def test_fit_with_inm(
prune_count_method='inverse_nm_dot_s',
seed=0,
used_by_another_test=False,
):
lnl = LearningWithNoisyLabels(
seed=seed,
prune_count_method=prune_count_method,
)
inm = compute_inv_noise_matrix(
data["py"],
data["noise_matrix"],
data["ps"],
)
# Learn with noisy labels with inverse noise matrix given
lnl.fit(data['X_train'], data['s'], inverse_noise_matrix=inm)
score_inm = lnl.score(data['X_test'], data['y_test'])
# Learn with noisy labels and estimate the inv noise matrix.
lnl2 = LearningWithNoisyLabels(
seed=seed,
prune_count_method=prune_count_method,
)
lnl2.fit(
data['X_train'],
data['s'],
)
score = lnl2.score(data['X_test'], data['y_test'])
if used_by_another_test:
return score, score_inm
else:
assert (score < score_inm + 1e-4)
def test_clf_fit_nm_inm(sparse):
data = SPARSE_DATA if sparse else DATA
lnl = LearningWithNoisyLabels(seed=SEED)
nm = data['noise_matrix']
inm = compute_inv_noise_matrix(
data["py"],
nm,
data["ps"],
)
lnl.fit(
X=data['X_train'],
s=data['s'],
noise_matrix=nm,
inverse_noise_matrix=inm,
)
score_nm_inm = lnl.score(data['X_test'], data['y_test'])
# Learn with noisy labels and estimate the inv noise matrix.
lnl2 = LearningWithNoisyLabels(seed=SEED)
lnl2.fit(
data['X_train'],
data['s'],
)
score = lnl2.score(data['X_test'], data['y_test'])
assert (score < score_nm_inm + 1e-4)
def test_fit_with_inm(
sparse,
seed=SEED,
used_by_another_test=False,
):
data = SPARSE_DATA if sparse else DATA
lnl = LearningWithNoisyLabels(seed=seed, )
inm = compute_inv_noise_matrix(
data["py"],
data["noise_matrix"],
data["ps"],
)
# Learn with noisy labels with inverse noise matrix given
lnl.fit(data['X_train'], data['s'], inverse_noise_matrix=inm)
score_inm = lnl.score(data['X_test'], data['y_test'])
# Learn with noisy labels and estimate the inv noise matrix.
lnl2 = LearningWithNoisyLabels(seed=seed, )
lnl2.fit(
data['X_train'],
data['s'],
)
score = lnl2.score(data['X_test'], data['y_test'])
if used_by_another_test:
return score, score_inm
else:
assert (score < score_inm + 1e-4)
def test_fit_psx():
from cleanlab.latent_estimation import estimate_cv_predicted_probabilities
lnl = LearningWithNoisyLabels()
psx = estimate_cv_predicted_probabilities(
X=data['X_train'],
labels=data['y_train'],
)
lnl.fit(X=data['X_train'], s=data['y_train'], psx=psx)
score_with_psx = lnl.score(data['X_test'], data['y_test'])
lnl = LearningWithNoisyLabels()
lnl.fit(
X=data['X_train'],
s=data['y_train'],
)
score_no_psx = lnl.score(data['X_test'], data['y_test'])
assert (abs(score_with_psx - score_no_psx) < 1e-6)
def test_rp():
rp = LearningWithNoisyLabels(clf=LogisticRegression(
multi_class='auto', solver='lbfgs', random_state=seed))
rp.fit(data["X_train"], data["s"])
score = rp.score(data["X_test"], data["y_test"])
print(score)
# Check that this runs without error.
assert (True)
def test_fit_with_nm(
seed=0,
used_by_another_test=False,
):
lnl = LearningWithNoisyLabels(seed=seed, )
nm = data['noise_matrix']
# Learn with noisy labels with noise matrix given
lnl.fit(data['X_train'], data['s'], noise_matrix=nm)
score_nm = lnl.score(data['X_test'], data['y_test'])
# Learn with noisy labels and estimate the noise matrix.
lnl2 = LearningWithNoisyLabels(seed=seed, )
lnl2.fit(
data['X_train'],
data['s'],
)
score = lnl2.score(data['X_test'], data['y_test'])
if used_by_another_test:
return score, score_nm
else:
assert (score < score_nm + 1e-4)
def test_no_score():
class Struct():
def fit(self):
pass
def predict_proba(self):
pass
def predict(self, X):
return data['y_test']
lnl = LearningWithNoisyLabels(clf=Struct())
score = lnl.score(data['X_test'], data['y_test'])
assert (abs(score - 1) < 1e-6)
def test_score():
phrase = 'cleanlab is dope'
class Struct():
def fit(self):
pass
def predict_proba(self):
pass
def predict(self):
pass
def score(self, X, y):
return phrase
lnl = LearningWithNoisyLabels(clf=Struct())
score = lnl.score(data['X_test'], data['y_test'])
assert (score == phrase)
def train_without_noisy_labels(X_train, y_train, X_test, y_test, clf=None):
if clf is None:
model = baseclf(**params)
clf = LearningWithNoisyLabels(clf=model, seed=seed, n_jobs=cpu_count())
clf.fit(X_train, y_train)
return clf.score(X_test, y_test)