def test_logistic():
for Y, T in [(np.random.binomial(1,0.5,size=(10,)),
np.ones(10)),
(np.random.binomial(1,0.5,size=(10,)),
None),
(np.random.binomial(3,0.5,size=(10,)),
3*np.ones(10))]:
X = np.random.standard_normal((10,5))
L = lasso.logistic(X, Y, 0.1, trials=T)
L.fit()
L = lasso.logistic(X, Y, 0.1, trials=T)
L.fit()
C = L.constraints
np.testing.assert_array_less( \
np.dot(L.constraints.linear_part, L.onestep_estimator),
L.constraints.offset)
P = L.summary()['pval']
return L, C, P
def test_logistic():
for Y, T in [(np.random.binomial(1,0.5,size=(10,)),
np.ones(10)),
(np.random.binomial(1,0.5,size=(10,)),
None),
(np.random.binomial(3,0.5,size=(10,)),
3*np.ones(10))]:
X = np.random.standard_normal((10,5))
L = lasso.logistic(X, Y, 0.1, trials=T)
L.fit()
L = lasso.logistic(X, Y, 0.1, trials=T)
L.fit()
C = L.constraints
np.testing.assert_array_less( \
np.dot(L.constraints.linear_part, L.onestep_estimator),
L.constraints.offset)
P = L.summary()['pval']
return L, C, P
def test_logistic_pvals(n=500, p=200, s=3, sigma=2, rho=0.3, snr=7.):
counter = 0
while True:
counter += 1
X, y, beta, active, sigma = instance(n=n,
p=p,
s=s,
sigma=sigma,
rho=rho,
snr=snr)
z = (y > 0)
X = np.hstack([np.ones((n, 1)), X])
active = np.array(active)
active += 1
active = [0] + list(active)
L = lasso.logistic(X, z, [0] * 1 + [1.2] * p)
L.fit()
S = L.summary('onesided')
if set(active).issubset(L.active) > 0:
return [
p for p, v in zip(S['pval'], S['variable']) if v not in active
]
return []
def test_logistic_pvals(n=500,
p=200,
s=3,
sigma=2,
rho=0.3,
snr=7.):
counter = 0
while True:
counter += 1
X, y, beta, active, sigma = instance(n=n,
p=p,
s=s,
sigma=sigma,
rho=rho,
snr=snr)
z = (y > 0)
X = np.hstack([np.ones((n,1)), X])
active = np.array(active)
active += 1
active = [0] + list(active)
L = lasso.logistic(X, z, [0]*1 + [1.2]*p)
L.fit()
S = L.summary('onesided')
if set(active).issubset(L.active) > 0:
return [p for p, v in zip(S['pval'], S['variable']) if v not in active]
return []
def test_logistic_pvals(n=500,
p=200,
s=3,
sigma=2,
rho=0.3,
snr=7.):
X, y, beta, true_active, sigma = instance(n=n,
p=p,
s=s,
sigma=sigma,
rho=rho,
snr=snr)
z = (y > 0)
X = np.hstack([np.ones((n,1)), X])
active = np.array(true_active)
active += 1
active = [0] + list(active)
L = lasso.logistic(X, z, [0]*1 + [1.2]*p)
L.fit()
S = L.summary('onesided')
true_active = np.nonzero(active)[0]
if set(true_active).issubset(L.active) > 0:
return S['pval'], [v in true_active for v in S['variable']]
def test_logistic_pvals(n=500,
p=200,
s=3,
rho=0.3,
signal=15.):
X, y, beta, true_active = logistic_instance(n=n,
p=p,
s=s,
rho=rho,
signal=signal,
equicorrelated=False)
X = np.hstack([np.ones((n,1)), X])
print(true_active, 'true')
active = np.array(true_active)
active += 1
active = [0] + list(active)
true_active = active
L = lasso.logistic(X, y, [0]*1 + [1.2]*p)
L.fit()
S = L.summary('onesided')
print(true_active, L.active)
if set(true_active).issubset(L.active):
return S['pval'], [v in true_active for v in S['variable']]
def test_logistic():
"""
Check that logistic results agree with R
"""
tol = 1.e-4
R_code = """
library(selectiveInference)
set.seed(43)
n = 50
p = 10
sigma = 10
x = matrix(rnorm(n*p),n,p)
x=scale(x,TRUE,TRUE)
beta = c(3,2,rep(0,p-2))
y = x %*% beta + sigma * rnorm(n)
y=1*(y>mean(y))
# first run glmnet
gfit = glmnet(x,y,standardize=FALSE,family="binomial")
# extract coef for a given lambda; note the 1/n factor!
# (and here we DO include the intercept term)
lambda = .8
beta_hat = as.numeric(coef(gfit, s=lambda/n, exact=TRUE))
# compute fixed lambda p-values and selection intervals
out = fixedLassoInf(x,y,beta_hat,lambda,family="binomial")
vlo = out$vlo
vup = out$vup
sdvar = out$sd
coef=out$coef0
info_mat=out$info.matrix
beta_hat = beta_hat[c(1, out$vars+1)]
out
pval = out$pv
vars_logit = out$var
"""
rpy.r(R_code)
R_pvals = np.asarray(rpy.r('pval'))
selected_vars = np.asarray(rpy.r('vars_logit'))
y = np.asarray(rpy.r('y'))
y = y.reshape(-1)
beta_hat = np.asarray(rpy.r('as.numeric(beta_hat)'))
x = np.asarray(rpy.r('x'))
x = np.hstack([np.ones((x.shape[0], 1)), x])
L = lasso.logistic(x, y, [0] + [0.8] * (x.shape[1] - 1))
beta2 = L.fit()[L.active]
yield np.testing.assert_equal, L.active[1:], selected_vars
yield np.testing.assert_allclose, beta2, beta_hat, tol, tol, False, 'logistic coef'
yield np.testing.assert_allclose, L.summary(
'onesided')['pval'][1:], R_pvals, tol, tol, False, 'logistic pvalues'
def test_logistic():
tol = 1.e-4
R_code = """
library(selectiveInference)
set.seed(43)
n = 50
p = 10
sigma = 10
x = matrix(rnorm(n*p),n,p)
x=scale(x,TRUE,TRUE)
beta = c(3,2,rep(0,p-2))
y = x %*% beta + sigma * rnorm(n)
y=1*(y>mean(y))
# first run glmnet
gfit = glmnet(x,y,standardize=FALSE,family="binomial")
# extract coef for a given lambda; note the 1/n factor!
# (and here we DO include the intercept term)
lambda = .8
beta_hat = as.numeric(coef(gfit, s=lambda/n, exact=TRUE))
# compute fixed lambda p-values and selection intervals
out = fixedLassoInf(x,y,beta_hat,lambda,family="binomial")
vlo = out$vlo
vup = out$vup
sdvar = out$sd
coef=out$coef0
info_mat=out$info.matrix
beta_hat = beta_hat[c(1, out$vars+1)]
out
pval = out$pv
vars_logit = out$var
"""
rpy.r(R_code)
R_pvals = np.asarray(rpy.r('pval'))
selected_vars = np.asarray(rpy.r('vars_logit'))
y = np.asarray(rpy.r('y'))
y = y.reshape(-1)
beta_hat = np.asarray(rpy.r('as.numeric(beta_hat)'))
x = np.asarray(rpy.r('x'))
x = np.hstack([np.ones((x.shape[0],1)), x])
L = lasso.logistic(x, y, [0] + [0.8] * (x.shape[1]-1))
beta2 = L.fit()[L.active]
yield np.testing.assert_equal, L.active[1:], selected_vars
yield np.testing.assert_allclose, beta2, beta_hat, tol, tol, False, 'logistic coef'
yield np.testing.assert_allclose, L.summary('onesided')['pval'][1:], R_pvals, tol, tol, False, 'logistic pvalues'
def test_logistic():
for Y, T in [(np.random.binomial(1,0.5,size=(10,)),
np.ones(10)),
(np.random.binomial(1,0.5,size=(10,)),
None),
(np.random.binomial(3,0.5,size=(10,)),
3*np.ones(10))]:
X = np.random.standard_normal((10,5))
L = lasso.logistic(X, Y, 0.1, trials=T)
L.fit()
C = L.constraints
np.testing.assert_array_less( \
np.dot(L.constraints.linear_part, L._onestep),
L.constraints.offset)
I = L.intervals
P = L.active_pvalues
return L, C, I, P