def test_apply_models(simulated_dl1_file, simulated_dl2_file, rf_models):
from lstchain.reco.dl1_to_dl2 import apply_models
import joblib
dl1 = pd.read_hdf(simulated_dl1_file, key=dl1_params_lstcam_key)
dl1 = filter_events(
dl1,
filters=standard_config["events_filters"],
finite_params=standard_config['energy_regression_features'] +
standard_config['disp_regression_features'] +
standard_config['particle_classification_features'] +
standard_config['disp_classification_features'])
reg_energy = joblib.load(rf_models["energy"])
reg_cls_gh = joblib.load(rf_models["gh_sep"])
reg_disp_norm = joblib.load(rf_models["disp_norm"])
cls_disp_sign = joblib.load(rf_models["disp_sign"])
dl2 = apply_models(dl1,
reg_cls_gh,
reg_energy,
reg_disp_norm=reg_disp_norm,
cls_disp_sign=cls_disp_sign,
custom_config=standard_config)
dl2 = apply_models(dl1,
rf_models["gh_sep"],
rf_models["energy"],
reg_disp_norm=rf_models["disp_norm"],
cls_disp_sign=rf_models["disp_sign"],
custom_config=standard_config)
dl2.to_hdf(simulated_dl2_file, key=dl2_params_lstcam_key)
def main():
custom_config = {}
if args.config_file is not None:
try:
custom_config = read_configuration_file(os.path.abspath(args.config_file))
except("Custom configuration could not be loaded !!!"):
pass
config = replace_config(standard_config, custom_config)
data = pd.read_hdf(args.datafile, key=dl1_params_lstcam_key)
data = filter_events(data, filters=config["events_filters"])
#Load the trained RF for reconstruction:
fileE = args.path_models + "/reg_energy.sav"
fileD = args.path_models + "/reg_disp_vector.sav"
fileH = args.path_models + "/cls_gh.sav"
reg_energy = joblib.load(fileE)
reg_disp_vector = joblib.load(fileD)
cls_gh = joblib.load(fileH)
#Apply the models to the data
dl2 = dl1_to_dl2.apply_models(data, cls_gh, reg_energy, reg_disp_vector, custom_config=config)
os.makedirs(args.outdir, exist_ok=True)
outfile = args.outdir + '/dl2_' + os.path.basename(args.datafile)
shutil.copyfile(args.datafile, outfile)
write_dl2_dataframe(dl2.astype(float), outfile)
def test_apply_models():
from lstchain.reco.dl1_to_dl2 import apply_models
import pandas as pd
from sklearn.externals import joblib
dl1_file = 'dl1_gamma_test_large.h5'
dl1 = pd.read_hdf(dl1_file, key='events/LSTCam')
features = ['intensity', 'width', 'length']
# Load the trained RF for reconstruction:
file_energy = 'rf_energy.pkl'
file_disp = 'rf_disp.pkl'
file_cls_gh = 'rf_cls_gh.pkl'
reg_energy = joblib.load(file_energy)
reg_disp = joblib.load(file_disp)
reg_cls_gh = joblib.load(file_cls_gh)
apply_models(dl1, features, reg_cls_gh, reg_energy, reg_disp)
def main():
custom_config = {}
if args.config_file is not None:
try:
custom_config = read_configuration_file(
os.path.abspath(args.config_file))
except ("Custom configuration could not be loaded !!!"):
pass
config = replace_config(standard_config, custom_config)
data = pd.read_hdf(args.datafile, key=dl1_params_lstcam_key)
if config['source_dependent']:
data = pd.concat(
[data, pd.read_hdf(data, key=dl1_params_src_dep_lstcam_key)],
axis=1)
# Dealing with pointing missing values. This happened when `ucts_time` was invalid.
if 'alt_tel' in data.columns and 'az_tel' in data.columns \
and (np.isnan(data.alt_tel).any() or np.isnan(data.az_tel).any()):
# make sure there is a least one good pointing value to interp from.
if np.isfinite(data.alt_tel).any() and np.isfinite(data.az_tel).any():
data = impute_pointing(data)
else:
data.alt_tel = -np.pi / 2.
data.az_tel = -np.pi / 2.
data = filter_events(data, filters=config["events_filters"])
#Load the trained RF for reconstruction:
fileE = args.path_models + "/reg_energy.sav"
fileD = args.path_models + "/reg_disp_vector.sav"
fileH = args.path_models + "/cls_gh.sav"
reg_energy = joblib.load(fileE)
reg_disp_vector = joblib.load(fileD)
cls_gh = joblib.load(fileH)
#Apply the models to the data
dl2 = dl1_to_dl2.apply_models(data,
cls_gh,
reg_energy,
reg_disp_vector,
custom_config=config)
os.makedirs(args.outdir, exist_ok=True)
outfile = os.path.join(
args.outdir,
os.path.basename(args.datafile).replace('dl1', 'dl2'))
shutil.copyfile(args.datafile, outfile)
write_dl2_dataframe(dl2.astype(float), outfile)
def test_apply_models():
from lstchain.reco.dl1_to_dl2 import apply_models
import pandas as pd
from sklearn.externals import joblib
dl1 = pd.read_hdf(dl1_file, key=lstcam_key)
reg_energy = joblib.load(file_model_energy)
reg_disp = joblib.load(file_model_disp)
reg_cls_gh = joblib.load(file_model_gh_sep)
dl2 = apply_models(dl1,
reg_cls_gh,
reg_energy,
reg_disp,
custom_config=custom_config)
dl2.to_hdf(dl2_file, key=lstcam_key)
def test_apply_models():
from lstchain.reco.dl1_to_dl2 import apply_models
import joblib
dl1 = pd.read_hdf(dl1_file, key=dl1_params_lstcam_key)
dl1 = filter_events(dl1, filters=custom_config["events_filters"])
reg_energy = joblib.load(file_model_energy)
reg_disp = joblib.load(file_model_disp)
reg_cls_gh = joblib.load(file_model_gh_sep)
dl2 = apply_models(dl1,
reg_cls_gh,
reg_energy,
reg_disp,
custom_config=custom_config)
dl2.to_hdf(dl2_file, key=dl2_params_lstcam_key)
def test_apply_models():
from lstchain.reco.dl1_to_dl2 import apply_models
import joblib
dl1 = pd.read_hdf(dl1_file, key=dl1_params_lstcam_key)
dl1 = filter_events(
dl1,
filters=standard_config["events_filters"],
finite_params=standard_config['regression_features'] +
standard_config['classification_features'],
)
reg_energy = joblib.load(file_model_energy)
reg_disp = joblib.load(file_model_disp)
reg_cls_gh = joblib.load(file_model_gh_sep)
dl2 = apply_models(dl1,
reg_cls_gh,
reg_energy,
reg_disp,
custom_config=standard_config)
dl2.to_hdf(dl2_file, key=dl2_params_lstcam_key)
def main():
custom_config = {}
if args.config_file is not None:
try:
custom_config = read_configuration_file(args.config_file)
except ("Custom configuration could not be loaded !!!"):
pass
config = replace_config(standard_config, custom_config)
reg_energy, reg_disp_vector, cls_gh = dl1_to_dl2.build_models(
args.gammafile,
args.protonfile,
save_models=args.storerf,
path_models=args.path_models,
custom_config=config,
)
gammas = filter_events(
pd.read_hdf(args.gammatest, key=dl1_params_lstcam_key),
config["events_filters"],
)
proton = filter_events(
pd.read_hdf(args.protontest, key=dl1_params_lstcam_key),
config["events_filters"],
)
data = pd.concat([gammas, proton], ignore_index=True)
dl2 = dl1_to_dl2.apply_models(data,
cls_gh,
reg_energy,
reg_disp_vector,
custom_config=config)
####PLOT SOME RESULTS#####
selected_gammas = dl2.query('reco_type==0 & mc_type==0')
if (len(selected_gammas) == 0):
log.warning('No gammas selected, I will not plot any output')
sys.exit()
plot_dl2.plot_features(dl2)
if not args.batch:
plt.show()
plot_dl2.energy_results(selected_gammas)
if not args.batch:
plt.show()
plot_dl2.direction_results(selected_gammas)
if not args.batch:
plt.show()
plot_dl2.plot_disp_vector(selected_gammas)
if not args.batch:
plt.show()
plot_dl2.plot_pos(dl2)
if not args.batch:
plt.show()
plot_dl2.plot_roc_gamma(dl2)
if not args.batch:
plt.show()
plot_dl2.plot_models_features_importances(args.path_models,
args.config_file)
if not args.batch:
plt.show()
plt.hist(dl2[dl2['mc_type'] == 101]['gammaness'], bins=100)
plt.hist(dl2[dl2['mc_type'] == 0]['gammaness'], bins=100)
if not args.batch:
plt.show()
def main():
args = parser.parse_args()
custom_config = {}
if args.config_file is not None:
try:
custom_config = read_configuration_file(
os.path.abspath(args.config_file))
except ("Custom configuration could not be loaded !!!"):
pass
config = replace_config(standard_config, custom_config)
data = pd.read_hdf(args.input_file, key=dl1_params_lstcam_key)
if 'lh_fit_config' in config.keys():
lhfit_data = pd.read_hdf(args.input_file,
key=dl1_likelihood_params_lstcam_key)
if np.all(lhfit_data['obs_id'] == data['obs_id']) & np.all(
lhfit_data['event_id'] == data['event_id']):
lhfit_data.drop({'obs_id', 'event_id'}, axis=1, inplace=True)
lhfit_keys = lhfit_data.keys()
data = pd.concat([data, lhfit_data], axis=1)
# if real data, add deltat t to dataframe keys
data = add_delta_t_key(data)
# Dealing with pointing missing values. This happened when `ucts_time` was invalid.
if 'alt_tel' in data.columns and 'az_tel' in data.columns \
and (np.isnan(data.alt_tel).any() or np.isnan(data.az_tel).any()):
# make sure there is a least one good pointing value to interp from.
if np.isfinite(data.alt_tel).any() and np.isfinite(data.az_tel).any():
data = impute_pointing(data)
else:
data.alt_tel = -np.pi / 2.
data.az_tel = -np.pi / 2.
# Get trained RF path for reconstruction:
file_reg_energy = os.path.join(args.path_models, 'reg_energy.sav')
file_cls_gh = os.path.join(args.path_models, 'cls_gh.sav')
if config['disp_method'] == 'disp_vector':
file_disp_vector = os.path.join(args.path_models,
'reg_disp_vector.sav')
elif config['disp_method'] == 'disp_norm_sign':
file_disp_norm = os.path.join(args.path_models, 'reg_disp_norm.sav')
file_disp_sign = os.path.join(args.path_models, 'cls_disp_sign.sav')
subarray_info = SubarrayDescription.from_hdf(args.input_file)
tel_id = config["allowed_tels"][0] if "allowed_tels" in config else 1
focal_length = subarray_info.tel[tel_id].optics.equivalent_focal_length
# Apply the models to the data
# Source-independent analysis
if not config['source_dependent']:
data = filter_events(
data,
filters=config["events_filters"],
finite_params=config['energy_regression_features'] +
config['disp_regression_features'] +
config['particle_classification_features'] +
config['disp_classification_features'],
)
if config['disp_method'] == 'disp_vector':
dl2 = dl1_to_dl2.apply_models(data,
file_cls_gh,
file_reg_energy,
reg_disp_vector=file_disp_vector,
focal_length=focal_length,
custom_config=config)
elif config['disp_method'] == 'disp_norm_sign':
dl2 = dl1_to_dl2.apply_models(data,
file_cls_gh,
file_reg_energy,
reg_disp_norm=file_disp_norm,
cls_disp_sign=file_disp_sign,
focal_length=focal_length,
custom_config=config)
# Source-dependent analysis
if config['source_dependent']:
# if source-dependent parameters are already in dl1 data, just read those data.
if dl1_params_src_dep_lstcam_key in get_dataset_keys(args.input_file):
data_srcdep = get_srcdep_params(args.input_file)
# if not, source-dependent parameters are added now
else:
data_srcdep = pd.concat(dl1_to_dl2.get_source_dependent_parameters(
data, config, focal_length=focal_length),
axis=1)
dl2_srcdep_dict = {}
srcindep_keys = data.keys()
srcdep_assumed_positions = data_srcdep.columns.levels[0]
for i, k in enumerate(srcdep_assumed_positions):
data_with_srcdep_param = pd.concat([data, data_srcdep[k]], axis=1)
data_with_srcdep_param = filter_events(
data_with_srcdep_param,
filters=config["events_filters"],
finite_params=config['energy_regression_features'] +
config['disp_regression_features'] +
config['particle_classification_features'] +
config['disp_classification_features'],
)
if config['disp_method'] == 'disp_vector':
dl2_df = dl1_to_dl2.apply_models(
data_with_srcdep_param,
file_cls_gh,
file_reg_energy,
reg_disp_vector=file_disp_vector,
focal_length=focal_length,
custom_config=config)
elif config['disp_method'] == 'disp_norm_sign':
dl2_df = dl1_to_dl2.apply_models(data_with_srcdep_param,
file_cls_gh,
file_reg_energy,
reg_disp_norm=file_disp_norm,
cls_disp_sign=file_disp_sign,
focal_length=focal_length,
custom_config=config)
dl2_srcdep = dl2_df.drop(srcindep_keys, axis=1)
dl2_srcdep_dict[k] = dl2_srcdep
if i == 0:
dl2_srcindep = dl2_df[srcindep_keys]
os.makedirs(args.output_dir, exist_ok=True)
output_file = os.path.join(
args.output_dir,
os.path.basename(args.input_file).replace('dl1', 'dl2', 1))
if os.path.exists(output_file):
raise IOError(output_file + ' exists, exiting.')
dl1_keys = get_dataset_keys(args.input_file)
if dl1_images_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_images_lstcam_key)
if dl1_params_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_params_lstcam_key)
if dl1_params_src_dep_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_params_src_dep_lstcam_key)
if dl1_likelihood_params_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_likelihood_params_lstcam_key)
metadata = global_metadata()
write_metadata(metadata, output_file)
with open_file(args.input_file, 'r') as h5in:
with open_file(output_file, 'a') as h5out:
# Write the selected DL1 info
for k in dl1_keys:
if not k.startswith('/'):
k = '/' + k
path, name = k.rsplit('/', 1)
if path not in h5out:
grouppath, groupname = path.rsplit('/', 1)
g = h5out.create_group(grouppath,
groupname,
createparents=True)
else:
g = h5out.get_node(path)
h5in.copy_node(k, g, overwrite=True)
# need container to use lstchain.io.add_global_metadata and lstchain.io.add_config_metadata
if not config['source_dependent']:
if 'lh_fit_config' not in config.keys():
write_dl2_dataframe(dl2, output_file, config=config, meta=metadata)
else:
dl2_onlylhfit = dl2[lhfit_keys]
dl2.drop(lhfit_keys, axis=1, inplace=True)
write_dl2_dataframe(dl2, output_file, config=config, meta=metadata)
write_dataframe(dl2_onlylhfit,
output_file,
dl2_likelihood_params_lstcam_key,
config=config,
meta=metadata)
else:
write_dl2_dataframe(dl2_srcindep,
output_file,
config=config,
meta=metadata)
write_dataframe(pd.concat(dl2_srcdep_dict, axis=1),
output_file,
dl2_params_src_dep_lstcam_key,
config=config,
meta=metadata)
def main():
custom_config = {}
if args.config_file is not None:
try:
custom_config = read_configuration_file(args.config_file)
except ("Custom configuration could not be loaded !!!"):
pass
config = replace_config(standard_config, custom_config)
reg_energy, reg_disp_vector, cls_gh = dl1_to_dl2.build_models(
args.gammafile,
args.protonfile,
save_models=args.storerf,
path_models=args.path_models,
custom_config=config,
)
gammas = filter_events(
pd.read_hdf(args.gammatest, key=dl1_params_lstcam_key),
config["events_filters"],
)
proton = filter_events(
pd.read_hdf(args.protontest, key=dl1_params_lstcam_key),
config["events_filters"],
)
data = pd.concat([gammas, proton], ignore_index=True)
dl2 = dl1_to_dl2.apply_models(data,
cls_gh,
reg_energy,
reg_disp_vector,
custom_config=config)
####PLOT SOME RESULTS#####
gammas = dl2[dl2.gammaness >= 0.5]
protons = dl2[dl2.gammaness < 0.5]
gammas.reco_type = 0
protons.reco_type = 1
focal_length = 28 * u.m
src_pos_reco = utils.reco_source_position_sky(
gammas.x.values * u.m, gammas.y.values * u.m,
gammas.reco_disp_dx.values * u.m, gammas.reco_disp_dy.values * u.m,
focal_length, gammas.mc_alt_tel.values * u.rad,
gammas.mc_az_tel.values * u.rad)
plot_dl2.plot_features(dl2)
plt.show()
plot_dl2.plot_e(gammas, 10, 1.5, 3.5)
plt.show()
plot_dl2.calc_resolution(gammas)
plt.show()
plot_dl2.plot_e_resolution(gammas, 10, 1.5, 3.5)
plt.show()
plot_dl2.plot_disp_vector(gammas)
plt.show()
try:
ctaplot.plot_theta2(
gammas.mc_alt,
np.arctan(np.tan(gammas.mc_az)),
src_pos_reco.alt.rad,
np.arctan(np.tan(src_pos_reco.az.rad)),
bins=50,
range=(0, 1),
)
plt.show()
ctaplot.plot_angular_res_per_energy(
src_pos_reco.alt.rad, np.arctan(np.tan(src_pos_reco.az.rad)),
gammas.mc_alt, np.arctan(np.tan(gammas.mc_az)), gammas.mc_energy)
plt.show()
except:
pass
regression_features = config["regression_features"]
classification_features = config["classification_features"]
plt.show()
plot_dl2.plot_pos(dl2)
plt.show()
plot_dl2.plot_ROC(cls_gh, dl2, classification_features, -1)
plt.show()
plot_dl2.plot_importances(cls_gh, classification_features)
plt.show()
plot_dl2.plot_importances(reg_energy, regression_features)
plt.show()
plot_dl2.plot_importances(reg_disp_vector, regression_features)
plt.show()
plt.hist(dl2[dl2['mc_type'] == 101]['gammaness'], bins=100)
plt.hist(dl2[dl2['mc_type'] == 0]['gammaness'], bins=100)
plt.show()
def main():
custom_config = {}
if args.config_file is not None:
try:
custom_config = read_configuration_file(
os.path.abspath(args.config_file))
except ("Custom configuration could not be loaded !!!"):
pass
config = replace_config(standard_config, custom_config)
data = pd.read_hdf(args.input_file, key=dl1_params_lstcam_key)
if config['source_dependent']:
data_src_dep = pd.read_hdf(args.input_file,
key=dl1_params_src_dep_lstcam_key)
data = pd.concat([data, data_src_dep], axis=1)
# Dealing with pointing missing values. This happened when `ucts_time` was invalid.
if 'alt_tel' in data.columns and 'az_tel' in data.columns \
and (np.isnan(data.alt_tel).any() or np.isnan(data.az_tel).any()):
# make sure there is a least one good pointing value to interp from.
if np.isfinite(data.alt_tel).any() and np.isfinite(data.az_tel).any():
data = impute_pointing(data)
else:
data.alt_tel = -np.pi / 2.
data.az_tel = -np.pi / 2.
data = filter_events(
data,
filters=config["events_filters"],
finite_params=config['regression_features'] +
config['classification_features'],
)
#Load the trained RF for reconstruction:
fileE = args.path_models + "/reg_energy.sav"
fileD = args.path_models + "/reg_disp_vector.sav"
fileH = args.path_models + "/cls_gh.sav"
reg_energy = joblib.load(fileE)
reg_disp_vector = joblib.load(fileD)
cls_gh = joblib.load(fileH)
#Apply the models to the data
dl2 = dl1_to_dl2.apply_models(data,
cls_gh,
reg_energy,
reg_disp_vector,
custom_config=config)
os.makedirs(args.output_dir, exist_ok=True)
output_file = os.path.join(
args.output_dir,
os.path.basename(args.input_file).replace('dl1', 'dl2'))
if os.path.exists(output_file):
raise IOError(output_file + ' exists, exiting.')
dl1_keys = get_dataset_keys(args.input_file)
if dl1_images_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_images_lstcam_key)
if dl1_params_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_params_lstcam_key)
if dl1_params_src_dep_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_params_src_dep_lstcam_key)
with open_file(args.input_file, 'r') as h5in:
with open_file(output_file, 'a') as h5out:
# Write the selected DL1 info
for k in dl1_keys:
if not k.startswith('/'):
k = '/' + k
path, name = k.rsplit('/', 1)
if path not in h5out:
grouppath, groupname = path.rsplit('/', 1)
g = h5out.create_group(grouppath,
groupname,
createparents=True)
else:
g = h5out.get_node(path)
h5in.copy_node(k, g, overwrite=True)
write_dl2_dataframe(dl2, output_file)
data = filter_events(data, filters=config["events_filters"])
#Load the trained RF for reconstruction:
fileE = args.path_models + "/reg_energy.sav"
fileD = args.path_models + "/reg_disp_vector.sav"
fileH = args.path_models + "/cls_gh.sav"
reg_energy = joblib.load(fileE)
reg_disp_vector = joblib.load(fileD)
cls_gh = joblib.load(fileH)
#Apply the models to the data
dl2 = dl1_to_dl2.apply_models(data,
cls_gh,
reg_energy,
reg_disp_vector,
custom_config=config)
if args.storeresults == True:
#Store results
os.makedirs(args.outdir, exist_ok=True)
outfile = args.outdir + '/dl2_' + os.path.basename(
args.datafile).split('.')[0] + '.h5'
dl2.to_hdf(outfile, key="events/LSTCam", mode="w")
keys = get_dataset_keys(dl1_file)
groups = set([k.split('/')[0] for k in keys])
groups.remove('events') # we don't want to copy DL1 events
def main():
args = parser.parse_args()
custom_config = {}
if args.config_file is not None:
custom_config = read_configuration_file(args.config_file)
config = replace_config(standard_config, custom_config)
subarray_info = SubarrayDescription.from_hdf(args.gammatest)
tel_id = config["allowed_tels"][0] if "allowed_tels" in config else 1
focal_length = subarray_info.tel[tel_id].optics.equivalent_focal_length
reg_energy, reg_disp_norm, cls_disp_sign, cls_gh = dl1_to_dl2.build_models(
args.gammafile,
args.protonfile,
save_models=args.save_models,
path_models=args.path_models,
custom_config=config,
)
gammas = filter_events(
pd.read_hdf(args.gammatest, key=dl1_params_lstcam_key),
config["events_filters"],
)
proton = filter_events(
pd.read_hdf(args.protontest, key=dl1_params_lstcam_key),
config["events_filters"],
)
data = pd.concat([gammas, proton], ignore_index=True)
dl2 = dl1_to_dl2.apply_models(data,
cls_gh,
reg_energy,
reg_disp_norm=reg_disp_norm,
cls_disp_sign=cls_disp_sign,
focal_length=focal_length,
custom_config=config)
####PLOT SOME RESULTS#####
selected_gammas = dl2.query('reco_type==0 & mc_type==0')
if (len(selected_gammas) == 0):
log.warning('No gammas selected, I will not plot any output')
sys.exit()
plot_dl2.plot_features(dl2)
if not args.batch:
plt.show()
plot_dl2.energy_results(selected_gammas)
if not args.batch:
plt.show()
plot_dl2.direction_results(selected_gammas)
if not args.batch:
plt.show()
plot_dl2.plot_disp_vector(selected_gammas)
if not args.batch:
plt.show()
plot_dl2.plot_pos(dl2)
if not args.batch:
plt.show()
plot_dl2.plot_roc_gamma(dl2)
if not args.batch:
plt.show()
plot_dl2.plot_models_features_importances(args.path_models,
args.config_file)
if not args.batch:
plt.show()
plt.hist(dl2[dl2['mc_type'] == 101]['gammaness'], bins=100)
plt.hist(dl2[dl2['mc_type'] == 0]['gammaness'], bins=100)
if not args.batch:
plt.show()
]
reg_energy, reg_disp, cls_gh = dl1_to_dl2.build_models(
args.gammafile,
args.protonfile,
features,
save_models=args.storerf,
path_models=args.path_models,
)
#Get out the data from the Simtelarray file:
data = dl0_to_dl1.get_events(args.datafile, False)
#Apply the models to the data
dl2 = dl1_to_dl2.apply_models(data, features, cls_gh, reg_energy, reg_disp)
if args.storeresults == True:
#Store results
if not os.path.exists(args.outdir):
os.mkdir(args.outdir)
outfile = args.outdir + "/dl2_events.hdf5"
dl2.to_hdf(outfile, key="dl2_events", mode="w")
#Plot some results
plot_dl2.plot_features(dl2)
plt.show()
plot_dl2.plot_E(dl2)
plt.show()
plot_dl2.plot_disp(dl2)
fileH = args.path_models + "/cls_gh.sav"
RFreg_Energy = joblib.load(fileE)
RFreg_Disp = joblib.load(fileD)
RFcls_GH = joblib.load(fileH)
#Apply the models to the data
features = ['intensity',
'time_gradient',
'width',
'length',
'wl',
'phi',
'psi']
dl2 = dl1_to_dl2.apply_models(data, features, RFcls_GH, RFreg_Energy, RFreg_Disp)
if args.storeresults==True:
#Store results
os.makedirs(args.outdir, exist_ok=True)
outfile = args.outdir+"/dl2_events.hdf5"
dl2.to_hdf(outfile, key="dl2_events", mode="w")
#Plot some results
plot_dl2.plot_features(dl2)
plt.show()
plot_dl2.plot_e(dl2)
plt.show()
plot_dl2.plot_disp(dl2)
plt.show()
def main():
custom_config = {}
if args.config_file is not None:
try:
custom_config = read_configuration_file(
os.path.abspath(args.config_file))
except ("Custom configuration could not be loaded !!!"):
pass
config = replace_config(standard_config, custom_config)
data = pd.read_hdf(args.input_file, key=dl1_params_lstcam_key)
# if real data, add deltat t to dataframe keys
data = add_delta_t_key(data)
# Dealing with pointing missing values. This happened when `ucts_time` was invalid.
if 'alt_tel' in data.columns and 'az_tel' in data.columns \
and (np.isnan(data.alt_tel).any() or np.isnan(data.az_tel).any()):
# make sure there is a least one good pointing value to interp from.
if np.isfinite(data.alt_tel).any() and np.isfinite(data.az_tel).any():
data = impute_pointing(data)
else:
data.alt_tel = -np.pi / 2.
data.az_tel = -np.pi / 2.
# Load the trained RF for reconstruction:
fileE = args.path_models + "/reg_energy.sav"
fileD = args.path_models + "/reg_disp_vector.sav"
fileH = args.path_models + "/cls_gh.sav"
reg_energy = joblib.load(fileE)
reg_disp_vector = joblib.load(fileD)
cls_gh = joblib.load(fileH)
subarray_info = SubarrayDescription.from_hdf(args.input_file)
tel_id = config["allowed_tels"][0] if "allowed_tels" in config else 1
focal_length = subarray_info.tel[tel_id].optics.equivalent_focal_length
# Apply the models to the data
# Source-independent analysis
if not config['source_dependent']:
data = filter_events(
data,
filters=config["events_filters"],
finite_params=config['regression_features'] +
config['classification_features'],
)
dl2 = dl1_to_dl2.apply_models(data,
cls_gh,
reg_energy,
reg_disp_vector,
focal_length=focal_length,
custom_config=config)
# Source-dependent analysis
if config['source_dependent']:
data_srcdep = pd.read_hdf(args.input_file,
key=dl1_params_src_dep_lstcam_key)
data_srcdep.columns = pd.MultiIndex.from_tuples([
tuple(col[1:-1].replace('\'', '').replace(' ', '').split(","))
for col in data_srcdep.columns
])
dl2_srcdep_dict = {}
for i, k in enumerate(data_srcdep.columns.levels[0]):
data_with_srcdep_param = pd.concat([data, data_srcdep[k]], axis=1)
data_with_srcdep_param = filter_events(
data_with_srcdep_param,
filters=config["events_filters"],
finite_params=config['regression_features'] +
config['classification_features'],
)
dl2_df = dl1_to_dl2.apply_models(data_with_srcdep_param,
cls_gh,
reg_energy,
reg_disp_vector,
focal_length=focal_length,
custom_config=config)
dl2_srcdep = dl2_df.drop(data.keys(), axis=1)
dl2_srcdep_dict[k] = dl2_srcdep
if i == 0:
dl2_srcindep = dl2_df.drop(data_srcdep[k].keys(), axis=1)
os.makedirs(args.output_dir, exist_ok=True)
output_file = os.path.join(
args.output_dir,
os.path.basename(args.input_file).replace('dl1', 'dl2'))
if os.path.exists(output_file):
raise IOError(output_file + ' exists, exiting.')
dl1_keys = get_dataset_keys(args.input_file)
if dl1_images_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_images_lstcam_key)
if dl1_params_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_params_lstcam_key)
if dl1_params_src_dep_lstcam_key in dl1_keys:
dl1_keys.remove(dl1_params_src_dep_lstcam_key)
with open_file(args.input_file, 'r') as h5in:
with open_file(output_file, 'a') as h5out:
# Write the selected DL1 info
for k in dl1_keys:
if not k.startswith('/'):
k = '/' + k
path, name = k.rsplit('/', 1)
if path not in h5out:
grouppath, groupname = path.rsplit('/', 1)
g = h5out.create_group(grouppath,
groupname,
createparents=True)
else:
g = h5out.get_node(path)
h5in.copy_node(k, g, overwrite=True)
if not config['source_dependent']:
write_dl2_dataframe(dl2, output_file)
else:
write_dl2_dataframe(dl2_srcindep, output_file)
write_dataframe(pd.concat(dl2_srcdep_dict, axis=1), output_file,
dl2_params_src_dep_lstcam_key)
