def test_log_pdf(self, dtype, mean, mean_isSamples, var, var_isSamples,
rv, rv_isSamples, num_samples):
from scipy.stats import norm
isSamples_any = any([mean_isSamples, var_isSamples, rv_isSamples])
rv_shape = rv.shape[1:] if rv_isSamples else rv.shape
n_dim = 1 + len(rv.shape) if isSamples_any and not rv_isSamples else len(rv.shape)
mean_np = numpy_array_reshape(mean, mean_isSamples, n_dim)
var_np = numpy_array_reshape(var, var_isSamples, n_dim)
rv_np = numpy_array_reshape(rv, rv_isSamples, n_dim)
log_pdf_np = norm.logpdf(rv_np, mean_np, np.sqrt(var_np))
normal = Normal.define_variable(shape=rv_shape, dtype=dtype).factor
mean_mx = mx.nd.array(mean, dtype=dtype)
if not mean_isSamples:
mean_mx = add_sample_dimension(mx.nd, mean_mx)
var_mx = mx.nd.array(var, dtype=dtype)
if not var_isSamples:
var_mx = add_sample_dimension(mx.nd, var_mx)
rv_mx = mx.nd.array(rv, dtype=dtype)
if not rv_isSamples:
rv_mx = add_sample_dimension(mx.nd, rv_mx)
variables = {normal.mean.uuid: mean_mx, normal.variance.uuid: var_mx, normal.random_variable.uuid: rv_mx}
log_pdf_rt = normal.log_pdf(F=mx.nd, variables=variables)
assert np.issubdtype(log_pdf_rt.dtype, dtype)
assert array_has_samples(mx.nd, log_pdf_rt) == isSamples_any
if isSamples_any:
assert get_num_samples(mx.nd, log_pdf_rt) == num_samples
if np.issubdtype(dtype, np.float64):
rtol, atol = 1e-7, 1e-10
else:
rtol, atol = 1e-4, 1e-5
assert np.allclose(log_pdf_np, log_pdf_rt.asnumpy(), rtol=rtol, atol=atol)
def test_draw_samples(self, dtype, mean, mean_isSamples, var,
var_isSamples, rv_shape, num_samples):
n_dim = 1 + len(rv_shape)
mean_np = numpy_array_reshape(mean, mean_isSamples, n_dim)
var_np = numpy_array_reshape(var, var_isSamples, n_dim)
rand = np.random.randn(num_samples, *rv_shape)
rv_samples_np = mean_np + rand * np.sqrt(var_np)
rand_gen = MockMXNetRandomGenerator(mx.nd.array(rand.flatten(), dtype=dtype))
normal = Normal.define_variable(shape=rv_shape, dtype=dtype,
rand_gen=rand_gen).factor
mean_mx = mx.nd.array(mean, dtype=dtype)
if not mean_isSamples:
mean_mx = add_sample_dimension(mx.nd, mean_mx)
var_mx = mx.nd.array(var, dtype=dtype)
if not var_isSamples:
var_mx = add_sample_dimension(mx.nd, var_mx)
variables = {normal.mean.uuid: mean_mx, normal.variance.uuid: var_mx}
rv_samples_rt = normal.draw_samples(
F=mx.nd, variables=variables, num_samples=num_samples)
assert np.issubdtype(rv_samples_rt.dtype, dtype)
assert array_has_samples(mx.nd, rv_samples_rt)
assert get_num_samples(mx.nd, rv_samples_rt) == num_samples
if np.issubdtype(dtype, np.float64):
rtol, atol = 1e-7, 1e-10
else:
rtol, atol = 1e-4, 1e-5
assert np.allclose(rv_samples_np, rv_samples_rt.asnumpy(), rtol=rtol, atol=atol)
def test_draw_samples_non_mock(self, plot=False):
# Also make sure the non-mock sampler works
dtype = np.float32
num_samples = 100000
mean = np.array([0.5])
variance = np.array([2])
rv_shape = (1,)
mean_mx = add_sample_dimension(mx.nd, mx.nd.array(mean, dtype=dtype))
variance_mx = add_sample_dimension(mx.nd, mx.nd.array(variance, dtype=dtype))
rand_gen = None
var = Normal.define_variable(shape=rv_shape, rand_gen=rand_gen, dtype=dtype).factor
variables = {var.mean.uuid: mean_mx, var.variance.uuid: variance_mx}
rv_samples_rt = var.draw_samples(F=mx.nd, variables=variables, num_samples=num_samples)
assert array_has_samples(mx.nd, rv_samples_rt)
assert get_num_samples(mx.nd, rv_samples_rt) == num_samples
assert rv_samples_rt.dtype == dtype
from scipy.stats import norm
if plot:
plot_univariate(samples=rv_samples_rt, dist=norm, loc=mean[0], scale=np.sqrt(variance[0]))
mean_est, scale_est = norm.fit(rv_samples_rt.asnumpy().ravel())
mean_tol = 1e-1
variance_tol = 1e-1
assert np.abs(mean[0] - mean_est) < mean_tol
assert np.abs(variance[0] - scale_est ** 2) < variance_tol
def test_with_samples(self):
from mxfusion.common import config
config.DEFAULT_DTYPE = 'float64'
dtype = 'float64'
D, X, Y, noise_var, lengthscale, variance = self.gen_data()
m = Model()
m.N = Variable()
m.X = Normal.define_variable(mean=0, variance=1, shape=(m.N, 3))
m.noise_var = Variable(transformation=PositiveTransformation(),
initial_value=mx.nd.array(noise_var,
dtype=dtype))
kernel = RBF(input_dim=3,
ARD=True,
variance=mx.nd.array(variance, dtype=dtype),
lengthscale=mx.nd.array(lengthscale, dtype=dtype),
dtype=dtype)
m.Y = GPRegression.define_variable(X=m.X,
kernel=kernel,
noise_var=m.noise_var,
shape=(m.N, D))
q = create_Gaussian_meanfield(model=m, observed=[m.Y])
infr = GradBasedInference(
inference_algorithm=StochasticVariationalInference(
model=m, posterior=q, num_samples=10, observed=[m.Y]))
infr.run(Y=mx.nd.array(Y, dtype='float64'),
max_iter=2,
learning_rate=0.1,
verbose=True)
infr2 = Inference(
ForwardSamplingAlgorithm(model=m, observed=[m.X], num_samples=5))
infr2.run(X=mx.nd.array(X, dtype='float64'))
infr_pred = TransferInference(ModulePredictionAlgorithm(
model=m, observed=[m.X], target_variables=[m.Y]),
infr_params=infr.params)
xt = np.random.rand(13, 3)
res = infr_pred.run(X=mx.nd.array(xt, dtype=dtype))[0]
gp = m.Y.factor
gp.attach_prediction_algorithms(
targets=gp.output_names,
conditionals=gp.input_names,
algorithm=GPRegressionSamplingPrediction(gp._module_graph,
gp._extra_graphs[0],
[gp._module_graph.X]),
alg_name='gp_predict')
gp.gp_predict.diagonal_variance = False
gp.gp_predict.jitter = 1e-6
infr_pred2 = TransferInference(ModulePredictionAlgorithm(
model=m, observed=[m.X], target_variables=[m.Y]),
infr_params=infr.params)
xt = np.random.rand(13, 3)
res = infr_pred2.run(X=mx.nd.array(xt, dtype=dtype))[0]
def test_change_default_dtype(self):
from mxfusion.common import config
config.DEFAULT_DTYPE = 'float64'
np.random.seed(0)
mean_groundtruth = 3.
variance_groundtruth = 5.
N = 100
data = np.random.randn(N)*np.sqrt(variance_groundtruth) + mean_groundtruth
m = Model()
m.mu = Variable()
m.s = Variable(transformation=PositiveTransformation())
m.Y = Normal.define_variable(mean=m.mu, variance=m.s, shape=(100,))
infr = GradBasedInference(inference_algorithm=MAP(model=m, observed=[m.Y]))
infr.run(Y=mx.nd.array(data, dtype='float64'), learning_rate=0.1, max_iters=2)
config.DEFAULT_DTYPE = 'float32'