Skip to content

[MRG] Speed up plot_discretization_classification.py #21661

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 7 commits into from
Nov 16, 2021
Merged

[MRG] Speed up plot_discretization_classification.py #21661

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
cccb390
Speed up plot_discretization_classification.py
yuanx749 Nov 14, 2021
8323bf7
Add comment
yuanx749 Nov 15, 2021
aafb038
Reduce length of comment
yuanx749 Nov 15, 2021
69f5ff4
Improve comment
yuanx749 Nov 15, 2021
4f8fe6c
Merge remote-tracking branch 'upstream/main' into plot_discretization…
yuanx749 Nov 15, 2021
fecca54
Merge main
yuanx749 Nov 15, 2021
c28e5b6
Merge remote-tracking branch 'upstream/main' into plot_discretization…
yuanx749 Nov 15, 2021
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
61 changes: 40 additions & 21 deletions examples/preprocessing/plot_discretization_classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,33 +61,53 @@ def get_name(estimator):


# list of (estimator, param_grid), where param_grid is used in GridSearchCV
# The parameter spaces in this example are limited to a narrow band to reduce
# its runtime. In a real use case, a broader search space for the algorithms
# should be used.
classifiers = [
(LogisticRegression(random_state=0), {"C": np.logspace(-2, 7, 10)}),
(LinearSVC(random_state=0), {"C": np.logspace(-2, 7, 10)}),
(
make_pipeline(StandardScaler(), LogisticRegression(random_state=0)),
{"logisticregression__C": np.logspace(-1, 1, 3)},
),
(
make_pipeline(StandardScaler(), LinearSVC(random_state=0)),
{"linearsvc__C": np.logspace(-1, 1, 3)},
),
(
make_pipeline(
KBinsDiscretizer(encode="onehot"), LogisticRegression(random_state=0)
StandardScaler(),
KBinsDiscretizer(encode="onehot"),
LogisticRegression(random_state=0),
),
{
"kbinsdiscretizer__n_bins": np.arange(2, 10),
"logisticregression__C": np.logspace(-2, 7, 10),
"kbinsdiscretizer__n_bins": np.arange(5, 8),
"logisticregression__C": np.logspace(-1, 1, 3),
},
),
(
make_pipeline(KBinsDiscretizer(encode="onehot"), LinearSVC(random_state=0)),
make_pipeline(
StandardScaler(),
KBinsDiscretizer(encode="onehot"),
LinearSVC(random_state=0),
),
{
"kbinsdiscretizer__n_bins": np.arange(2, 10),
"linearsvc__C": np.logspace(-2, 7, 10),
"kbinsdiscretizer__n_bins": np.arange(5, 8),
"linearsvc__C": np.logspace(-1, 1, 3),
},
),
(
GradientBoostingClassifier(n_estimators=50, random_state=0),
{"learning_rate": np.logspace(-4, 0, 10)},
make_pipeline(
StandardScaler(), GradientBoostingClassifier(n_estimators=5, random_state=0)
),
{"gradientboostingclassifier__learning_rate": np.logspace(-2, 0, 5)},
),
(
make_pipeline(StandardScaler(), SVC(random_state=0)),
{"svc__C": np.logspace(-1, 1, 3)},
),
(SVC(random_state=0), {"C": np.logspace(-2, 7, 10)}),
]

names = [get_name(e) for e, g in classifiers]
names = [get_name(e).replace("StandardScaler + ", "") for e, _ in classifiers]

n_samples = 100
datasets = [
Expand All @@ -107,15 +127,14 @@ def get_name(estimator):
nrows=len(datasets), ncols=len(classifiers) + 1, figsize=(21, 9)
)

cm = plt.cm.PiYG
cm_piyg = plt.cm.PiYG
cm_bright = ListedColormap(["#b30065", "#178000"])

# iterate over datasets
for ds_cnt, (X, y) in enumerate(datasets):
print("\ndataset %d\n---------" % ds_cnt)
print(f"\ndataset {ds_cnt}\n---------")

# preprocess dataset, split into training and test part
X = StandardScaler().fit_transform(X)
# split into training and test part
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.5, random_state=42
)
Expand Down Expand Up @@ -148,18 +167,18 @@ def get_name(estimator):
with ignore_warnings(category=ConvergenceWarning):
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
print("%s: %.2f" % (name, score))
print(f"{name}: {score:.2f}")

# plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]*[y_min, y_max].
if hasattr(clf, "decision_function"):
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
Z = clf.decision_function(np.column_stack([xx.ravel(), yy.ravel()]))
else:
Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
Z = clf.predict_proba(np.column_stack([xx.ravel(), yy.ravel()]))[:, 1]

# put the result into a color plot
Z = Z.reshape(xx.shape)
ax.contourf(xx, yy, Z, cmap=cm, alpha=0.8)
ax.contourf(xx, yy, Z, cmap=cm_piyg, alpha=0.8)

# plot the training points
ax.scatter(
Expand All @@ -184,7 +203,7 @@ def get_name(estimator):
ax.text(
0.95,
0.06,
("%.2f" % score).lstrip("0"),
(f"{score:.2f}").lstrip("0"),
size=15,
bbox=dict(boxstyle="round", alpha=0.8, facecolor="white"),
transform=ax.transAxes,
Expand Down