def calculate_residual_2D(efficiency_data: Hist, efficiency_function: Callable[..., float],
efficiency_period: Any, centrality_bin: int) -> Tuple[np.ndarray, List[float], List[float]]:
""" Calculate residual for 2D tracking efficiency.
There is a separate 1D and 2D function for convenience. If there is no entries for a particular
bin, we set the value to NaN so that it can be ignored later when plotting.
Args:
efficiency_data: 2D efficiency data.
efficiency_function: Efficiency function.
efficiency_period: Efficiency period.
centrality_bin: Centrality bin.
Returns:
Calculated residual, pt values where it was evaluated, eta values where it was evaluated.
"""
pts = [efficiency_data.GetXaxis().GetBinCenter(x) for x in range(1, efficiency_data.GetXaxis().GetNbins() + 1)]
etas = [efficiency_data.GetYaxis().GetBinCenter(y) for y in range(1, efficiency_data.GetYaxis().GetNbins() + 1)]
residual = np.zeros(shape = (efficiency_data.GetXaxis().GetNbins(),
efficiency_data.GetYaxis().GetNbins()))
# Loop over all of the bins in the data histogram.
chi_2 = []
for pt_index, pt in enumerate(pts):
for eta_index, eta in enumerate(etas):
x = pt_index + 1
y = eta_index + 1
# Calculate the efficiency. It's calculated again here to ensure that it's evaluated at exactly
# the same location as in the data histogram.
efficiency_at_value = efficiency_function(pt, eta, centrality_bin, efficiency_period, "task_name")
# Determine the histogram value, setting it to NaN if there's no entries.
if np.abs(efficiency_data.GetBinContent(x, y)) < epsilon:
value = np.nan
else:
value = (efficiency_data.GetBinContent(x, y) - efficiency_at_value) / efficiency_at_value * 100.
# The points around the edges aren't super reliable for calcuating chi squared
if pt > 1 and np.abs(eta) < 0.8:
chi_2.append(np.power(efficiency_data.GetBinContent(x, y) - efficiency_at_value, 2) / np.power(efficiency_data.GetBinError(x, y), 2))
residual[pt_index, eta_index] = value
# Check max values
logger.debug(f"min efficiency_data: {efficiency_data.GetMinimum()}, "
f"max efficiency_data: {efficiency_data.GetMaximum()}")
logger.debug(f"min residual: {np.nanmin(residual)}, max residual: {np.nanmax(residual)}")
logger.debug(f"standard mean: {np.nanmean(residual)}")
logger.debug(f"restricted mean: {np.nanmean(residual[:,np.abs(etas) < 0.8])}")
logger.debug(f"len(pts): {len(pts)}, len(etas): {len(etas)}")
# Check chi squared
chi_squared = np.sum(chi_2)
# 23 is the number of parameters (10 + 13) at any given point
ndf = len(chi_2) - 23
logger.warning("NOTE: The restricted chi squared value calculated here may not be super reliable.")
logger.info(f"Chi squared: {chi_squared}")
logger.info(f"NDF: {ndf}")
logger.info(f"chi2/ndf: {chi_squared / ndf}")
return residual, pts, etas
def _access_set_of_values_associated_with_a_bin(
hist: Hist, bin_of_interest: int,
response_normalization: ResponseNormalization
) -> Tuple[np.ndarray, np.ndarray]:
""" Access a set of bins associated with a particular bin value in the other axis.
For example, if the hist looks like this graphically:
a b c
d e f
g h i <- values (here and above)
1 2 3 <- bin number
then in the case of accessing a set of y bins associated with an x bin, for example, x bin 2,
it would return values h, e, and b.
Args:
hist: The histogram whose bins should be accessed. This must be a 2D hist.
bin_of_interest: Bin which we would like to access.
response_normalization: Response normalization convention, which dictates which axis to retrieve the bins from.
Returns:
Array of the bin contents, Array of bin errors
"""
# Initial setup
axis, get_bin = _setup_access_bins(
response_normalization=response_normalization)
#logger.debug(f"Axis: {axis(hist)}, getBin: {get_bin}")
set_of_bins_content = np.zeros(axis(hist).GetNbins())
set_of_bins_errors = np.zeros(axis(hist).GetNbins())
for array_index, bin_index in enumerate(range(1,
axis(hist).GetNbins() + 1)):
set_of_bins_content[array_index] = hist.GetBinContent(
get_bin(hist, bin_of_interest, bin_index))
set_of_bins_errors[array_index] = hist.GetBinError(
get_bin(hist, bin_of_interest, bin_index))
return set_of_bins_content, set_of_bins_errors
