def job_mmd_med(p, data_source, tr, te, r):
"""
MMD test of Gretton et al., 2012 used as a goodness-of-fit test.
Require the ability to sample from p i.e., the UnnormalizedDensity p has
to be able to return a non-None from get_datasource()
"""
# full data
data = tr + te
X = data.data()
with util.ContextTimer() as t:
# median heuristic
pds = p.get_datasource()
datY = pds.sample(data.sample_size(), seed=r + 294)
Y = datY.data()
XY = np.vstack((X, Y))
# If p, q differ very little, the median may be very small, rejecting H0
# when it should not?
medx = util.meddistance(X, subsample=1000)
medy = util.meddistance(Y, subsample=1000)
medxy = util.meddistance(XY, subsample=1000)
med_avg = (medx + medy + medxy) / 3.0
k = kernel.KGauss(med_avg**2)
mmd_test = mgof.QuadMMDGof(p, k, n_permute=400, alpha=alpha, seed=r)
mmd_result = mmd_test.perform_test(data)
return {'test_result': mmd_result, 'time_secs': t.secs}
def job_mmd_opt(p, data_source, tr, te, r):
"""
MMD test of Gretton et al., 2012 used as a goodness-of-fit test.
Require the ability to sample from p i.e., the UnnormalizedDensity p has
to be able to return a non-None from get_datasource()
With optimization. Gaussian kernel.
"""
data = tr + te
X = data.data()
with util.ContextTimer() as t:
# median heuristic
pds = p.get_datasource()
datY = pds.sample(data.sample_size(), seed=r+294)
Y = datY.data()
XY = np.vstack((X, Y))
med = util.meddistance(XY, subsample=1000)
# Construct a list of kernels to try based on multiples of the median
# heuristic
#list_gwidth = np.hstack( (np.linspace(20, 40, 10), (med**2)
# *(2.0**np.linspace(-2, 2, 20) ) ) )
list_gwidth = (med**2)*(2.0**np.linspace(-4, 4, 30) )
list_gwidth.sort()
candidate_kernels = [kernel.KGauss(gw2) for gw2 in list_gwidth]
mmd_opt = mgof.QuadMMDGofOpt(p, n_permute=300, alpha=alpha, seed=r)
mmd_result = mmd_opt.perform_test(data,
candidate_kernels=candidate_kernels,
tr_proportion=tr_proportion, reg=1e-3)
return { 'test_result': mmd_result, 'time_secs': t.secs}
def job_mmd_dgauss_opt(p, data_source, tr, te, r):
"""
MMD test of Gretton et al., 2012 used as a goodness-of-fit test.
Require the ability to sample from p i.e., the UnnormalizedDensity p has
to be able to return a non-None from get_datasource()
With optimization. Diagonal Gaussian kernel where there is one Gaussian width
for each dimension.
"""
data = tr + te
X = data.data()
d = X.shape[1]
with util.ContextTimer() as t:
# median heuristic
pds = p.get_datasource()
datY = pds.sample(data.sample_size(), seed=r+294)
Y = datY.data()
XY = np.vstack((X, Y))
# Get the median heuristic for each dimension
meds = np.zeros(d)
for i in range(d):
medi = util.meddistance(XY[:, [i]], subsample=1000)
meds[i] = medi
# Construct a list of kernels to try based on multiples of the median
# heuristic
med_factors = 2.0**np.linspace(-4, 4, 20)
candidate_kernels = []
for i in range(len(med_factors)):
ki = kernel.KDiagGauss( (meds**2)*med_factors[i] )
candidate_kernels.append(ki)
mmd_opt = mgof.QuadMMDGofOpt(p, n_permute=300, alpha=alpha, seed=r+56)
mmd_result = mmd_opt.perform_test(data,
candidate_kernels=candidate_kernels,
tr_proportion=tr_proportion, reg=1e-3)
return { 'test_result': mmd_result, 'time_secs': t.secs}