def test_scaling(
snr=15,
s=5,
n=200,
p=20,
rho=0.1,
burnin=20000,
ndraw=30000,
scale=0.9,
nsim=None, # needed for decorator
frac=0.5
): # 0.9 has roughly same screening probability as 50% data splitting, i.e. around 10%
randomizer = randomization.laplace((p, ), scale=scale)
X, y, beta, _ = generate_data(n=n, p=p, s=s, rho=rho, snr=snr)
nonzero = np.where(beta)[0]
lam_frac = 1.
loss = rr.glm.logistic(X, y)
epsilon = 1. / np.sqrt(n)
lam = lam_frac * np.mean(
np.fabs(np.dot(X.T, np.random.binomial(1, 1. / 2, (n, 10000)))).max(0))
W = np.ones(p) * lam
penalty = rr.group_lasso(np.arange(p),
weights=dict(zip(np.arange(p), W)),
lagrange=1.)
M_est = glm_group_lasso(loss, epsilon, penalty, randomizer)
mv = multiple_queries([M_est])
mv.solve()
active = M_est.selection_variable['variables']
nactive = active.sum()
if set(nonzero).issubset(np.nonzero(active)[0]):
pvalues = []
active_set = np.nonzero(active)[0]
inactive_selected = I = [
i for i in np.arange(active_set.shape[0])
if active_set[i] not in nonzero
]
active_selected = A = [
i for i in np.arange(active_set.shape[0])
if active_set[i] in nonzero
]
if not I:
return None
idx = I[0]
inactive = ~M_est.selection_variable['variables']
boot_target, target_observed = pairs_bootstrap_glm(loss,
active,
inactive=inactive)
if DEBUG:
sampler = lambda: np.random.choice(n, size=(n, ), replace=True)
print(boot_target(sampler())[-3:], 'boot target')
form_covariances = glm_nonparametric_bootstrap(n, n)
mv.setup_sampler(form_covariances)
# null saturated
def null_target(indices):
result = boot_target(indices)
return result[idx]
null_observed = np.zeros(1)
null_observed[0] = target_observed[idx]
target_sampler = mv.setup_target(null_target, null_observed)
#target_scaling = 5 * np.linalg.svd(target_sampler.target_transform[0][0])[1].max()**2# should have something do with noise scale too
print(target_sampler.crude_lipschitz(), 'crude')
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat,
test_stat(null_observed),
burnin=burnin,
ndraw=ndraw,
stepsize=.5 /
target_sampler.crude_lipschitz()) # twosided by default
pvalues.append(pval)
# true saturated
idx = A[0]
def active_target(indices):
result = boot_target(indices)
return result[idx]
active_observed = np.zeros(1)
active_observed[0] = target_observed[idx]
target_sampler = mv.setup_target(active_target, active_observed)
target_scaling = 5 * np.linalg.svd(
target_sampler.target_transform[0]
[0])[1].max()**2 # should have something do with noise scale too
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat,
test_stat(active_observed),
burnin=burnin,
ndraw=ndraw,
stepsize=.5 /
target_sampler.crude_lipschitz()) # twosided by default
pvalues.append(pval)
# null selected
idx = I[0]
def null_target(indices):
result = boot_target(indices)
return np.hstack([result[idx], result[nactive:]])
null_observed = np.zeros_like(null_target(range(n)))
null_observed[0] = target_observed[idx]
null_observed[1:] = target_observed[nactive:]
target_sampler = mv.setup_target(null_target,
null_observed) #, target_set=[0])
target_scaling = 5 * np.linalg.svd(
target_sampler.target_transform[0]
[0])[1].max()**2 # should have something do with noise scale too
print(target_sampler.crude_lipschitz(), 'crude')
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat,
test_stat(null_observed),
burnin=burnin,
ndraw=ndraw,
stepsize=.5 /
target_sampler.crude_lipschitz()) # twosided by default
pvalues.append(pval)
# true selected
idx = A[0]
def active_target(indices):
result = boot_target(indices)
return np.hstack([result[idx], result[nactive:]])
active_observed = np.zeros_like(active_target(range(n)))
active_observed[0] = target_observed[idx]
active_observed[1:] = target_observed[nactive:]
target_sampler = mv.setup_target(active_target,
active_observed) #, target_set=[0])
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat,
test_stat(active_observed),
burnin=burnin,
ndraw=ndraw,
stepsize=.5 /
target_sampler.crude_lipschitz()) # twosided by default
pvalues.append(pval)
# condition on opt variables
### NOT WORKING -- need to implement conditioning within M_estimator!!!
if False:
# null saturated
idx = I[0]
def null_target(indices):
result = boot_target(indices)
return result[idx]
null_observed = np.zeros(1)
null_observed[0] = target_observed[idx]
target_sampler = mv.setup_target(null_target, null_observed)
print(target_sampler.crude_lipschitz(), 'crude')
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat,
test_stat(null_observed),
burnin=burnin,
ndraw=ndraw,
stepsize=.5 /
target_sampler.crude_lipschitz()) # twosided by default
pvalues.append(pval)
# true saturated
idx = A[0]
def active_target(indices):
result = boot_target(indices)
return result[idx]
active_observed = np.zeros(1)
active_observed[0] = target_observed[idx]
sampler = lambda: np.random.choice(n, size=(n, ), replace=True)
target_sampler = mv.setup_target(active_target, active_observed)
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat,
test_stat(active_observed),
burnin=burnin,
ndraw=ndraw,
stepsize=.5 /
target_sampler.crude_lipschitz()) # twosided by default
pvalues.append(pval)
# true selected
# oracle p-value -- draws a new data set
X, y, beta, _ = generate_data(n=n, p=p, s=s, rho=rho, snr=snr)
X_E = X[:, active_set]
active_var = [False, True, False, True]
if statsmodels_available:
try:
model = sm.GLM(y, X_E, family=sm.families.Binomial())
model_results = model.fit()
pvalues.extend(
[model_results.pvalues[I[0]], model_results.pvalues[A[0]]])
active_var.extend([False, True])
except sm.tools.sm_exceptions.PerfectSeparationError:
pass
else:
pass
# data splitting-ish p-value -- draws a new data set of smaller size
# frac is presumed to be how much data was used in stage 1, we get (1-frac)*n for stage 2
# frac defaults to 0.5
Xs, ys, beta, _ = generate_data(n=n, p=p, s=s, rho=rho, snr=snr)
Xs = Xs[:int((1 - frac) * n)]
ys = ys[:int((1 - frac) * n)]
X_Es = Xs[:, active_set]
if statsmodels_available:
try:
model = sm.GLM(ys, X_Es, family=sm.families.Binomial())
model_results = model.fit()
pvalues.extend(
[model_results.pvalues[I[0]], model_results.pvalues[A[0]]])
active_var.extend([False, False])
except sm.tools.sm_exceptions.PerfectSeparationError:
pass
else:
pass
return pvalues, active_var
def test_logistic_saturated_active_coordinate():
s, n, p = 5, 200, 20
randomizer = randomization.laplace((p, ), scale=1.)
X, y, beta, _ = logistic_instance(n=n, p=p, s=s, rho=0.1, snr=14)
nonzero = np.where(beta)[0]
lam_frac = 1.
loss = rr.glm.logistic(X, y)
epsilon = 1.
lam = lam_frac * np.mean(
np.fabs(np.dot(X.T, np.random.binomial(1, 1. / 2, (n, 10000)))).max(0))
W = np.ones(p) * lam
penalty = rr.group_lasso(np.arange(p),
weights=dict(zip(np.arange(p), W)),
lagrange=1.)
print(lam)
# our randomization
M_est1 = glm_group_lasso(loss, epsilon, penalty, randomizer)
mv = multiple_queries([M_est1])
mv.solve()
active = M_est1.selection_variable['variables']
nactive = active.sum()
if set(nonzero).issubset(np.nonzero(active)[0]):
active_set = np.nonzero(active)[0]
inactive_selected = I = [
i for i in np.arange(active_set.shape[0])
if active_set[i] not in nonzero
]
active_selected = A = [
i for i in np.arange(active_set.shape[0])
if active_set[i] in nonzero
]
idx = A[0]
inactive = ~M_est1.selection_variable['variables']
boot_target, target_observed = pairs_bootstrap_glm(loss,
active,
inactive=inactive)
def active_target(indices):
result = boot_target(indices)
return result[idx]
active_observed = np.zeros(1)
active_observed[0] = target_observed[idx]
# the active_observed[1:] is only used as a
# starting point for chain -- could be 0
# active_observed[1:] = target_observed[nactive:]
form_covariances = glm_nonparametric_bootstrap(n, n)
mv.setup_sampler(form_covariances)
target_sampler = mv.setup_target(active_target, active_observed)
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat, test_stat(active_observed), burnin=10000,
ndraw=10000) # twosided by default
return pval, True
def test_fixedX(ndraw=10000, burnin=2000): # nsim needed for decorator
s, n, p = 5, 200, 20
randomizer = randomization.laplace((p, ), scale=1.)
X, Y, beta, nonzero, sigma = gaussian_instance(n=n,
p=p,
s=s,
rho=0.1,
snr=7)
lam_frac = 1.
lam = lam_frac * np.mean(
np.fabs(X.T.dot(np.random.standard_normal((n, 50000)))).max(0)) * sigma
W = np.ones(p) * lam
epsilon = 1. / np.sqrt(n)
penalty = rr.group_lasso(np.arange(p),
weights=dict(zip(np.arange(p), W)),
lagrange=1.)
M_est = fixedX_group_lasso(X, Y, epsilon, penalty, randomizer)
mv = multiple_queries([M_est])
mv.solve()
active = M_est.selection_variable['variables']
nactive = active.sum()
if set(nonzero).issubset(
np.nonzero(active)[0]) and active.sum() > len(nonzero):
pvalues = []
active_set = np.nonzero(active)[0]
inactive_selected = I = [
i for i in np.arange(active_set.shape[0])
if active_set[i] not in nonzero
]
active_selected = A = [
i for i in np.arange(active_set.shape[0])
if active_set[i] in nonzero
]
if not I:
return None
idx = I[0]
boot_target, target_observed = resid_bootstrap(M_est.loss, active)
X_active = X[:, active]
beta_hat = np.linalg.pinv(X_active).dot(Y)
resid_hat = Y - X_active.dot(beta_hat)
form_covariances = glm_nonparametric_bootstrap(n, n)
mv.setup_sampler(form_covariances)
# null saturated
def null_target(Y_star):
result = boot_target(Y_star)
return result[idx]
null_observed = np.zeros(1)
null_observed[0] = target_observed[idx]
target_sampler = mv.setup_target(null_target, null_observed)
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat, null_observed, burnin=burnin,
ndraw=ndraw) # twosided by default
pvalues.append(pval)
# null selected
def null_target(Y_star):
result = boot_target(Y_star)
return np.hstack([result[idx], result[nactive:]])
null_observed = np.zeros_like(null_target(
np.random.standard_normal(n)))
null_observed[0] = target_observed[idx]
null_observed[1:] = target_observed[nactive:]
target_sampler = mv.setup_target(null_target,
null_observed,
target_set=[0])
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat, null_observed, burnin=burnin,
ndraw=ndraw) # twosided by default
pvalues.append(pval)
# true saturated
idx = A[0]
def active_target(Y_star):
result = boot_target(Y_star)
return result[idx]
active_observed = np.zeros(1)
active_observed[0] = target_observed[idx]
sampler = lambda: np.random.choice(n, size=(n, ), replace=True)
target_sampler = mv.setup_target(active_target, active_observed)
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat, active_observed, burnin=burnin,
ndraw=ndraw) # twosided by default
pvalues.append(pval)
# true selected
def active_target(Y_star):
result = boot_target(Y_star)
return np.hstack([result[idx], result[nactive:]])
active_observed = np.zeros_like(
active_target(np.random.standard_normal(n)))
active_observed[0] = target_observed[idx]
active_observed[1:] = target_observed[nactive:]
target_sampler = mv.setup_target(active_target,
active_observed,
target_set=[0])
test_stat = lambda x: x[0]
pval = target_sampler.hypothesis_test(
test_stat, active_observed, burnin=burnin,
ndraw=ndraw) # twosided by default
pvalues.append(pval)
return pvalues, [False, False, True, True]
def test_threshold_score(ndraw=10000,
burnin=2000,
nsim=None): # nsim needed for decorator
s, n, p = 5, 200, 20
threshold = 0.5
X, y, beta, _ = logistic_instance(n=n, p=p, s=s, rho=0.1, signal=7)
nonzero = np.where(beta)[0]
lam_frac = 1.
loss = rr.glm.logistic(X, y)
active_bool = np.zeros(p, np.bool)
active_bool[range(3)] = 1
inactive_bool = ~active_bool
randomizer = randomization.laplace((inactive_bool.sum(), ), scale=0.5)
# threshold the score
thresh = glm_threshold_score(loss, threshold, randomizer, active_bool,
inactive_bool)
mv = multiple_queries([thresh])
mv.solve()
boundary = thresh.selection_variable['boundary_set']
new_active = np.nonzero(np.arange(3, 20)[boundary])[0]
active_set = np.array(sorted(set(range(3)).union(new_active)))
if set(nonzero).issubset(active_set):
full_active = np.zeros(p, np.bool)
full_active[active_set] = 1
nactive = active_set.shape[0]
inactive_selected = I = [
i for i in np.arange(active_set.shape[0])
if active_set[i] not in nonzero
]
if not I:
return None
inactive_indicators_mat = np.zeros((len(inactive_selected), nactive))
j = 0
for i in range(nactive):
if active_set[i] not in nonzero:
inactive_indicators_mat[j, i] = 1
j += 1
form_covariances = glm_nonparametric_bootstrap(n, n)
mv.setup_sampler(form_covariances)
boot_target, target_observed = pairs_bootstrap_glm(loss, full_active)
inactive_target = lambda indices: boot_target(indices)[
inactive_selected]
inactive_observed = target_observed[inactive_selected]
# param_cov = _parametric_cov_glm(loss, active_union)
target_sampler = mv.setup_target(inactive_target, inactive_observed)
test_stat = lambda x: np.linalg.norm(x)
pval = target_sampler.hypothesis_test(
test_stat,
np.linalg.norm(inactive_observed),
alternative='twosided',
ndraw=ndraw,
burnin=burnin)
print(pval)
return pval, False