def test_gnb_priors():
"""Test whether the class prior override is properly used"""
clf = GaussianNB(priors=np.array([0.3, 0.7])).fit(X, y)
assert_array_almost_equal(
clf.predict_proba([[-0.1, -0.1]]),
np.array([[0.825303662161683, 0.174696337838317]]), 8)
assert_array_almost_equal(clf.class_prior_, np.array([0.3, 0.7]))
def test_check_accuracy_on_digits():
# Non regression test to make sure that any further refactoring / optim
# of the NB models do not harm the performance on a slightly non-linearly
# separable dataset
X, y = load_digits(return_X_y=True)
binary_3v8 = np.logical_or(y == 3, y == 8)
X_3v8, y_3v8 = X[binary_3v8], y[binary_3v8]
# Multinomial NB
scores = cross_val_score(MultinomialNB(alpha=10), X, y, cv=10)
assert scores.mean() > 0.86
scores = cross_val_score(MultinomialNB(alpha=10), X_3v8, y_3v8, cv=10)
assert scores.mean() > 0.94
# Bernoulli NB
scores = cross_val_score(BernoulliNB(alpha=10), X > 4, y, cv=10)
assert scores.mean() > 0.83
scores = cross_val_score(BernoulliNB(alpha=10), X_3v8 > 4, y_3v8, cv=10)
assert scores.mean() > 0.92
# Gaussian NB
scores = cross_val_score(GaussianNB(), X, y, cv=10)
assert scores.mean() > 0.77
scores = cross_val_score(GaussianNB(var_smoothing=0.1), X, y, cv=10)
assert scores.mean() > 0.89
scores = cross_val_score(GaussianNB(), X_3v8, y_3v8, cv=10)
assert scores.mean() > 0.86
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_gnb_prior():
# Test whether class priors are properly set.
clf = GaussianNB().fit(X, y)
assert_array_almost_equal(np.array([3, 3]) / 6.0, clf.class_prior_, 8)
clf.fit(X1, y1)
# Check that the class priors sum to 1
assert_array_almost_equal(clf.class_prior_.sum(), 1)
def test_gnb_pfit_wrong_nb_features():
"""Test whether an error is raised when the number of feature changes
between two partial fit"""
clf = GaussianNB()
# Fit for the first time the GNB
clf.fit(X, y)
# Partial fit a second time with an incoherent X
assert_raises(ValueError, clf.partial_fit, np.hstack((X, X)), y)
def test_gnb_priors_sum_isclose():
# test whether the class prior sum is properly tested"""
X = np.array([[-1, -1], [-2, -1], [-3, -2], [-4, -5], [-5, -4], [1, 1],
[2, 1], [3, 2], [4, 4], [5, 5]])
priors = np.array(
[0.08, 0.14, 0.03, 0.16, 0.11, 0.16, 0.07, 0.14, 0.11, 0.0])
Y = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
clf = GaussianNB(priors)
# smoke test for issue #9633
clf.fit(X, Y)
def test_gnb_sample_weight():
"""Test whether sample weights are properly used in GNB. """
# Sample weights all being 1 should not change results
sw = np.ones(6)
clf = GaussianNB().fit(X, y)
clf_sw = GaussianNB().fit(X, y, sw)
assert_array_almost_equal(clf.theta_, clf_sw.theta_)
assert_array_almost_equal(clf.sigma_, clf_sw.sigma_)
# Fitting twice with half sample-weights should result
# in same result as fitting once with full weights
sw = rng.rand(y.shape[0])
clf1 = GaussianNB().fit(X, y, sample_weight=sw)
clf2 = GaussianNB().partial_fit(X, y, classes=[1, 2], sample_weight=sw / 2)
clf2.partial_fit(X, y, sample_weight=sw / 2)
assert_array_almost_equal(clf1.theta_, clf2.theta_)
assert_array_almost_equal(clf1.sigma_, clf2.sigma_)
# Check that duplicate entries and correspondingly increased sample
# weights yield the same result
ind = rng.randint(0, X.shape[0], 20)
sample_weight = np.bincount(ind, minlength=X.shape[0])
clf_dupl = GaussianNB().fit(X[ind], y[ind])
clf_sw = GaussianNB().fit(X, y, sample_weight)
assert_array_almost_equal(clf_dupl.theta_, clf_sw.theta_)
assert_array_almost_equal(clf_dupl.sigma_, clf_sw.sigma_)
def test_transform():
"""Check transform method of VotingClassifier on 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]])
y = np.array([1, 1, 2, 2])
eclf1 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft').fit(X, y)
eclf2 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
flatten_transform=True).fit(X, y)
eclf3 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
flatten_transform=False).fit(X, y)
assert_array_equal(eclf1.transform(X).shape, (4, 6))
assert_array_equal(eclf2.transform(X).shape, (4, 6))
assert_array_equal(eclf3.transform(X).shape, (3, 4, 2))
assert_array_almost_equal(eclf1.transform(X),
eclf2.transform(X))
assert_array_almost_equal(
eclf3.transform(X).swapaxes(0, 1).reshape((4, 6)),
eclf2.transform(X)
)
def test_set_params():
"""set_params should be able to set estimators"""
clf1 = LogisticRegression(random_state=123, C=1.0)
clf2 = RandomForestClassifier(random_state=123, max_depth=None)
clf3 = GaussianNB()
eclf1 = VotingClassifier([('lr', clf1), ('rf', clf2)], voting='soft',
weights=[1, 2])
assert 'lr' in eclf1.named_estimators
assert eclf1.named_estimators.lr is eclf1.estimators[0][1]
assert eclf1.named_estimators.lr is eclf1.named_estimators['lr']
eclf1.fit(X, y)
assert 'lr' in eclf1.named_estimators_
assert eclf1.named_estimators_.lr is eclf1.estimators_[0]
assert eclf1.named_estimators_.lr is eclf1.named_estimators_['lr']
eclf2 = VotingClassifier([('lr', clf1), ('nb', clf3)], voting='soft',
weights=[1, 2])
eclf2.set_params(nb=clf2).fit(X, y)
assert not hasattr(eclf2, 'nb')
assert_array_equal(eclf1.predict(X), eclf2.predict(X))
assert_array_almost_equal(eclf1.predict_proba(X), eclf2.predict_proba(X))
assert eclf2.estimators[0][1].get_params() == clf1.get_params()
assert eclf2.estimators[1][1].get_params() == clf2.get_params()
eclf1.set_params(lr__C=10.0)
eclf2.set_params(nb__max_depth=5)
assert eclf1.estimators[0][1].get_params()['C'] == 10.0
assert eclf2.estimators[1][1].get_params()['max_depth'] == 5
assert (eclf1.get_params()["lr__C"] ==
eclf1.get_params()["lr"].get_params()['C'])
def test_gnb_naive_bayes_scale_invariance():
# Scaling the data should not change the prediction results
iris = load_iris()
X, y = iris.data, iris.target
labels = [
GaussianNB().fit(f * X, y).predict(f * X) for f in [1E-10, 1, 1E10]
]
assert_array_equal(labels[0], labels[1])
assert_array_equal(labels[1], labels[2])
def test_majority_label_iris():
"""Check classification by majority label on dataset iris."""
clf1 = LogisticRegression(solver='liblinear', random_state=123)
clf2 = RandomForestClassifier(n_estimators=10, random_state=123)
clf3 = GaussianNB()
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='hard')
scores = cross_val_score(eclf, X, y, scoring='accuracy')
assert_almost_equal(scores.mean(), 0.95, decimal=2)
def test_gnb_check_update_with_no_data():
""" Test when the partial fit is called without any data"""
# Create an empty array
prev_points = 100
mean = 0.
var = 1.
x_empty = np.empty((0, X.shape[1]))
tmean, tvar = GaussianNB._update_mean_variance(prev_points, mean, var,
x_empty)
assert tmean == mean
assert tvar == var
def test_weights_iris():
"""Check classification by average probabilities on dataset iris."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
weights=[1, 2, 10])
scores = cross_val_score(eclf, X, y, scoring='accuracy')
assert_almost_equal(scores.mean(), 0.93, decimal=2)
def test_set_estimator_none(drop):
"""VotingClassifier set_params should be able to set estimators as None or
drop"""
# Test predict
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(n_estimators=10, random_state=123)
clf3 = GaussianNB()
eclf1 = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('nb', clf3)],
voting='hard', weights=[1, 0, 0.5]).fit(X, y)
eclf2 = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('nb', clf3)],
voting='hard', weights=[1, 1, 0.5])
eclf2.set_params(rf=drop).fit(X, y)
assert_array_equal(eclf1.predict(X), eclf2.predict(X))
assert dict(eclf2.estimators)["rf"] is drop
assert len(eclf2.estimators_) == 2
assert all(isinstance(est, (LogisticRegression, GaussianNB))
for est in eclf2.estimators_)
assert eclf2.get_params()["rf"] is drop
eclf1.set_params(voting='soft').fit(X, y)
eclf2.set_params(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))
msg = 'All estimators are None or "drop". At least one is required!'
assert_raise_message(
ValueError, msg, eclf2.set_params(lr=drop, rf=drop, nb=drop).fit, X, y)
# Test soft voting transform
X1 = np.array([[1], [2]])
y1 = np.array([1, 2])
eclf1 = VotingClassifier(estimators=[('rf', clf2), ('nb', clf3)],
voting='soft', weights=[0, 0.5],
flatten_transform=False).fit(X1, y1)
eclf2 = VotingClassifier(estimators=[('rf', clf2), ('nb', clf3)],
voting='soft', weights=[1, 0.5],
flatten_transform=False)
eclf2.set_params(rf=drop).fit(X1, y1)
assert_array_almost_equal(eclf1.transform(X1),
np.array([[[0.7, 0.3], [0.3, 0.7]],
[[1., 0.], [0., 1.]]]))
assert_array_almost_equal(eclf2.transform(X1),
np.array([[[1., 0.],
[0., 1.]]]))
eclf1.set_params(voting='hard')
eclf2.set_params(voting='hard')
assert_array_equal(eclf1.transform(X1), np.array([[0, 0], [1, 1]]))
assert_array_equal(eclf2.transform(X1), np.array([[0], [1]]))
def test_gridsearch():
"""Check GridSearch support."""
clf1 = LogisticRegression(random_state=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft')
params = {'lr__C': [1.0, 100.0],
'voting': ['soft', 'hard'],
'weights': [[0.5, 0.5, 0.5], [1.0, 0.5, 0.5]]}
grid = GridSearchCV(estimator=eclf, param_grid=params)
grid.fit(iris.data, iris.target)
def test_predict_proba_on_toy_problem():
"""Calculate predicted probabilities on 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]])
y = np.array([1, 1, 2, 2])
clf1_res = np.array([[0.59790391, 0.40209609],
[0.57622162, 0.42377838],
[0.50728456, 0.49271544],
[0.40241774, 0.59758226]])
clf2_res = np.array([[0.8, 0.2],
[0.8, 0.2],
[0.2, 0.8],
[0.3, 0.7]])
clf3_res = np.array([[0.9985082, 0.0014918],
[0.99845843, 0.00154157],
[0., 1.],
[0., 1.]])
t00 = (2*clf1_res[0][0] + clf2_res[0][0] + clf3_res[0][0]) / 4
t11 = (2*clf1_res[1][1] + clf2_res[1][1] + clf3_res[1][1]) / 4
t21 = (2*clf1_res[2][1] + clf2_res[2][1] + clf3_res[2][1]) / 4
t31 = (2*clf1_res[3][1] + clf2_res[3][1] + clf3_res[3][1]) / 4
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
weights=[2, 1, 1])
eclf_res = eclf.fit(X, y).predict_proba(X)
assert_almost_equal(t00, eclf_res[0][0], decimal=1)
assert_almost_equal(t11, eclf_res[1][1], decimal=1)
assert_almost_equal(t21, eclf_res[2][1], decimal=1)
assert_almost_equal(t31, eclf_res[3][1], decimal=1)
with pytest.raises(
AttributeError,
match="predict_proba is not available when voting='hard'"):
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='hard')
eclf.fit(X, y).predict_proba(X)
def test_gnb_partial_fit():
clf = GaussianNB().fit(X, y)
clf_pf = GaussianNB().partial_fit(X, y, np.unique(y))
assert_array_almost_equal(clf.theta_, clf_pf.theta_)
assert_array_almost_equal(clf.sigma_, clf_pf.sigma_)
assert_array_almost_equal(clf.class_prior_, clf_pf.class_prior_)
clf_pf2 = GaussianNB().partial_fit(X[0::2, :], y[0::2], np.unique(y))
clf_pf2.partial_fit(X[1::2], y[1::2])
assert_array_almost_equal(clf.theta_, clf_pf2.theta_)
assert_array_almost_equal(clf.sigma_, clf_pf2.sigma_)
assert_array_almost_equal(clf.class_prior_, clf_pf2.class_prior_)
def test_parallel_fit():
"""Check parallel backend of VotingClassifier on 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]])
y = np.array([1, 1, 2, 2])
eclf1 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
n_jobs=1).fit(X, y)
eclf2 = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
n_jobs=2).fit(X, y)
assert_array_equal(eclf1.predict(X), eclf2.predict(X))
assert_array_almost_equal(eclf1.predict_proba(X), eclf2.predict_proba(X))
def test_gnb():
# Gaussian Naive Bayes classification.
# This checks that GaussianNB implements fit and predict and returns
# correct values for a simple toy dataset.
clf = GaussianNB()
y_pred = clf.fit(X, y).predict(X)
assert_array_equal(y_pred, y)
y_pred_proba = clf.predict_proba(X)
y_pred_log_proba = clf.predict_log_proba(X)
assert_array_almost_equal(np.log(y_pred_proba), y_pred_log_proba, 8)
# Test whether label mismatch between target y and classes raises
# an Error
# FIXME Remove this test once the more general partial_fit tests are merged
assert_raises(ValueError, GaussianNB().partial_fit, X, y, classes=[0, 1])
names = [
"Nearest Neighbors", "Linear SVM", "RBF SVM", "Gaussian Process",
"Decision Tree", "Random Forest", "Neural Net", "AdaBoost", "Naive Bayes",
"QDA"
]
classifiers = [
KNeighborsClassifier(3),
SVC(kernel="linear", C=0.025),
SVC(gamma=2, C=1),
GaussianProcessClassifier(1.0 * RBF(1.0)),
DecisionTreeClassifier(max_depth=5),
RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
MLPClassifier(alpha=1, max_iter=1000),
AdaBoostClassifier(),
GaussianNB(),
QuadraticDiscriminantAnalysis()
]
X, y = make_classification(n_features=2,
n_redundant=0,
n_informative=2,
random_state=1,
n_clusters_per_class=1)
rng = np.random.RandomState(2)
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)
datasets = [
make_moons(noise=0.3, random_state=0),
make_circles(noise=0.2, factor=0.5, random_state=1), linearly_separable
X, y = datasets.make_classification(n_samples=100000,
n_features=20,
n_informative=2,
n_redundant=2)
train_samples = 100 # Samples used for training the models
X_train = X[:train_samples]
X_test = X[train_samples:]
y_train = y[:train_samples]
y_test = y[train_samples:]
# Create classifiers
lr = LogisticRegression()
gnb = GaussianNB()
svc = LinearSVC(C=1.0)
rfc = RandomForestClassifier()
# #############################################################################
# Plot calibration plots
plt.figure(figsize=(10, 10))
ax1 = plt.subplot2grid((3, 1), (0, 0), rowspan=2)
ax2 = plt.subplot2grid((3, 1), (2, 0))
ax1.plot([0, 1], [0, 1], "k:", label="Perfectly calibrated")
for clf, name in [(lr, 'Logistic'), (gnb, 'Naive Bayes'),
(svc, 'Support Vector Classification'),
(rfc, 'Random Forest')]:
clf.fit(X_train, y_train)
axes[2].set_ylabel("Score")
axes[2].set_title("Performance of the model")
return plt
fig, axes = plt.subplots(3, 2, figsize=(10, 15))
X, y = load_digits(return_X_y=True)
title = "Learning Curves (Naive Bayes)"
# Cross validation with 100 iterations to get smoother mean test and train
# score curves, each time with 20% data randomly selected as a validation set.
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
estimator = GaussianNB()
plot_learning_curve(estimator,
title,
X,
y,
axes=axes[:, 0],
ylim=(0.7, 1.01),
cv=cv,
n_jobs=4)
title = r"Learning Curves (SVM, RBF kernel, $\gamma=0.001$)"
# SVC is more expensive so we do a lower number of CV iterations:
cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
estimator = SVC(gamma=0.001)
plot_learning_curve(estimator,
title,
def test_gnb_wrong_nb_priors():
""" Test whether an error is raised if the number of prior is different
from the number of class"""
clf = GaussianNB(priors=np.array([.25, .25, .25, .25]))
assert_raises(ValueError, clf.fit, X, y)
print("\tRecall: %1.3f" % recall_score(y_test, y_pred))
print("\tF1: %1.3f\n" % f1_score(y_test, y_pred))
fraction_of_positives, mean_predicted_value = \
calibration_curve(y_test, prob_pos, n_bins=10)
ax1.plot(mean_predicted_value, fraction_of_positives, "s-",
label="%s (%1.3f)" % (name, clf_score))
ax2.hist(prob_pos, range=(0, 1), bins=10, label=name,
histtype="step", lw=2)
ax1.set_ylabel("Fraction of positives")
ax1.set_ylim([-0.05, 1.05])
ax1.legend(loc="lower right")
ax1.set_title('Calibration plots (reliability curve)')
ax2.set_xlabel("Mean predicted value")
ax2.set_ylabel("Count")
ax2.legend(loc="upper center", ncol=2)
plt.tight_layout()
# Plot calibration curve for Gaussian Naive Bayes
plot_calibration_curve(GaussianNB(), "Naive Bayes", 1)
# Plot calibration curve for Linear SVC
plot_calibration_curve(LinearSVC(max_iter=10000), "SVC", 2)
plt.show()
def test_gnb_neg_priors():
"""Test whether an error is raised in case of negative priors"""
clf = GaussianNB(priors=np.array([-1., 2.]))
assert_raises(ValueError, clf.fit, X, y)
def test_gnb_prior_greater_one():
"""Test if an error is raised if the sum of prior greater than one"""
clf = GaussianNB(priors=np.array([2., 1.]))
assert_raises(ValueError, clf.fit, X, y)
def test_gnb_prior_large_bias():
"""Test if good prediction when class prior favor largely one class"""
clf = GaussianNB(priors=np.array([0.01, 0.99]))
clf.fit(X, y)
assert clf.predict([[-0.1, -0.1]]) == np.array([2])
n_features=2,
cluster_std=1.0,
centers=centers,
shuffle=False,
random_state=42)
y[:n_samples // 2] = 0
y[n_samples // 2:] = 1
sample_weight = np.random.RandomState(42).rand(y.shape[0])
# split train, test for calibration
X_train, X_test, y_train, y_test, sw_train, sw_test = \
train_test_split(X, y, sample_weight, test_size=0.9, random_state=42)
# Gaussian Naive-Bayes with no calibration
clf = GaussianNB()
clf.fit(X_train, y_train) # GaussianNB itself does not support sample-weights
prob_pos_clf = clf.predict_proba(X_test)[:, 1]
# Gaussian Naive-Bayes with isotonic calibration
clf_isotonic = CalibratedClassifierCV(clf, cv=2, method='isotonic')
clf_isotonic.fit(X_train, y_train, sw_train)
prob_pos_isotonic = clf_isotonic.predict_proba(X_test)[:, 1]
# Gaussian Naive-Bayes with sigmoid calibration
clf_sigmoid = CalibratedClassifierCV(clf, cv=2, method='sigmoid')
clf_sigmoid.fit(X_train, y_train, sw_train)
prob_pos_sigmoid = clf_sigmoid.predict_proba(X_test)[:, 1]
print("Brier scores: (the smaller the better)")
# License: BSD 3 clause
RANDOM_STATE = 42
FIG_SIZE = (10, 7)
features, target = load_wine(return_X_y=True)
# Make a train/test split using 30% test size
X_train, X_test, y_train, y_test = train_test_split(features,
target,
test_size=0.30,
random_state=RANDOM_STATE)
# Fit to data and predict using pipelined GNB and PCA.
unscaled_clf = make_pipeline(PCA(n_components=2), GaussianNB())
unscaled_clf.fit(X_train, y_train)
pred_test = unscaled_clf.predict(X_test)
# Fit to data and predict using pipelined scaling, GNB and PCA.
std_clf = make_pipeline(StandardScaler(), PCA(n_components=2), GaussianNB())
std_clf.fit(X_train, y_train)
pred_test_std = std_clf.predict(X_test)
# Show prediction accuracies in scaled and unscaled data.
print('\nPrediction accuracy for the normal test dataset with PCA')
print('{:.2%}\n'.format(metrics.accuracy_score(y_test, pred_test)))
print('\nPrediction accuracy for the standardized test dataset with PCA')
print('{:.2%}\n'.format(metrics.accuracy_score(y_test, pred_test_std)))
mean = X_train.mean(axis=0)
std = X_train.std(axis=0)
mean[10:] = 0.0
std[10:] = 1.0
X_train = (X_train - mean) / std
X_test = (X_test - mean) / std
return X_train, X_test, y_train, y_test
ESTIMATORS = {
'GBRT': GradientBoostingClassifier(n_estimators=250),
'ExtraTrees': ExtraTreesClassifier(n_estimators=20),
'RandomForest': RandomForestClassifier(n_estimators=20),
'CART': DecisionTreeClassifier(min_samples_split=5),
'SGD': SGDClassifier(alpha=0.001),
'GaussianNB': GaussianNB(),
'liblinear': LinearSVC(loss="l2",
penalty="l2",
C=1000,
dual=False,
tol=1e-3),
'SAG': LogisticRegression(solver='sag', max_iter=2, C=1000)
}
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--classifiers',
nargs="+",
choices=ESTIMATORS,
type=str,
default=['liblinear', 'GaussianNB', 'SGD', 'CART'],
