def predict_proba(self, x: DNDarray) -> DNDarray:
"""
Adapted to HeAT from scikit-learn.
Return probability estimates for the test tensor x of the samples for each class in
the model. The columns correspond to the classes in sorted
order, as they appear in the attribute ``classes_``.
Parameters
----------
x : DNDarray
Input data. Shape = (n_samples, n_features).
"""
return ht.exp(self.predict_log_proba(x))
def test_exp(self):
elements = 10
tmp = torch.arange(elements,
dtype=torch.float64,
device=self.device.torch_device).exp()
comparison = ht.array(tmp)
# exponential of float32
float32_tensor = ht.arange(elements, dtype=ht.float32)
float32_exp = ht.exp(float32_tensor)
self.assertIsInstance(float32_exp, ht.DNDarray)
self.assertEqual(float32_exp.dtype, ht.float32)
self.assertTrue(ht.allclose(float32_exp,
comparison.astype(ht.float32)))
# exponential of float64
float64_tensor = ht.arange(elements, dtype=ht.float64)
float64_exp = ht.exp(float64_tensor)
self.assertIsInstance(float64_exp, ht.DNDarray)
self.assertEqual(float64_exp.dtype, ht.float64)
self.assertTrue(ht.allclose(float64_exp, comparison))
# exponential of ints, automatic conversion to intermediate floats
int32_tensor = ht.arange(elements, dtype=ht.int32)
int32_exp = ht.exp(int32_tensor)
self.assertIsInstance(int32_exp, ht.DNDarray)
self.assertEqual(int32_exp.dtype, ht.float32)
self.assertTrue(ht.allclose(int32_exp, ht.float32(comparison)))
# exponential of longs, automatic conversion to intermediate floats
int64_tensor = ht.arange(elements, dtype=ht.int64)
int64_exp = int64_tensor.exp()
self.assertIsInstance(int64_exp, ht.DNDarray)
self.assertEqual(int64_exp.dtype, ht.float64)
self.assertTrue(ht.allclose(int64_exp, comparison))
# check exceptions
with self.assertRaises(TypeError):
ht.exp([1, 2, 3])
with self.assertRaises(TypeError):
ht.exp("hello world")
# Tests with split
expected = torch.arange(10,
dtype=torch.float32,
device=self.device.torch_device).exp()
actual = ht.arange(10, split=0, dtype=ht.float32).exp()
self.assertEqual(actual.gshape, tuple(expected.shape))
self.assertEqual(actual.split, 0)
actual = actual.resplit_(None)
self.assertEqual(actual.lshape, expected.shape)
self.assertTrue(torch.equal(expected, actual.larray))
self.assertEqual(actual.dtype, ht.float32)
def test_exp(self):
elements = 10
comparison = torch.arange(elements, dtype=torch.float64).exp()
# exponential of float32
float32_tensor = ht.arange(elements, dtype=ht.float32)
float32_exp = ht.exp(float32_tensor)
self.assertIsInstance(float32_exp, ht.tensor)
self.assertEqual(float32_exp.dtype, ht.float32)
self.assertEqual(float32_exp.dtype, ht.float32)
in_range = (float32_exp._tensor__array - comparison.type(torch.float32)) < FLOAT_EPSILON
self.assertTrue(in_range.all())
# exponential of float64
float64_tensor = ht.arange(elements, dtype=ht.float64)
float64_exp = ht.exp(float64_tensor)
self.assertIsInstance(float64_exp, ht.tensor)
self.assertEqual(float64_exp.dtype, ht.float64)
self.assertEqual(float64_exp.dtype, ht.float64)
in_range = (float64_exp._tensor__array - comparison) < FLOAT_EPSILON
self.assertTrue(in_range.all())
# exponential of ints, automatic conversion to intermediate floats
int32_tensor = ht.arange(elements, dtype=ht.int32)
int32_exp = ht.exp(int32_tensor)
self.assertIsInstance(int32_exp, ht.tensor)
self.assertEqual(int32_exp.dtype, ht.float64)
self.assertEqual(int32_exp.dtype, ht.float64)
in_range = (int32_exp._tensor__array - comparison) < FLOAT_EPSILON
self.assertTrue(in_range.all())
# exponential of longs, automatic conversion to intermediate floats
int64_tensor = ht.arange(elements, dtype=ht.int64)
int64_exp = ht.exp(int64_tensor)
self.assertIsInstance(int64_exp, ht.tensor)
self.assertEqual(int64_exp.dtype, ht.float64)
self.assertEqual(int64_exp.dtype, ht.float64)
in_range = (int64_exp._tensor__array - comparison) < FLOAT_EPSILON
self.assertTrue(in_range.all())
# check exceptions
with self.assertRaises(TypeError):
ht.exp([1, 2, 3])
with self.assertRaises(TypeError):
ht.exp('hello world')
def predict_proba(self, X):
"""
Adapted to HeAT from scikit-learn.
Return probability estimates for the test tensor X.
Parameters
----------
X : ht.tensor of shape (n_samples, n_features)
Returns
-------
C : ht.tensor of shape (n_samples, n_classes)
Returns the probability of the samples for each class in
the model. The columns correspond to the classes in sorted
order, as they appear in the attribute `classes_`.
"""
return ht.exp(self.predict_log_proba(X))
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