def test_gaussian_parameters(priors, var_smoothing, nlp_20news):
x_dtype = cp.float32
y_dtype = cp.int32
nrows = 150
X, y = nlp_20news
X = sparse_scipy_to_cp(X[:nrows], x_dtype).todense()
y = y.astype(y_dtype)[:nrows]
if priors == 'balanced':
priors = cp.array([1 / 20] * 20)
elif priors == 'unbalanced':
priors = cp.linspace(0.01, 0.09, 20)
model = GaussianNB(priors=priors, var_smoothing=var_smoothing)
model_sk = skGNB(priors=priors.get() if priors is not None else None,
var_smoothing=var_smoothing)
model.fit(X, y)
model_sk.fit(X.get(), y.get())
y_hat = model.predict(X)
y_hat_sk = model_sk.predict(X.get())
y_hat = cp.asnumpy(y_hat)
y = cp.asnumpy(y)
assert_allclose(model.epsilon_.get(), model_sk.epsilon_, rtol=1e-4)
assert_array_equal(y_hat, y_hat_sk)
def test_gaussian_fit_predict(x_dtype, y_dtype, is_sparse, nlp_20news):
"""
Cupy Test
"""
X, y = nlp_20news
model = GaussianNB()
n_rows = 500
n_cols = int(2e5)
X = sparse_scipy_to_cp(X, x_dtype)
X = X.tocsr()[:n_rows, :n_cols]
if is_sparse:
y = y.astype(y_dtype)[:n_rows]
model.fit(X, y)
else:
X = X.todense()
y = y[:n_rows].astype(y_dtype)
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)
assert accuracy_score(y, y_hat) >= 0.99
def test_gaussian_basic():
# Data is just 6 separable points in the plane
X = cp.array([[-2, -1, -1], [-1, -1, -1], [-1, -2, -1], [1, 1, 1],
[1, 2, 1], [2, 1, 1]],
dtype=cp.float32)
y = cp.array([1, 1, 1, 2, 2, 2])
skclf = skGNB()
skclf.fit(X.get(), y.get())
clf = GaussianNB()
clf.fit(X, y)
assert_array_almost_equal(clf.theta_.get(), skclf.theta_, 6)
assert_array_almost_equal(clf.sigma_.get(), skclf.sigma_, 6)
y_pred = clf.predict(X)
y_pred_proba = clf.predict_proba(X)
y_pred_log_proba = clf.predict_log_proba(X)
y_pred_proba_sk = skclf.predict_proba(X.get())
y_pred_log_proba_sk = skclf.predict_log_proba(X.get())
assert_array_equal(y_pred.get(), y.get())
assert_array_almost_equal(y_pred_proba.get(), y_pred_proba_sk, 8)
assert_allclose(y_pred_log_proba.get(),
y_pred_log_proba_sk,
atol=1e-2,
rtol=1e-2)
def test_gaussian_partial_fit(nlp_20news):
chunk_size = 250
n_rows = 1500
x_dtype, y_dtype = cp.float32, cp.int32
X, y = nlp_20news
X = sparse_scipy_to_cp(X, x_dtype).tocsr()[:n_rows]
y = y.astype(y_dtype)[:n_rows]
model = GaussianNB()
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) >= 0.99
# Test whether label mismatch between target y and classes raises an Error
assert_raises(ValueError,
GaussianNB().partial_fit,
X,
y,
classes=cp.array([0, 1]))
# Raise because classes is required on first call of partial_fit
assert_raises(ValueError, GaussianNB().partial_fit, X, y)