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_rdc_med(paired_source, tr, te, r, n_features=10):
"""
The Randomized Dependence Coefficient test.
- Gaussian width = median heuristic on the copula-transformed data
- 10 random features for each X andY
- Use full dataset for testing
"""
pdata = tr + te
# 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)
rdc = it.RDC(fmx, fmy, alpha=alpha)
rdc_result = rdc.perform_test(pdata)
return {'indtest': rdc, 'test_result': rdc_result, 'time_secs': t.secs}
def test_general(self):
n = 30
d = 4
X = np.random.randn(n, d) * 3 + 4
M = feature.MarginalCDFMap()
Z = M.gen_features(X)
# assert
self.assertEqual(Z.shape[1], d)
self.assertEqual(Z.shape[0], n)
self.assertEqual(M.num_features(X), d)
self.assertTrue(np.all(Z >= 0))
self.assertTrue(np.all(Z <= 1))
def job_nfsicJ10_cperm_stoopt(paired_source, tr, te, r):
"""
- Copula transform the data
- Use permutations to simulate from the null distribution.
"""
n_permute = 500
with util.ContextTimer() as t:
# copula transform to both X and Y
cop_map = fea.MarginalCDFMap()
xtr, ytr = tr.xy()
xte, yte = te.xy()
xtr = cop_map.gen_features(xtr)
ytr = cop_map.gen_features(ytr)
xte = cop_map.gen_features(xte)
yte = cop_map.gen_features(yte)
tr = data.PairedData(xtr, ytr)
te = data.PairedData(xte, yte)
to_return = job_nfsicJ10_stoopt(paired_source, tr, te, r, n_permute)
to_return['time_secs'] = t.secs
return to_return