File: plot_release_highlights_0_22_0.py

package info (click to toggle)
scikit-learn 0.23.2-5
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, bullseye, sid
  • size: 21,892 kB
  • sloc: python: 132,020; cpp: 5,765; javascript: 2,201; ansic: 831; makefile: 213; sh: 44
file content (264 lines) | stat: -rw-r--r-- 10,618 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
"""
========================================
Release Highlights for scikit-learn 0.22
========================================

.. currentmodule:: sklearn

We are pleased to announce the release of scikit-learn 0.22, which comes
with many bug fixes and new features! We detail below a few of the major
features of this release. For an exhaustive list of all the changes, please
refer to the :ref:`release notes <changes_0_22>`.

To install the latest version (with pip)::

    pip install --upgrade scikit-learn

or with conda::

    conda install scikit-learn
"""

##############################################################################
# New plotting API
# ----------------
#
# A new plotting API is available for creating visualizations. This new API
# allows for quickly adjusting the visuals of a plot without involving any
# recomputation. It is also possible to add different plots to the same
# figure. The following example illustrates :class:`~metrics.plot_roc_curve`,
# but other plots utilities are supported like
# :class:`~inspection.plot_partial_dependence`,
# :class:`~metrics.plot_precision_recall_curve`, and
# :class:`~metrics.plot_confusion_matrix`. Read more about this new API in the
# :ref:`User Guide <visualizations>`.

from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import plot_roc_curve
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
import matplotlib.pyplot as plt

X, y = make_classification(random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

svc = SVC(random_state=42)
svc.fit(X_train, y_train)
rfc = RandomForestClassifier(random_state=42)
rfc.fit(X_train, y_train)

svc_disp = plot_roc_curve(svc, X_test, y_test)
rfc_disp = plot_roc_curve(rfc, X_test, y_test, ax=svc_disp.ax_)
rfc_disp.figure_.suptitle("ROC curve comparison")

plt.show()

############################################################################
# Stacking Classifier and Regressor
# ---------------------------------
# :class:`~ensemble.StackingClassifier` and
# :class:`~ensemble.StackingRegressor`
# allow you to have a stack of estimators with a final classifier or
# a regressor.
# Stacked generalization consists in stacking the output of individual
# estimators and use a classifier to compute the final prediction. Stacking
# allows to use the strength of each individual estimator by using their output
# as input of a final estimator.
# Base estimators are fitted on the full ``X`` while
# the final estimator is trained using cross-validated predictions of the
# base estimators using ``cross_val_predict``.
#
# Read more in the :ref:`User Guide <stacking>`.

from sklearn.datasets import load_iris
from sklearn.svm import LinearSVC
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.ensemble import StackingClassifier
from sklearn.model_selection import train_test_split

X, y = load_iris(return_X_y=True)
estimators = [
    ('rf', RandomForestClassifier(n_estimators=10, random_state=42)),
    ('svr', make_pipeline(StandardScaler(),
                          LinearSVC(random_state=42)))
]
clf = StackingClassifier(
    estimators=estimators, final_estimator=LogisticRegression()
)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, stratify=y, random_state=42
)
clf.fit(X_train, y_train).score(X_test, y_test)

##############################################################################
# Permutation-based feature importance
# ------------------------------------
#
# The :func:`inspection.permutation_importance` can be used to get an
# estimate of the importance of each feature, for any fitted estimator:

from sklearn.ensemble import RandomForestClassifier
from sklearn.inspection import permutation_importance

X, y = make_classification(random_state=0, n_features=5, n_informative=3)
rf = RandomForestClassifier(random_state=0).fit(X, y)
result = permutation_importance(rf, X, y, n_repeats=10, random_state=0,
                                n_jobs=-1)

fig, ax = plt.subplots()
sorted_idx = result.importances_mean.argsort()
ax.boxplot(result.importances[sorted_idx].T,
           vert=False, labels=range(X.shape[1]))
ax.set_title("Permutation Importance of each feature")
ax.set_ylabel("Features")
fig.tight_layout()
plt.show()

##############################################################################
# Native support for missing values for gradient boosting
# -------------------------------------------------------
#
# The :class:`ensemble.HistGradientBoostingClassifier`
# and :class:`ensemble.HistGradientBoostingRegressor` now have native
# support for missing values (NaNs). This means that there is no need for
# imputing data when training or predicting.

from sklearn.experimental import enable_hist_gradient_boosting  # noqa
from sklearn.ensemble import HistGradientBoostingClassifier
import numpy as np

X = np.array([0, 1, 2, np.nan]).reshape(-1, 1)
y = [0, 0, 1, 1]

gbdt = HistGradientBoostingClassifier(min_samples_leaf=1).fit(X, y)
print(gbdt.predict(X))

############################################################################
# Precomputed sparse nearest neighbors graph
# ------------------------------------------
# Most estimators based on nearest neighbors graphs now accept precomputed
# sparse graphs as input, to reuse the same graph for multiple estimator fits.
# To use this feature in a pipeline, one can use the `memory` parameter, along
# with one of the two new transformers,
# :class:`neighbors.KNeighborsTransformer` and
# :class:`neighbors.RadiusNeighborsTransformer`. The precomputation
# can also be performed by custom estimators to use alternative
# implementations, such as approximate nearest neighbors methods.
# See more details in the :ref:`User Guide <neighbors_transformer>`.

from tempfile import TemporaryDirectory
from sklearn.neighbors import KNeighborsTransformer
from sklearn.manifold import Isomap
from sklearn.pipeline import make_pipeline

X, y = make_classification(random_state=0)

with TemporaryDirectory(prefix="sklearn_cache_") as tmpdir:
    estimator = make_pipeline(
        KNeighborsTransformer(n_neighbors=10, mode='distance'),
        Isomap(n_neighbors=10, metric='precomputed'),
        memory=tmpdir)
    estimator.fit(X)

    # We can decrease the number of neighbors and the graph will not be
    # recomputed.
    estimator.set_params(isomap__n_neighbors=5)
    estimator.fit(X)

##############################################################################
# KNN Based Imputation
# ------------------------------------
# We now support imputation for completing missing values using k-Nearest
# Neighbors.
#
# Each sample's missing values are imputed using the mean value from
# ``n_neighbors`` nearest neighbors found in the training set. Two samples are
# close if the features that neither is missing are close.
# By default, a euclidean distance metric
# that supports missing values,
# :func:`~metrics.nan_euclidean_distances`, is used to find the nearest
# neighbors.
#
# Read more in the :ref:`User Guide <knnimpute>`.

import numpy as np
from sklearn.impute import KNNImputer

X = [[1, 2, np.nan], [3, 4, 3], [np.nan, 6, 5], [8, 8, 7]]
imputer = KNNImputer(n_neighbors=2)
print(imputer.fit_transform(X))

#############################################################################
# Tree pruning
# ------------
#
# It is now possible to prune most tree-based estimators once the trees are
# built. The pruning is based on minimal cost-complexity. Read more in the
# :ref:`User Guide <minimal_cost_complexity_pruning>` for details.

X, y = make_classification(random_state=0)

rf = RandomForestClassifier(random_state=0, ccp_alpha=0).fit(X, y)
print("Average number of nodes without pruning {:.1f}".format(
    np.mean([e.tree_.node_count for e in rf.estimators_])))

rf = RandomForestClassifier(random_state=0, ccp_alpha=0.05).fit(X, y)
print("Average number of nodes with pruning {:.1f}".format(
    np.mean([e.tree_.node_count for e in rf.estimators_])))

############################################################################
# Retrieve dataframes from OpenML
# -------------------------------
# :func:`datasets.fetch_openml` can now return pandas dataframe and thus
# properly handle datasets with heterogeneous data:

from sklearn.datasets import fetch_openml

titanic = fetch_openml('titanic', version=1, as_frame=True)
print(titanic.data.head()[['pclass', 'embarked']])

############################################################################
# Checking scikit-learn compatibility of an estimator
# ---------------------------------------------------
# Developers can check the compatibility of their scikit-learn compatible
# estimators using :func:`~utils.estimator_checks.check_estimator`. For
# instance, the ``check_estimator(LinearSVC)`` passes.
#
# We now provide a ``pytest`` specific decorator which allows ``pytest``
# to run all checks independently and report the checks that are failing.

from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.utils.estimator_checks import parametrize_with_checks


@parametrize_with_checks([LogisticRegression, DecisionTreeRegressor])
def test_sklearn_compatible_estimator(estimator, check):
    check(estimator)

############################################################################
# ROC AUC now supports multiclass classification
# ----------------------------------------------
# The :func:`roc_auc_score` function can also be used in multi-class
# classification. Two averaging strategies are currently supported: the
# one-vs-one algorithm computes the average of the pairwise ROC AUC scores, and
# the one-vs-rest algorithm computes the average of the ROC AUC scores for each
# class against all other classes. In both cases, the multiclass ROC AUC scores
# are computed from the probability estimates that a sample belongs to a
# particular class according to the model. The OvO and OvR algorithms support
# weighting uniformly (``average='macro'``) and weighting by the prevalence
# (``average='weighted'``).
#
# Read more in the :ref:`User Guide <roc_metrics>`.


from sklearn.datasets import make_classification
from sklearn.svm import SVC
from sklearn.metrics import roc_auc_score

X, y = make_classification(n_classes=4, n_informative=16)
clf = SVC(decision_function_shape='ovo', probability=True).fit(X, y)
print(roc_auc_score(y, clf.predict_proba(X), multi_class='ovo'))