def test_bernoulli(x_dtype, y_dtype, is_sparse, nlp_20news):
X, y = nlp_20news
n_rows = 500
X = sparse_scipy_to_cp(X, x_dtype).astype(x_dtype)
y = y.astype(y_dtype)
X = X.tocsr()[:n_rows]
y = y[:n_rows]
if not is_sparse:
X = X.todense()
sk_model = skBNB()
cuml_model = BernoulliNB()
sk_model.fit(X.get(), y.get())
cuml_model.fit(X, y)
sk_score = sk_model.score(X.get(), y.get())
cuml_score = cuml_model.score(X, y)
cuml_proba = cuml_model.predict_log_proba(X).get()
sk_proba = sk_model.predict_log_proba(X.get())
THRES = 1e-3
assert_array_equal(sk_model.class_count_, cuml_model.class_count_.get())
assert_allclose(sk_model.class_log_prior_,
cuml_model.class_log_prior_.get(), 1e-6)
assert_allclose(cuml_proba, sk_proba, atol=1e-2, rtol=1e-2)
assert sk_score - THRES <= cuml_score <= sk_score + THRES
def test_bernoulli_partial_fit(x_dtype, y_dtype, nlp_20news):
chunk_size = 500
n_rows = 1500
X, y = nlp_20news
X = sparse_scipy_to_cp(X, x_dtype).astype(x_dtype)
y = y.astype(y_dtype)[:n_rows]
X = X.tocsr()[:n_rows]
model = BernoulliNB()
modelsk = skBNB()
classes = np.unique(y)
for i in range(math.ceil(X.shape[0] / chunk_size)):
upper = i * chunk_size + chunk_size
if upper > X.shape[0]:
upper = -1
if upper > 0:
x = X[i * chunk_size:upper]
y_c = y[i * chunk_size:upper]
else:
x = X[i * chunk_size:]
y_c = y[i * chunk_size:]
model.partial_fit(x, y_c, classes=classes)
modelsk.partial_fit(x.get(), y_c.get(), classes=classes.get())
if upper == -1:
break
y_hat = model.predict(X).get()
y_sk = modelsk.predict(X.get())
assert_allclose(y_hat, y_sk)
from sklearn.metrics import classification_report
from sklearn.naive_bayes import BernoulliNB as skBNB
from smlib.bayes.nb import BernoulliNB
X_train = np.array([[1, 1, 0], [1, 0, 0], [1, 1, 1], [0, 0, 0], [0, 0, 1]])
y_train = np.array([1, 0, 1, 0, 0])
X_test = np.array([
[1, 1, 0],
[0, 1, 0],
])
y_test = np.array([1, 0])
for classifier in [skBNB(), BernoulliNB()]:
classifier.fit(X_train, y_train)
print(classifier)
expected = y_test
predicted = classifier.predict(X_test)
print(classification_report(expected, predicted))
print('-' * 50)
X = np.random.randint(2, size=(6, 100))
Y = np.array([1, 2, 3, 4, 4, 5])
skbnb = skBNB()
skbnb.fit(X, Y)
print(skbnb.predict(X[2:3]))