def test_select_proportional_to_weight(self):
# Tests that multinomial_wo_replacement selects elements, on average,
# proportional to the their probabilities
th_rng = RandomStreams(12345)
p = tensor.fmatrix()
n = tensor.iscalar()
m = th_rng.multinomial_wo_replacement(pvals=p, n=n)
f = function([p, n], m, allow_input_downcast=True)
n_elements = 100
n_selected = 10
mean_rtol = 0.0005
np.random.seed(12345)
pvals = np.random.randint(1, 100,
(1, n_elements)).astype(config.floatX)
pvals /= pvals.sum(1)
avg_pvals = np.zeros((n_elements, ), dtype=config.floatX)
for rep in range(10000):
res = f(pvals, n_selected)
res = np.squeeze(res)
avg_pvals[res] += 1
avg_pvals /= avg_pvals.sum()
avg_diff = np.mean(abs(avg_pvals - pvals))
assert avg_diff < mean_rtol
def test_undefined_grad_opt():
# Make sure that undefined grad get removed in optimized graph.
random = RandomStreams(np.random.randint(1, 2147462579))
pvals = aesara.shared(np.random.rand(10, 20).astype(aesara.config.floatX))
pvals = pvals / pvals.sum(axis=1)
pvals = gradient.zero_grad(pvals)
samples = random.multinomial(pvals=pvals, n=1)
samples = aesara.tensor.cast(samples, pvals.dtype)
samples = gradient.zero_grad(samples)
cost = aesara.tensor.sum(samples + pvals)
grad = aesara.tensor.grad(cost, samples)
f = aesara.function([], grad)
aesara.printing.debugprint(f)
assert not any([
isinstance(node.op, gradient.UndefinedGrad)
for node in f.maker.fgraph.apply_nodes
])
def test_fail_select_alot(self):
# Tests that multinomial_wo_replacement fails when asked to sample more
# elements than the actual number of elements
th_rng = RandomStreams(12345)
p = tensor.fmatrix()
n = tensor.iscalar()
m = th_rng.multinomial_wo_replacement(pvals=p, n=n)
f = function([p, n], m, allow_input_downcast=True)
n_elements = 100
n_selected = 200
np.random.seed(12345)
pvals = np.random.randint(1, 100,
(1, n_elements)).astype(config.floatX)
pvals /= pvals.sum(1)
with pytest.raises(ValueError):
f(pvals, n_selected)
def test_select_distinct(self):
# Tests that multinomial_wo_replacement always selects distinct elements
th_rng = RandomStreams(12345)
p = tensor.fmatrix()
n = tensor.iscalar()
m = th_rng.multinomial_wo_replacement(pvals=p, n=n)
f = function([p, n], m, allow_input_downcast=True)
n_elements = 1000
all_indices = range(n_elements)
np.random.seed(12345)
for i in [5, 10, 50, 100, 500, n_elements]:
pvals = np.random.randint(1, 100,
(1, n_elements)).astype(config.floatX)
pvals /= pvals.sum(1)
res = f(pvals, i)
res = np.squeeze(res)
assert len(res) == i
assert np.all(np.in1d(np.unique(res), all_indices)), res