def test_data_carving_coxph(n=400,
p=20,
split_frac=0.8,
lam_frac=1.2,
ndraw=8000,
burnin=2000,
df=np.inf,
compute_intervals=True,
return_only_screening=True):
X = np.random.standard_normal((n,p))
T = np.random.standard_exponential(n)
S = np.random.binomial(1, 0.5, size=(n,))
true_active = []
s = 0
active = np.array(true_active)
idx = np.arange(n)
np.random.shuffle(idx)
stage_one = idx[:int(n*split_frac)]
n1 = len(stage_one)
lam_theor = 10. * np.ones(p)
lam_theor[0] = 0.
DC = data_carving.coxph(X, T, S, feature_weights=lam_theor,
stage_one=stage_one)
DC.fit()
if len(DC.active) < n - int(n*split_frac):
DS = data_splitting.coxph(X, T, S, 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
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_like(DC.active, np.bool)
active[true_active] = 1
v = (carve, split, active)
return v
def test_data_carving_coxph(n=100,
p=20,
split_frac=0.8,
lam_frac=1.2,
ndraw=8000,
burnin=2000,
df=np.inf,
coverage=0.90,
compute_intervals=True,
nsim=None):
counter = 0
return_value = []
while True:
counter += 1
X = np.random.standard_normal((n, p))
T = np.random.standard_exponential(n)
S = np.random.binomial(1, 0.5, size=(n, ))
active = []
s = 0
active = np.array(active)
idx = np.arange(n)
np.random.shuffle(idx)
stage_one = idx[:int(n * split_frac)]
n1 = len(stage_one)
lam_theor = 10. * np.ones(p)
lam_theor[0] = 0.
DC = data_carving.coxph(X,
T,
S,
feature_weights=lam_theor,
stage_one=stage_one)
DC.fit()
if len(DC.active) < n - int(n * split_frac):
DS = data_splitting.coxph(X,
T,
S,
feature_weights=lam_theor,
stage_one=stage_one)
DS.fit()
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_coxph(n=100,
p=20,
split_frac=0.8,
lam_frac=1.2,
ndraw=8000,
burnin=2000,
df=np.inf,
coverage=0.90,
compute_intervals=True,
nsim=None):
counter = 0
return_value = []
while True:
counter += 1
X = np.random.standard_normal((n,p))
T = np.random.standard_exponential(n)
S = np.random.binomial(1, 0.5, size=(n,))
active = []
s = 0
active = np.array(active)
idx = np.arange(n)
np.random.shuffle(idx)
stage_one = idx[:int(n*split_frac)]
n1 = len(stage_one)
lam_theor = 10. * np.ones(p)
lam_theor[0] = 0.
DC = data_carving.coxph(X, T, S, feature_weights=lam_theor,
stage_one=stage_one)
DC.fit()
if len(DC.active) < n - int(n*split_frac):
DS = data_splitting.coxph(X, T, S, feature_weights=lam_theor,
stage_one=stage_one)
DS.fit()
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