Skip to content
Snippets Groups Projects
Commit 520574f9 authored by Thomas Kluyver's avatar Thomas Kluyver
Browse files

Add use_oauth2 option to allow using proxy without oauth

parent e2d2f621
No related branches found
No related tags found
1 merge request!676[LPD] [Correct] Make virtual cxi for each worker's chunk
Hide whitespace changes
Inline Side-by-side
notebooks/LPD/LPD_Correct_Fast.ipynb
+ 1
− 0
View file @ 520574f9
%% Cell type:markdown id: tags:
# LPD Offline Correction #
Author: European XFEL Data Analysis Group
%% Cell type:code id: tags:
``` python
# Input parameters
in_folder = "/gpfs/exfel/exp/FXE/202201/p003073/raw/" # the folder to read data from, required
out_folder = "/gpfs/exfel/data/scratch/schmidtp/random/LPD_test" # the folder to output to, required
metadata_folder = '' # Directory containing calibration_metadata.yml when run by xfel-calibrate.
sequences = [-1] # Sequences to correct, use [-1] for all
modules = [-1] # Modules indices to correct, use [-1] for all, only used when karabo_da is empty
karabo_da = [''] # Data aggregators names to correct, use [''] for all
run = 10 # runs to process, required
# Source parameters
karabo_id = 'FXE_DET_LPD1M-1' # Karabo domain for detector.
input_source = '{karabo_id}/DET/{module_index}CH0:xtdf' # Input fast data source.
output_source = '' # Output fast data source, empty to use same as input.
# CalCat parameters
use_dir_creation_date = True # Use the creation date of the directory for database time derivation.
cal_db_interface = '' # Not needed, compatibility with current webservice.
cal_db_timeout = 0 # Not needed, compatbility with current webservice.
cal_db_root = '/gpfs/exfel/d/cal/caldb_store'
# Operating conditions
mem_cells = 512 # Memory cells, LPD constants are always taken with 512 cells.
bias_voltage = 250.0 # Detector bias voltage.
capacitor = '5pF' # Capacitor setting: 5pF or 50pF
photon_energy = 9.2 # Photon energy in keV.
category = 0 # Whom to blame.
# Correction parameters
offset_corr = True # Offset correction.
rel_gain = True # Gain correction based on RelativeGain constant.
ff_map = True # Gain correction based on FFMap constant.
gain_amp_map = True # Gain correction based on GainAmpMap constant.
# Output options
overwrite = True # set to True if existing data should be overwritten
chunks_data = 32 # HDF chunk size for pixel data in number of frames.
chunks_ids = 32 # HDF chunk size for cellId and pulseId datasets.
# Parallelization options
sequences_per_node = 1 # Sequence files to process per node
num_workers = 8 # Worker processes per node, 8 is safe on 768G nodes but won't work on 512G.
num_threads_per_worker = 32 # Number of threads per worker.
def balance_sequences(in_folder, run, sequences, sequences_per_node, karabo_da):
from xfel_calibrate.calibrate import balance_sequences as bs
return bs(in_folder, run, sequences, sequences_per_node, karabo_da)
```
%% Cell type:code id: tags:
``` python
from collections import OrderedDict
from pathlib import Path
from time import perf_counter
import gc
import re
import warnings
import numpy as np
import h5py
import matplotlib
matplotlib.use('agg')
import matplotlib.pyplot as plt
%matplotlib inline
from calibration_client import CalibrationClient
from calibration_client.modules import CalibrationConstantVersion
import extra_data as xd
import extra_geom as xg
import pasha as psh
from extra_data.components import LPD1M
from cal_tools.lpdalgs import correct_lpd_frames
from cal_tools.tools import CalibrationMetadata, get_dir_creation_date, write_compressed_frames
from cal_tools.files import DataFile
from cal_tools.restful_config import restful_config
```
%% Cell type:markdown id: tags:
# Prepare environment
%% Cell type:code id: tags:
``` python
file_re = re.compile(r'^RAW-R(\d{4})-(\w+\d+)-S(\d{5})$') # This should probably move to cal_tools
run_folder = Path(in_folder) / f'r{run:04d}'
out_folder = Path(out_folder)
out_folder.mkdir(exist_ok=True)
output_source = output_source or input_source
cal_db_root = Path(cal_db_root)
metadata = CalibrationMetadata(metadata_folder or out_folder)
if use_dir_creation_date:
creation_time = get_dir_creation_date(in_folder, run)
else:
from datetime import datetime
creation_time = datetime.now()
print(f'Using {creation_time.isoformat()} as creation time')
# Pick all modules/aggregators or those selected.
if not karabo_da or karabo_da == ['']:
if not modules or modules == [-1]:
modules = list(range(16))
karabo_da = [f'LPD{i:02d}' for i in modules]
# Pick all sequences or those selected.
if not sequences or sequences == [-1]:
do_sequence = lambda seq: True
else:
do_sequence = [int(x) for x in sequences].__contains__
# List of detector sources.
det_inp_sources = [input_source.format(karabo_id=karabo_id, module_index=int(da[-2:])) for da in karabo_da]
```
%% Cell type:markdown id: tags:
# Select data to process
%% Cell type:code id: tags:
``` python
data_to_process = []
for inp_path in run_folder.glob('RAW-*.h5'):
match = file_re.match(inp_path.stem)
if match[2] not in karabo_da or not do_sequence(int(match[3])):
continue
outp_path = out_folder / 'CORR-R{run:04d}-{aggregator}-S{seq:05d}.h5'.format(
run=int(match[1]), aggregator=match[2], seq=int(match[3]))
data_to_process.append((match[2], inp_path, outp_path))
print('Files to process:')
for data_descr in sorted(data_to_process, key=lambda x: f'{x[0]}{x[1]}'):
print(f'{data_descr[0]}\t{data_descr[1]}')
```
%% Cell type:markdown id: tags:
# Obtain and prepare calibration constants
%% Cell type:code id: tags:
``` python
# Connect to CalCat.
calcat_config = restful_config['calcat']
client = CalibrationClient(
use_oauth2=calcat_config['use-oauth2'],
client_id=calcat_config['user-id'],
client_secret=calcat_config['user-secret'],
user_email=calcat_config['user-email'],
base_api_url=calcat_config['base-api-url'],
token_url=calcat_config['token-url'],
refresh_url=calcat_config['refresh-url'],
auth_url=calcat_config['auth-url'],
scope='')
```
%% Cell type:code id: tags:
``` python
dark_calibrations = {
1: 'Offset', # np.float32
14: 'BadPixelsDark' # should be np.uint32, but is np.float64
}
dark_condition = [
dict(parameter_id=1, value=bias_voltage), # Sensor bias voltage
dict(parameter_id=7, value=mem_cells), # Memory cells
dict(parameter_id=15, value=capacitor), # Feedback capacitor
dict(parameter_id=13, value=256), # Pixels X
dict(parameter_id=14, value=256), # Pixels Y
]
illuminated_calibrations = {
20: 'BadPixelsFF', # np.uint32
42: 'GainAmpMap', # np.float32
43: 'FFMap', # np.float32
44: 'RelativeGain' # np.float32
}
illuminated_condition = dark_condition.copy()
illuminated_condition += [
dict(parameter_id=3, value=photon_energy), # Source energy
dict(parameter_id=25, value=category) # category
]
const_data = {}
const_load_mp = psh.ProcessContext(num_workers=24)
print('Querying calibration database', end='', flush=True)
start = perf_counter()
for calibrations, condition in [
(dark_calibrations, dark_condition),
(illuminated_calibrations, illuminated_condition)
]:
resp = CalibrationConstantVersion.get_closest_by_time_by_detector_conditions(
client, karabo_id, list(calibrations.keys()),
{'parameters_conditions_attributes': condition},
karabo_da='', event_at=creation_time.isoformat(), snapshot_at=None)
if not resp['success']:
raise RuntimeError(resp)
for ccv in resp['data']:
cc = ccv['calibration_constant']
da = ccv['physical_detector_unit']['karabo_da']
calibration_name = calibrations[cc['calibration_id']]
dtype = np.uint32 if calibration_name.startswith('BadPixels') else np.float32
const_data[(da, calibration_name)] = dict(
path=Path(ccv['path_to_file']) / ccv['file_name'],
dataset=ccv['data_set_name'],
data=const_load_mp.alloc(shape=(256, 256, mem_cells, 3), dtype=dtype)
)
print('.', end='', flush=True)
total_time = perf_counter() - start
print(f'{total_time:.1f}s')
```
%% Cell type:code id: tags:
``` python
def load_constant_dataset(wid, index, const_descr):
ccv_entry = const_data[const_descr]
with h5py.File(cal_db_root / ccv_entry['path'], 'r') as fp:
fp[ccv_entry['dataset'] + '/data'].read_direct(ccv_entry['data'])
print('.', end='', flush=True)
print('Loading calibration data', end='', flush=True)
start = perf_counter()
const_load_mp.map(load_constant_dataset, list(const_data.keys()))
total_time = perf_counter() - start
print(f'{total_time:.1f}s')
```
%% Cell type:code id: tags:
``` python
# These are intended in order cell, X, Y, gain
ccv_offsets = {}
ccv_gains = {}
ccv_masks = {}
ccv_shape = (mem_cells, 256, 256, 3)
constant_order = {
'Offset': (2, 1, 0, 3),
'BadPixelsDark': (2, 1, 0, 3),
'RelativeGain': (2, 1, 0, 3),
'FFMap': (2, 0, 1, 3),
'BadPixelsFF': (2, 0, 1, 3),
'GainAmpMap': (2, 0, 1, 3),
}
def prepare_constants(wid, index, aggregator):
consts = {calibration_name: entry['data']
for (aggregator_, calibration_name), entry
in const_data.items()
if aggregator == aggregator_}
def _prepare_data(calibration_name, dtype):
return consts[calibration_name] \
.transpose(constant_order[calibration_name]) \
.astype(dtype, copy=True) # Make sure array is contiguous.
if offset_corr and 'Offset' in consts:
ccv_offsets[aggregator] = _prepare_data('Offset', np.float32)
else:
ccv_offsets[aggregator] = np.zeros(ccv_shape, dtype=np.float32)
ccv_gains[aggregator] = np.ones(ccv_shape, dtype=np.float32)
if 'BadPixelsDark' in consts:
ccv_masks[aggregator] = _prepare_data('BadPixelsDark', np.uint32)
else:
ccv_masks[aggregator] = np.zeros(ccv_shape, dtype=np.uint32)
if rel_gain and 'RelativeGain' in consts:
ccv_gains[aggregator] *= _prepare_data('RelativeGain', np.float32)
if ff_map and 'FFMap' in consts:
ccv_gains[aggregator] *= _prepare_data('FFMap', np.float32)
if 'BadPixelsFF' in consts:
np.bitwise_or(ccv_masks[aggregator], _prepare_data('BadPixelsFF', np.uint32),
out=ccv_masks[aggregator])
if gain_amp_map and 'GainAmpMap' in consts:
ccv_gains[aggregator] *= _prepare_data('GainAmpMap', np.float32)
print('.', end='', flush=True)
print('Preparing constants', end='', flush=True)
start = perf_counter()
psh.ThreadContext(num_workers=len(karabo_da)).map(prepare_constants, karabo_da)
total_time = perf_counter() - start
print(f'{total_time:.1f}s')
const_data.clear() # Clear raw constants data now to save memory.
gc.collect();
```
%% Cell type:code id: tags:
``` python
def correct_file(wid, index, work):
aggregator, inp_path, outp_path = work
module_index = int(aggregator[-2:])
start = perf_counter()
dc = xd.H5File(inp_path).select('*', 'image.*', require_all=True)
inp_source = dc[input_source.format(karabo_id=karabo_id, module_index=module_index)]
open_time = perf_counter() - start
# Load raw data for this file.
start = perf_counter()
in_raw = inp_source['image.data'].ndarray().squeeze()
in_cell = inp_source['image.cellId'].ndarray().squeeze()
in_pulse = inp_source['image.pulseId'].ndarray().squeeze()
read_time = perf_counter() - start
# Allocate output arrays.
out_data = np.zeros((in_raw.shape[0], 256, 256), dtype=np.float32)
out_gain = np.zeros((in_raw.shape[0], 256, 256), dtype=np.uint8)
out_mask = np.zeros((in_raw.shape[0], 256, 256), dtype=np.uint32)
start = perf_counter()
correct_lpd_frames(in_raw, in_cell,
out_data, out_gain, out_mask,
ccv_offsets[aggregator], ccv_gains[aggregator], ccv_masks[aggregator],
num_threads=num_threads_per_worker)
correct_time = perf_counter() - start
image_counts = inp_source['image.data'].data_counts(labelled=False)
start = perf_counter()
if (not outp_path.exists() or overwrite) and image_counts.sum() > 0:
fa = dc.files[0]
sel_trains = np.isin(fa.train_ids, dc.train_ids)
outp_source_name = output_source.format(karabo_id=karabo_id, module_index=module_index)
with DataFile(outp_path, 'w') as outp_file:
outp_file.create_index(
train_ids=dc.train_ids,
timestamps=fa.file['INDEX/timestamp'][sel_trains],
flags=fa.validity_flag[sel_trains])
outp_file.create_metadata(like=dc, instrument_channels=(f'{outp_source_name}/image',))
outp_source = outp_file.create_instrument_source(outp_source_name)
outp_source.create_index(image=image_counts)
outp_source.create_key('image.cellId', data=in_cell,
chunks=(chunks_ids,))
outp_source.create_key('image.pulseId', data=in_pulse,
chunks=(chunks_ids,))
outp_source.create_key('image.data', data=out_data,
chunks=(chunks_data, 256, 256))
write_compressed_frames(
out_gain, outp_file, f'INSTRUMENT/{outp_source_name}/image/gain', comp_threads=8)
write_compressed_frames(
out_mask, outp_file, f'INSTRUMENT/{outp_source_name}/image/mask', comp_threads=8)
write_time = perf_counter() - start
total_time = open_time + read_time + correct_time + write_time
frame_rate = in_raw.shape[0] / total_time
print('{}\t{}\t{:.3f}\t{:.3f}\t{:.3f}\t{:.3f}\t{:.3f}\t{}\t{:.1f}'.format(
wid, aggregator, open_time, read_time, correct_time, write_time, total_time,
in_raw.shape[0], frame_rate))
in_raw = None
in_cell = None
in_pulse = None
out_data = None
out_gain = None
out_mask = None
gc.collect()
print('worker\tDA\topen\tread\tcorrect\twrite\ttotal\tframes\trate')
start = perf_counter()
psh.ProcessContext(num_workers=num_workers).map(correct_file, data_to_process)
total_time = perf_counter() - start
print(f'Total time: {total_time:.1f}s')
```
%% Cell type:markdown id: tags:
# Data preview for first train
%% Cell type:code id: tags:
``` python
geom = xg.LPD_1MGeometry.from_quad_positions(
[(11.4, 299), (-11.5, 8), (254.5, -16), (278.5, 275)])
output_paths = [outp_path for _, _, outp_path in data_to_process if outp_path.exists()]
dc = xd.DataCollection.from_paths(output_paths).select_trains(np.s_[0])
det = LPD1M(dc, detector_name=karabo_id)
data = det.get_array('image.data')
```
%% Cell type:markdown id: tags:
### Intensity histogram across all cells
%% Cell type:code id: tags:
``` python
left_edge_ratio = 0.01
right_edge_ratio = 0.99
fig, ax = plt.subplots(num=1, clear=True, figsize=(15, 6))
values, bins, _ = ax.hist(np.ravel(data.data), bins=2000, range=(-1500, 2000))
def find_nearest_index(array, value):
return (np.abs(array - value)).argmin()
cum_values = np.cumsum(values)
vmin = bins[find_nearest_index(cum_values, cum_values[-1]*left_edge_ratio)]
vmax = bins[find_nearest_index(cum_values, cum_values[-1]*right_edge_ratio)]
max_value = values.max()
ax.vlines([vmin, vmax], 0, max_value, color='red', linewidth=5, alpha=0.2)
ax.text(vmin, max_value, f'{left_edge_ratio*100:.0f}%',
color='red', ha='center', va='bottom', size='large')
ax.text(vmax, max_value, f'{right_edge_ratio*100:.0f}%',
color='red', ha='center', va='bottom', size='large')
ax.text(vmax+(vmax-vmin)*0.01, max_value/2, 'Colormap interval',
color='red', rotation=90, ha='left', va='center', size='x-large')
ax.set_xlim(vmin-(vmax-vmin)*0.1, vmax+(vmax-vmin)*0.1)
ax.set_ylim(0, max_value*1.1)
pass
```
%% Cell type:markdown id: tags:
### First memory cell
%% Cell type:code id: tags:
``` python
fig, ax = plt.subplots(num=2, figsize=(15, 15), clear=True, nrows=1, ncols=1)
geom.plot_data_fast(data[:, 0, 0], ax=ax, vmin=vmin, vmax=vmax)
pass
```
%% Cell type:markdown id: tags:
### Train average
%% Cell type:code id: tags:
``` python
fig, ax = plt.subplots(num=3, figsize=(15, 15), clear=True, nrows=1, ncols=1)
geom.plot_data_fast(data[:, 0].mean(axis=1), ax=ax, vmin=vmin, vmax=vmax)
pass
```
%% Cell type:markdown id: tags:
### Lowest gain stage per pixel
%% Cell type:code id: tags:
``` python
highest_gain_stage = det.get_array('image.gain', pulses=np.s_[:]).max(axis=(1, 2))
fig, ax = plt.subplots(num=4, figsize=(15, 15), clear=True, nrows=1, ncols=1)
p = geom.plot_data_fast(highest_gain_stage, ax=ax, vmin=0, vmax=2);
cb = ax.images[0].colorbar
cb.set_ticks([0, 1, 2])
cb.set_ticklabels(['High gain', 'Medium gain', 'Low gain'])
```
......
src/cal_tools/restful_config.yaml
+ 1
− 0
View file @ 520574f9
......@@ -10,6 +10,7 @@ mdc:
user-secret: '@note add this to secrets file'
calcat:
use-oauth2: true
auth-url: https://in.xfel.eu/calibration/oauth/authorize
base-api-url: https://in.xfel.eu/calibration/api
refresh-url: https://in.xfel.eu/calibration/oauth/token
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment

Legal Notice | Contacts