def simulation(n, p, sigma, nnz=0, nsim=1000,
reduced=True,
reduced_full=True): # nnz = number nonzero
beta = np.zeros(p)
if nnz > 0:
beta[:nnz] = np.linspace(4,4.5,nnz)
beta = beta * sigma
splitP = []
covtestP = []
spacings = []
reduced_known = []
reduced_unknown = []
reduced_known_full = []
reduced_unknown_full = []
hypotheses = []
hypotheses_full = []
for i in range(nsim):
X = (np.random.standard_normal((n,p)) +
0.7 * np.random.standard_normal(n)[:,None])
X -= X.mean(0)[None,:]
X /= (X.std(0)[None,:] * np.sqrt(n))
Y = np.random.standard_normal(n) * sigma + np.dot(X, beta)
Y -= Y.mean()
split = sample_split(X.copy(),
Y.copy(),
sigma=sigma,
burnin=2000,
ndraw=5000,
nstep=10,
reduced=reduced)
splitP.append(split[0])
reduced_known.append(split[1])
reduced_unknown.append(split[2])
spacings.append(split[3])
covtestP.append(split[4])
hypotheses.append([var in range(nnz) for var in split[5]])
if reduced_full:
fs = forward_step(X, Y,
sigma=sigma,
burnin=2000,
ndraw=5000,
nstep=10)
reduced_known_full.append(fs[1])
reduced_unknown_full.append(fs[2])
hypotheses_full.append([var in range(nnz) for var in fs[4]])
for D, name in zip([splitP, spacings, covtestP], ['split', 'spacings', 'covtest']):
means = map(lambda x: x[~np.isnan(x)].mean(), np.array(D).T)[:(nnz+3)]
SDs = map(lambda x: x[~np.isnan(x)].std(), np.array(D).T)[:(nnz+3)]
print means, SDs, name
if reduced:
print (np.mean(np.array(reduced_known)[:,:(nnz+3)],0),
np.std(np.array(reduced_known)[:,:(nnz+3)],0), 'reduced known split')
print (np.mean(np.array(reduced_unknown)[:,:(nnz+3)],0),
np.std(np.array(reduced_unknown)[:,:(nnz+3)],0), 'reduced unknown split'), i
if reduced_full:
print (np.mean(np.array(reduced_unknown_full)[:,:(nnz+3)],0),
np.std(np.array(reduced_unknown_full)[:,:(nnz+3)],0), 'reduced unknown full'), i
print (np.mean(np.array(reduced_known_full)[:,:(nnz+3)],0),
np.std(np.array(reduced_known_full)[:,:(nnz+3)],0), 'reduced known full'), i
value = np.mean(beta)
if reduced:
np.save('reduced_split_known%d.npy' % (nnz,), np.array(reduced_known))
np.save('reduced_split_unknown%d.npy' % (nnz,), np.array(reduced_unknown))
np.save('split%d.npy' % (nnz,), np.array(splitP))
np.save('spacings_split%d.npy' % (nnz,), np.array(spacings))
np.save('covtest_split%d.npy' % (nnz,), np.array(covtestP))
np.save('hypotheses_split_%d.npy' % (nnz,), np.array(hypotheses))
if reduced_full:
np.save('hypotheses_splitfull_%d.npy' % (nnz,), np.array(hypotheses_full))
np.save('reduced_splitfull_known%d.npy' % (nnz,), np.array(reduced_known_full))
np.save('reduced_splitfull_unknown%d.npy' % (nnz,), np.array(reduced_unknown_full))
def simulation(n,
p,
sigma,
nsim=500,
label=0,
reduced=True,
reduced_full=True): # nnz = number nonzero
splitP = []
covtestP = []
spacings = []
reduced_known = []
reduced_unknown = []
reduced_known_full = []
reduced_unknown_full = []
hypotheses = []
hypotheses_full = []
for i in range(nsim):
X, Y, nnz = instance()
Y -= Y.mean()
split = sample_split(X.copy(),
Y.copy(),
sigma=sigma,
burnin=1000,
ndraw=2000,
nstep=10,
reduced=reduced)
splitP.append(split[0])
reduced_known.append(split[1])
reduced_unknown.append(split[2])
spacings.append(split[3])
covtestP.append(split[4])
hypotheses.append([var in range(nnz) for var in split[5]])
if reduced_full:
fs = forward_step(X,
Y,
sigma=sigma,
burnin=1000,
ndraw=2000,
nstep=10)
reduced_known_full.append(fs[1])
reduced_unknown_full.append(fs[2])
hypotheses_full.append([var in range(nnz) for var in fs[4]])
for D, name in zip([splitP, spacings, covtestP],
['split', 'spacings', 'covtest']):
means = map(lambda x: x[~np.isnan(x)].mean(),
np.array(D).T)[:(nnz + 3)]
SDs = map(lambda x: x[~np.isnan(x)].std(),
np.array(D).T)[:(nnz + 3)]
print means, SDs, name
if reduced:
print(np.mean(np.array(reduced_known)[:, :(nnz + 3)], 0),
np.std(np.array(reduced_known)[:, :(nnz + 3)],
0), 'reduced known split')
print(np.mean(np.array(reduced_unknown)[:, :(nnz + 3)], 0),
np.std(np.array(reduced_unknown)[:, :(nnz + 3)],
0), 'reduced unknown split'), i
if reduced_full:
print(np.mean(np.array(reduced_unknown_full)[:, :(nnz + 3)], 0),
np.std(np.array(reduced_unknown_full)[:, :(nnz + 3)],
0), 'reduced unknown full'), i
print(np.mean(np.array(reduced_known_full)[:, :(nnz + 3)], 0),
np.std(np.array(reduced_known_full)[:, :(nnz + 3)],
0), 'reduced known full'), i
if reduced:
np.save('reduced_split_known_alex%d.npy' % (label, ),
np.array(reduced_known))
np.save('reduced_split_unknown_alex%d.npy' % (label, ),
np.array(reduced_unknown))
np.save('split_alex%d.npy' % (label, ), np.array(splitP))
np.save('spacings_split_alex%d.npy' % (label, ), np.array(spacings))
np.save('covtest_split_alex%d.npy' % (label, ), np.array(covtestP))
np.save('hypotheses_split__alex%d.npy' % (label, ),
np.array(hypotheses))
if reduced_full:
np.save('hypotheses_splitfull__alex%d.npy' % (label, ),
np.array(hypotheses_full))
np.save('reduced_splitfull_known_alex%d.npy' % (label, ),
np.array(reduced_known_full))
np.save('reduced_splitfull_unknown_alex%d.npy' % (label, ),
np.array(reduced_unknown_full))
def simulation(n, p, sigma, nsim=500,
label=0,
reduced=True,
reduced_full=True): # nnz = number nonzero
splitP = []
covtestP = []
spacings = []
reduced_known = []
reduced_unknown = []
reduced_known_full = []
reduced_unknown_full = []
hypotheses = []
hypotheses_full = []
for i in range(nsim):
X, Y, nnz = instance()
nnz = 0
Y -= Y.mean()
Y *= sigma
split = sample_split(X.copy(),
Y.copy(),
sigma=sigma,
burnin=1000,
ndraw=2000,
nstep=10,
reduced=reduced)
splitP.append(split[0])
reduced_known.append(split[1])
reduced_unknown.append(split[2])
spacings.append(split[3])
covtestP.append(split[4])
hypotheses.append([var in range(nnz) for var in split[5]])
if reduced_full:
fs = forward_step(X, Y,
sigma=sigma,
burnin=1000,
ndraw=2000,
nstep=10)
reduced_known_full.append(fs[1])
reduced_unknown_full.append(fs[2])
hypotheses_full.append([var in range(nnz) for var in fs[4]])
for D, name in zip([splitP, spacings, covtestP], ['split', 'spacings', 'covtest']):
means = map(lambda x: x[~np.isnan(x)].mean(), np.array(D).T)[:(nnz+3)]
SDs = map(lambda x: x[~np.isnan(x)].std(), np.array(D).T)[:(nnz+3)]
print means, SDs, name
if reduced:
print (np.mean(np.array(reduced_known)[:,:(nnz+3)],0),
np.std(np.array(reduced_known)[:,:(nnz+3)],0), 'reduced known split')
print (np.mean(np.array(reduced_unknown)[:,:(nnz+3)],0),
np.std(np.array(reduced_unknown)[:,:(nnz+3)],0), 'reduced unknown split'), i
if reduced_full:
print (np.mean(np.array(reduced_unknown_full)[:,:(nnz+3)],0),
np.std(np.array(reduced_unknown_full)[:,:(nnz+3)],0), 'reduced unknown full'), i
print (np.mean(np.array(reduced_known_full)[:,:(nnz+3)],0),
np.std(np.array(reduced_known_full)[:,:(nnz+3)],0), 'reduced known full'), i
if reduced:
np.save('reduced_split_known_alexnull%d.npy' % (label,), np.array(reduced_known))
np.save('reduced_split_unknown_alexnull%d.npy' % (label,), np.array(reduced_unknown))
np.save('split_alexnull%d.npy' % (label,), np.array(splitP))
np.save('spacings_split_alexnull%d.npy' % (label,), np.array(spacings))
np.save('covtest_split_alexnull%d.npy' % (label,), np.array(covtestP))
np.save('hypotheses_split__alexnull%d.npy' % (label,), np.array(hypotheses))
if reduced_full:
np.save('hypotheses_splitfull__alexnull%d.npy' % (label,), np.array(hypotheses_full))
np.save('reduced_splitfull_known_alexnull%d.npy' % (label,), np.array(reduced_known_full))
np.save('reduced_splitfull_unknown_alexnull%d.npy' % (label,), np.array(reduced_unknown_full))
