def job_lin_mmd(sample_source, tr, te, r):
"""Linear mmd with grid search to choose the best Gaussian width."""
# should be completely deterministic
# If n is too large, pairwise meddian computation can cause a memory error.
with util.ContextTimer() as t:
X, Y = tr.xy()
Xr = X[:min(X.shape[0], 1000), :]
Yr = Y[:min(Y.shape[0], 1000), :]
med = util.meddistance(np.vstack((Xr, Yr)))
widths = [(med * f) for f in 2.0**np.linspace(-1, 4, 40)]
list_kernels = [kernel.KGauss(w**2) for w in widths]
# grid search to choose the best Gaussian width
besti, powers = tst.LinearMMDTest.grid_search_kernel(
tr, list_kernels, alpha)
# perform test
best_ker = list_kernels[besti]
lin_mmd_test = tst.LinearMMDTest(best_ker, alpha)
test_result = lin_mmd_test.perform_test(te)
result = {
'test_method': lin_mmd_test,
'test_result': test_result,
'time_secs': t.secs
}
return result
def mmd(p, q, alpha=0.05):
if (p.ndim == 1): p = p[:, np.newaxis]
if (q.ndim == 1): q = q[:, np.newaxis]
d = data.TSTData(p, q)
d_tr, d_te = d.split_tr_te(tr_proportion=0.5)
med = util.meddistance(d_tr.stack_xy())
widths = [(med * f) for f in 2.0**np.linspace(-1, 4, 20)]
list_kernels = [kernel.KGauss(w**2) for w in widths]
besti, powers = tst.LinearMMDTest.grid_search_kernel(
d_tr, list_kernels, alpha)
best_ker = list_kernels[besti]
lin_mmd_test = tst.LinearMMDTest(best_ker, alpha)
r = lin_mmd_test.perform_test(d_te)
return r['test_stat'], r['pvalue']
