Skip to content

Commit

Permalink
DOC Release highlights order (scikit-learn#15552)
Browse files Browse the repository at this point in the history
  • Loading branch information
@NicolasHug @jnothman
NicolasHug authored and jnothman committed Nov 7, 2019
1 parent 2e881f5 commit faaeba4
Show file tree
Hide file tree
Showing 2 changed files with 121 additions and 109 deletions.
10 changes: 10 additions & 0 deletions doc/whats_new/v0.22.rst
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,12 @@ refer to

.. include:: changelog_legend.inc

Website update
--------------

`Our website <https://scikit-learn.org/>`_ was revamped and given a fresh
new look. :pr:`14849` by `Thomas Fan`_.

Clear definition of the public API
----------------------------------

Expand Down Expand Up @@ -51,6 +57,10 @@ been moved to ``_birch.py``).
reference, that means it should either be private or documented. Please
let us know by opening an issue!

This work was tracked in `issue 9250
<https://github.com/scikit-learn/scikit-learn/issues/9250>`_ and `issue
12927 <https://github.com/scikit-learn/scikit-learn/issues/12927>`_.


Deprecations: using ``FutureWarning`` from now on
-------------------------------------------------
Expand Down
220 changes: 111 additions & 109 deletions examples/release_highlights/plot_release_highlights_0_22_0.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -20,27 +20,73 @@
"""

##############################################################################
# KNN Based Imputation
# ------------------------------------
# We now support imputation for completing missing values using k-Nearest
# Neighbors.
# New plotting API
# ----------------
#
# 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.
# 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. See more examples 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 <knnimpute>`.
# Read more in the :ref:`User Guide <stacking>`.

import numpy as np
from sklearn.impute import KNNImputer
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 = [[1, 2, np.nan], [3, 4, 3], [np.nan, 6, 5], [8, 8, 7]]
imputer = KNNImputer(n_neighbors=2)
print(imputer.fit_transform(X))
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
Expand All @@ -50,9 +96,7 @@
# estimate of the importance of each feature, for any fitted estimator:

from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
from sklearn.inspection import permutation_importance
import matplotlib.pyplot as plt

X, y = make_classification(random_state=0, n_features=5, n_informative=3)
rf = RandomForestClassifier(random_state=0).fit(X, y)
Expand Down Expand Up @@ -87,32 +131,60 @@
gbdt = HistGradientBoostingClassifier(min_samples_leaf=1).fit(X, y)
print(gbdt.predict(X))

##############################################################################
# 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. See more examples in the :ref:`User Guide <visualizations>`.
############################################################################
# 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 sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import plot_roc_curve
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)
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)
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)

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

plt.show()
##############################################################################
# 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
Expand Down Expand Up @@ -143,76 +215,6 @@
titanic = fetch_openml('titanic', version=1, as_frame=True)
print(titanic.data.head()[['pclass', 'embarked']])

############################################################################
# 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

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)

############################################################################
# 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.ensemble import RandomForestClassifier
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)

############################################################################
# Checking scikit-learn compatibility of an estimator
# ---------------------------------------------------
Expand Down

0 comments on commit faaeba4

Please sign in to comment.