def calc_wde1(dist_code, num_obvs, sample_no, wave_name, **kwargs):
"""
Calculates WDE CV for given params
"""
dist = dist_from_code(dist_code)
#what = what + ('.single_%s' % single)
k = kwargs['k']
#what = what + ('.k_%d' % k)
j0 = kwargs['j0']
#what = what + ('.j0_%d' % j0)
delta_j = kwargs['delta_j']
# plot
plot = kwargs['plot']
source = sample_name(dist_code, num_obvs, sample_no)
data = read_data(source)
assert data.shape[0] == num_obvs
t0 = datetime.now()
wde = WaveletDensityEstimator(((wave_name, j0), (wave_name, j0)), k=k, delta_j=delta_j)
wde.fit(data)
if plot:
import plotlib
fname = 'test.png'
plotlib.do_plot_wde(wde, fname, dist, plot)
else:
elapsed = (datetime.now() - t0).total_seconds()
hd, corr_factor = hellinger_distance(dist, wde)
params = wde.pdf.nparams
print('RESULT', dist_code, num_obvs, sample_no, wave_name, k, delta_j, params, None, None, None, hd, elapsed)
def _kde(sample_no, data):
t0 = datetime.now()
kde = KDEMultivariate(data, 'c' * data.shape[1], bw='cv_ml') ## cv_ml
elapsed = (datetime.now() - t0).total_seconds()
hd, corr_factor = hellinger_distance(dist, kde)
return (dist_code, num_obvs, sample_no, 'KDE', '', '', '', 0,
0, 0, num_obvs, 0.0, hd, elapsed)
def gen():
for ix, k, delta_j in itt.product(sample_range, k_range, delta_j_range):
source = sample_name(dist_code, num_obvs, ix)
data = read_data(source)
assert data.shape[0] == num_obvs
t0 = datetime.now()
wde = WaveletDensityEstimator(((wave_name, j0),(wave_name, j0)) , k=k, delta_j=delta_j)
wde.fit(data)
elapsed = (datetime.now() - t0).total_seconds()
hd, corr_factor = hellinger_distance(dist, wde)
params = wde.pdf.nparams
yield result_wde_classic(dist_code, num_obvs, ix, wave_name, k, delta_j, params, hd, elapsed)
for loss, ordering, is_single in WaveletDensityEstimator.valid_options(single):
t0 = datetime.now()
wde.cvfit(data, loss, ordering, is_single=is_single)
elapsed = (datetime.now() - t0).total_seconds()
hd, corr_factor = hellinger_distance(dist, wde)
params = wde.pdf.nparams
yield result_wde_cv(dist_code, num_obvs, ix, wave_name, k, delta_j, params, loss, ordering, is_single, hd, elapsed)
def gen():
for ix in sample_range:
source = sample_name(dist_code, num_obvs, ix)
data = read_data(source)
assert data.shape[0] == num_obvs
t0 = datetime.now()
kde = KDEMultivariate(data, 'c' * data.shape[1], bw='cv_ml') ## cv_ml
elapsed = (datetime.now() - t0).total_seconds()
hd, corr_factor = hellinger_distance(dist, kde)
yield result_kde(dist_code, num_obvs, ix, hd, elapsed)