
cnp.int64_t[::1] n_categories,
double y_mean,
double y_variance,
Expand Down
13 changes: 13 additions & 0 deletions sklearn/preprocessing/tests/test_target_encoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -701,3 +701,16 @@ def test_target_encoding_for_linear_regression(smooth, global_random_seed):
# cardinality yet non-informative feature instead of the lower
# cardinality yet informative feature:
assert abs(coef[0]) < abs(coef[2])


def test_pandas_copy_on_write():
"""
Test target-encoder cython code when y is read-only.

The numpy array underlying df["y"] is read-only when copy-on-write is enabled.
Non-regression test for gh-27879.
"""
pd = pytest.importorskip("pandas", minversion="2.0")
with pd.option_context("mode.copy_on_write", True):
df = pd.DataFrame({"x": ["a", "b", "b"], "y": [4.0, 5.0, 6.0]})
TargetEncoder(target_type="continuous").fit(df[["x"]], df["y"])
Loading