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_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)
