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_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_ovr_always_present():
# Test that ovr works with classes that are always present or absent.
# Note: tests is the case where _ConstantPredictor is utilised
X = np.ones((10, 2))
X[:5, :] = 0
# Build an indicator matrix where two features are always on.
# As list of lists, it would be: [[int(i >= 5), 2, 3] for i in range(10)]
y = np.zeros((10, 3))
y[5:, 0] = 1
y[:, 1] = 1
y[:, 2] = 1
ovr = OneVsRestClassifier(LogisticRegression())
assert_warns(UserWarning, ovr.fit, X, y)
y_pred = ovr.predict(X)
assert_array_equal(np.array(y_pred), np.array(y))
y_pred = ovr.decision_function(X)
assert np.unique(y_pred[:, -2:]) == 1
y_pred = ovr.predict_proba(X)
assert_array_equal(y_pred[:, -1], np.ones(X.shape[0]))
# y has a constantly absent label
y = np.zeros((10, 2))
y[5:, 0] = 1 # variable label
ovr = OneVsRestClassifier(LogisticRegression())
assert_warns(UserWarning, ovr.fit, X, y)
y_pred = ovr.predict_proba(X)
assert_array_equal(y_pred[:, -1], np.zeros(X.shape[0]))
def test_compute_class_weight_invariance():
# Test that results with class_weight="balanced" is invariant wrt
# class imbalance if the number of samples is identical.
# The test uses a balanced two class dataset with 100 datapoints.
# It creates three versions, one where class 1 is duplicated
# resulting in 150 points of class 1 and 50 of class 0,
# one where there are 50 points in class 1 and 150 in class 0,
# and one where there are 100 points of each class (this one is balanced
# again).
# With balancing class weights, all three should give the same model.
X, y = make_blobs(centers=2, random_state=0)
# create dataset where class 1 is duplicated twice
X_1 = np.vstack([X] + [X[y == 1]] * 2)
y_1 = np.hstack([y] + [y[y == 1]] * 2)
# create dataset where class 0 is duplicated twice
X_0 = np.vstack([X] + [X[y == 0]] * 2)
y_0 = np.hstack([y] + [y[y == 0]] * 2)
# duplicate everything
X_ = np.vstack([X] * 2)
y_ = np.hstack([y] * 2)
# results should be identical
logreg1 = LogisticRegression(class_weight="balanced").fit(X_1, y_1)
logreg0 = LogisticRegression(class_weight="balanced").fit(X_0, y_0)
logreg = LogisticRegression(class_weight="balanced").fit(X_, y_)
assert_array_almost_equal(logreg1.coef_, logreg0.coef_)
assert_array_almost_equal(logreg.coef_, logreg0.coef_)
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_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_scoring_is_not_metric():
assert_raises_regexp(ValueError, 'make_scorer', check_scoring,
LogisticRegression(), f1_score)
assert_raises_regexp(ValueError, 'make_scorer', check_scoring,
LogisticRegression(), roc_auc_score)
assert_raises_regexp(ValueError, 'make_scorer', check_scoring, Ridge(),
r2_score)
assert_raises_regexp(ValueError, 'make_scorer', check_scoring, KMeans(),
cluster_module.adjusted_rand_score)
def test_predictproba_hardvoting():
eclf = VotingClassifier(estimators=[('lr1', LogisticRegression()),
('lr2', LogisticRegression())],
voting='hard')
msg = "predict_proba is not available when voting='hard'"
with pytest.raises(AttributeError, match=msg):
eclf.predict_proba
assert not hasattr(eclf, "predict_proba")
eclf.fit(X, y)
assert not hasattr(eclf, "predict_proba")
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_classifier_chain_fit_and_predict_with_sparse_data():
# Fit classifier chain with sparse data
X, Y = generate_multilabel_dataset_with_correlations()
X_sparse = sp.csr_matrix(X)
classifier_chain = ClassifierChain(LogisticRegression())
classifier_chain.fit(X_sparse, Y)
Y_pred_sparse = classifier_chain.predict(X_sparse)
classifier_chain = ClassifierChain(LogisticRegression())
classifier_chain.fit(X, Y)
Y_pred_dense = classifier_chain.predict(X)
assert_array_equal(Y_pred_sparse, Y_pred_dense)
def test_multiclass_multioutput_estimator_predict_proba():
seed = 542
# make test deterministic
rng = np.random.RandomState(seed)
# random features
X = rng.normal(size=(5, 5))
# random labels
y1 = np.array(['b', 'a', 'a', 'b', 'a']).reshape(5, 1) # 2 classes
y2 = np.array(['d', 'e', 'f', 'e', 'd']).reshape(5, 1) # 3 classes
Y = np.concatenate([y1, y2], axis=1)
clf = MultiOutputClassifier(
LogisticRegression(solver='liblinear', random_state=seed))
clf.fit(X, Y)
y_result = clf.predict_proba(X)
y_actual = [
np.array([[0.23481764, 0.76518236], [0.67196072, 0.32803928],
[0.54681448, 0.45318552], [0.34883923, 0.65116077],
[0.73687069, 0.26312931]]),
np.array([[0.5171785, 0.23878628, 0.24403522],
[0.22141451, 0.64102704, 0.13755846],
[0.16751315, 0.18256843, 0.64991843],
[0.27357372, 0.55201592, 0.17441036],
[0.65745193, 0.26062899, 0.08191907]])
]
for i in range(len(y_actual)):
assert_almost_equal(y_result[i], y_actual[i])
def test_permutation_importance_mixed_types_pandas():
pd = pytest.importorskip("pandas")
rng = np.random.RandomState(42)
n_repeats = 5
# Last column is correlated with y
X = pd.DataFrame({
'col1': [1.0, 2.0, 3.0, np.nan],
'col2': ['a', 'b', 'a', 'b']
})
y = np.array([0, 1, 0, 1])
num_preprocess = make_pipeline(SimpleImputer(), StandardScaler())
preprocess = ColumnTransformer([('num', num_preprocess, ['col1']),
('cat', OneHotEncoder(), ['col2'])])
clf = make_pipeline(preprocess, LogisticRegression(solver='lbfgs'))
clf.fit(X, y)
result = permutation_importance(clf,
X,
y,
n_repeats=n_repeats,
random_state=rng)
assert result.importances.shape == (X.shape[1], n_repeats)
# the correlated feature with y is the last column and should
# have the highest importance
assert np.all(result.importances_mean[-1] > result.importances_mean[:-1])
def test_estimator_init():
eclf = VotingClassifier(estimators=[])
msg = ('Invalid `estimators` attribute, `estimators` should be'
' a list of (string, estimator) tuples')
assert_raise_message(AttributeError, msg, eclf.fit, X, y)
clf = LogisticRegression(random_state=1)
eclf = VotingClassifier(estimators=[('lr', clf)], voting='error')
msg = ('Voting must be \'soft\' or \'hard\'; got (voting=\'error\')')
assert_raise_message(ValueError, msg, eclf.fit, X, y)
eclf = VotingClassifier(estimators=[('lr', clf)], weights=[1, 2])
msg = ('Number of `estimators` and weights must be equal'
'; got 2 weights, 1 estimators')
assert_raise_message(ValueError, msg, eclf.fit, X, y)
eclf = VotingClassifier(estimators=[('lr', clf), ('lr', clf)],
weights=[1, 2])
msg = "Names provided are not unique: ['lr', 'lr']"
assert_raise_message(ValueError, msg, eclf.fit, X, y)
eclf = VotingClassifier(estimators=[('lr__', clf)])
msg = "Estimator names must not contain __: got ['lr__']"
assert_raise_message(ValueError, msg, eclf.fit, X, y)
eclf = VotingClassifier(estimators=[('estimators', clf)])
msg = "Estimator names conflict with constructor arguments: ['estimators']"
assert_raise_message(ValueError, msg, eclf.fit, X, y)
def test_auto_weight():
# Test class weights for imbalanced data
from mrex.linear_model import LogisticRegression
# We take as dataset the two-dimensional projection of iris so
# that it is not separable and remove half of predictors from
# class 1.
# We add one to the targets as a non-regression test:
# class_weight="balanced"
# used to work only when the labels where a range [0..K).
from mrex.utils import compute_class_weight
X, y = iris.data[:, :2], iris.target + 1
unbalanced = np.delete(np.arange(y.size), np.where(y > 2)[0][::2])
classes = np.unique(y[unbalanced])
class_weights = compute_class_weight('balanced', classes, y[unbalanced])
assert np.argmax(class_weights) == 2
for clf in (svm.SVC(kernel='linear'), svm.LinearSVC(random_state=0),
LogisticRegression()):
# check that score is better when class='balanced' is set.
y_pred = clf.fit(X[unbalanced], y[unbalanced]).predict(X)
clf.set_params(class_weight='balanced')
y_pred_balanced = clf.fit(
X[unbalanced],
y[unbalanced],
).predict(X)
assert (metrics.f1_score(y, y_pred, average='macro') <=
metrics.f1_score(y, y_pred_balanced, average='macro'))
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_nested_pipeline():
estimator = Pipeline([
('a', Pipeline([
('b', DummyRegressor())
]))
])
estimator.set_params(a__b__alpha=0.001, a__b=Lasso())
estimator.set_params(a__steps=[('b', LogisticRegression())], a__b__C=5)
def test_notfitted():
eclf = VotingClassifier(estimators=[('lr1', LogisticRegression()),
('lr2', LogisticRegression())],
voting='soft')
ereg = VotingRegressor([('dr', DummyRegressor())])
msg = ("This %s instance is not fitted yet. Call \'fit\'"
" with appropriate arguments before using this method.")
assert_raise_message(NotFittedError, msg % 'VotingClassifier',
eclf.predict, X)
assert_raise_message(NotFittedError, msg % 'VotingClassifier',
eclf.predict_proba, X)
assert_raise_message(NotFittedError, msg % 'VotingClassifier',
eclf.transform, X)
assert_raise_message(NotFittedError, msg % 'VotingRegressor',
ereg.predict, X_r)
assert_raise_message(NotFittedError, msg % 'VotingRegressor',
ereg.transform, X_r)
def test_classifier_single_class():
"""tests if ValueError is thrown with only one class"""
X = [[1, 2], [3, 4]]
y = [1, 1]
assert_raise_message(
ValueError, "This solver needs samples of at least 2 classes "
"in the data",
LogisticRegression(solver='sag').fit, X, y)
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 plot_calibration_curve(est, name, fig_index):
"""Plot calibration curve for est w/o and with calibration. """
# Calibrated with isotonic calibration
isotonic = CalibratedClassifierCV(est, cv=2, method='isotonic')
# Calibrated with sigmoid calibration
sigmoid = CalibratedClassifierCV(est, cv=2, method='sigmoid')
# Logistic regression with no calibration as baseline
lr = LogisticRegression(C=1.)
fig = plt.figure(fig_index, 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'),
(est, name),
(isotonic, name + ' + Isotonic'),
(sigmoid, name + ' + Sigmoid')]:
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
if hasattr(clf, "predict_proba"):
prob_pos = clf.predict_proba(X_test)[:, 1]
else: # use decision function
prob_pos = clf.decision_function(X_test)
prob_pos = \
(prob_pos - prob_pos.min()) / (prob_pos.max() - prob_pos.min())
clf_score = brier_score_loss(y_test, prob_pos, pos_label=y.max())
print("%s:" % name)
print("\tBrier: %1.3f" % (clf_score))
print("\tPrecision: %1.3f" % precision_score(y_test, y_pred))
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()
def test_score_samples_on_pipeline_without_score_samples():
X = np.array([[1], [2]])
y = np.array([1, 2])
# Test that a pipeline does not have score_samples method when the final
# step of the pipeline does not have score_samples defined.
pipe = make_pipeline(LogisticRegression())
pipe.fit(X, y)
with pytest.raises(AttributeError,
match="'LogisticRegression' object has no attribute "
"'score_samples'"):
pipe.score_samples(X)
def test_classifier_chain_vs_independent_models():
# Verify that an ensemble of classifier chains (each of length
# N) can achieve a higher Jaccard similarity score than N independent
# models
X, Y = generate_multilabel_dataset_with_correlations()
X_train = X[:600, :]
X_test = X[600:, :]
Y_train = Y[:600, :]
Y_test = Y[600:, :]
ovr = OneVsRestClassifier(LogisticRegression())
ovr.fit(X_train, Y_train)
Y_pred_ovr = ovr.predict(X_test)
chain = ClassifierChain(LogisticRegression())
chain.fit(X_train, Y_train)
Y_pred_chain = chain.predict(X_test)
assert (jaccard_score(Y_test, Y_pred_chain, average='samples') >
jaccard_score(Y_test, Y_pred_ovr, average='samples'))
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_base_chain_fit_and_predict_with_sparse_data_and_cv():
# Fit base chain with sparse data cross_val_predict
X, Y = generate_multilabel_dataset_with_correlations()
X_sparse = sp.csr_matrix(X)
base_chains = [
ClassifierChain(LogisticRegression(), cv=3),
RegressorChain(Ridge(), cv=3)
]
for chain in base_chains:
chain.fit(X_sparse, Y)
Y_pred = chain.predict(X_sparse)
assert Y_pred.shape == Y.shape
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_classes_property():
iris = load_iris()
X = iris.data
y = iris.target
reg = make_pipeline(SelectKBest(k=1), LinearRegression())
reg.fit(X, y)
assert_raises(AttributeError, getattr, reg, "classes_")
clf = make_pipeline(SelectKBest(k=1), LogisticRegression(random_state=0))
assert_raises(AttributeError, getattr, clf, "classes_")
clf.fit(X, y)
assert_array_equal(clf.classes_, np.unique(y))
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_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])