def generate_X(self):
n, p, s, rho = self.n, self.p, self.s, self.rho
X = gaussian_instance(n=n, p=p, equicorrelated=False, rho=rho)[0]
X *= np.sqrt(n)
return X
def simulate(n=2000,
p=1000,
s=10,
signal=(0.5, 1),
sigma=2,
alpha=0.1,
B=4000):
# description of statistical problem
X, y, truth = gaussian_instance(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.5,
sigma=sigma,
signal=signal,
random_signs=True,
scale=False)[:3]
dispersion = sigma**2
S = X.T.dot(y)
covS = dispersion * X.T.dot(X)
smooth_sampler = normal_sampler(S, covS)
def meta_algorithm(X, XTXi, resid, sampler):
S = sampler(scale=0.) # deterministic with scale=0
ynew = X.dot(XTXi).dot(S) + resid # will be ok for n>p and non-degen X
G = lasso_glmnet(X, ynew, *[None] * 4)
select = G.select()
print(select)
return set(list(select[0]))
XTX = X.T.dot(X)
XTXi = np.linalg.inv(XTX)
resid = y - X.dot(XTXi.dot(X.T.dot(y)))
dispersion = np.linalg.norm(resid)**2 / (n - p)
selection_algorithm = functools.partial(meta_algorithm, X, XTXi, resid)
# run selection algorithm
return full_model_inference(X,
y,
truth,
selection_algorithm,
smooth_sampler,
success_params=(1, 1),
B=B,
fit_probability=keras_fit,
fit_args={
'epochs': 10,
'sizes': [100] * 5,
'dropout': 0.,
'activation': 'relu'
})
def generate_X(self):
(n, p, s, rho) = (self.n,
self.p,
self.s,
self.rho)
X_equi = gaussian_instance(n=n,
p=p,
equicorrelated=True,
rho=self.equicor_rho)[0]
X_AR = gaussian_instance(n=n,
p=p,
equicorrelated=False,
rho=rho)[0]
X = np.sqrt(self.AR_weight) * X_AR + np.sqrt(1 - self.AR_weight) * X_equi
X /= np.sqrt((X**2).mean(0))[None, :]
return X
def generate_X(self):
(n, p, s, rho) = (self.n,
self.p,
self.s,
self.rho)
X = gaussian_instance(n=n, p=p, equicorrelated=True, rho=rho, s=0)[0]
X /= np.sqrt((X**2).sum(0))[None, :]
X *= np.sqrt(n)
return X
def generate(n=200, p=100, s=10, signal=(0.5, 1), sigma=2, **ignored):
X, y, truth = gaussian_instance(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.5,
sigma=sigma,
signal=signal,
random_signs=True,
scale=False)[:3]
return X, y, truth
def simulate(n=200, p=100, s=10, signal=(0.5, 1), sigma=2, alpha=0.1):
# description of statistical problem
X, y, truth = gaussian_instance(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.5,
sigma=sigma,
signal=signal,
random_signs=True,
scale=False)[:3]
dispersion = sigma**2
S = X.T.dot(y)
covS = dispersion * X.T.dot(X)
splitting_sampler = split_sampler(X * y[:, None], covS)
def meta_algorithm(X, XTXi, resid, sampler):
S = sampler(scale=0.) # deterministic with scale=0
ynew = X.dot(XTXi).dot(S) + resid # will be ok for n>p and non-degen X
G = lasso_glmnet(X, ynew, *[None] * 4)
select = G.select()
return set(list(select[0]))
XTX = X.T.dot(X)
XTXi = np.linalg.inv(XTX)
resid = y - X.dot(XTXi.dot(X.T.dot(y)))
dispersion = np.linalg.norm(resid)**2 / (n - p)
selection_algorithm = functools.partial(meta_algorithm, X, XTXi, resid)
# run selection algorithm
return full_model_inference(X,
y,
truth,
selection_algorithm,
splitting_sampler,
success_params=(1, 1),
B=B,
fit_probability=probit_fit,
fit_args={'df': 20},
how_many=1)
def simulate(n=2000,
p=1000,
s=10,
signal=(0.5, 1),
sigma=2,
alpha=0.1,
B=4000):
# description of statistical problem
X, y, truth = generate(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.5,
sigma=sigma,
signal=signal,
random_signs=True,
scale=False)[:3]
# description of statistical problem
X, y, truth = gaussian_instance(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.5,
sigma=sigma,
signal=signal,
random_signs=True,
scale=False)[:3]
dispersion = sigma**2
S = X.T.dot(y)
covS = dispersion * X.T.dot(X)
smooth_sampler = normal_sampler(S, covS)
def meta_algorithm(X, XTXi, resid, lam, sampler):
p = XTX.shape[0]
success = np.zeros(p)
loss = rr.quadratic_loss((p, ), Q=XTX)
pen = rr.l1norm(p, lagrange=lam)
scale = 0.
noisy_S = sampler(scale=scale)
loss.quadratic = rr.identity_quadratic(0, 0, -noisy_S, 0)
problem = rr.simple_problem(loss, pen)
soln = problem.solve(max_its=100, tol=1.e-10)
success += soln != 0
return set(np.nonzero(success)[0])
XTX = X.T.dot(X)
XTXi = np.linalg.inv(XTX)
resid = y - X.dot(XTXi.dot(X.T.dot(y)))
dispersion = np.linalg.norm(resid)**2 / (n - p)
lam = 5. * np.sqrt(n)
selection_algorithm = functools.partial(meta_algorithm, X, XTXi, resid,
lam)
# run selection algorithm
print('SNR',
np.linalg.norm(X.dot(truth)) / np.linalg.norm(y - X.dot(truth)))
print('R2', 1 - np.linalg.norm(y - X.dot(truth))**2 / np.linalg.norm(y)**2)
return full_model_inference(X,
y,
truth,
selection_algorithm,
smooth_sampler,
success_params=(1, 1),
B=B,
fit_probability=keras_fit,
fit_args={
'epochs': 10,
'sizes': [100] * 5,
'dropout': 0.,
'activation': 'relu'
})
def simulate(n=1000, p=100, s=10, signal=(0.5, 1), sigma=2, alpha=0.1, B=2000):
# description of statistical problem
X, y, truth = gaussian_instance(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.5,
sigma=sigma,
signal=signal,
random_signs=True,
scale=False,
center=False)[:3]
dispersion = sigma**2
S = X.T.dot(y)
covS = dispersion * X.T.dot(X)
smooth_sampler = normal_sampler(S, covS)
idx = np.random.choice(np.arange(n), int(n / 2), replace=False)
def meta_algorithm(X, XTXi, resid, idx, sampler):
n, p = X.shape
S = sampler(scale=0.) # deterministic with scale=0
ynew = X.dot(XTXi).dot(S) + resid # will be ok for n>p and non-degen X
G = lasso_glmnet(X[idx], ynew[idx], *[None] * 4)
select = G.select()
return set(list(select[0]))
XTX = X.T.dot(X)
XTXi = np.linalg.inv(XTX)
resid = y - X.dot(XTXi.dot(X.T.dot(y)))
dispersion = np.linalg.norm(resid)**2 / (n - p)
selection_algorithm = functools.partial(meta_algorithm, X, XTXi, resid,
idx)
# run selection algorithm
df = full_model_inference(X,
y,
truth,
selection_algorithm,
smooth_sampler,
success_params=(1, 1),
B=B,
fit_probability=keras_fit,
fit_args={
'epochs': 20,
'sizes': [100] * 5,
'dropout': 0.,
'activation': 'relu'
})
if df is not None:
observed_set = list(df['variable'])
split_df = split_full_model_inference(X,
y,
idx,
dispersion,
truth,
observed_set,
alpha=alpha)
df = pd.merge(df, split_df, on='variable')
return df
def simulate(n=200,
p=100,
s=10,
signal=(0.5, 1),
sigma=2,
alpha=0.1,
seed=0,
B=3000):
# description of statistical problem
X, y, truth = gaussian_instance(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.5,
sigma=sigma,
signal=signal,
random_signs=True,
scale=False,
center=False)[:3]
dispersion = sigma**2
S = X.T.dot(y)
covS = dispersion * X.T.dot(X)
smooth_sampler = normal_sampler(S, covS)
def meta_algorithm(X, XTXi, resid, sampler):
n, p = X.shape
rho = 0.8
S = sampler(scale=0.) # deterministic with scale=0
ynew = X.dot(XTXi).dot(S) + resid # will be ok for n>p and non-degen X
Xnew = rho * X + np.sqrt(1 - rho**2) * np.random.standard_normal(
X.shape)
X_full = np.hstack([X, Xnew])
beta_full = np.linalg.pinv(X_full).dot(ynew)
winners = np.fabs(beta_full)[:p] > np.fabs(beta_full)[p:]
return set(np.nonzero(winners)[0])
XTX = X.T.dot(X)
XTXi = np.linalg.inv(XTX)
resid = y - X.dot(XTXi.dot(X.T.dot(y)))
dispersion = np.linalg.norm(resid)**2 / (n - p)
selection_algorithm = functools.partial(meta_algorithm, X, XTXi, resid)
# run selection algorithm
return full_model_inference(X,
y,
truth,
selection_algorithm,
smooth_sampler,
success_params=(8, 10),
B=B,
fit_probability=gbm_fit_sk,
fit_args={'n_estimators': 1000})
def simulate(n=200, p=100, s=10, signal=(0.5, 1), sigma=2, alpha=0.1, B=2000):
# description of statistical problem
X, y, truth = gaussian_instance(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.1,
sigma=sigma,
signal=signal,
random_signs=True,
scale=True)[:3]
dispersion = sigma**2
S = X.T.dot(y)
covS = dispersion * X.T.dot(X)
splitting_sampler = split_sampler(X * y[:, None], covS)
def meta_algorithm(XTX, XTXi, sampler):
min_success = 6
ntries = 10
def _alpha_grid(X, y, center, XTX):
n, p = X.shape
alphas, coefs, _ = lasso_path(X, y, Xy=center, precompute=XTX)
nselected = np.count_nonzero(coefs, axis=0)
return alphas[nselected < np.sqrt(0.8 * p)]
alpha_grid = _alpha_grid(X, y, sampler(scale=0.), XTX)
success = np.zeros((p, alpha_grid.shape[0]))
for _ in range(ntries):
scale = 1. # corresponds to sub-samples of 50%
noisy_S = sampler(scale=scale)
_, coefs, _ = lasso_path(X, y, Xy = noisy_S, precompute=XTX, alphas=alpha_grid)
success += np.abs(np.sign(coefs))
selected = np.apply_along_axis(lambda row: any(x>min_success for x in row), 1, success)
vars = set(np.nonzero(selected)[0])
return vars
XTX = X.T.dot(X)
XTXi = np.linalg.inv(XTX)
resid = y - X.dot(XTXi.dot(X.T.dot(y)))
dispersion = np.linalg.norm(resid)**2 / (n-p)
selection_algorithm = functools.partial(meta_algorithm, XTX, XTXi)
# run selection algorithm
return full_model_inference(X,
y,
truth,
selection_algorithm,
splitting_sampler,
success_params=(1, 1),
B=B,
fit_probability=keras_fit,
fit_args={'epochs':10, 'sizes':[100]*5, 'dropout':0., 'activation':'relu'})
def simulate(n=200, p=100, s=10, signal=(0.5, 1), sigma=2, alpha=0.1, B=8000):
# description of statistical problem
X, y, truth = gaussian_instance(n=n,
p=p,
s=s,
equicorrelated=False,
rho=0.5,
sigma=sigma,
signal=signal,
random_signs=True,
scale=False)[:3]
dispersion = sigma**2
S = X.T.dot(y)
covS = dispersion * X.T.dot(X)
smooth_sampler = normal_sampler(S, covS)
def meta_algorithm(XTX, XTXi, lam, sampler):
p = XTX.shape[0]
success = np.zeros(p)
loss = rr.quadratic_loss((p, ), Q=XTX)
pen = rr.l1norm(p, lagrange=lam)
scale = 0.
noisy_S = sampler(scale=scale)
loss.quadratic = rr.identity_quadratic(0, 0, -noisy_S, 0)
problem = rr.simple_problem(loss, pen)
soln = problem.solve(max_its=100, tol=1.e-10)
success += soln != 0
return tuple(sorted(np.nonzero(success)[0]))
XTX = X.T.dot(X)
XTXi = np.linalg.inv(XTX)
resid = y - X.dot(XTXi.dot(X.T.dot(y)))
dispersion = np.linalg.norm(resid)**2 / (n - p)
lam = 4. * np.sqrt(n)
selection_algorithm = functools.partial(meta_algorithm, XTX, XTXi, lam)
# run selection algorithm
df = partial_model_inference(X,
y,
truth,
selection_algorithm,
smooth_sampler,
fit_probability=gbm_fit_sk,
fit_args={'n_estimators': 1000},
success_params=(1, 1),
B=B,
alpha=alpha,
learner_klass=sparse_mixture_learner)
lee_df = lee_inference(X, y, lam, dispersion, truth, alpha=alpha)
return pd.merge(df, lee_df, on='variable')