def test_bad_size(self):
R = MRG_RandomStream(234)
for size in [
(0, 100),
(-1, 100),
(1, 0),
]:
with pytest.raises(ValueError):
R.uniform(size)
with pytest.raises(ValueError):
R.binomial(size)
with pytest.raises(ValueError):
R.multinomial(size, 1, [])
with pytest.raises(ValueError):
R.normal(size)
with pytest.raises(ValueError):
R.truncated_normal(size)
def test_undefined_grad_opt():
# Make sure that undefined grad get removed in optimized graph.
random = MRG_RandomStream(np.random.randint(1, 2147462579))
pvals = theano.shared(np.random.rand(10, 20).astype(theano.config.floatX))
pvals = pvals / pvals.sum(axis=1)
pvals = theano.gradient.zero_grad(pvals)
samples = random.multinomial(pvals=pvals, n=1)
samples = theano.tensor.cast(samples, pvals.dtype)
samples = theano.gradient.zero_grad(samples)
cost = theano.tensor.sum(samples + pvals)
grad = theano.tensor.grad(cost, samples)
f = theano.function([], grad)
assert not any([
isinstance(node.op, theano.gradient.UndefinedGrad)
for node in f.maker.fgraph.apply_nodes
])
def test_target_parameter():
srng = MRG_RandomStream()
pvals = np.array([[0.98, 0.01, 0.01], [0.01, 0.49, 0.50]])
def basic_target_parameter_test(x):
f = theano.function([], x)
assert isinstance(f(), np.ndarray)
basic_target_parameter_test(srng.uniform((3, 2), target="cpu"))
basic_target_parameter_test(srng.normal((3, 2), target="cpu"))
basic_target_parameter_test(srng.truncated_normal((3, 2), target="cpu"))
basic_target_parameter_test(srng.binomial((3, 2), target="cpu"))
basic_target_parameter_test(
srng.multinomial(pvals=pvals.astype("float32"), target="cpu"))
basic_target_parameter_test(
srng.choice(p=pvals.astype("float32"), replace=False, target="cpu"))
basic_target_parameter_test(
srng.multinomial_wo_replacement(pvals=pvals.astype("float32"),
target="cpu"))
def test_multinomial():
steps = 100
if (config.mode in ["DEBUG_MODE", "DebugMode", "FAST_COMPILE"]
or config.mode == "Mode" and config.linker in ["py"]):
sample_size = (49, 5)
else:
sample_size = (450, 6)
pvals = np.asarray(np.random.uniform(size=sample_size))
pvals = np.apply_along_axis(lambda row: row / np.sum(row), 1, pvals)
R = MRG_RandomStream(234)
# Note: we specify `nstreams` to avoid a warning.
m = R.multinomial(pvals=pvals, dtype=config.floatX, nstreams=30 * 256)
f = theano.function([], m)
f()
basic_multinomialtest(f,
steps,
sample_size,
pvals,
n_samples=1,
prefix="mrg ")
def test_multinomial_n_samples():
if (config.mode in ["DEBUG_MODE", "DebugMode", "FAST_COMPILE"]
or config.mode == "Mode" and config.linker in ["py"]):
sample_size = (49, 5)
else:
sample_size = (450, 6)
pvals = np.asarray(np.random.uniform(size=sample_size))
pvals = np.apply_along_axis(lambda row: row / np.sum(row), 1, pvals)
R = MRG_RandomStream(234)
for n_samples, steps in zip([5, 10, 100, 1000], [20, 10, 1, 1]):
m = R.multinomial(pvals=pvals,
n=n_samples,
dtype=config.floatX,
nstreams=30 * 256)
f = theano.function([], m)
basic_multinomialtest(f,
steps,
sample_size,
pvals,
n_samples,
prefix="mrg ")
sys.stdout.flush()
def test_undefined_grad():
srng = MRG_RandomStream(seed=1234)
# checking uniform distribution
low = tensor.scalar()
out = srng.uniform((), low=low)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, low)
high = tensor.scalar()
out = srng.uniform((), low=0, high=high)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, high)
out = srng.uniform((), low=low, high=high)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, (low, high))
# checking binomial distribution
prob = tensor.scalar()
out = srng.binomial((), p=prob)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, prob)
# checking multinomial distribution
prob1 = tensor.scalar()
prob2 = tensor.scalar()
p = [theano.tensor.as_tensor_variable([prob1, 0.5, 0.25])]
out = srng.multinomial(size=None, pvals=p, n=4)[0]
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(theano.tensor.sum(out), prob1)
p = [theano.tensor.as_tensor_variable([prob1, prob2])]
out = srng.multinomial(size=None, pvals=p, n=4)[0]
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(theano.tensor.sum(out), (prob1, prob2))
# checking choice
p = [theano.tensor.as_tensor_variable([prob1, prob2, 0.1, 0.2])]
out = srng.choice(a=None, size=1, p=p, replace=False)[0]
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out[0], (prob1, prob2))
p = [theano.tensor.as_tensor_variable([prob1, prob2])]
out = srng.choice(a=None, size=1, p=p, replace=False)[0]
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out[0], (prob1, prob2))
p = [theano.tensor.as_tensor_variable([prob1, 0.2, 0.3])]
out = srng.choice(a=None, size=1, p=p, replace=False)[0]
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out[0], prob1)
# checking normal distribution
avg = tensor.scalar()
out = srng.normal((), avg=avg)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, avg)
std = tensor.scalar()
out = srng.normal((), avg=0, std=std)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, std)
out = srng.normal((), avg=avg, std=std)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, (avg, std))
# checking truncated normal distribution
avg = tensor.scalar()
out = srng.truncated_normal((), avg=avg)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, avg)
std = tensor.scalar()
out = srng.truncated_normal((), avg=0, std=std)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, std)
out = srng.truncated_normal((), avg=avg, std=std)
with pytest.raises(theano.gradient.NullTypeGradError):
theano.grad(out, (avg, std))