def _fit(Xy, classes, kwargs):
X, y = Xy
model = MNB(**kwargs)
model.partial_fit(X, y, classes=classes)
return model
def test_basic_fit_predict_sparse(x_dtype, y_dtype, nlp_20news):
"""
Cupy Test
"""
X, y = nlp_20news
X = sparse_scipy_to_cp(X, x_dtype).astype(x_dtype)
y = y.astype(y_dtype)
# Priming it seems to lower the end-to-end runtime
model = MultinomialNB()
model.fit(X, y)
cp.cuda.Stream.null.synchronize()
with cp.prof.time_range(message="start", color_id=10):
model = MultinomialNB()
model.fit(X, y)
y_hat = model.predict(X)
y_hat = cp.asnumpy(y_hat)
y = cp.asnumpy(y)
assert accuracy_score(y, y_hat) >= 0.924
def test_partial_fit(x_dtype, y_dtype, nlp_20news):
chunk_size = 500
X, y = nlp_20news
X = sparse_scipy_to_cp(X, x_dtype).astype(x_dtype)
y = y.astype(y_dtype)
X = X.tocsr()
model = MultinomialNB()
classes = np.unique(y)
total_fit = 0
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)
total_fit += (upper - (i * chunk_size))
if upper == -1:
break
y_hat = model.predict(X)
y_hat = cp.asnumpy(y_hat)
y = cp.asnumpy(y)
assert accuracy_score(y, y_hat) >= 0.924
def test_basic_fit_predict_dense_numpy(x_dtype, y_dtype, nlp_20news):
"""
Cupy Test
"""
X, y = nlp_20news
X = sparse_scipy_to_cp(X, cp.float32)
y = y.astype(y_dtype)
X = X.tocsr()[0:500].todense()
y = y[:500]
model = MultinomialNB()
model.fit(np.ascontiguousarray(cp.asnumpy(X).astype(x_dtype)), y)
y_hat = model.predict(X)
y_hat = cp.asnumpy(y_hat)
y = cp.asnumpy(y)
accuracy_score(y, y_hat) >= 0.911
def test_predict_log_proba(x_dtype, y_dtype, nlp_20news):
X, y = nlp_20news
cu_X = sparse_scipy_to_cp(X, x_dtype).astype(x_dtype)
cu_y = y.astype(y_dtype)
cu_X = cu_X.tocsr()
y = y.get()
cuml_model = MultinomialNB()
sk_model = skNB()
cuml_model.fit(cu_X, cu_y)
sk_model.fit(X, y)
cuml_proba = cuml_model.predict_log_proba(cu_X).get()
sk_proba = sk_model.predict_log_proba(X)
assert_allclose(cuml_proba, sk_proba, atol=1e-2, rtol=1e-2)
def test_naive_bayes(nlp_20news):
X, y = nlp_20news
X = sparse_scipy_to_cp(X, cp.float32).astype(cp.float32)
y = y.astype(cp.int32)
with cupy_using_allocator(dummy_allocator):
model = MultinomialNB()
model.fit(X, y)
y_hat = model.predict(X)
y_hat = model.predict(X)
y_hat = model.predict_proba(X)
y_hat = model.predict_log_proba(X)
y_hat = model.score(X, y)
del y_hat
def test_score(x_dtype, y_dtype, nlp_20news):
X, y = nlp_20news
cu_X = sparse_scipy_to_cp(X, x_dtype).astype(x_dtype)
cu_y = y.astype(y_dtype)
cu_X = cu_X.tocsr()
y = y.get()
cuml_model = MultinomialNB()
sk_model = skNB()
cuml_model.fit(cu_X, cu_y)
sk_model.fit(X, y)
cuml_score = cuml_model.score(cu_X, cu_y)
sk_score = sk_model.score(X, y)
THRES = 1e-4
assert sk_score - THRES <= cuml_score <= sk_score + THRES
def test_sparse_integral_dtype_fails(x_dtype, y_dtype, nlp_20news):
X, y = nlp_20news
X = X.astype(x_dtype)
y = y.astype(y_dtype)
# Priming it seems to lower the end-to-end runtime
model = MultinomialNB()
with pytest.raises(ValueError):
model.fit(X, y)
X = X.astype(cp.float32)
model.fit(X, y)
X = X.astype(x_dtype)
with pytest.raises(ValueError):
model.predict(X)
def test_multinomial_basic_fit_predict_dense_numpy(x_dtype, y_dtype,
nlp_20news):
"""
Cupy Test
"""
X, y = nlp_20news
n_rows = 500
X = sparse_scipy_to_cp(X, cp.float32).tocsr()[:n_rows]
y = y[:n_rows].astype(y_dtype)
model = MultinomialNB()
model.fit(np.ascontiguousarray(cp.asnumpy(X.todense()).astype(x_dtype)), y)
y_hat = model.predict(X).get()
modelsk = skNB()
modelsk.fit(X.get(), y.get())
y_sk = model.predict(X.get())
assert_allclose(y_hat, y_sk)
