def test_point_density(scale, dist_source):
scale_mid = scale.low + scale.width / 2
rv = logistic(loc=scale_mid, scale=scale.width / 30)
xs = scale.denormalize_points(constants.target_xs)
orig_densities = rv.pdf(xs)
orig_cdfs = rv.cdf(xs)
orig_pairs = [{
"x": x,
"density": density
} for (x, density) in zip(xs, orig_densities)]
direct_dist = PointDensity.from_pairs(orig_pairs, scale)
if dist_source == "direct":
dist = direct_dist
elif dist_source == "from_pairs":
orig_pairs = [{
"x": x,
"density": density
} for (x, density) in zip(xs, orig_densities)]
dist = PointDensity.from_pairs(orig_pairs, scale)
elif dist_source == "to_arrays":
_xs, _density = direct_dist.to_arrays()
pairs = [{"x": x, "density": d} for x, d in zip(_xs, _density)]
dist = PointDensity.from_pairs(pairs, scale)
elif dist_source == "to_arrays/2":
_xs, _density = direct_dist.to_arrays(
num_xs=int(constants.point_density_default_num_points / 2),
add_endpoints=True,
)
pairs = [{"x": x, "density": d} for x, d in zip(_xs, _density)]
dist = PointDensity.from_pairs(pairs, scale)
elif dist_source == "structured":
dist = PointDensity.structure(direct_dist.destructure())
elif dist_source == "denormalized":
dist = direct_dist.normalize().denormalize(scale)
elif dist_source == "from_conditions":
cond = CrossEntropyCondition(p_dist=direct_dist)
dist = PointDensity.from_conditions([cond], scale=scale)
# PDF
dist_densities = np.array([float(dist.pdf(x)) for x in xs])
if dist_source == "to_arrays/2":
assert dist_densities == pytest.approx(orig_densities, abs=0.08)
else:
assert dist_densities == pytest.approx(orig_densities, abs=0.01)
# CDF
dist_cdfs = np.array([float(dist.cdf(x)) for x in xs])
assert dist_cdfs == pytest.approx(orig_cdfs, abs=0.06)
# PPF
MIN_CHECK_DENSITY = 1e-3
check_idxs = [
i for i in range(constants.point_density_default_num_points)
if orig_densities[i] > MIN_CHECK_DENSITY
]
dist_ppfs = np.array([float(dist.ppf(c)) for c in orig_cdfs[check_idxs]])
assert dist_ppfs == pytest.approx(xs[check_idxs], rel=0.25)
def test_zero_log_issue():
"""
Regression test for a bug where
1. distribution is specified which has 0 density in some bins, and
2. a condition or method that uses self.normed_log_densities or similar is called
"""
pairs = [
{
"x": 0,
"density": 1
},
{
"x": 0.2,
"density": 0
},
{
"x": 0.4,
"density": 0
},
{
"x": 0.6,
"density": 1
},
{
"x": 1,
"density": 1
},
]
dist = PointDensity.from_pairs(pairs, scale=Scale(0, 1))
sc = SmoothnessCondition()
fit = sc.describe_fit(dist)
assert not np.isnan(fit["loss"])
def test_density_frompairs():
pairs = [
{
"x": 0,
"density": 1
},
{
"x": 0.2,
"density": 1
},
{
"x": 0.4,
"density": 1
},
{
"x": 0.6,
"density": 1
},
{
"x": 1,
"density": 1
},
]
dist = PointDensity.from_pairs(pairs, scale=Scale(0, 1))
for condition in dist.percentiles():
assert condition.max == pytest.approx(condition.p, abs=0.01)
def test_mean(scale: Scale):
true_mean = scale.low + scale.width / 2
rv = norm(loc=true_mean, scale=scale.width / 10)
xs = constants.target_xs
pairs = [{
"x": x,
"density": rv.pdf(x)
} for x in scale.denormalize_points(xs)]
pd_norm = PointDensity.from_pairs(pairs, scale)
calculated_mean = float(pd_norm.mean())
assert true_mean == pytest.approx(calculated_mean, rel=1e-3, abs=1e-3)
def point_density_from_scale(scale: Scale):
scale_mid = scale.low + scale.width / 2
rv = logistic(loc=scale_mid, scale=scale.width / 30)
xs = scale.denormalize_points(constants.target_xs)
densities = rv.pdf(xs)
pairs = [{
"x": x,
"density": density
} for (x, density) in zip(xs, densities)]
return PointDensity.from_pairs(pairs, scale)