def test_multinomial_vector(self):
random = RandomStreams(utt.fetch_seed())
n = tensor.lvector()
pvals = tensor.matrix()
out = random.multinomial(n=n, pvals=pvals)
assert out.ndim == 2
f = function([n, pvals], out)
n_val = [1, 2, 3]
pvals_val = [[0.1, 0.9], [0.2, 0.8], [0.3, 0.7]]
pvals_val = np.asarray(pvals_val, dtype=config.floatX)
seed_gen = np.random.RandomState(utt.fetch_seed())
numpy_rng = np.random.RandomState(int(seed_gen.randint(2**30)))
# Arguments of size (3,)
val0 = f(n_val, pvals_val)
numpy_val0 = np.asarray([
numpy_rng.multinomial(n=nv, pvals=pv)
for nv, pv in zip(n_val, pvals_val)
])
assert np.all(val0 == numpy_val0)
# arguments of size (2,)
val1 = f(n_val[:-1], pvals_val[:-1])
numpy_val1 = np.asarray([
numpy_rng.multinomial(n=nv, pvals=pv)
for nv, pv in zip(n_val[:-1], pvals_val[:-1])
])
assert np.all(val1 == numpy_val1)
# Specifying the size explicitly
g = function([n, pvals],
random.multinomial(n=n, pvals=pvals, size=(3, )))
val2 = g(n_val, pvals_val)
numpy_rng = np.random.RandomState(int(seed_gen.randint(2**30)))
numpy_val2 = np.asarray([
numpy_rng.multinomial(n=nv, pvals=pv)
for nv, pv in zip(n_val, pvals_val)
])
assert np.all(val2 == numpy_val2)
with pytest.raises(ValueError):
g(n_val[:-1], pvals_val[:-1])
def test_multinomial(self):
# Test that RandomStreams.multinomial generates the same results as numpy
# Check over two calls to see if the random state is correctly updated.
random = RandomStreams(utt.fetch_seed())
fn = function([],
random.multinomial((4, 4), 1, [0.1] * 10),
updates=random.updates())
fn_val0 = fn()
fn_val1 = fn()
rng_seed = np.random.RandomState(utt.fetch_seed()).randint(2**30)
rng = np.random.RandomState(int(rng_seed)) # int() is for 32bit
numpy_val0 = rng.multinomial(1, [0.1] * 10, size=(4, 4))
numpy_val1 = rng.multinomial(1, [0.1] * 10, size=(4, 4))
assert np.all(fn_val0 == numpy_val0)
assert np.all(fn_val1 == numpy_val1)
def test_default_shape(self):
random = RandomStreams(utt.fetch_seed())
f = function([], random.uniform())
g = function([], random.multinomial())
# seed_rng is generator for generating *seeds* for RandomStates
seed_rng = np.random.RandomState(utt.fetch_seed())
uniform_rng = np.random.RandomState(int(seed_rng.randint(2**30)))
multinomial_rng = np.random.RandomState(int(seed_rng.randint(2**30)))
val0 = f()
val1 = f()
numpy_val0 = uniform_rng.uniform()
numpy_val1 = uniform_rng.uniform()
assert np.allclose(val0, numpy_val0)
assert np.allclose(val1, numpy_val1)
for i in range(
10
): # every test has 50% chance of passing even with non-matching random states
val2 = g()
numpy_val2 = multinomial_rng.multinomial(n=1, pvals=[0.5, 0.5])
assert np.all(val2 == numpy_val2)