Skip to content
Snippets Groups Projects

[AGIPD][DARK] Sort dark runs

Merged [AGIPD][DARK] Sort dark runs
feat/sort_dark_runs_agipd2 into master
All threads resolved!
Merged Karim Ahmed requested to merge feat/sort_dark_runs_agipd2 into master
All threads resolved!
Compare
and
4 files
+ 96
− 64
Compare changes
  • Side-by-side
  • Inline
Files
4
notebooks/AGIPD/Characterize_AGIPD_Gain_Darks_NBC.ipynb
+ 24
− 29
%% Cell type:markdown id: tags:
# AGIPD Characterize Dark Images #
Author: European XFEL Detector Group, Version: 2.0
The following code analyzes a set of dark images taken with the AGIPD detector to deduce detector offsets , noise, bad-pixel maps and thresholding. All four types of constants are evaluated per-pixel and per-memory cell. Data for the detector's three gain stages needs to be present, separated into separate runs.
The evaluated calibration constants are stored locally and injected in the calibration data base.
%% Cell type:code id: tags:
``` python
in_folder = "/gpfs/exfel/d/raw/CALLAB/202031/p900113" # path to input data, required
out_folder = "" # path to output to, required
metadata_folder = "" # Directory containing calibration_metadata.yml when run by xfel-calibrate
modules = [-1] # list of modules to evaluate, RANGE ALLOWED
run_high = 9985 # run number in which high gain data was recorded, required
run_med = 9984 # run number in which medium gain data was recorded, required
run_low = 9983 # run number in which low gain data was recorded, required
operation_mode = "ADAPTIVE_GAIN" # Detector operation mode, optional (defaults to "ADAPTIVE_GAIN")
karabo_id = "HED_DET_AGIPD500K2G" # karabo karabo_id
karabo_da = ['-1'] # a list of data aggregators names, Default [-1] for selecting all data aggregators
receiver_template = "{}CH0" # inset for receiver devices
instrument_source_template = '{}/DET/{}:xtdf' # path in the HDF5 file to images
ctrl_source_template = '{}/MDL/FPGA_COMP' # path to control information
karabo_id_control = "HED_EXP_AGIPD500K2G" # karabo-id for control device '
use_dir_creation_date = True # use dir creation date as data production reference date
cal_db_interface = "tcp://max-exfl-cal001:8020" # the database interface to use
cal_db_timeout = 3000000 # timeout on caldb requests"
local_output = True # output constants locally
db_output = False # output constants to database
+1
sort_runs = True # Sort the selected dark runs. This flag is added for old data (e.g. 900174 r0011).
mem_cells = 0 # number of memory cells used, set to 0 to automatically infer
bias_voltage = 0 # bias voltage, set to 0 to use stored value in slow data.
gain_setting = -1 # the gain setting, use -1 to use value stored in slow data.
gain_mode = -1 # gain mode, use -1 to use value stored in slow data.
integration_time = -1 # integration time, negative values for auto-detection.
acq_rate = 0. # the detector acquisition rate, use 0 to try to auto-determine
interlaced = False # assume interlaced data format, for data prior to Dec. 2017
thresholds_offset_sigma = 3. # offset sigma thresholds for offset deduced bad pixels
thresholds_offset_hard = [0, 0] # For setting the same threshold offset for the 3 gains. Left for backward compatibility. Default [0, 0] to take the following parameters.
thresholds_offset_hard_hg = [3000, 7000] # High-gain thresholds in absolute ADU terms for offset deduced bad pixels
thresholds_offset_hard_mg = [6000, 10000] # Medium-gain thresholds in absolute ADU terms for offset deduced bad pixels
thresholds_offset_hard_lg = [6000, 10000] # Low-gain thresholds in absolute ADU terms for offset deduced bad pixels
thresholds_offset_hard_hg_fixed = [3500, 6500] # Same as thresholds_offset_hard_hg, but for fixed gain operation
thresholds_offset_hard_mg_fixed = [3500, 6500] # Same as thresholds_offset_hard_mg, but for fixed gain operation
thresholds_offset_hard_lg_fixed = [3500, 6500] # Same as thresholds_offset_hard_lg, but for fixed gain operation
thresholds_noise_sigma = 5. # noise sigma thresholds for offset deduced bad pixels
thresholds_noise_hard = [0, 0] # For setting the same threshold noise for the 3 gains. Left for backward compatibility. Default [0, 0] to take the following parameters.
thresholds_noise_hard_hg = [4, 20] # High-gain thresholds in absolute ADU terms for offset deduced bad pixels
thresholds_noise_hard_mg = [4, 20] # Medium-gain thresholds in absolute ADU terms for offset deduced bad pixels
thresholds_noise_hard_lg = [4, 20] # Low-gain thresholds in absolute ADU terms for offset deduced bad pixels
thresholds_gain_sigma = 5. # Gain separation sigma threshold
max_trains = 550 # Maximum number of trains to use for processing dark. Set to 0 to process all available trains. 550 added for ~500GB nodes to temporarily avoid memory issues.
min_trains = 1 # Minimum number of trains for processing dark. If run folder has less than minimum trains, processing is stopped.
high_res_badpix_3d = False # set this to True if you need high-resolution 3d bad pixel plots. ~7mins extra time for 64 memory cells
# This is used if modules is not specified:
def find_modules(in_folder, run_high, modules):
if (modules is not None) and modules != [-1]:
return modules
from pathlib import Path
import re
modules = set()
for file in Path(in_folder, f'r{run_high:04d}').iterdir():
m = re.search(r'-AGIPD(\d{2})-', file.name)
if m:
modules.add(int(m.group(1)))
return sorted(modules)
```
%% Cell type:code id: tags:
``` python
import itertools
import multiprocessing
import os
from collections import OrderedDict
from datetime import timedelta
from pathlib import Path
from typing import List, Tuple
from typing import Tuple
import matplotlib
import numpy as np
import pasha as psh
import tabulate
import yaml
from IPython.display import Latex, Markdown, display
from extra_data import RunDirectory
matplotlib.use('agg')
import iCalibrationDB
import matplotlib.pyplot as plt
from cal_tools.agipdlib import AgipdCtrlRuns
from cal_tools.enums import BadPixels
from cal_tools.plotting import (
create_constant_overview,
plot_badpix_3d,
show_overview,
show_processed_modules,
)
from cal_tools.tools import (
get_dir_creation_date,
get_from_db,
get_pdu_from_db,
get_random_db_interface,
get_report,
module_index_to_qm,
run_prop_seq_from_path,
save_const_to_h5,
send_to_db,
)
%matplotlib inline
```
%% Cell type:code id: tags:
``` python
# insert control device if format string (does nothing otherwise)
ctrl_src = ctrl_source_template.format(karabo_id_control)
runs_dict = OrderedDict()
run_numbers = [run_high, run_med, run_low]
for gain_idx, (run_name, run_number) in enumerate(zip(["high", "med", "low"], run_numbers)):
runs_dict[run_name] = {
"number": run_number,
"gain": gain_idx,
"dc": RunDirectory(f'{in_folder}/r{run_number:04d}/')
}
creation_time=None
if use_dir_creation_date:
creation_time = get_dir_creation_date(in_folder, run_high)
print(f"Using {creation_time} as creation time of constant.")
run, prop, seq = run_prop_seq_from_path(in_folder)
# Read report path and create file location tuple to add with the injection
file_loc = f"proposal:{prop} runs:{run_low} {run_med} {run_high}"
report = get_report(metadata_folder)
cal_db_interface = get_random_db_interface(cal_db_interface)
print(f'Calibration database interface: {cal_db_interface}')
instrument = karabo_id.split("_")[0]
if instrument == "SPB":
dinstance = "AGIPD1M1"
nmods = 16
elif instrument == "MID":
dinstance = "AGIPD1M2"
nmods = 16
elif instrument == "HED":
dinstance = "AGIPD500K"
nmods = 8
instrument_src = instrument_source_template.format(karabo_id, receiver_template)
def create_karabo_da_list(modules):
return(["AGIPD{:02d}".format(i) for i in modules])
if karabo_da[0] == '-1':
if modules[0] == -1:
modules = list(range(nmods))
karabo_da = create_karabo_da_list(modules)
else:
modules = [int(x[-2:]) for x in karabo_da]
print(f"Detector in use is {karabo_id}")
print(f"Instrument {instrument}")
print(f"Detector instance {dinstance}")
```
%% Cell type:code id: tags:
``` python
# Create out_folder if it doesn't exist.
Path(out_folder).mkdir(parents=True, exist_ok=True)
mod_image_size = []
for run_dict in runs_dict.values():
for run in run_numbers:
missing_modules = [] # modules with no images within a run.
n_trains_list = [] # list of the number of trains for each module within a run.
# This is important in case of no slurm parallelization over modules is done.
# (e.g. running notebook interactively)
for m in modules:
# validate that there are trains for the selected modules and run.
dc = run_dict["dc"].select(
dc = RunDirectory(f'{in_folder}/r{run:04d}/').select(
instrument_src.format(m), "*", require_all=True)
n_trains = len(dc.train_ids)
if n_trains == 0:
print(f"WARNING: No images for module AGIPD{m:02d}, run {run_dict['number']}.")
print(f"WARNING: No images for module AGIPD{m:02d}, run {run}.")
missing_modules.append(m)
# Raise a warning if the module has less trains than expected.
elif n_trains < min_trains:
print(f"WARNING: AGIPD{m:02d}, run {run_dict['number']} "
print(f"WARNING: AGIPD{m:02d}, run {run} "
f"has trains less than minimum trains: {min_trains}.")
else:
print(f"Processing {max_trains if max_trains < n_trains else n_trains} "
f"for AGIPD{m:02d}, run {run_dict['number']} ")
f"for AGIPD{m:02d}, run {run} ")
n_trains_list.append(n_trains)
mod_image_size.append(np.product(dc[instrument_src.format(m), "image.data"].shape) * 2 / 1e9)
if max(n_trains_list) == 0:
raise ValueError(f"No images to process for run: {run_dict['number']}")
raise ValueError(f"No images to process for run: {run}")
elif max(n_trains_list) < min_trains:
raise ValueError(f"{run_dict['number']} has less than minimum trains: {min_trains}")
raise ValueError(f"{run} has less than minimum trains: {min_trains}")
# Update modules and karabo_da lists based on available modules to processes.
modules = [m for m in modules if m not in missing_modules]
karabo_da = create_karabo_da_list(modules)
print(f"Will process data of ({sum(mod_image_size):.02f} GB).")
```
%% Cell type:markdown id: tags:
## Read and validate the runs control data.
%% Cell type:code id: tags:
``` python
# Read slow data from 1st channel only.
# Read all modules in one notebook and validate the conditions across detectors?
# Currently slurm jobs run per one module.
# TODO: what if first module is not available. Maybe only channel 2 available
instrument_src_mod = instrument_src.format(modules[0])
agipd_ctrl_dark = AgipdCtrlRuns(
raw_folder=in_folder,
runs=[r["number"] for r in runs_dict.values()],
runs=run_numbers,
image_src=instrument_src_mod,
ctrl_src=ctrl_src,
sort_dark_runs_enabled=sort_runs
)
# Update run_numbers list in case it was sorted.
run_numbers = agipd_ctrl_dark.runs
if mem_cells == 0:
mem_cells = agipd_ctrl_dark.get_memory_cells()
if acq_rate == 0:
acq_rate = agipd_ctrl_dark.get_acq_rate()
if bias_voltage == 0:
bias_voltage = agipd_ctrl_dark.get_bias_voltage(karabo_id_control)
fixed_gain_mode = False
agipd_ctrl_dark.validate_gain_modes()
if gain_mode == -1:
gain_mode = agipd_ctrl_dark.gain_modes
fixed_gain_mode = agipd_ctrl_dark.fixed_gain_mode()
if gain_setting == -1:
gain_setting = agipd_ctrl_dark.get_gain_setting()
if integration_time == -1:
integration_time = agipd_ctrl_dark.get_integration_time()
```
%% Cell type:code id: tags:
``` python
# Determine the gain operation mode based on the gain_mode stored in control h5file.
if operation_mode not in ("ADAPTIVE_GAIN", "FIXED_GAIN"):
print(f"WARNING: unknown operation_mode \"{operation_mode}\" parameter set")
if fixed_gain_mode and operation_mode == "ADAPTIVE_GAIN":
print(
"WARNING: Operation_mode parameter is ADAPTIVE_GAIN, but"
"slow data indicates FIXED_GAIN. Processing fixed gain constants.")
elif not fixed_gain_mode and operation_mode == "FIXED_GAIN":
print(
"WARNING: Operation_mode parameter is FIXED_GAIN, "
"slow data indicates ADAPTIVE_GAIN. Processing adaptive gain constants.")
```
%% Cell type:code id: tags:
``` python
print("Parameters are:")
print(f"Proposal: {prop}")
print(f"Acquisition rate: {acq_rate}")
print(f"Memory cells: {mem_cells}")
print(f"Runs: {run_numbers}")
print(f"Interlaced mode: {interlaced}")
print(f"Using DB: {db_output}")
print(f"Input: {in_folder}")
print(f"Output: {out_folder}")
print(f"Bias voltage: {bias_voltage}V")
print(f"Gain setting: {gain_setting}")
print(f"Integration time: {integration_time}")
print(f"Operation mode is {'fixed' if fixed_gain_mode else 'adaptive'} gain mode")
```
%% Cell type:code id: tags:
``` python
if thresholds_offset_hard != [0, 0]:
# if set, this will override the individual parameters
thresholds_offset_hard = [thresholds_offset_hard] * 3
elif fixed_gain_mode:
thresholds_offset_hard = [
thresholds_offset_hard_hg_fixed,
thresholds_offset_hard_mg_fixed,
thresholds_offset_hard_lg_fixed,
]
else:
thresholds_offset_hard = [
thresholds_offset_hard_hg,
thresholds_offset_hard_mg,
thresholds_offset_hard_lg,
]
print("Will use the following hard offset thresholds")
for name, value in zip(("High", "Medium", "Low"), thresholds_offset_hard):
print(f"- {name} gain: {value}")
if thresholds_noise_hard != [0, 0]:
thresholds_noise_hard = [thresholds_noise_hard] * 3
else:
thresholds_noise_hard = [
thresholds_noise_hard_hg,
thresholds_noise_hard_mg,
thresholds_noise_hard_lg,
]
```
%% Cell type:markdown id: tags:
## Calculate Offsets, Noise and Thresholds ##
The calculation is performed per-pixel and per-memory-cell. Offsets are simply the median value for a set of dark data taken at a given gain, noise the standard deviation, and gain-bit values the medians of the gain array.
%% Cell type:code id: tags:
``` python
parallel_num_procs = min(6, len(modules)*3)
parallel_num_threads = multiprocessing.cpu_count() // parallel_num_procs
print(f"Will use {parallel_num_procs} processes with {parallel_num_threads} threads each")
def characterize_module(
channel: int, runs_dict: dict,
channel: int, gain_run: Tuple[int, int],
) -> Tuple[int, int, np.array, np.array, np.array, np.array, np.array]:
gain_index, run = gain_run
# Select the corresponding module channel.
instrument_src_mod = instrument_src.format(channel)
run_dc = runs_dict["dc"].select(instrument_src_mod, require_all=True)
run_dc = RunDirectory(f'{in_folder}/r{run:04d}/').select(instrument_src_mod, require_all=True)
if max_trains != 0:
run_dc = run_dc.select_trains(np.s_[:max_trains])
gain_index = runs_dict["gain"]
# Read module's image and cellId data.
im = run_dc[instrument_src_mod, "image.data"].ndarray()
cell_ids = np.squeeze(run_dc[instrument_src_mod, "image.cellId"].ndarray())
local_thresholds_offset_hard = thresholds_offset_hard[gain_index]
local_thresholds_noise_hard = thresholds_noise_hard[gain_index]
if interlaced:
if not fixed_gain_mode:
ga = im[1::2, 0, ...]
im = im[0::2, 0, ...].astype(np.float32)
cell_ids = cell_ids[::2]
else:
if not fixed_gain_mode:
ga = im[:, 1, ...]
im = im[:, 0, ...].astype(np.float32)
im = np.transpose(im)
if not fixed_gain_mode:
ga = np.transpose(ga)
context = psh.context.ThreadContext(num_workers=parallel_num_threads)
offset = context.alloc(shape=(im.shape[0], im.shape[1], mem_cells), dtype=np.float64)
noise = context.alloc(like=offset)
if fixed_gain_mode:
gains = None
gains_std = None
else:
gains = context.alloc(like=offset)
gains_std = context.alloc(like=offset)
def process_cell(worker_id, array_index, cell_number):
cell_slice_index = (cell_ids == cell_number)
im_slice = im[..., cell_slice_index]
offset[..., cell_number] = np.median(im_slice, axis=2)
noise[..., cell_number] = np.std(im_slice, axis=2)
if not fixed_gain_mode:
ga_slice = ga[..., cell_slice_index]
gains[..., cell_number] = np.median(ga_slice, axis=2)
gains_std[..., cell_number] = np.std(ga_slice, axis=2)
unique_cell_ids = np.unique(cell_ids)
# We assume cells are accepted starting 0.
if np.any(unique_cell_ids > mem_cells):
raise ValueError(
f"Invalid cells found {unique_cell_ids} "
f"for run: {run_dc.run_metadata()['runNumber']}.")
context.map(process_cell, unique_cell_ids)
# bad pixels
bp = np.zeros_like(offset, dtype=np.uint32)
# offset related bad pixels
offset_mn = np.nanmedian(offset, axis=(0,1))
offset_std = np.nanstd(offset, axis=(0,1))
bp[(offset < offset_mn-thresholds_offset_sigma*offset_std) |
(offset > offset_mn+thresholds_offset_sigma*offset_std)] |= BadPixels.OFFSET_OUT_OF_THRESHOLD
bp[(offset < local_thresholds_offset_hard[0]) |
(offset > local_thresholds_offset_hard[1])] |= BadPixels.OFFSET_OUT_OF_THRESHOLD
bp[~np.isfinite(offset)] |= BadPixels.OFFSET_NOISE_EVAL_ERROR
# noise related bad pixels
noise_mn = np.nanmedian(noise, axis=(0,1))
noise_std = np.nanstd(noise, axis=(0,1))
bp[(noise < noise_mn-thresholds_noise_sigma*noise_std) |
(noise > noise_mn+thresholds_noise_sigma*noise_std)] |= BadPixels.NOISE_OUT_OF_THRESHOLD
bp[(noise < local_thresholds_noise_hard[0]) | (noise > local_thresholds_noise_hard[1])] |= BadPixels.NOISE_OUT_OF_THRESHOLD
bp[~np.isfinite(noise)] |= BadPixels.OFFSET_NOISE_EVAL_ERROR
return channel, gain_index, offset, noise, gains, gains_std, bp
```
%% Cell type:code id: tags:
``` python
with multiprocessing.Pool(processes=parallel_num_procs) as pool:
results = pool.starmap(
characterize_module, itertools.product(modules, list(runs_dict.values())))
characterize_module, itertools.product(modules, list(enumerate(run_numbers))))
# mapped values for processing 2 modules example:
# [
# 0, {"gain": 0, "run_number": <run-high>, "dc": <high-dc>},
# 0, {"gain": 1, "run_number": <run-med>, "dc": <med-dc>},
# 0, {"gain": 2, "run_number": <run-low>, "dc": <low-dc>},
# 1, {"gain": 0, "run_number": <run-high>, "dc": <high-dc>},
# 1, {"gain": 1, "run_number": <run-med>, "dc": <med-dc>},
# 1, {"gain": 2, "run_number": <run-low>, "dc": <low-dc>},
# [(0, (0, 9013))
# 0, (0, run-high),
# 0, (1, run-med),
# 0, (2, run-low),
# 1, (0, run-high),
# 1, (1, run-med),
# 1, (2, run-low),,
# ]
```
%% Cell type:code id: tags:
``` python
offset_g = OrderedDict()
noise_g = OrderedDict()
badpix_g = OrderedDict()
if not fixed_gain_mode:
gain_g = OrderedDict()
gainstd_g = OrderedDict()
for module_index, gain_index, offset, noise, gains, gains_std, bp in results:
qm = module_index_to_qm(module_index)
if qm not in offset_g:
offset_g[qm] = np.zeros((offset.shape[0], offset.shape[1], offset.shape[2], 3))
noise_g[qm] = np.zeros_like(offset_g[qm])
badpix_g[qm] = np.zeros_like(offset_g[qm], np.uint32)
if not fixed_gain_mode:
gain_g[qm] = np.zeros_like(offset_g[qm])
gainstd_g[qm] = np.zeros_like(offset_g[qm])
offset_g[qm][..., gain_index] = offset
noise_g[qm][..., gain_index] = noise
badpix_g[qm][..., gain_index] = bp
if not fixed_gain_mode:
gain_g[qm][..., gain_index] = gains
gainstd_g[qm][..., gain_index] = gains_std
```
%% Cell type:code id: tags:
``` python
# Add bad pixels due to bad gain separation
if not fixed_gain_mode:
for qm in gain_g.keys():
for g in range(2):
# Bad pixels during bad gain separation.
# Fraction of pixels in the module with separation lower than "thresholds_gain_sigma".
bad_sep = (gain_g[qm][..., g+1] - gain_g[qm][..., g]) / \
np.sqrt(gainstd_g[qm][..., g+1]**2 + gainstd_g[qm][..., g]**2)
badpix_g[qm][...,g+1][bad_sep<thresholds_gain_sigma] |= \
BadPixels.GAIN_THRESHOLDING_ERROR
```
%% Cell type:markdown id: tags:
The thresholds for gain switching are then defined as the mean value between in individual gain bit levels. Note that these thresholds need to be refined with charge induced thresholds, as the two are not the same.
%% Cell type:code id: tags:
``` python
if not fixed_gain_mode:
thresholds_g = {}
for qm in gain_g.keys():
thresholds_g[qm] = np.zeros((gain_g[qm].shape[0], gain_g[qm].shape[1], gain_g[qm].shape[2], 5))
thresholds_g[qm][...,0] = (gain_g[qm][...,1]+gain_g[qm][...,0])/2
thresholds_g[qm][...,1] = (gain_g[qm][...,2]+gain_g[qm][...,1])/2
for i in range(3):
thresholds_g[qm][...,2+i] = gain_g[qm][...,i]
```
%% Cell type:code id: tags:
``` python
res = OrderedDict()
for i in modules:
qm = module_index_to_qm(i)
res[qm] = {
'Offset': offset_g[qm],
'Noise': noise_g[qm],
'BadPixelsDark': badpix_g[qm]
}
if not fixed_gain_mode:
res[qm]['ThresholdsDark'] = thresholds_g[qm]
```
%% Cell type:code id: tags:
``` python
# set the operating condition
# note: iCalibrationDB only adds gain_mode if it is truthy, so we don't need to handle None
condition = iCalibrationDB.Conditions.Dark.AGIPD(
memory_cells=mem_cells,
bias_voltage=bias_voltage,
acquisition_rate=acq_rate,
gain_setting=gain_setting,
gain_mode=fixed_gain_mode,
integration_time=integration_time
)
```
%% Cell type:code id: tags:
``` python
# Create mapping from module(s) (qm) to karabo_da(s) and PDU(s)
qm_dict = OrderedDict()
all_pdus = get_pdu_from_db(
karabo_id,
karabo_da,
constant=iCalibrationDB.CalibrationConstant(),
condition=condition,
cal_db_interface=cal_db_interface,
snapshot_at=creation_time.isoformat() if creation_time else None,
timeout=cal_db_timeout
)
for module_index, module_da, module_pdu in zip(modules, karabo_da, all_pdus):
qm = module_index_to_qm(module_index)
qm_dict[qm] = {
"karabo_da": module_da,
"db_module": module_pdu
}
```
%% Cell type:markdown id: tags:
## Sending calibration constants to the database.
%% Cell type:code id: tags:
``` python
md = None
for qm in res:
db_module = qm_dict[qm]["db_module"]
for const in res[qm]:
dconst = getattr(iCalibrationDB.Constants.AGIPD, const)()
dconst.data = res[qm][const]
if db_output:
md = send_to_db(db_module, karabo_id, dconst, condition, file_loc,
report, cal_db_interface, creation_time=creation_time,
timeout=cal_db_timeout)
if local_output:
md = save_const_to_h5(db_module, karabo_id, dconst, condition, dconst.data,
file_loc, report, creation_time, out_folder)
print(f"Calibration constant {const} for {qm} is stored locally in {file_loc}.\n")
print("Constants parameter conditions are:\n")
print(f"• memory_cells: {mem_cells}\n• bias_voltage: {bias_voltage}\n"
f"• acquisition_rate: {acq_rate}\n• gain_setting: {gain_setting}\n"
f"• gain_mode: {fixed_gain_mode}\n• integration_time: {integration_time}\n"
f"• creation_time: {md.calibration_constant_version.begin_at if md is not None else creation_time}\n")
```
%% Cell type:markdown id: tags:
## Retrieving previous calibration constants for comparison.
%% Cell type:code id: tags:
``` python
# Start retrieving existing constants for comparison
qm_x_const = [(qm, const) for const in res[qm] for qm in res]
def retrieve_old_constant(qm, const):
dconst = getattr(iCalibrationDB.Constants.AGIPD, const)()
data, mdata = get_from_db(
karabo_id=karabo_id,
karabo_da=qm_dict[qm]["karabo_da"],
constant=dconst,
condition=condition,
empty_constant=None,
cal_db_interface=cal_db_interface,
creation_time=creation_time-timedelta(seconds=1) if creation_time else None,
strategy="pdu_prior_in_time",
verbosity=1,
timeout=cal_db_timeout
)
if mdata is None or data is None:
timestamp = "Not found"
filepath = None
h5path = None
else:
timestamp = mdata.calibration_constant_version.begin_at.isoformat()
filepath = os.path.join(
mdata.calibration_constant_version.hdf5path,
mdata.calibration_constant_version.filename
)
h5path = mdata.calibration_constant_version.h5path
return data, timestamp, filepath, h5path
old_retrieval_pool = multiprocessing.Pool()
old_retrieval_res = old_retrieval_pool.starmap_async(
retrieve_old_constant, qm_x_const
)
old_retrieval_pool.close()
```
%% Cell type:code id: tags:
``` python
mnames=[]
for i in modules:
qm = module_index_to_qm(i)
mnames.append(qm)
display(Markdown(f'## Position of the module {qm} and its ASICs'))
show_processed_modules(dinstance, constants=None, mnames=mnames, mode="position")
```
%% Cell type:markdown id: tags:
## Single-Cell Overviews ##
Single cell overviews allow to identify potential effects on all memory cells, e.g. on sensor level. Additionally, they should serve as a first sanity check on expected behaviour, e.g. if structuring on the ASIC level is visible in the offsets, but otherwise no immediate artifacts are visible.
%% Cell type:markdown id: tags:
### High Gain ###
%% Cell type:code id: tags:
``` python
cell = 3
gain = 0
show_overview(res, cell, gain, infix="{}-{}-{}".format(*run_numbers))
```
%% Cell type:markdown id: tags:
### Medium Gain ###
%% Cell type:code id: tags:
``` python
cell = 3
gain = 1
show_overview(res, cell, gain, infix="{}-{}-{}".format(*run_numbers))
```
%% Cell type:markdown id: tags:
### Low Gain ###
%% Cell type:code id: tags:
``` python
cell = 3
gain = 2
show_overview(res, cell, gain, infix="{}-{}-{}".format(*run_numbers))
```
%% Cell type:code id: tags:
``` python
if high_res_badpix_3d:
cols = {
BadPixels.NOISE_OUT_OF_THRESHOLD: (BadPixels.NOISE_OUT_OF_THRESHOLD.name, '#FF000080'),
BadPixels.OFFSET_NOISE_EVAL_ERROR: (BadPixels.OFFSET_NOISE_EVAL_ERROR.name, '#0000FF80'),
BadPixels.OFFSET_OUT_OF_THRESHOLD: (BadPixels.OFFSET_OUT_OF_THRESHOLD.name, '#00FF0080'),
BadPixels.GAIN_THRESHOLDING_ERROR: (BadPixels.GAIN_THRESHOLDING_ERROR.name, '#FF40FF40'),
BadPixels.OFFSET_OUT_OF_THRESHOLD | BadPixels.NOISE_OUT_OF_THRESHOLD: ('OFFSET_OUT_OF_THRESHOLD + NOISE_OUT_OF_THRESHOLD', '#DD00DD80'),
BadPixels.OFFSET_OUT_OF_THRESHOLD | BadPixels.NOISE_OUT_OF_THRESHOLD |
BadPixels.GAIN_THRESHOLDING_ERROR: ('MIXED', '#BFDF009F')
}
display(Markdown("""
## Global Bad Pixel Behaviour ##
The following plots show the results of bad pixel evaluation for all evaluated memory cells.
Cells are stacked in the Z-dimension, while pixels values in x/y are rebinned with a factor of 2.
This excludes single bad pixels present only in disconnected pixels.
Hence, any bad pixels spanning at least 4 pixels in the x/y-plane, or across at least two memory cells are indicated.
Colors encode the bad pixel type, or mixed type.
"""))
gnames = ['High Gain', 'Medium Gain', 'Low Gain']
for gain in range(3):
display(Markdown(f'### {gnames[gain]} ###'))
for mod, data in badpix_g.items():
plot_badpix_3d(data[...,gain], cols, title=mod, rebin_fac=1)
plt.show()
```
%% Cell type:markdown id: tags:
## Aggregate values, and per Cell behaviour ##
The following tables and plots give an overview of statistical aggregates for each constant, as well as per cell behavior.
%% Cell type:code id: tags:
``` python
create_constant_overview(offset_g, "Offset (ADU)", mem_cells, 4000, 8000,
badpixels=[badpix_g, np.nan])
```
%% Cell type:code id: tags:
``` python
create_constant_overview(noise_g, "Noise (ADU)", mem_cells, 0, 100,
badpixels=[badpix_g, np.nan])
```
%% Cell type:code id: tags:
``` python
if not fixed_gain_mode:
# Plot only three gain threshold maps.
bp_thresh = OrderedDict()
for mod, con in badpix_g.items():
bp_thresh[mod] = np.zeros((con.shape[0], con.shape[1], con.shape[2], 5), dtype=con.dtype)
bp_thresh[mod][...,:2] = con[...,:2]
bp_thresh[mod][...,2:] = con
create_constant_overview(thresholds_g, "Threshold (ADU)", mem_cells, 4000, 10000, 5,
badpixels=[bp_thresh, np.nan],
gmap=['HG-MG Threshold', 'MG-LG Threshold', 'High gain', 'Medium gain', 'low gain'],
marker=['d','d','','','']
)
```
%% Cell type:code id: tags:
``` python
bad_pixel_aggregate_g = OrderedDict()
for m, d in badpix_g.items():
bad_pixel_aggregate_g[m] = d.astype(np.bool).astype(np.float)
create_constant_overview(bad_pixel_aggregate_g, "Bad pixel fraction", mem_cells, 0, 0.10, 3)
```
%% Cell type:markdown id: tags:
## Summary tables ##
The following tables show summary information for the evaluated module. Values for currently evaluated constants are compared with values for pre-existing constants retrieved from the calibration database.
%% Cell type:code id: tags:
``` python
# now we need the old constants
old_const = {}
old_mdata = {}
old_retrieval_res.wait()
for (qm, const), (data, timestamp, filepath, h5path) in zip(qm_x_const, old_retrieval_res.get()):
old_const.setdefault(qm, {})[const] = data
old_mdata.setdefault(qm, {})[const] = {
"timestamp": timestamp,
"filepath": filepath,
"h5path": h5path
}
```
%% Cell type:code id: tags:
``` python
display(Markdown("The following pre-existing constants are used for comparison:"))
for qm, consts in old_mdata.items():
display(Markdown(f"- {qm}"))
for const in consts:
display(Markdown(f" - {const} at {consts[const]['timestamp']}"))
# saving locations of old constants for summary notebook
with open(f"{out_folder}/module_metadata_{qm}.yml", "w") as fd:
yaml.safe_dump(
{
"module": qm,
"pdu": qm_dict[qm]["db_module"],
"old-constants": old_mdata[qm]
},
fd,
)
```
%% Cell type:code id: tags:
``` python
table = []
gain_names = ['High', 'Medium', 'Low']
bits = [BadPixels.NOISE_OUT_OF_THRESHOLD, BadPixels.OFFSET_OUT_OF_THRESHOLD, BadPixels.OFFSET_NOISE_EVAL_ERROR, BadPixels.GAIN_THRESHOLDING_ERROR]
for qm in badpix_g.keys():
for gain in range(3):
l_data = []
l_data_old = []
data = np.copy(badpix_g[qm][:,:,:,gain])
datau32 = data.astype(np.uint32)
l_data.append(len(datau32[datau32>0].flatten()))
for bit in bits:
l_data.append(np.count_nonzero(badpix_g[qm][:,:,:,gain] & bit))
if old_const[qm]['BadPixelsDark'] is not None:
dataold = np.copy(old_const[qm]['BadPixelsDark'][:, :, :, gain])
datau32old = dataold.astype(np.uint32)
l_data_old.append(len(datau32old[datau32old>0].flatten()))
for bit in bits:
l_data_old.append(np.count_nonzero(old_const[qm]['BadPixelsDark'][:, :, :, gain] & bit))
l_data_name = ['All bad pixels', 'NOISE_OUT_OF_THRESHOLD',
'OFFSET_OUT_OF_THRESHOLD', 'OFFSET_NOISE_EVAL_ERROR', 'GAIN_THRESHOLDING_ERROR']
l_threshold = ['', f'{thresholds_noise_sigma}' f'{thresholds_noise_hard[gain]}',
f'{thresholds_offset_sigma}' f'{thresholds_offset_hard[gain]}',
'', f'{thresholds_gain_sigma}']
for i in range(len(l_data)):
line = [f'{l_data_name[i]}, {gain_names[gain]} gain', l_threshold[i], l_data[i]]
if old_const[qm]['BadPixelsDark'] is not None:
line += [l_data_old[i]]
else:
line += ['-']
table.append(line)
table.append(['', '', '', ''])
display(Markdown('''
### Number of bad pixels
One pixel can be bad for different reasons, therefore, the sum of all types of bad pixels can be more than the number of all bad pixels.
'''))
if len(table)>0:
md = display(Latex(tabulate.tabulate(table, tablefmt='latex',
headers=["Pixel type", "Threshold",
"New constant", "Old constant"])))
```
%% Cell type:code id: tags:
``` python
header = ['Parameter',
"New constant", "Old constant ",
"New constant", "Old constant ",
"New constant", "Old constant ",
"New constant", "Old constant "]
if fixed_gain_mode:
constants = ['Offset', 'Noise']
else:
constants = ['Offset', 'Noise', 'ThresholdsDark']
constants_x_qms = list(itertools.product(constants, res.keys()))
def compute_table(const, qm):
if const == 'ThresholdsDark':
table = [['','HG-MG threshold', 'HG-MG threshold', 'MG-LG threshold', 'MG-LG threshold']]
else:
table = [['','High gain', 'High gain', 'Medium gain', 'Medium gain', 'Low gain', 'Low gain']]
compare_with_old_constant = old_const[qm][const] is not None and \
old_const[qm]['BadPixelsDark'] is not None
data = np.copy(res[qm][const])
if const == 'ThresholdsDark':
data[...,0][res[qm]['BadPixelsDark'][...,0]>0] = np.nan
data[...,1][res[qm]['BadPixelsDark'][...,1]>0] = np.nan
else:
data[res[qm]['BadPixelsDark']>0] = np.nan
if compare_with_old_constant:
data_old = np.copy(old_const[qm][const])
if const == 'ThresholdsDark':
data_old[...,0][old_const[qm]['BadPixelsDark'][...,0]>0] = np.nan
data_old[...,1][old_const[qm]['BadPixelsDark'][...,1]>0] = np.nan
else:
data_old[old_const[qm]['BadPixelsDark']>0] = np.nan
f_list = [np.nanmedian, np.nanmean, np.nanstd, np.nanmin, np.nanmax]
n_list = ['Median', 'Mean', 'Std', 'Min', 'Max']
def compute_row(i):
line = [n_list[i]]
for gain in range(3):
# Compare only 3 threshold gain-maps
if gain == 2 and const == 'ThresholdsDark':
continue
stat_measure = f_list[i](data[...,gain])
line.append(f"{stat_measure:6.1f}")
if compare_with_old_constant:
old_stat_measure = f_list[i](data_old[...,gain])
line.append(f"{old_stat_measure:6.1f}")
else:
line.append("-")
return line
with multiprocessing.pool.ThreadPool(processes=multiprocessing.cpu_count() // len(constants_x_qms)) as pool:
rows = pool.map(compute_row, range(len(f_list)))
table.extend(rows)
return table
with multiprocessing.Pool(processes=len(constants_x_qms)) as pool:
tables = pool.starmap(compute_table, constants_x_qms)
for (const, qm), table in zip(constants_x_qms, tables):
display(Markdown(f"### {qm}: {const} [ADU], good pixels only"))
display(Latex(tabulate.tabulate(table, tablefmt='latex', headers=header)))
```

Legal Notice | Contacts