def test_vars_view(self):
_, model, _ = models.multidimensional_model()
with model:
app = self.inference().approx
posterior = app.random(10)
x_sampled = app.view(posterior, 'x').eval()
assert x_sampled.shape == (10, ) + model['x'].dshape
def test_vars_view(self):
_, model, _ = models.multidimensional_model()
with model:
app = self.inference().approx
posterior = app.random(10)
x_sampled = app.view(posterior, 'x').eval()
assert x_sampled.shape == (10,) + model['x'].dshape
def test_approximate(self):
with models.multidimensional_model()[1]:
meth = ADVI()
fit(10, method=meth)
with pytest.raises(KeyError):
fit(10, method='undefined')
with pytest.raises(TypeError):
fit(10, method=1)
def test_combined(self):
with models.multidimensional_model()[1]:
self.assertRaises(ValueError,
fit,
10,
method='advi->fullrank_advi',
frac=1)
fit(10, method='advi->fullrank_advi', frac=.5)
def test_sampling(self):
with models.multidimensional_model()[1]:
full_rank = FullRankADVI()
approx = full_rank.fit(20)
trace0 = approx.sample_vp(10000)
histogram = Histogram(trace0)
trace1 = histogram.sample_vp(100000)
np.testing.assert_allclose(trace0['x'].mean(0), trace1['x'].mean(0), atol=0.01)
np.testing.assert_allclose(trace0['x'].var(0), trace1['x'].var(0), atol=0.01)
def test_sampling(self):
with models.multidimensional_model()[1]:
full_rank = FullRankADVI()
approx = full_rank.fit(20)
trace0 = approx.sample(10000)
approx = Empirical(trace0)
trace1 = approx.sample(100000)
np.testing.assert_allclose(trace0['x'].mean(0), trace1['x'].mean(0), atol=0.01)
np.testing.assert_allclose(trace0['x'].var(0), trace1['x'].var(0), atol=0.01)
def test_length_of_hist(self):
with models.multidimensional_model()[1]:
inf = self.inference()
assert len(inf.hist) == 0
inf.fit(10)
assert len(inf.hist) == 10
assert not np.isnan(inf.hist).any()
inf.fit(self.NITER, obj_optimizer=self.optimizer)
assert len(inf.hist) == self.NITER + 10
assert not np.isnan(inf.hist).any()
def test_length_of_hist(self):
with models.multidimensional_model()[1]:
inf = self.inference()
assert len(inf.hist) == 0
inf.fit(10)
assert len(inf.hist) == 10
assert not np.isnan(inf.hist).any()
inf.fit(self.NITER, obj_optimizer=self.optimizer)
assert len(inf.hist) == self.NITER + 10
assert not np.isnan(inf.hist).any()
def test_vars_view_dynamic_size(self):
_, model, _ = models.multidimensional_model()
with model:
app = self.inference().approx
i = tt.iscalar('i')
i.tag.test_value = 1
posterior = app.random(i)
x_sampled = app.view(posterior, 'x').eval({i: 10})
assert x_sampled.shape == (10,) + model['x'].dshape
x_sampled = app.view(posterior, 'x').eval({i: 1})
assert x_sampled.shape == (1,) + model['x'].dshape
def test_vars_view_dynamic_size(self):
_, model, _ = models.multidimensional_model()
with model:
app = self.inference().approx
i = tt.iscalar('i')
i.tag.test_value = 1
posterior = app.random(i)
x_sampled = app.view(posterior, 'x').eval({i: 10})
assert x_sampled.shape == (10, ) + model['x'].dshape
x_sampled = app.view(posterior, 'x').eval({i: 1})
assert x_sampled.shape == (1, ) + model['x'].dshape
def test_vars_view_dynamic_size_numpy(self):
_, model, _ = models.multidimensional_model()
with model:
app = self.inference().approx
i = tt.iscalar('i')
i.tag.test_value = 1
x_sampled = app.view(app.random_fn(10), 'x')
assert x_sampled.shape == (10, ) + model['x'].dshape
x_sampled = app.view(app.random_fn(1), 'x')
assert x_sampled.shape == (1, ) + model['x'].dshape
x_sampled = app.view(app.random_fn(), 'x')
assert x_sampled.shape == () + model['x'].dshape
def test_vars_view_dynamic_size_numpy(self):
_, model, _ = models.multidimensional_model()
with model:
app = self.inference().approx
i = tt.iscalar('i')
i.tag.test_value = 1
x_sampled = app.view(app.random_fn(10), 'x')
assert x_sampled.shape == (10,) + model['x'].dshape
x_sampled = app.view(app.random_fn(1), 'x')
assert x_sampled.shape == (1,) + model['x'].dshape
x_sampled = app.view(app.random_fn(), 'x')
assert x_sampled.shape == () + model['x'].dshape
def test_combined(self):
with models.multidimensional_model()[1]:
fit(10, method='advi->fullrank_advi', frac=.5)
def test_combined(self):
with models.multidimensional_model()[1]:
with pytest.raises(ValueError):
fit(10, method='advi->fullrank_advi', frac=1)
fit(10, method='advi->fullrank_advi', frac=.5)
def test_pickling(self):
with models.multidimensional_model()[1]:
inference = self.inference()
inference = pickle.loads(pickle.dumps(inference))
inference.fit(20)
def test_init_from_noize(self):
with models.multidimensional_model()[1]:
approx = Empirical.from_noise(100)
assert approx.histogram.eval().shape == (100, 6)
def test_from_advi(self):
with models.multidimensional_model()[1]:
advi = ADVI()
full_rank = FullRankADVI.from_advi(advi)
full_rank.fit(20)
def test_from_mean_field(self):
with models.multidimensional_model()[1]:
advi = ADVI()
full_rank = FullRankADVI.from_mean_field(advi.approx)
full_rank.fit(20)
def test_profile(self):
with models.multidimensional_model()[1]:
self.inference().run_profiling(10)
def test_profile(self):
with models.multidimensional_model()[1]:
self.inference().run_profiling(10)
def test_pickling(self):
with models.multidimensional_model()[1]:
inference = self.inference()
inference = pickle.loads(pickle.dumps(inference))
inference.fit(20)
def test_approximate(self):
with models.multidimensional_model()[1]:
fit(10, method='fullrank_advi')
def test_from_mean_field(self):
with models.multidimensional_model()[1]:
advi = ADVI()
full_rank = FullRankADVI.from_mean_field(advi.approx)
full_rank.fit(20)
def test_approximate(self):
with models.multidimensional_model()[1]:
meth = ADVI()
fit(10, method=meth)
self.assertRaises(KeyError, fit, 10, method='undefined')
self.assertRaises(TypeError, fit, 10, method=1)
def test_from_advi(self):
with models.multidimensional_model()[1]:
advi = ADVI()
full_rank = FullRankADVI.from_advi(advi)
full_rank.fit(20)
def test_init_from_noize(self):
with models.multidimensional_model()[1]:
histogram = Histogram.from_noise(100)
assert histogram.histogram.eval().shape == (100, 6)
