def __joint_log_likelihood(self, X):
"""
Adapted to HeAT from scikit-learn.
Calculates joint log-likelihood for n_samples to be assigned to each class.
Returns ht.DNDarray joint_log_likelihood(n_samples, n_classes).
"""
jll_size = self.classes_._DNDarray__array.numel()
jll_shape = (X.shape[0], jll_size)
joint_log_likelihood = ht.empty(jll_shape, dtype=X.dtype, split=X.split, device=X.device)
for i in range(jll_size):
jointi = ht.log(self.class_prior_[i])
n_ij = -0.5 * ht.sum(ht.log(2.0 * ht.pi * self.sigma_[i, :]))
n_ij -= 0.5 * ht.sum(((X - self.theta_[i, :]) ** 2) / (self.sigma_[i, :]), 1)
joint_log_likelihood[:, i] = jointi + n_ij
return joint_log_likelihood
def test_log2(self):
elements = 15
comparison = torch.arange(1, elements, dtype=torch.float64).log()
# logarithm of float32
float32_tensor = ht.arange(1, elements, dtype=ht.float32)
float32_log = ht.log(float32_tensor)
self.assertIsInstance(float32_log, ht.tensor)
self.assertEqual(float32_log.dtype, ht.float32)
self.assertEqual(float32_log.dtype, ht.float32)
in_range = (float32_log._tensor__array - comparison.type(torch.float32)) < FLOAT_EPSILON
self.assertTrue(in_range.all())
# logarithm of float64
float64_tensor = ht.arange(1, elements, dtype=ht.float64)
float64_log = ht.log(float64_tensor)
self.assertIsInstance(float64_log, ht.tensor)
self.assertEqual(float64_log.dtype, ht.float64)
self.assertEqual(float64_log.dtype, ht.float64)
in_range = (float64_log._tensor__array - comparison) < FLOAT_EPSILON
self.assertTrue(in_range.all())
# logarithm of ints, automatic conversion to intermediate floats
int32_tensor = ht.arange(1, elements, dtype=ht.int32)
int32_log = ht.log(int32_tensor)
self.assertIsInstance(int32_log, ht.tensor)
self.assertEqual(int32_log.dtype, ht.float64)
self.assertEqual(int32_log.dtype, ht.float64)
in_range = (int32_log._tensor__array - comparison) < FLOAT_EPSILON
self.assertTrue(in_range.all())
# logarithm of longs, automatic conversion to intermediate floats
int64_tensor = ht.arange(1, elements, dtype=ht.int64)
int64_log = ht.log(int64_tensor)
self.assertIsInstance(int64_log, ht.tensor)
self.assertEqual(int64_log.dtype, ht.float64)
self.assertEqual(int64_log.dtype, ht.float64)
in_range = (int64_log._tensor__array - comparison) < FLOAT_EPSILON
self.assertTrue(in_range.all())
# check exceptions
with self.assertRaises(TypeError):
ht.log([1, 2, 3])
with self.assertRaises(TypeError):
ht.log('hello world')
def test_log(self):
elements = 15
tmp = torch.arange(1,
elements,
dtype=torch.float64,
device=self.device.torch_device).log()
comparison = ht.array(tmp)
# logarithm of float32
float32_tensor = ht.arange(1, elements, dtype=ht.float32)
float32_log = ht.log(float32_tensor)
self.assertIsInstance(float32_log, ht.DNDarray)
self.assertEqual(float32_log.dtype, ht.float32)
self.assertEqual(float32_log.dtype, ht.float32)
self.assertTrue(ht.allclose(float32_log,
comparison.astype(ht.float32)))
# logarithm of float64
float64_tensor = ht.arange(1, elements, dtype=ht.float64)
float64_log = ht.log(float64_tensor)
self.assertIsInstance(float64_log, ht.DNDarray)
self.assertEqual(float64_log.dtype, ht.float64)
self.assertEqual(float64_log.dtype, ht.float64)
self.assertTrue(ht.allclose(float64_log, comparison))
# logarithm of ints, automatic conversion to intermediate floats
int32_tensor = ht.arange(1, elements, dtype=ht.int32)
int32_log = ht.log(int32_tensor)
self.assertIsInstance(int32_log, ht.DNDarray)
self.assertEqual(int32_log.dtype, ht.float64)
self.assertEqual(int32_log.dtype, ht.float64)
self.assertTrue(ht.allclose(int32_log, comparison))
# logarithm of longs, automatic conversion to intermediate floats
int64_tensor = ht.arange(1, elements, dtype=ht.int64)
int64_log = int64_tensor.log()
self.assertIsInstance(int64_log, ht.DNDarray)
self.assertEqual(int64_log.dtype, ht.float64)
self.assertEqual(int64_log.dtype, ht.float64)
self.assertTrue(ht.allclose(int64_log, comparison))
# check exceptions
with self.assertRaises(TypeError):
ht.log([1, 2, 3])
with self.assertRaises(TypeError):
ht.log("hello world")
def logsumexp(self,
a,
axis=None,
b=None,
keepdim=False,
return_sign=False):
"""
Adapted to HeAT from scikit-learn.
Compute the log of the sum of exponentials of input elements.
Parameters
----------
a : ht.tensor
Input array.
axis : None or int or tuple of ints, optional
Axis or axes over which the sum is taken. By default `axis` is None,
and all elements are summed.
keepdim : bool, optional
If this is set to True, the axes which are reduced are left in the
result as dimensions with size one. With this option, the result
will broadcast correctly against the original array.
b : ht.tensor, optional
Scaling factor for exp(`a`) must be of the same shape as `a` or
broadcastable to `a`. These values may be negative in order to
implement subtraction.
#return_sign : bool, optional
If this is set to True, the result will be a pair containing sign
information; if False, results that are negative will be returned
as NaN. Default is False (no sign information).
#TODO: returns NotImplementedYet error.
Returns
-------
res : ht.tensor
The result, ``np.log(np.sum(np.exp(a)))`` calculated in a numerically
more stable way. If `b` is given then ``np.log(np.sum(b*np.exp(a)))``
is returned.
#TODO sgn : ndarray NOT IMPLEMENTED YET
If return_sign is True, this will be an array of floating-point
numbers matching res and +1, 0, or -1 depending on the sign
of the result. If False, only one result is returned.
"""
if b is not None:
raise NotImplementedError("Not implemented for weighted logsumexp")
a_max = ht.max(a, axis=axis, keepdim=True)
# TODO: sanitize a_max / implement isfinite(): sanitation module, cf. #468
# if a_max.numdims > 0:
# a_max[~np.isfinite(a_max)] = 0
# elif not np.isfinite(a_max):
# a_max = 0
# TODO: reinstate after allowing b not None
# if b is not None:
# b = np.asarray(b)
# tmp = b * np.exp(a - a_max)
# else:
tmp = ht.exp(a - a_max)
s = ht.sum(tmp, axis=axis, keepdim=keepdim)
if return_sign:
raise NotImplementedError("Not implemented for return_sign")
# sgn = np.sign(s) # TODO: np.sign
# s *= sgn # /= makes more sense but we need zero -> zero
out = ht.log(s)
if not keepdim:
a_max = ht.squeeze(a_max, axis=axis)
out += a_max
# if return_sign: #TODO: np.sign
# return out, sgn
# else:
return out