def job_rdcperm_med(paired_source, tr, te, r, n_features=10):
"""
The Randomized Dependence Coefficient test with permutations.
"""
pdata = tr + te
n_permute = 500
# n_features=10 from Lopez-Paz et al., 2013 paper.
with util.ContextTimer() as t:
# get the median distances
X, Y = pdata.xy()
# copula transform to both X and Y
cop_map = fea.MarginalCDFMap()
Xcdf = cop_map.gen_features(X)
Ycdf = cop_map.gen_features(Y)
medx = util.meddistance(Xcdf, subsample=1000)
medy = util.meddistance(Ycdf, subsample=1000)
sigmax2 = medx**2
sigmay2 = medy**2
fmx = fea.RFFKGauss(sigmax2, n_features=n_features, seed=r + 19)
fmy = fea.RFFKGauss(sigmay2, n_features=n_features, seed=r + 220)
rdcperm = it.RDCPerm(fmx,
fmy,
n_permute=n_permute,
alpha=alpha,
seed=r + 100)
rdcperm_result = rdcperm.perform_test(pdata)
return {
'indtest': rdcperm,
'test_result': rdcperm_result,
'time_secs': t.secs
}
def job_rdcperm_nc_med(paired_source, tr, te, r, n_features=10):
"""
The Randomized Dependence Coefficient test with permutations.
No copula transformtation. Use median heuristic on the data.
"""
pdata = tr + te
n_permute = 500
# n_features=10 from Lopez-Paz et al., 2013 paper.
with util.ContextTimer() as t:
# get the median distances
X, Y = pdata.xy()
medx = util.meddistance(X, subsample=1000)
medy = util.meddistance(Y, subsample=1000)
sigmax2 = medx**2
sigmay2 = medy**2
fmx = fea.RFFKGauss(sigmax2, n_features=n_features, seed=r + 19)
fmy = fea.RFFKGauss(sigmay2, n_features=n_features, seed=r + 220)
rdcperm = it.RDCPerm(fmx,
fmy,
n_permute=n_permute,
alpha=alpha,
seed=r + 100,
use_copula=False)
rdcperm_result = rdcperm.perform_test(pdata)
return {
'indtest': rdcperm,
'test_result': rdcperm_result,
'time_secs': t.secs
}