Skip to content

Commit 8954e7b

Browse files
jeremiedbbogrisel
andcommitted
DOC Release highlights for 1.9 (#34147)
Co-authored-by: Olivier Grisel <[email protected]>
1 parent 73a3eab commit 8954e7b

1 file changed

Lines changed: 183 additions & 0 deletions

File tree

Lines changed: 183 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,183 @@
1+
# ruff: noqa: CPY001, E501
2+
"""
3+
=======================================
4+
Release Highlights for scikit-learn 1.9
5+
=======================================
6+
7+
.. currentmodule:: sklearn
8+
9+
We are pleased to announce the release of scikit-learn 1.9! Many bug fixes
10+
and improvements were added, as well as some key new features. Below we
11+
detail the highlights of this release. **For an exhaustive list of
12+
all the changes**, please refer to the :ref:`release notes <release_notes_1_9>`.
13+
14+
To install the latest version (with pip)::
15+
16+
pip install --upgrade scikit-learn
17+
18+
or with conda::
19+
20+
conda install -c conda-forge scikit-learn
21+
22+
"""
23+
24+
# %%
25+
# Callbacks
26+
# ---------
27+
# This release introduces **experimental** support for callbacks in scikit-learn. They
28+
# are objects that can be registered on estimators, through the `set_callbacks` method,
29+
# to be invoked at the beginning and end of key steps during fit. See the
30+
# :ref:`user guide <callbacks_user>` for more details. **Only a few estimators support
31+
# callbacks for now**, see the
32+
# :ref:`list of supported estimators <callback_compatible_estimators>`.
33+
#
34+
# Two built-in callbacks are provided in this release:
35+
#
36+
# - :class:`~sklearn.callback.ProgressBar`, to display progress bars.
37+
# - :class:`~sklearn.callback.ScoringMonitor`, to compute and log scoring metrics.
38+
39+
from sklearn.callback import ProgressBar, ScoringMonitor
40+
from sklearn.datasets import make_classification
41+
from sklearn.linear_model import LogisticRegression
42+
43+
X, y = make_classification(
44+
n_samples=1000, n_features=50, n_classes=10, n_informative=20, random_state=0
45+
)
46+
47+
scoring_monitor = ScoringMonitor(scoring="d2_log_loss_score")
48+
logreg = LogisticRegression(solver="lbfgs")
49+
logreg.set_callbacks(scoring_monitor, ProgressBar())
50+
logreg.fit(X, y)
51+
52+
log = scoring_monitor.get_logs().data_as_pandas
53+
log[["task_name", "task_id", "d2_log_loss_score"]]
54+
55+
# %%
56+
# Progress bars can also be displayed for compositions of estimators.
57+
#
58+
# .. code-block:: python
59+
#
60+
# from sklearn.callback import ProgressBar
61+
# from sklearn.datasets import load_iris
62+
# from sklearn.linear_model import LogisticRegression
63+
# from sklearn.model_selection import GridSearchCV
64+
#
65+
# X, y = load_iris(return_X_y=True)
66+
# logreg = LogisticRegression(solver="lbfgs")
67+
# grid_search = GridSearchCV(logreg, {"C": [10, 1, 0.1]}, n_jobs=2)
68+
# grid_search.set_callbacks(ProgressBar())
69+
# grid_search.fit(X, y)
70+
#
71+
# Intermediate output. Note that two sub-tasks progress concurrently because we
72+
# set `n_jobs=2`::
73+
#
74+
# GridSearchCV - fit ━━━━━━╸ 17% 0:00:02
75+
# GridSearchCV - search #0 ━━━━━━━━━━━━━╸ 34% 0:00:01
76+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #1 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
77+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #0 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
78+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #2 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
79+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #3 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
80+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #4 ━━━━━━━━━━━━━━━━━━━━━╸ 54% 0:00:01
81+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #5 ━━━━━━━━━━━━━━━━━ 44% 0:00:01
82+
#
83+
# Final output displaying all the completed nested subtasks::
84+
#
85+
# GridSearchCV - fit ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
86+
# GridSearchCV - search #0 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
87+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #1 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
88+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #0 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
89+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #2 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
90+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #3 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
91+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #4 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
92+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #5 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
93+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #6 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
94+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #7 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
95+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #8 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
96+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #9 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
97+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #10 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
98+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #11 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
99+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #12 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
100+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #13 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
101+
# GridSearchCV - candidate-split-evaluation | LogisticRegression - fit #14 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
102+
# GridSearchCV - refit-with-best-params | LogisticRegression - fit #1 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
103+
104+
# %%
105+
# There is also a public API to implement callback support in third-party estimators and
106+
# to implement custom callbacks. See the :ref:`developer's guide <callbacks>` for more
107+
# details.
108+
#
109+
# New callbacks and callback support in more estimators will be added in future
110+
# releases. The callback API is experimental and may evolve without deprecation.
111+
112+
# %%
113+
# Improvements to the HTML representation of estimators
114+
# -----------------------------------------------------
115+
# The HTML representation of estimators now includes information made available after
116+
# fit. There is a new "Fitted attributes" table that lists the fitted attributes and
117+
# their type and values. In addition, the HTML representation of transformers includes
118+
# new visual blocks showing the number and names of the output features.
119+
#
120+
# Expand the diagram below by clicking on the different visual blocks to see the new
121+
# features.
122+
123+
import pandas as pd
124+
125+
from sklearn.compose import make_column_transformer
126+
from sklearn.linear_model import LogisticRegression
127+
from sklearn.pipeline import make_pipeline
128+
from sklearn.preprocessing import OneHotEncoder, StandardScaler
129+
130+
X = pd.DataFrame({"num": [0.1, 0.2, 0.3, 0.4], "cat": ["A", "C", "B", "C"]})
131+
y = [1, 3, 1, 2]
132+
133+
pipe = make_pipeline(
134+
make_column_transformer((StandardScaler(), ["num"]), (OneHotEncoder(), ["cat"])),
135+
LogisticRegression(),
136+
)
137+
pipe.fit(X, y)
138+
139+
# %%
140+
# Computing metrics across thresholds
141+
# -----------------------------------
142+
# A new function :func:`~sklearn.metrics.metric_at_thresholds` has been added to compute
143+
# an arbitrary binary classification metric across all possible decision thresholds.
144+
145+
import matplotlib.pyplot as plt
146+
147+
from sklearn.datasets import make_classification
148+
from sklearn.linear_model import LogisticRegression
149+
from sklearn.metrics import accuracy_score, f1_score, metric_at_thresholds
150+
151+
X, y = make_classification(weights=[0.9, 0.1], random_state=0)
152+
lr = LogisticRegression(random_state=0).fit(X, y)
153+
y_score = lr.predict_proba(X)[:, 1]
154+
155+
accuracy, thresholds = metric_at_thresholds(y, y_score, accuracy_score)
156+
f1, _ = metric_at_thresholds(y, y_score, f1_score)
157+
158+
_, ax = plt.subplots()
159+
ax.plot(thresholds, accuracy, label="Accuracy")
160+
ax.plot(thresholds, f1, label="F1")
161+
ax.set_xlabel("threshold")
162+
ax.set_ylabel("metric value")
163+
ax.legend()
164+
plt.show()
165+
166+
# %%
167+
# Sparse array configuration
168+
# --------------------------
169+
# A new configuration key `"sparse_interface"` has been added to control the type of
170+
# sparse objects produced by functions and estimators. It is now possible to produce
171+
# sparse arrays instead of sparse matrices (default).
172+
# This continues the effort to prepare for
173+
# `SciPy's migration from sparse matrices to sparse arrays <https://docs.scipy.org/doc/scipy/reference/sparse.migration_to_sparray.html>`_.
174+
175+
import sklearn
176+
from sklearn.preprocessing import OneHotEncoder
177+
178+
X = [["fox", "dog", "cat"]]
179+
ohe = OneHotEncoder()
180+
181+
with sklearn.config_context(sparse_interface="sparray"):
182+
Xt = ohe.fit_transform(X)
183+
Xt

0 commit comments

Comments
 (0)