Skip to content

Comparison of Data and MC Distributions with gammas and dl3 #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jebuss wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Comparison of Data and MC Distributions with gammas and dl3 #33

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3a62a12
add kind gammas
jebuss Jun 14, 2019
310ed0a
add option to merge dl3 features to perform theta and prediction cut
jebuss Jun 14, 2019
ac33f9b
readd calc_weight_change_index
jebuss Jun 14, 2019
8061c7f
print event rate in per hour
jebuss Jun 14, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 33 additions & 3 deletions fact_plots/scripts/plot_data_mc_compare.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
from fact.io import read_h5py
from fact.analysis.statistics import calc_proton_obstime, calc_weight_change_index
from fact.analysis.statistics import calc_proton_obstime, calc_gamma_obstime, calc_weight_change_index
import astropy.units as u
import numpy as np
import click
Expand All @@ -10,6 +10,11 @@
from tqdm import tqdm
from fnmatch import fnmatch

dl3_ids = dict(
observations=['event_num','run_id','night'],
gammas=['event_num','run_id','corsika_run_header_run_number','corsika_event_header_event_number'],
protons=['event_num','run_id','corsika_run_header_run_number','corsika_event_header_event_number'],
)

def wrap_angle(angle):
angle = np.asanyarray(angle).copy()
Expand Down Expand Up @@ -94,10 +99,18 @@ def main(config, outputfile):

# get columns available in all datasets and calculate weights
weights = OrderedDict()
dl3 = OrderedDict()
for i, dataset in enumerate(config['datasets']):
l = dataset['label']
df = read_h5py(dataset['path'], key='events', last=1)

if 'prediction' in config.keys():
if 'dl3_path' in dataset.keys():
dl3[l] = read_h5py(dataset['dl3_path'], key='events')
dl3[l] = dl3[l].query(f"gamma_prediction >= {config['prediction']['threshold']}")
dl3[l] = dl3[l].query(f"theta_deg <= {np.sqrt(config['prediction']['theta'])}")


if i == 0:
common_columns = set(df.columns)
else:
Expand All @@ -121,6 +134,21 @@ def main(config, outputfile):
)
weights[l] = 1 / (ontime.to_value(u.hour) * sample_fraction)

elif dataset['kind'] == 'gammas':

norm = dataset['phi_0']
norm = u.Quantity(norm['value'], norm['unit'])
sample_fraction = dataset.get('sample_fraction', 1.0)
ontime = calc_gamma_obstime(
n_events=float(dataset['n_showers']),
spectral_index=dataset['spectral_index'],
max_impact=dataset['max_impact'] * u.m,
e_min=float(dataset['e_min']) * u.GeV,
e_max=float(dataset['e_max']) * u.GeV,
flux_normalization=norm,
)
weights[l] = 1 / (ontime.to_value(u.hour) * sample_fraction)

# select columns
columns = config.get('include_columns')
if columns is not None:
Expand Down Expand Up @@ -157,7 +185,7 @@ def excluded(column):
dfs = OrderedDict()
for dataset in config['datasets']:
l = dataset['label']
dfs[l] = read_h5py(dataset['path'], key='events', columns=[column])
dfs[l] = read_h5py(dataset['path'], key='events', columns=[column]+dl3_ids[dataset['kind']])
dfs[l]['weight'] = weights[l]

if dataset['kind'] == 'protons':
Expand All @@ -178,11 +206,13 @@ def excluded(column):
).to_value(u.dimensionless_unscaled)

dfs[l]['weight'] *= index_weights[l]
if l in dl3.keys():
dfs[l] = dl3[l].merge(dfs[l], on=dl3_ids[dataset['kind']])


if i == 0:
for l, df in dfs.items():
print(f'{l: <15}', f'{df["weight"].sum() / 3600:.1f} Events/s')
print(f'{l: <15}', f'{df["weight"].sum() / 60:.1f} Events/h ')

ax_hist.cla()
try:
Expand Down