From 799bc785ba9537e93d15913ca2c68c0d21354a2a Mon Sep 17 00:00:00 2001
From: Alessio Berti <alessioberti90@gmail.com>
Date: Tue, 21 Apr 2020 18:26:42 +0200
Subject: [PATCH] [__init__.py]: added mask to recognize superstar files (real
and MC). Added class member containing a string with the data level (for the
moment calibrated or superstar).
---
ctapipe_io_magic/__init__.py | 45 ++++++++++++++++++++++++++++--------
1 file changed, 36 insertions(+), 9 deletions(-)
diff --git a/ctapipe_io_magic/__init__.py b/ctapipe_io_magic/__init__.py
index 0344d12..67294a8 100644
--- a/ctapipe_io_magic/__init__.py
+++ b/ctapipe_io_magic/__init__.py
@@ -71,14 +71,19 @@ class MAGICEventSource(EventSource):
run_info = list(map(self._get_run_info_from_name, self.file_list))
run_numbers = [i[0] for i in run_info]
is_mc_runs = [i[1] for i in run_info]
+ data_levels = [i[2] for i in run_info]
self.run_numbers, indices = np.unique(run_numbers, return_index=True)
is_mc_runs = [is_mc_runs[i] for i in indices]
is_mc_runs = np.unique(is_mc_runs)
+ data_levels = np.unique(data_levels)
# Checking if runt type (data/MC) is consistent:
if len(is_mc_runs) > 1:
raise ValueError("Loaded files contain data and MC runs. Please load only data OR Monte Carlos.")
+ if len(data_levels) > 1:
+ raise ValueError("Loaded files of different data level. Please load only data at the same level.")
self.is_mc = is_mc_runs[0]
+ self.data_level = data_levels[0]
# # Setting up the current run with the first run present in the data
# self.current_run = self._set_active_run(run_number=0)
@@ -155,25 +160,47 @@ class MAGICEventSource(EventSource):
A run number of the file.
"""
- mask_data = r".*\d+_M\d+_(\d+)\.\d+_Y_.*"
- mask_mc = r".*_M\d_za\d+to\d+_\d_(\d+)_Y_.*"
- mask_mc_alt = r".*_M\d_\d_(\d+)_.*"
- if len(re.findall(mask_data, file_name)) > 0:
- parsed_info = re.findall(mask_data, file_name)
+ mask_data_calibrated = r".*\d{6}_M\d+_(\d+)\.\d+_Y_.*"
+ mask_data_superstar = r".*\d{6}_(\d+)_S_.*"
+ mask_mc_calibrated = r".*_M\d_za\d+to\d+_\d_(\d+)_Y_.*"
+ mask_mc_calibrated_alt = r".*_M\d_\d_(\d+)_.*"
+ mask_mc_superstar = r".*_za\d+to\d+_\d_S_w0_(\d).*"
+ mask_mc_superstar_alt = r".*_za\d+to\d+_\d_S_w0__(\d).*"
+ if len(re.findall(mask_data_calibrated, file_name)) > 0:
+ parsed_info = re.findall(mask_data_calibrated, file_name)
is_mc = False
- elif len(re.findall(mask_mc, file_name)) > 0:
- parsed_info = re.findall(mask_mc, file_name)
+ data_level = 'calibrated'
+ elif len(re.findall(mask_data_superstar, file_name)) > 0:
+ parsed_info = re.findall(mask_data_superstar, file_name)
+ is_mc = False
+ data_level = 'superstar'
+ elif len(re.findall(mask_mc_calibrated, file_name)) > 0:
+ parsed_info = re.findall(mask_mc_calibrated, file_name)
+ is_mc = True
+ data_level = 'calibrated'
+ elif len(re.findall(mask_mc_calibrated_alt, file_name)) > 0:
+ parsed_info = re.findall(mask_mc_calibrated_alt, file_name)
+ is_mc = True
+ data_level = 'calibrated'
+ elif len(re.findall(mask_mc_superstar, file_name)) > 0:
+ parsed_info = re.findall(mask_mc_superstar, file_name)
+ is_mc = True
+ data_level = 'superstar'
+ elif len(re.findall(mask_mc_superstar_alt, file_name)) > 0:
+ parsed_info = re.findall(mask_mc_superstar_alt, file_name)
is_mc = True
+ data_level = 'superstar'
else:
- parsed_info = re.findall(mask_mc_alt, file_name)
+ parsed_info = re.findall(mask_mc_calibrated_alt, file_name)
is_mc = True
+ data_level = 'unknown'
try:
run_number = int(parsed_info[0])
except IndexError:
raise IndexError('Can not identify the run number and type (data/MC) of the file {:s}'.format(file_name))
- return run_number, is_mc
+ return run_number, is_mc, data_level
def _set_active_run(self, run_number):
"""
--
GitLab