def setUp(self):
session.init("test_cross_entropy")
self.sigmoid_loss = SigmoidBinaryCrossEntropyLoss()
self.y_list = [i % 2 for i in range(100)]
self.predict_list = [random.random() for i in range(100)]
self.y = session.parallelize(self.y_list, include_key=False, partition=16)
self.predict = session.parallelize(self.predict_list, include_key=False, partition=16)
class TestSigmoidBinaryCrossEntropyLoss(unittest.TestCase):
def setUp(self):
session.init("test_cross_entropy")
self.sigmoid_loss = SigmoidBinaryCrossEntropyLoss()
self.y_list = [i % 2 for i in range(100)]
self.predict_list = [random.random() for i in range(100)]
self.y = session.parallelize(self.y_list, include_key=False, partition=16)
self.predict = session.parallelize(self.predict_list, include_key=False, partition=16)
def test_predict(self):
for i in range(1, 10):
np_v = 1.0 / (1.0 + np.exp(-1.0 / i))
self.assertTrue(np.fabs(self.sigmoid_loss.predict(1.0 / i) - np_v) < consts.FLOAT_ZERO)
def test_compute_gradient(self):
for i in range(10):
pred = random.random()
y = i % 2
grad = pred - y
self.assertTrue(np.fabs(self.sigmoid_loss.compute_grad(y, pred) - grad) < consts.FLOAT_ZERO)
def test_compute_hess(self):
for i in range(10):
pred = random.random()
y = i % 2
hess = pred * (1 - pred)
self.assertTrue(np.fabs(self.sigmoid_loss.compute_hess(y, pred) - hess) < consts.FLOAT_ZERO)
def test_compute_loss(self):
sklearn_loss = metrics.log_loss(self.y_list, self.predict_list)
sigmoid_loss = self.sigmoid_loss.compute_loss(self.y, self.predict)
self.assertTrue(np.fabs(sigmoid_loss - sklearn_loss) < consts.FLOAT_ZERO)
def tearDown(self):
session.stop()
def setUp(self):
eggroll.init("test_cross_entropy")
self.sigmoid_loss = SigmoidBinaryCrossEntropyLoss()
self.y_list = [i % 2 for i in range(100)]
self.predict_list = [random.random() for i in range(100)]
self.y = eggroll.parallelize(self.y_list, include_key=False)
self.predict = eggroll.parallelize(self.predict_list,
include_key=False)
def set_loss(self, objective_param):
loss_type = objective_param.objective
params = objective_param.params
LOGGER.info("set objective, objective is {}".format(loss_type))
if self.task_type == consts.CLASSIFICATION:
if loss_type == "cross_entropy":
if self.num_classes == 2:
self.loss = SigmoidBinaryCrossEntropyLoss()
else:
self.loss = SoftmaxCrossEntropyLoss()
else:
raise NotImplementedError("objective %s not supported yet" %
(loss_type))
elif self.task_type == consts.REGRESSION:
if loss_type == "lse":
self.loss = LeastSquaredErrorLoss()
elif loss_type == "lae":
self.loss = LeastAbsoluteErrorLoss()
elif loss_type == "huber":
self.loss = HuberLoss(params[0])
elif loss_type == "fair":
self.loss = FairLoss(params[0])
elif loss_type == "tweedie":
self.loss = TweedieLoss(params[0])
elif loss_type == "log_cosh":
self.loss = LogCoshLoss()
else:
raise NotImplementedError("objective %s not supported yet" %
(loss_type))
else:
raise NotImplementedError("objective %s not supported yet" %
(loss_type))
def set_loss(self, loss_type):
LOGGER.info("set loss, loss type is {}".format(loss_type))
if self.task_type == "classification":
if loss_type == "cross_entropy":
if self.num_classes == 2:
self.loss = SigmoidBinaryCrossEntropyLoss()
else:
self.loss = SoftmaxCrossEntropyLoss()
else:
raise NotImplementedError("Loss type %s not supported yet" %
(self.loss_type))
else:
raise NotImplementedError("Loss type %s not supported yet" %
(self.loss_type))