def optimize_auto_init(p, dat, J, **ops):
"""
Optimize parameters by calling optimize_locs_widths(). Automatically
initialize the test locations and the Gaussian width.
Return optimized locations, Gaussian width, optimization info
"""
assert J > 0
# Use grid search to initialize the gwidth
X = dat.data()
n_gwidth_cand = 5
gwidth_factors = 2.0**np.linspace(-3, 3, n_gwidth_cand)
med2 = util.meddistance(X, 1000)**2
k = kernel.KGauss(med2 * 2)
# fit a Gaussian to the data and draw to initialize V0
V0 = util.fit_gaussian_draw(X, J, seed=829, reg=1e-6)
list_gwidth = np.hstack(((med2) * gwidth_factors))
besti, objs = GaussFSSD.grid_search_gwidth(p, dat, V0, list_gwidth)
gwidth = list_gwidth[besti]
assert util.is_real_num(
gwidth), 'gwidth not real. Was %s' % str(gwidth)
assert gwidth > 0, 'gwidth not positive. Was %.3g' % gwidth
logging.info('After grid search, gwidth=%.3g' % gwidth)
V_opt, gwidth_opt, info = GaussFSSD.optimize_locs_widths(
p, dat, gwidth, V0, **ops)
# set the width bounds
#fac_min = 5e-2
#fac_max = 5e3
#gwidth_lb = fac_min*med2
#gwidth_ub = fac_max*med2
#gwidth_opt = max(gwidth_lb, min(gwidth_opt, gwidth_ub))
return V_opt, gwidth_opt, info
def job_fssdJ1q_med(p, data_source, tr, te, r, J=1, null_sim=None):
"""
FSSD test with a Gaussian kernel, where the test locations are randomized,
and the Gaussian width is set with the median heuristic. Use full sample.
No training/testing splits.
p: an UnnormalizedDensity
data_source: a DataSource
tr, te: Data
r: trial number (positive integer)
"""
if null_sim is None:
null_sim = gof.FSSDH0SimCovObs(n_simulate=2000, seed=r)
# full data
data = tr + te
X = data.data()
with util.ContextTimer() as t:
# median heuristic
med = util.meddistance(X, subsample=1000)
k = kernel.KGauss(med**2)
V = util.fit_gaussian_draw(X, J, seed=r + 3)
fssd_med = gof.FSSD(p, k, V, null_sim=null_sim, alpha=alpha)
fssd_med_result = fssd_med.perform_test(data)
return {
'goftest': fssd_med,
'test_result': fssd_med_result,
'time_secs': t.secs
}
def test_ustat_h1_mean_variance(self):
seed = 20
# sample
n = 200
alpha = 0.01
for d in [1, 4]:
mean = np.zeros(d)
variance = 1
isonorm = density.IsotropicNormal(mean, variance)
draw_mean = mean + 2
draw_variance = variance + 1
X = util.randn(n, d,
seed=seed) * np.sqrt(draw_variance) + draw_mean
dat = data.Data(X)
# Test
for J in [1, 3]:
sig2 = util.meddistance(X, subsample=1000)**2
k = kernel.KGauss(sig2)
# random test locations
V = util.fit_gaussian_draw(X, J, seed=seed + 1)
null_sim = gof.FSSDH0SimCovObs(n_simulate=200, seed=3)
fssd = gof.FSSD(isonorm, k, V, null_sim=null_sim, alpha=alpha)
fea_tensor = fssd.feature_tensor(X)
u_mean, u_variance = gof.FSSD.ustat_h1_mean_variance(
fea_tensor)
# assertions
self.assertGreaterEqual(u_variance, 0)
# should reject H0
self.assertGreaterEqual(u_mean, 0)
def job_fssdJ1q_imq_optv(p,
data_source,
tr,
te,
r,
J=1,
b=-0.5,
null_sim=None):
"""
FSSD with optimization on tr. Test on te. Use an inverse multiquadric
kernel (IMQ). Optimize only the test locations (V). Fix the kernel
parameters to b = -0.5, c=1. These are the recommended values from
Measuring Sample Quality with Kernels
Jackson Gorham, Lester Mackey
"""
if null_sim is None:
null_sim = gof.FSSDH0SimCovObs(n_simulate=2000, seed=r)
Xtr = tr.data()
with util.ContextTimer() as t:
# IMQ kernel parameters: b and c
c = 1.0
# fit a Gaussian to the data and draw to initialize V0
V0 = util.fit_gaussian_draw(Xtr, J, seed=r + 1, reg=1e-6)
ops = {
'reg': 1e-5,
'max_iter': 30,
'tol_fun': 1e-6,
'disp': True,
'locs_bounds_frac': 20.0,
}
V_opt, info = gof.IMQFSSD.optimize_locs(p, tr, b, c, V0, **ops)
k_imq = kernel.KIMQ(b=b, c=c)
# Use the optimized parameters to construct a test
fssd_imq = gof.FSSD(p, k_imq, V_opt, null_sim=null_sim, alpha=alpha)
fssd_imq_result = fssd_imq.perform_test(te)
return {
'test_result': fssd_imq_result,
'time_secs': t.secs,
'goftest': fssd_imq,
'opt_info': info,
}
def job_fssdJ1q_opt(p, data_source, tr, te, r, J=1, null_sim=None):
"""
FSSD with optimization on tr. Test on te. Use a Gaussian kernel.
"""
if null_sim is None:
null_sim = gof.FSSDH0SimCovObs(n_simulate=2000, seed=r)
Xtr = tr.data()
with util.ContextTimer() as t:
# Use grid search to initialize the gwidth
n_gwidth_cand = 5
gwidth_factors = 2.0**np.linspace(-3, 3, n_gwidth_cand)
med2 = util.meddistance(Xtr, 1000)**2
k = kernel.KGauss(med2 * 2)
# fit a Gaussian to the data and draw to initialize V0
V0 = util.fit_gaussian_draw(Xtr, J, seed=r + 1, reg=1e-6)
list_gwidth = np.hstack(((med2) * gwidth_factors))
besti, objs = gof.GaussFSSD.grid_search_gwidth(p, tr, V0, list_gwidth)
gwidth = list_gwidth[besti]
assert util.is_real_num(
gwidth), 'gwidth not real. Was %s' % str(gwidth)
assert gwidth > 0, 'gwidth not positive. Was %.3g' % gwidth
logging.info('After grid search, gwidth=%.3g' % gwidth)
ops = {
'reg': 1e-2,
'max_iter': 40,
'tol_fun': 1e-4,
'disp': True,
'locs_bounds_frac': 10.0,
'gwidth_lb': 1e-1,
'gwidth_ub': 1e4,
}
V_opt, gwidth_opt, info = gof.GaussFSSD.optimize_locs_widths(
p, tr, gwidth, V0, **ops)
# Use the optimized parameters to construct a test
k_opt = kernel.KGauss(gwidth_opt)
fssd_opt = gof.FSSD(p, k_opt, V_opt, null_sim=null_sim, alpha=alpha)
fssd_opt_result = fssd_opt.perform_test(te)
return {
'test_result': fssd_opt_result,
'time_secs': t.secs,
'goftest': fssd_opt,
'opt_info': info,
}
def job_fssdJ1q_imq_optbv(p, data_source, tr, te, r, J=1, null_sim=None):
"""
FSSD with optimization on tr. Test on te. Use an inverse multiquadric
kernel (IMQ). Optimize the test locations (V), and b. Fix c (in the kernel)
"""
if null_sim is None:
null_sim = gof.FSSDH0SimCovObs(n_simulate=2000, seed=r)
Xtr = tr.data()
with util.ContextTimer() as t:
# Initial IMQ kernel parameters: b and c
b0 = -0.5
# Fix c to this value
c = 1.0
c0 = c
# fit a Gaussian to the data and draw to initialize V0
V0 = util.fit_gaussian_draw(Xtr, J, seed=r + 1, reg=1e-6)
ops = {
'reg': 1e-5,
'max_iter': 40,
'tol_fun': 1e-6,
'disp': True,
'locs_bounds_frac': 20.0,
# IMQ kernel bounds
'b_lb': -20,
'c_lb': c,
'c_ub': c,
}
V_opt, b_opt, c_opt, info = gof.IMQFSSD.optimize_locs_params(
p, tr, b0, c0, V0, **ops)
k_imq = kernel.KIMQ(b=b_opt, c=c_opt)
# Use the optimized parameters to construct a test
fssd_imq = gof.FSSD(p, k_imq, V_opt, null_sim=null_sim, alpha=alpha)
fssd_imq_result = fssd_imq.perform_test(te)
return {
'test_result': fssd_imq_result,
'time_secs': t.secs,
'goftest': fssd_imq,
'opt_info': info,
}
def test_optimized_fssd(self):
"""
Test FSSD test with parameter optimization.
"""
seed = 4
# sample size
n = 179
alpha = 0.01
for d in [1, 3]:
mean = np.zeros(d)
variance = 1.0
p = density.IsotropicNormal(mean, variance)
# Mean difference. obvious reject
ds = data.DSIsotropicNormal(mean + 4, variance + 0)
dat = ds.sample(n, seed=seed)
# test
for J in [1, 4]:
opts = {
'reg': 1e-2,
'max_iter': 10,
'tol_fun': 1e-3,
'disp': False
}
tr, te = dat.split_tr_te(tr_proportion=0.3, seed=seed + 1)
Xtr = tr.X
gwidth0 = util.meddistance(Xtr, subsample=1000)**2
# random test locations
V0 = util.fit_gaussian_draw(Xtr, J, seed=seed + 1)
V_opt, gw_opt, opt_result = \
gof.GaussFSSD.optimize_locs_widths(p, tr, gwidth0, V0, **opts)
# construct a test
k_opt = kernel.KGauss(gw_opt)
null_sim = gof.FSSDH0SimCovObs(n_simulate=2000, seed=10)
fssd_opt = gof.FSSD(p,
k_opt,
V_opt,
null_sim=null_sim,
alpha=alpha)
fssd_opt_result = fssd_opt.perform_test(
te, return_simulated_stats=True)
assert fssd_opt_result['h0_rejected']
def test_basic(self):
"""
Nothing special. Just test basic things.
"""
seed = 12
# sample
n = 100
alpha = 0.01
for d in [1, 4]:
mean = np.zeros(d)
variance = 1
isonorm = density.IsotropicNormal(mean, variance)
# only one dimension of the mean is shifted
#draw_mean = mean + np.hstack((1, np.zeros(d-1)))
draw_mean = mean + 0
draw_variance = variance + 1
X = util.randn(n, d,
seed=seed) * np.sqrt(draw_variance) + draw_mean
dat = data.Data(X)
# Test
for J in [1, 3]:
sig2 = util.meddistance(X, subsample=1000)**2
k = kernel.KGauss(sig2)
# random test locations
V = util.fit_gaussian_draw(X, J, seed=seed + 1)
null_sim = gof.FSSDH0SimCovObs(n_simulate=200, seed=3)
fssd = gof.FSSD(isonorm, k, V, null_sim=null_sim, alpha=alpha)
tresult = fssd.perform_test(dat, return_simulated_stats=True)
# assertions
self.assertGreaterEqual(tresult['pvalue'], 0)
self.assertLessEqual(tresult['pvalue'], 1)
