def test_compute_cut():
random = RandomState()
predictions = random.permutation(100)
labels = numpy.ones(100)
for eff in [0.1, 0.5, 0.75, 0.99]:
cut = compute_cut_for_efficiency(eff, labels, predictions)
assert numpy.sum(predictions > cut) / len(predictions) == eff, 'the cut was set wrongly'
weights = numpy.array(random.exponential(size=100))
for eff in random.uniform(size=100):
cut = compute_cut_for_efficiency(eff, labels, predictions, sample_weight=weights)
lower = numpy.sum(weights[predictions > cut + 1]) / numpy.sum(weights)
upper = numpy.sum(weights[predictions > cut - 1]) / numpy.sum(weights)
assert lower < eff < upper
def compute_sde_on_groups(y_pred,
mask,
groups_indices,
target_efficiencies,
sample_weight=None,
power=2.):
y_pred = column_or_1d(y_pred)
sample_weight = check_sample_weight(y_pred, sample_weight=sample_weight)
group_weights = compute_group_weights_by_indices(
groups_indices, sample_weight=sample_weight)
divided_weight = compute_divided_weight_by_indices(
groups_indices, sample_weight=sample_weight * mask)
cuts = compute_cut_for_efficiency(target_efficiencies,
mask=mask,
y_pred=y_pred,
sample_weight=sample_weight)
sde = 0.
for cut in cuts:
group_efficiencies = compute_group_efficiencies_by_indices(
y_pred,
groups_indices=groups_indices,
cut=cut,
divided_weight=divided_weight)
# print('FROM SDE function', cut, group_efficiencies)
sde += weighted_deviation(group_efficiencies,
weights=group_weights,
power=power)
return (sde / len(cuts))**(1. / power)
def compute_sde_on_bins(y_pred,
mask,
bin_indices,
target_efficiencies,
power=2.,
sample_weight=None):
# ignoring events from other classes
sample_weight = check_sample_weight(y_pred, sample_weight=sample_weight)
y_pred = y_pred[mask]
bin_indices = bin_indices[mask]
sample_weight = sample_weight[mask]
bin_weights = compute_bin_weights(bin_indices=bin_indices,
sample_weight=sample_weight)
cuts = compute_cut_for_efficiency(target_efficiencies,
mask=numpy.ones(len(y_pred), dtype=bool),
y_pred=y_pred,
sample_weight=sample_weight)
result = 0.
for cut in cuts:
bin_efficiencies = compute_bin_efficiencies(
y_pred,
bin_indices=bin_indices,
cut=cut,
sample_weight=sample_weight)
result += weighted_deviation(bin_efficiencies,
weights=bin_weights,
power=power)
return (result / len(cuts))**(1. / power)
def compute_theil_on_bins(y_pred, mask, bin_indices, target_efficiencies,
sample_weight):
y_pred = column_or_1d(y_pred)
sample_weight = check_sample_weight(y_pred, sample_weight=sample_weight)
# ignoring events from other classes
y_pred = y_pred[mask]
bin_indices = bin_indices[mask]
sample_weight = sample_weight[mask]
bin_weights = compute_bin_weights(bin_indices=bin_indices,
sample_weight=sample_weight)
cuts = compute_cut_for_efficiency(target_efficiencies,
mask=numpy.ones(len(y_pred), dtype=bool),
y_pred=y_pred,
sample_weight=sample_weight)
result = 0.
for cut in cuts:
bin_efficiencies = compute_bin_efficiencies(
y_pred,
bin_indices=bin_indices,
cut=cut,
sample_weight=sample_weight)
result += theil(bin_efficiencies, weights=bin_weights)
return result / len(cuts)
def test_compute_cut():
random = RandomState()
predictions = random.permutation(100)
labels = numpy.ones(100)
for eff in [0.1, 0.5, 0.75, 0.99]:
cut = compute_cut_for_efficiency(eff, labels, predictions)
assert numpy.sum(predictions > cut) / len(
predictions) == eff, 'the cut was set wrongly'
weights = numpy.array(random.exponential(size=100))
for eff in random.uniform(size=100):
cut = compute_cut_for_efficiency(eff,
labels,
predictions,
sample_weight=weights)
lower = numpy.sum(weights[predictions > cut + 1]) / numpy.sum(weights)
upper = numpy.sum(weights[predictions > cut - 1]) / numpy.sum(weights)
assert lower < eff < upper
def compute_theil_on_groups(y_pred, mask, groups_indices, target_efficiencies, sample_weight):
y_pred = column_or_1d(y_pred)
sample_weight = check_sample_weight(y_pred, sample_weight=sample_weight)
groups_weights = compute_group_weights_by_indices(groups_indices, sample_weight=sample_weight)
divided_weight = compute_divided_weight_by_indices(groups_indices, sample_weight=sample_weight * mask)
cuts = compute_cut_for_efficiency(target_efficiencies, mask=mask,
y_pred=y_pred, sample_weight=sample_weight)
result = 0.
for cut in cuts:
groups_efficiencies = compute_group_efficiencies_by_indices(y_pred, groups_indices=groups_indices,
cut=cut, divided_weight=divided_weight)
result += theil(groups_efficiencies, groups_weights)
return result / len(cuts)
def compute_sde_on_groups(y_pred, mask, groups_indices, target_efficiencies, sample_weight=None, power=2.):
y_pred = column_or_1d(y_pred)
sample_weight = check_sample_weight(y_pred, sample_weight=sample_weight)
group_weights = compute_group_weights_by_indices(groups_indices, sample_weight=sample_weight)
divided_weight = compute_divided_weight_by_indices(groups_indices, sample_weight=sample_weight * mask)
cuts = compute_cut_for_efficiency(target_efficiencies, mask=mask, y_pred=y_pred, sample_weight=sample_weight)
sde = 0.
for cut in cuts:
group_efficiencies = compute_group_efficiencies_by_indices(y_pred, groups_indices=groups_indices,
cut=cut, divided_weight=divided_weight)
# print('FROM SDE function', cut, group_efficiencies)
sde += weighted_deviation(group_efficiencies, weights=group_weights, power=power)
return (sde / len(cuts)) ** (1. / power)
def compute_theil_on_bins(y_pred, mask, bin_indices, target_efficiencies, sample_weight):
y_pred = column_or_1d(y_pred)
sample_weight = check_sample_weight(y_pred, sample_weight=sample_weight)
# ignoring events from other classes
y_pred = y_pred[mask]
bin_indices = bin_indices[mask]
sample_weight = sample_weight[mask]
bin_weights = compute_bin_weights(bin_indices=bin_indices, sample_weight=sample_weight)
cuts = compute_cut_for_efficiency(target_efficiencies, mask=numpy.ones(len(y_pred), dtype=bool),
y_pred=y_pred, sample_weight=sample_weight)
result = 0.
for cut in cuts:
bin_efficiencies = compute_bin_efficiencies(y_pred, bin_indices=bin_indices,
cut=cut, sample_weight=sample_weight)
result += theil(bin_efficiencies, weights=bin_weights)
return result / len(cuts)
def compute_sde_on_bins(y_pred, mask, bin_indices, target_efficiencies, power=2., sample_weight=None):
# ignoring events from other classes
sample_weight = check_sample_weight(y_pred, sample_weight=sample_weight)
y_pred = y_pred[mask]
bin_indices = bin_indices[mask]
sample_weight = sample_weight[mask]
bin_weights = compute_bin_weights(bin_indices=bin_indices, sample_weight=sample_weight)
cuts = compute_cut_for_efficiency(target_efficiencies, mask=numpy.ones(len(y_pred), dtype=bool),
y_pred=y_pred, sample_weight=sample_weight)
result = 0.
for cut in cuts:
bin_efficiencies = compute_bin_efficiencies(y_pred, bin_indices=bin_indices,
cut=cut, sample_weight=sample_weight)
result += weighted_deviation(bin_efficiencies, weights=bin_weights, power=power)
return (result / len(cuts)) ** (1. / power)
def compute_theil_on_groups(y_pred, mask, groups_indices, target_efficiencies,
sample_weight):
y_pred = column_or_1d(y_pred)
sample_weight = check_sample_weight(y_pred, sample_weight=sample_weight)
groups_weights = compute_group_weights_by_indices(
groups_indices, sample_weight=sample_weight)
divided_weight = compute_divided_weight_by_indices(
groups_indices, sample_weight=sample_weight * mask)
cuts = compute_cut_for_efficiency(target_efficiencies,
mask=mask,
y_pred=y_pred,
sample_weight=sample_weight)
result = 0.
for cut in cuts:
groups_efficiencies = compute_group_efficiencies_by_indices(
y_pred,
groups_indices=groups_indices,
cut=cut,
divided_weight=divided_weight)
result += theil(groups_efficiencies, groups_weights)
return result / len(cuts)
