def test_unbatched(self):
W1 = np.array(
[1, -2, 3, 6, 3, -2, 1, 2, 5, 3, 0.5, 1, 1, 1, 1, 1, 1, 1])
T1 = data_dependent_threshhold(W1, fdr=0.2)
expected = np.abs(W1).min()
self.assertTrue(
T1 == expected,
msg=
f"Incorrect data dependent threshhold: T1 should be 0, not {T1}",
)
W2 = np.array([-1, -2, -3])
T2 = data_dependent_threshhold(W2, fdr=0.3)
self.assertTrue(
T2 == np.inf,
msg=
f"Incorrect data dependent threshhold: T2 should be inf, not {T2}",
)
W3 = np.array([-5, -1, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
T3 = data_dependent_threshhold(W3, fdr=0.2)
self.assertTrue(
T3 == 5,
msg=
f"Incorrect data dependent threshhold: T3 should be 5, not {T3}",
)
def Z2selections(Z, groups, q, **kwargs):
# Calculate W statistics
W = kstats.combine_Z_stats(Z, groups, **kwargs)
# Calculate selections
T = kstats.data_dependent_threshhold(W=W, fdr=q)
selected_flags = (W >= T).astype("float32")
return selected_flags, W
def test_batched(self):
W1 = np.array([1] * 10)
W2 = np.array([-2, -1, 1, 2, 3, 4, 5, 6, 7, 8])
W3 = np.array([-1] * 10)
combined = np.stack([W1, W2, W3]).transpose()
Ts = data_dependent_threshhold(combined, fdr=0.2)
expected = np.array([1, 2, np.inf])
np.testing.assert_array_almost_equal(
Ts,
expected,
err_msg=
f"Incorrect data dependent threshhold (batched): Ts should be {expected}, not {Ts}",
)
def check_kstat_fit(
self,
fstat,
fstat_name,
fstat_kwargs={},
min_power=0.8,
max_l2norm=9,
seed=110,
group_features=False,
**sample_kwargs,
):
""" fstat should be a class instance inheriting from FeatureStatistic """
# Add defaults to sample kwargs
if "method" not in sample_kwargs:
sample_kwargs["method"] = "blockequi"
if "gamma" not in sample_kwargs:
sample_kwargs["gamma"] = 1
if "n" not in sample_kwargs:
sample_kwargs["n"] = 200
if "p" not in sample_kwargs:
sample_kwargs["p"] = 50
if "rho" not in sample_kwargs:
sample_kwargs["rho"] = 0.5
if "y_dist" not in sample_kwargs:
sample_kwargs["y_dist"] = "gaussian"
n = sample_kwargs["n"]
p = sample_kwargs["p"]
rho = sample_kwargs["rho"]
y_dist = sample_kwargs["y_dist"]
# Create data generating process
np.random.seed(seed)
dgprocess = dgp.DGP()
X, y, beta, _, corr_matrix = dgprocess.sample_data(**sample_kwargs)
# Create groups
if group_features:
groups = np.random.randint(1, p + 1, size=(p, ))
groups = utilities.preprocess_groups(groups)
else:
groups = np.arange(1, p + 1, 1)
# Create knockoffs
ksampler = knockpy.knockoffs.GaussianSampler(
X=X,
groups=groups,
Sigma=corr_matrix,
verbose=False,
S=(1 - rho) * np.eye(p),
)
Xk = ksampler.sample_knockoffs()
S = ksampler.fetch_S()
# Fit and extract coeffs/T
fstat.fit(
X,
Xk,
y,
groups=groups,
**fstat_kwargs,
)
W = fstat.W
T = data_dependent_threshhold(W, fdr=0.2)
# Test L2 norm
m = np.unique(groups).shape[0]
if m == p:
pair_W = W
else:
pair_W = kstats.combine_Z_stats(fstat.Z, antisym="cd")
l2norm = np.power(pair_W - np.abs(beta), 2)
l2norm = l2norm.mean()
self.assertTrue(
l2norm < max_l2norm,
msg=
f"{fstat_name} fits {y_dist} data very poorly (l2norm = {l2norm} btwn real {beta} / fitted {pair_W} coeffs)",
)
# Test power for non-grouped setting.
# (For group setting, power will be much lower.)
selections = (W >= T).astype("float32")
group_nnulls = utilities.fetch_group_nonnulls(beta, groups)
power = (
(group_nnulls != 0) * selections).sum() / np.sum(group_nnulls != 0)
fdp = ((group_nnulls == 0) * selections).sum() / max(
np.sum(selections), 1)
self.assertTrue(
power >= min_power,
msg=
f"Power {power} for {fstat_name} in equicor case (n={n},p={p},rho={rho}, y_dist {y_dist}, grouped={group_features}) should be > {min_power}. W stats are {W}, beta is {beta}",
)