8000 EXA Use tick_labels in boxplot for matplotlib>=3.9 by nithish08 · Pull Request #29471 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

EXA Use tick_labels in boxplot for matplotlib>=3.9 #29471

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

Merged
merged 4 commits into from
Jul 15, 2024
Merged

EXA Use tick_labels in boxplot for matplotlib>=3.9 #29471

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4e88fcb
Refactor matplotlib tick label handling for compatibility
nithish08 Jul 11, 2024
163addd
Merge remote-tracking branch 'upstream/main' into nb/unpin-matplotlib
nithish08 Jul 12, 2024
8b69d88
handle tick_labels and labels in matplotlib boxplot
nithish08 Jul 15, 2024
73b3ada
Tweak comment
lesteve Jul 15, 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
19 changes: 15 additions & 4 deletions examples/ensemble/plot_gradient_boosting_regression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,15 @@
# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause

import matplotlib
import matplotlib.pyplot as plt
import numpy as np

from sklearn import datasets, ensemble
from sklearn.inspection import permutation_importance
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split
from sklearn.utils.fixes import parse_version

# %%
# Load the data
Expand Down Expand Up @@ -145,11 +147,20 @@
)
sorted_idx = result.importances_mean.argsort()
plt.subplot(1, 2, 2)
plt.boxplot(
result.importances[sorted_idx].T,
vert=False,
labels=np.array(diabetes.feature_names)[sorted_idx],

# `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been
# renamed to `tick_labels`. The following code handles this, but as a
# scikit-learn user you probably can write simpler code by using `labels=...`
# (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).
tick_labels_parameter_name = (
"tick_labels"
if parse_version(matplotlib.__version__) >= parse_version("3.9")
else "labels"
)
tick_labels_dict = {
tick_labels_parameter_name: np.array(diabetes.feature_names)[sorted_idx]
}
plt.boxplot(result.importances[sorted_idx].T, vert=False, **tick_labels_dict)
plt.title("Permutation Importance (test set)")
fig.tight_layout()
plt.show()
17 changes: 13 additions & 4 deletions examples/inspection/plot_permutation_importance_multicollinear.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,18 +26,27 @@
# ------------------------------------------------------
#
# First, we define a function to ease the plotting:
import matplotlib

from sklearn.inspection import permutation_importance
from sklearn.utils.fixes import parse_version


def plot_permutation_importance(clf, X, y, ax):
result = permutation_importance(clf, X, y, n_repeats=10, random_state=42, n_jobs=2)
perm_sorted_idx = result.importances_mean.argsort()

ax.boxplot(
result.importances[perm_sorted_idx].T,
vert=False,
labels=X.columns[perm_sorted_idx],
# `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been
# renamed to `tick_labels`. The following code handles this, but as a
# scikit-learn user you probably can write simpler code by using `labels=...`
# (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).
tick_labels_parameter_name = (
"tick_labels"
if parse_version(matplotlib.__version__) >= parse_version("3.9")
else "labels"
)
tick_labels_dict = {tick_labels_parameter_name: X.columns[perm_sorted_idx]}
ax.boxplot(result.importances[perm_sorted_idx].T, vert=False, **tick_labels_dict)
ax.axvline(x=0, color="k", linestyle="--")
return ax

Expand Down
15 changes: 13 additions & 2 deletions examples/release_highlights/plot_release_highlights_0_22_0.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@
# `plot_confusion_matrix`. Read more about this new API in the
# :ref:`User Guide <visualizations>`.

import matplotlib
import matplotlib.pyplot as plt

from sklearn.datasets import make_classification
Expand All @@ -43,6 +44,7 @@
from sklearn.metrics import RocCurveDisplay
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.utils.fixes import parse_version

X, y = make_classification(random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
Expand Down Expand Up @@ -117,9 +119,18 @@

fig, ax = plt.subplots()
sorted_idx = result.importances_mean.argsort()
ax.boxplot(
result.importances[sorted_idx].T, vert=False, labels=feature_names[sorted_idx]

# `labels` argument in boxplot is deprecated in matplotlib 3.9 and has been
# renamed to `tick_labels`. The following code handles this, but as a
# scikit-learn user you probably can write simpler code by using `labels=...`
# (matplotlib < 3.9) or `tick_labels=...` (matplotlib >= 3.9).
tick_labels_parameter_name = (
"tick_labels"
if parse_version(matplotlib.__version__) >= parse_version("3.9")
else "labels"
)
tick_labels_dict = {tick_labels_parameter_name: feature_names[sorted_idx]}
ax.boxplot(result.importances[sorted_idx].T, vert=False, **tick_labels_dict)
ax.set_title("Permutation Importance of each feature")
ax.set_ylabel("Features")
fig.tight_layout()
Expand Down
0