def test_data_carving_logistic(n=500,
p=300,
s=5,
sigma=5,
rho=0.05,
snr=4.,
split_frac=0.8,
ndraw=8000,
burnin=2000,
df=np.inf,
coverage=0.90,
compute_intervals=True,
nsim=None,
use_full_cov=False):
counter = 0
return_value = []
while True:
counter += 1
X, y, beta, active, sigma = instance(n=n,
p=p,
s=s,
sigma=sigma,
rho=rho,
snr=snr,
df=df)
mu = X.dot(beta)
prob = np.exp(mu) / (1 + np.exp(mu))
X = np.hstack([np.ones((n,1)), X])
z = np.random.binomial(1, prob)
active = np.array(active)
active += 1
s += 1
active = [0] + list(active)
idx = np.arange(n)
np.random.shuffle(idx)
stage_one = idx[:int(n*split_frac)]
n1 = len(stage_one)
lam_theor = 1.0 * np.ones(p+1)
lam_theor[0] = 0.
DC = data_carving.logistic(X, z, feature_weights=lam_theor,
stage_one=stage_one)
DC.fit()
if len(DC.active) < n - int(n*split_frac):
DS = data_splitting.logistic(X, z, feature_weights=lam_theor,
stage_one=stage_one)
DS.fit(use_full_cov=use_full_cov)
data_split = True
else:
print('not enough data for data splitting second stage')
print(DC.active)
data_split = False
if set(range(s)).issubset(DC.active):
carve = []
split = []
for var in DC.active:
carve.append(DC.hypothesis_test(var, burnin=burnin, ndraw=ndraw))
if data_split:
split.append(DS.hypothesis_test(var))
else:
split.append(np.random.sample())
Xa = X[:,DC.active]
split_coverage = np.nan
carve_coverage = np.nan
TP = s
FP = DC.active.shape[0] - TP
v = (carve[s:], split[s:], carve[:s], split[:s], counter, carve_coverage, split_coverage, TP, FP)
return_value.append(v)
break
else:
TP = len(set(DC.active).intersection(range(s)))
FP = DC.active.shape[0] - TP
v = (None, None, None, None, counter, np.nan, np.nan, TP, FP)
return_value.append(v)
return return_value
def test_data_carving_logistic(n=500,
p=300,
s=5,
sigma=5,
rho=0.05,
snr=4.,
split_frac=0.8,
ndraw=8000,
burnin=2000,
df=np.inf,
coverage=0.90,
compute_intervals=True,
nsim=None,
use_full_cov=False):
counter = 0
return_value = []
while True:
counter += 1
X, y, beta, active, sigma = instance(n=n,
p=p,
s=s,
sigma=sigma,
rho=rho,
snr=snr,
df=df)
mu = X.dot(beta)
prob = np.exp(mu) / (1 + np.exp(mu))
X = np.hstack([np.ones((n, 1)), X])
z = np.random.binomial(1, prob)
active = np.array(active)
active += 1
s += 1
active = [0] + list(active)
idx = np.arange(n)
np.random.shuffle(idx)
stage_one = idx[:int(n * split_frac)]
n1 = len(stage_one)
lam_theor = 1.0 * np.ones(p + 1)
lam_theor[0] = 0.
DC = data_carving.logistic(X,
z,
feature_weights=lam_theor,
stage_one=stage_one)
DC.fit()
if len(DC.active) < n - int(n * split_frac):
DS = data_splitting.logistic(X,
z,
feature_weights=lam_theor,
stage_one=stage_one)
DS.fit(use_full_cov=use_full_cov)
data_split = True
else:
print('not enough data for data splitting second stage')
print(DC.active)
data_split = False
if set(range(s)).issubset(DC.active):
carve = []
split = []
for var in DC.active:
carve.append(
DC.hypothesis_test(var, burnin=burnin, ndraw=ndraw))
if data_split:
split.append(DS.hypothesis_test(var))
else:
split.append(np.random.sample())
Xa = X[:, DC.active]
split_coverage = np.nan
carve_coverage = np.nan
TP = s
FP = DC.active.shape[0] - TP
v = (carve[s:], split[s:], carve[:s], split[:s], counter,
carve_coverage, split_coverage, TP, FP)
return_value.append(v)
break
else:
TP = len(set(DC.active).intersection(range(s)))
FP = DC.active.shape[0] - TP
v = (None, None, None, None, counter, np.nan, np.nan, TP, FP)
return_value.append(v)
return return_value
def test_data_carving_logistic(n=700,
p=300,
s=5,
rho=0.05,
signal=12.,
split_frac=0.8,
ndraw=8000,
burnin=2000,
df=np.inf,
compute_intervals=True,
use_full_cov=False,
return_only_screening=True):
X, y, beta, true_active, _ = logistic_instance(n=n,
p=p,
s=s,
rho=rho,
signal=signal,
equicorrelated=False)
mu = X.dot(beta)
prob = np.exp(mu) / (1 + np.exp(mu))
X = np.hstack([np.ones((n, 1)), X])
active = np.array(true_active)
active += 1
s += 1
active = [0] + list(active)
true_active = active
idx = np.arange(n)
np.random.shuffle(idx)
stage_one = idx[:int(n * split_frac)]
n1 = len(stage_one)
lam_theor = 1.0 * np.ones(p + 1)
lam_theor[0] = 0.
DC = data_carving.logistic(X,
y,
feature_weights=lam_theor,
stage_one=stage_one)
DC.fit()
if len(DC.active) < n - int(n * split_frac):
DS = data_splitting.logistic(X,
y,
feature_weights=lam_theor,
stage_one=stage_one)
DS.fit(use_full_cov=True)
data_split = True
else:
print('not enough data for data splitting second stage')
print(DC.active)
data_split = False
print(true_active, DC.active)
if set(true_active).issubset(DC.active):
carve = []
split = []
for var in DC.active:
carve.append(DC.hypothesis_test(var, burnin=burnin, ndraw=ndraw))
if data_split:
split.append(DS.hypothesis_test(var))
else:
split.append(np.random.sample())
Xa = X[:, DC.active]
active = np.zeros(p + 1, np.bool)
active[true_active] = 1
v = (carve, split, active)
return v