def test_classifier_results():
"""tests if classifier results match target"""
alpha = .1
n_features = 20
n_samples = 10
tol = .01
max_iter = 200
rng = np.random.RandomState(0)
X = rng.normal(size=(n_samples, n_features))
w = rng.normal(size=n_features)
y = np.dot(X, w)
y = np.sign(y)
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=max_iter,
tol=tol,
random_state=77)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
pred1 = clf1.predict(X)
pred2 = clf2.predict(X)
assert_almost_equal(pred1, y, decimal=12)
assert_almost_equal(pred2, y, decimal=12)
def test_binary_classifier_class_weight():
"""tests binary classifier with classweights for each class"""
alpha = .1
n_samples = 50
n_iter = 20
tol = .00001
fit_intercept = True
X, y = make_blobs(n_samples=n_samples,
centers=2,
random_state=10,
cluster_std=0.1)
step_size = get_step_size(X, alpha, fit_intercept, classification=True)
classes = np.unique(y)
y_tmp = np.ones(n_samples)
y_tmp[y != classes[1]] = -1
y = y_tmp
class_weight = {1: .45, -1: .55}
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=n_iter,
tol=tol,
random_state=77,
fit_intercept=fit_intercept,
multi_class='ovr',
class_weight=class_weight)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
le = LabelEncoder()
class_weight_ = compute_class_weight(class_weight, np.unique(y), y)
sample_weight = class_weight_[le.fit_transform(y)]
spweights, spintercept = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
sample_weight=sample_weight,
fit_intercept=fit_intercept)
spweights2, spintercept2 = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
sparse=True,
sample_weight=sample_weight,
fit_intercept=fit_intercept)
assert_array_almost_equal(clf1.coef_.ravel(), spweights.ravel(), decimal=2)
assert_almost_equal(clf1.intercept_, spintercept, decimal=1)
assert_array_almost_equal(clf2.coef_.ravel(),
spweights2.ravel(),
decimal=2)
assert_almost_equal(clf2.intercept_, spintercept2, decimal=1)
def test_sag_classifier_computed_correctly():
"""tests if the binary classifier is computed correctly"""
alpha = .1
n_samples = 50
n_iter = 50
tol = .00001
fit_intercept = True
X, y = make_blobs(n_samples=n_samples,
centers=2,
random_state=0,
cluster_std=0.1)
step_size = get_step_size(X, alpha, fit_intercept, classification=True)
classes = np.unique(y)
y_tmp = np.ones(n_samples)
y_tmp[y != classes[1]] = -1
y = y_tmp
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=n_iter,
tol=tol,
random_state=77,
fit_intercept=fit_intercept,
multi_class='ovr')
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
spweights, spintercept = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
fit_intercept=fit_intercept)
spweights2, spintercept2 = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
sparse=True,
fit_intercept=fit_intercept)
assert_array_almost_equal(clf1.coef_.ravel(), spweights.ravel(), decimal=2)
assert_almost_equal(clf1.intercept_, spintercept, decimal=1)
assert_array_almost_equal(clf2.coef_.ravel(),
spweights2.ravel(),
decimal=2)
assert_almost_equal(clf2.intercept_, spintercept2, decimal=1)
def test_classifier_matching():
n_samples = 20
X, y = make_blobs(n_samples=n_samples,
centers=2,
random_state=0,
cluster_std=0.1)
y[y == 0] = -1
alpha = 1.1
fit_intercept = True
step_size = get_step_size(X, alpha, fit_intercept)
for solver in ['sag', 'saga']:
if solver == 'sag':
n_iter = 80
else:
# SAGA variance w.r.t. stream order is higher
n_iter = 300
clf = LogisticRegression(solver=solver,
fit_intercept=fit_intercept,
tol=1e-11,
C=1. / alpha / n_samples,
max_iter=n_iter,
random_state=10,
multi_class='ovr')
clf.fit(X, y)
weights, intercept = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
fit_intercept=fit_intercept,
saga=solver == 'saga')
weights2, intercept2 = sag(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
fit_intercept=fit_intercept,
saga=solver == 'saga')
weights = np.atleast_2d(weights)
intercept = np.atleast_1d(intercept)
weights2 = np.atleast_2d(weights2)
intercept2 = np.atleast_1d(intercept2)
assert_array_almost_equal(weights, clf.coef_, decimal=9)
assert_array_almost_equal(intercept, clf.intercept_, decimal=9)
assert_array_almost_equal(weights2, clf.coef_, decimal=9)
assert_array_almost_equal(intercept2, clf.intercept_, decimal=9)
def test_predict_on_toy_problem():
"""Manually check predicted class labels for toy dataset."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
X = np.array([[-1.1, -1.5],
[-1.2, -1.4],
[-3.4, -2.2],
[1.1, 1.2],
[2.1, 1.4],
[3.1, 2.3]])
y = np.array([1, 1, 1, 2, 2, 2])
assert all(clf1.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
assert all(clf2.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
assert all(clf3.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='hard',
weights=[1, 1, 1])
assert all(eclf.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
weights=[1, 1, 1])
assert all(eclf.fit(X, y).predict(X)) == all([1, 1, 1, 2, 2, 2])
def test_sag_classifier_raises_error(solver):
# Following #13316, the error handling behavior changed in cython sag. This
# is simply a non-regression test to make sure numerical errors are
# properly raised.
# Train a classifier on a simple problem
rng = np.random.RandomState(42)
X, y = make_classification(random_state=rng)
clf = LogisticRegression(solver=solver, random_state=rng, warm_start=True)
clf.fit(X, y)
# Trigger a numerical error by:
# - corrupting the fitted coefficients of the classifier
# - fit it again starting from its current state thanks to warm_start
clf.coef_[:] = np.nan
with pytest.raises(ValueError, match="Floating-point under-/overflow"):
clf.fit(X, y)
def test_tie_situation():
"""Check voting classifier selects smaller class label in tie situation."""
clf1 = LogisticRegression(random_state=123, solver='liblinear')
clf2 = RandomForestClassifier(random_state=123)
eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2)],
voting='hard')
assert clf1.fit(X, y).predict(X)[73] == 2
assert clf2.fit(X, y).predict(X)[73] == 1
assert eclf.fit(X, y).predict(X)[73] == 1
def test_sample_weight():
"""Tests sample_weight parameter of VotingClassifier"""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = SVC(probability=True, random_state=123)
eclf1 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('svc', clf3)],
voting='soft').fit(X, y, sample_weight=np.ones((len(y),)))
eclf2 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('svc', clf3)],
voting='soft').fit(X, y)
assert_array_equal(eclf1.predict(X), eclf2.predict(X))
assert_array_almost_equal(eclf1.predict_proba(X), eclf2.predict_proba(X))
sample_weight = np.random.RandomState(123).uniform(size=(len(y),))
eclf3 = VotingClassifier(estimators=[('lr', clf1)], voting='soft')
eclf3.fit(X, y, sample_weight)
clf1.fit(X, y, sample_weight)
assert_array_equal(eclf3.predict(X), clf1.predict(X))
assert_array_almost_equal(eclf3.predict_proba(X), clf1.predict_proba(X))
# check that an error is raised and indicative if sample_weight is not
# supported.
clf4 = KNeighborsClassifier()
eclf3 = VotingClassifier(estimators=[
('lr', clf1), ('svc', clf3), ('knn', clf4)],
voting='soft')
msg = ('Underlying estimator KNeighborsClassifier does not support '
'sample weights.')
with pytest.raises(ValueError, match=msg):
eclf3.fit(X, y, sample_weight)
# check that _parallel_fit_estimator will raise the right error
# it should raise the original error if this is not linked to sample_weight
class ClassifierErrorFit(BaseEstimator, ClassifierMixin):
def fit(self, X, y, sample_weight):
raise TypeError('Error unrelated to sample_weight.')
clf = ClassifierErrorFit()
with pytest.raises(TypeError, match='Error unrelated to sample_weight'):
clf.fit(X, y, sample_weight=sample_weight)
def test_2d_coef():
X, y = datasets.make_classification(
n_samples=1000, n_features=10, n_informative=3, n_redundant=0,
n_repeated=0, shuffle=False, random_state=0, n_classes=4)
est = LogisticRegression()
for threshold, func in zip(["mean", "median"], [np.mean, np.median]):
for order in [1, 2, np.inf]:
# Fit SelectFromModel a multi-class problem
transformer = SelectFromModel(estimator=LogisticRegression(),
threshold=threshold,
norm_order=order)
transformer.fit(X, y)
assert hasattr(transformer.estimator_, 'coef_')
X_new = transformer.transform(X)
assert X_new.shape[1] < X.shape[1]
# Manually check that the norm is correctly performed
est.fit(X, y)
importances = np.linalg.norm(est.coef_, axis=0, ord=order)
feature_mask = importances > func(importances)
assert_array_almost_equal(X_new, X[:, feature_mask])
def test_thresholded_scorers():
# Test scorers that take thresholds.
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = LogisticRegression(random_state=0)
clf.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, clf.decision_function(X_test))
score3 = roc_auc_score(y_test, clf.predict_proba(X_test)[:, 1])
assert_almost_equal(score1, score2)
assert_almost_equal(score1, score3)
logscore = get_scorer('neg_log_loss')(clf, X_test, y_test)
logloss = log_loss(y_test, clf.predict_proba(X_test))
assert_almost_equal(-logscore, logloss)
# same for an estimator without decision_function
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, clf.predict_proba(X_test)[:, 1])
assert_almost_equal(score1, score2)
# test with a regressor (no decision_function)
reg = DecisionTreeRegressor()
reg.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(reg, X_test, y_test)
score2 = roc_auc_score(y_test, reg.predict(X_test))
assert_almost_equal(score1, score2)
# Test that an exception is raised on more than two classes
X, y = make_blobs(random_state=0, centers=3)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf.fit(X_train, y_train)
with pytest.raises(ValueError, match="multiclass format is not supported"):
get_scorer('roc_auc')(clf, X_test, y_test)
# test error is raised with a single class present in model
# (predict_proba shape is not suitable for binary auc)
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = DecisionTreeClassifier()
clf.fit(X_train, np.zeros_like(y_train))
with pytest.raises(ValueError, match="need classifier with two classes"):
get_scorer('roc_auc')(clf, X_test, y_test)
# for proba scorers
with pytest.raises(ValueError, match="need classifier with two classes"):
get_scorer('neg_log_loss')(clf, X_test, y_test)
def test_plot_roc_curve(pyplot, response_method, data_binary,
with_sample_weight, drop_intermediate):
X, y = data_binary
if with_sample_weight:
rng = np.random.RandomState(42)
sample_weight = rng.randint(1, 4, size=(X.shape[0]))
else:
sample_weight = None
lr = LogisticRegression()
lr.fit(X, y)
viz = plot_roc_curve(lr, X, y, alpha=0.8, sample_weight=sample_weight,
drop_intermediate=drop_intermediate)
y_pred = getattr(lr, response_method)(X)
if y_pred.ndim == 2:
y_pred = y_pred[:, 1]
fpr, tpr, _ = roc_curve(y, y_pred, sample_weight=sample_weight,
drop_intermediate=drop_intermediate)
assert_allclose(viz.roc_auc, auc(fpr, tpr))
assert_allclose(viz.fpr, fpr)
assert_allclose(viz.tpr, tpr)
assert viz.estimator_name == "LogisticRegression"
# cannot fail thanks to pyplot fixture
import matplotlib as mpl # noqal
assert isinstance(viz.line_, mpl.lines.Line2D)
assert viz.line_.get_alpha() == 0.8
assert isinstance(viz.ax_, mpl.axes.Axes)
assert isinstance(viz.figure_, mpl.figure.Figure)
expected_label = "LogisticRegression (AUC = {:0.2f})".format(viz.roc_auc)
assert viz.line_.get_label() == expected_label
assert viz.ax_.get_ylabel() == "True Positive Rate"
assert viz.ax_.get_xlabel() == "False Positive Rate"
def test_sag_pobj_matches_logistic_regression():
"""tests if the sag pobj matches log reg"""
n_samples = 100
alpha = 1.0
max_iter = 20
X, y = make_blobs(n_samples=n_samples,
centers=2,
random_state=0,
cluster_std=0.1)
clf1 = LogisticRegression(solver='sag',
fit_intercept=False,
tol=.0000001,
C=1. / alpha / n_samples,
max_iter=max_iter,
random_state=10,
multi_class='ovr')
clf2 = clone(clf1)
clf3 = LogisticRegression(fit_intercept=False,
tol=.0000001,
C=1. / alpha / n_samples,
max_iter=max_iter,
random_state=10,
multi_class='ovr')
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
clf3.fit(X, y)
pobj1 = get_pobj(clf1.coef_, alpha, X, y, log_loss)
pobj2 = get_pobj(clf2.coef_, alpha, X, y, log_loss)
pobj3 = get_pobj(clf3.coef_, alpha, X, y, log_loss)
assert_array_almost_equal(pobj1, pobj2, decimal=4)
assert_array_almost_equal(pobj2, pobj3, decimal=4)
assert_array_almost_equal(pobj3, pobj1, decimal=4)
def test_sag_multiclass_computed_correctly():
"""tests if the multiclass classifier is computed correctly"""
alpha = .1
n_samples = 20
tol = .00001
max_iter = 40
fit_intercept = True
X, y = make_blobs(n_samples=n_samples,
centers=3,
random_state=0,
cluster_std=0.1)
step_size = get_step_size(X, alpha, fit_intercept, classification=True)
classes = np.unique(y)
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=max_iter,
tol=tol,
random_state=77,
fit_intercept=fit_intercept,
multi_class='ovr')
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
coef1 = []
intercept1 = []
coef2 = []
intercept2 = []
for cl in classes:
y_encoded = np.ones(n_samples)
y_encoded[y != cl] = -1
spweights1, spintercept1 = sag_sparse(X,
y_encoded,
step_size,
alpha,
dloss=log_dloss,
n_iter=max_iter,
fit_intercept=fit_intercept)
spweights2, spintercept2 = sag_sparse(X,
y_encoded,
step_size,
alpha,
dloss=log_dloss,
n_iter=max_iter,
sparse=True,
fit_intercept=fit_intercept)
coef1.append(spweights1)
intercept1.append(spintercept1)
coef2.append(spweights2)
intercept2.append(spintercept2)
coef1 = np.vstack(coef1)
intercept1 = np.array(intercept1)
coef2 = np.vstack(coef2)
intercept2 = np.array(intercept2)
for i, cl in enumerate(classes):
assert_array_almost_equal(clf1.coef_[i].ravel(),
coef1[i].ravel(),
decimal=2)
assert_almost_equal(clf1.intercept_[i], intercept1[i], decimal=1)
assert_array_almost_equal(clf2.coef_[i].ravel(),
coef2[i].ravel(),
decimal=2)
assert_almost_equal(clf2.intercept_[i], intercept2[i], decimal=1)
model_params = models[model]
# Small number of epochs for fast runtime
for this_max_iter in model_params['iters']:
print('[model=%s, solver=%s] Number of epochs: %s' %
(model_params['name'], solver, this_max_iter))
lr = LogisticRegression(
solver=solver,
multi_class=model,
penalty='l1',
max_iter=this_max_iter,
random_state=42,
)
t1 = timeit.default_timer()
lr.fit(X_train, y_train)
train_time = timeit.default_timer() - t1
y_pred = lr.predict(X_test)
accuracy = np.sum(y_pred == y_test) / y_test.shape[0]
density = np.mean(lr.coef_ != 0, axis=1) * 100
accuracies.append(accuracy)
densities.append(density)
times.append(train_time)
models[model]['times'] = times
models[model]['densities'] = densities
models[model]['accuracies'] = accuracies
print('Test accuracy for model %s: %.4f' % (model, accuracies[-1]))
print('%% non-zero coefficients for model %s, '
'per class:\n %s' % (model, densities[-1]))
print('Run time (%i epochs) for model %s:'
l1_ratio = 0.5 # L1 weight in the Elastic-Net regularization
fig, axes = plt.subplots(3, 3)
# Set regularization parameter
for i, (C, axes_row) in enumerate(zip((1, 0.1, 0.01), axes)):
# turn down tolerance for short training time
clf_l1_LR = LogisticRegression(C=C, penalty='l1', tol=0.01, solver='saga')
clf_l2_LR = LogisticRegression(C=C, penalty='l2', tol=0.01, solver='saga')
clf_en_LR = LogisticRegression(C=C,
penalty='elasticnet',
solver='saga',
l1_ratio=l1_ratio,
tol=0.01)
clf_l1_LR.fit(X, y)
clf_l2_LR.fit(X, y)
clf_en_LR.fit(X, y)
coef_l1_LR = clf_l1_LR.coef_.ravel()
coef_l2_LR = clf_l2_LR.coef_.ravel()
coef_en_LR = clf_en_LR.coef_.ravel()
# coef_l1_LR contains zeros due to the
# L1 sparsity inducing norm
sparsity_l1_LR = np.mean(coef_l1_LR == 0) * 100
sparsity_l2_LR = np.mean(coef_l2_LR == 0) * 100
sparsity_en_LR = np.mean(coef_en_LR == 0) * 100
print("C=%.2f" % C)
def test_multiclass_classifier_class_weight():
"""tests multiclass with classweights for each class"""
alpha = .1
n_samples = 20
tol = .00001
max_iter = 50
class_weight = {0: .45, 1: .55, 2: .75}
fit_intercept = True
X, y = make_blobs(n_samples=n_samples,
centers=3,
random_state=0,
cluster_std=0.1)
step_size = get_step_size(X, alpha, fit_intercept, classification=True)
classes = np.unique(y)
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=max_iter,
tol=tol,
random_state=77,
fit_intercept=fit_intercept,
multi_class='ovr',
class_weight=class_weight)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
le = LabelEncoder()
class_weight_ = compute_class_weight(class_weight, np.unique(y), y)
sample_weight = class_weight_[le.fit_transform(y)]
coef1 = []
intercept1 = []
coef2 = []
intercept2 = []
for cl in classes:
y_encoded = np.ones(n_samples)
y_encoded[y != cl] = -1
spweights1, spintercept1 = sag_sparse(X,
y_encoded,
step_size,
alpha,
n_iter=max_iter,
dloss=log_dloss,
sample_weight=sample_weight)
spweights2, spintercept2 = sag_sparse(X,
y_encoded,
step_size,
alpha,
n_iter=max_iter,
dloss=log_dloss,
sample_weight=sample_weight,
sparse=True)
coef1.append(spweights1)
intercept1.append(spintercept1)
coef2.append(spweights2)
intercept2.append(spintercept2)
coef1 = np.vstack(coef1)
intercept1 = np.array(intercept1)
coef2 = np.vstack(coef2)
intercept2 = np.array(intercept2)
for i, cl in enumerate(classes):
assert_array_almost_equal(clf1.coef_[i].ravel(),
coef1[i].ravel(),
decimal=2)
assert_almost_equal(clf1.intercept_[i], intercept1[i], decimal=1)
assert_array_almost_equal(clf2.coef_[i].ravel(),
coef2[i].ravel(),
decimal=2)
assert_almost_equal(clf2.intercept_[i], intercept2[i], decimal=1)
n_estimators=n_estimator,
random_state=0)
rt_lm = LogisticRegression(max_iter=1000)
pipeline = make_pipeline(rt, rt_lm)
pipeline.fit(X_train, y_train)
y_pred_rt = pipeline.predict_proba(X_test)[:, 1]
fpr_rt_lm, tpr_rt_lm, _ = roc_curve(y_test, y_pred_rt)
# Supervised transformation based on random forests
rf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)
rf_enc = OneHotEncoder()
rf_lm = LogisticRegression(max_iter=1000)
rf.fit(X_train, y_train)
rf_enc.fit(rf.apply(X_train))
rf_lm.fit(rf_enc.transform(rf.apply(X_train_lr)), y_train_lr)
y_pred_rf_lm = rf_lm.predict_proba(rf_enc.transform(rf.apply(X_test)))[:, 1]
fpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)
# Supervised transformation based on gradient boosted trees
grd = GradientBoostingClassifier(n_estimators=n_estimator)
grd_enc = OneHotEncoder()
grd_lm = LogisticRegression(max_iter=1000)
grd.fit(X_train, y_train)
grd_enc.fit(grd.apply(X_train)[:, :, 0])
grd_lm.fit(grd_enc.transform(grd.apply(X_train_lr)[:, :, 0]), y_train_lr)
y_pred_grd_lm = grd_lm.predict_proba(
grd_enc.transform(grd.apply(X_test)[:, :, 0]))[:, 1]
fpr_grd_lm, tpr_grd_lm, _ = roc_curve(y_test, y_pred_grd_lm)
# License: BSD 3 clause import numpy as np import matplotlib.pyplot as plt from mrex.linear_model import LogisticRegression from mrex import datasets # import some data to play with iris = datasets.load_iris() X = iris.data[:, :2] # we only take the first two features. Y = iris.target logreg = LogisticRegression(C=1e5) # Create an instance of Logistic Regression Classifier and fit the data. logreg.fit(X, Y) # Plot the decision boundary. For that, we will assign a color to each # point in the mesh [x_min, x_max]x[y_min, y_max]. x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5 y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5 h = .02 # step size in the mesh xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h)) Z = logreg.predict(np.c_[xx.ravel(), yy.ravel()]) # Put the result into a color plot Z = Z.reshape(xx.shape) plt.figure(1, figsize=(4, 3)) plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired) # Plot also the training points
X = X[permutation]
y = y[permutation]
X = X.reshape((X.shape[0], -1))
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=train_samples, test_size=10000)
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
# Turn up tolerance for faster convergence
clf = LogisticRegression(
C=50. / train_samples, penalty='l1', solver='saga', tol=0.1
)
clf.fit(X_train, y_train)
sparsity = np.mean(clf.coef_ == 0) * 100
score = clf.score(X_test, y_test)
# print('Best C % .4f' % clf.C_)
print("Sparsity with L1 penalty: %.2f%%" % sparsity)
print("Test score with L1 penalty: %.4f" % score)
coef = clf.coef_.copy()
plt.figure(figsize=(10, 5))
scale = np.abs(coef).max()
for i in range(10):
l1_plot = plt.subplot(2, 5, i + 1)
l1_plot.imshow(coef[i].reshape(28, 28), interpolation='nearest',
cmap=plt.cm.RdBu, vmin=-scale, vmax=scale)
l1_plot.set_xticks(())
l1_plot.set_yticks(())