cal_tools/cal_tools/agipdlib.py

@@ -624,7 +624,7 @@ class AgipdCorrections:
         # slopeFF = slopeFFpix/avarege(slopeFFpix)
         # To apply them we have to / not *
         if self.corr_bools.get("xray_corr"):
-            data /= self.xray_cor[module_idx]
+            data /= self.xray_cor[module_idx][cellid, ...]
 
         # use sharedmem raw_data and t0_rgain
         # after calculating it while offset correcting.
@@ -818,7 +818,7 @@ class AgipdCorrections:
             uq, fidxv, cntsv = np.unique(trains, return_index=True,
                                          return_counts=True)
 
-            # Validate calculated CORR INDEX contents by checking 
+            # Validate calculated CORR INDEX contents by checking
             # difference between trainId stored in RAW data and trains from
             train_diff = np.isin(np.array(infile["/INDEX/trainId"]), uq,
                                  invert=True)
@@ -905,12 +905,12 @@ class AgipdCorrections:
         exists of the current AGIPD instances.
 
         Relative gain is derived both from pulse capacitor as well as low
-        intensity flat field data, information from flat field data is 
-        needed to 'calibrate' pulse capacitor data, if there is no 
+        intensity flat field data, information from flat field data is
+        needed to 'calibrate' pulse capacitor data, if there is no
         available FF data, relative gain for High Gain stage is set to 1:
 
-        * Relative gain for High gain stage - from the FF data we get 
-          the relative slopes of a given pixel and memory cells with 
+        * Relative gain for High gain stage - from the FF data we get
+          the relative slopes of a given pixel and memory cells with
           respect to all memory cells and all pixels in the module,
           Please note: Current slopesFF avaialble in calibibration
           constants are created per pixel only, not per memory cell:
@@ -923,9 +923,9 @@ class AgipdCorrections:
           between high and medium gain using slope information from
           fits to the linear part of high and medium gain:
 
-             rfpc_high_medium = m_h/m_m          
+             rfpc_high_medium = m_h/m_m
 
-          where m_h and m_m is the medium gain slope of given memory cells 
+          where m_h and m_m is the medium gain slope of given memory cells
           and pixel and m_h is the high gain slope as above
            rel_gain_medium = rel_high_gain * rfpc_high_medium
 
@@ -954,32 +954,16 @@ class AgipdCorrections:
 
         if self.corr_bools.get("xray_corr"):
             bpixels |= cons_data["BadPixelsFF"].astype(np.uint32)[..., :bpixels.shape[2], None]  # noqa
-            slopesFF = np.squeeze(cons_data["SlopesFF"])
-
+            slopesFF = cons_data["SlopesFF"]
             if len(slopesFF.shape) == 4:
                 slopesFF = slopesFF[..., 0]
-
-            # first 32 cells are known to behave differently so if we can avoid
-            # them
-            # when calculating the mean X-ray derived gain slope for each pixel
-            if slopesFF.shape[2] > 32:
-                xray_cor = np.nanmedian(
-                    slopesFF[..., 32:min(96, self.max_cells)], axis=2)
-            elif slopesFF.shape[2] > 2:
-                xray_cor = np.nanmedian(
-                    slopesFF[..., :min(96, self.max_cells)], axis=2)
-            else:
-                xray_cor = np.squeeze(slopesFF[..., 0])
+            # Memory cell resolved xray_cor correction
+            xray_cor = slopesFF  # (128, 512, mem_cells)
 
             # relative X-ray correction is normalized by the median
             # of all pixels
 
-            # TODO: A check is required to know why it is again divided by 
-            # median. If we have relative slopes in the constants
-            # and (we have!) 
-            # xray cor = (slopeFF/avarege_slopeFF)/avarege_slopeFF.
-            # It didn't not make sense and was removed. 
-            # xray_cor /= np.nanmedian(xray_cor)
+            xray_cor /= np.nanmedian(xray_cor)
 
             self.xray_cor[module_idx][...] = xray_cor.transpose()[...]
 
@@ -1041,13 +1025,19 @@ class AgipdCorrections:
             # ration between HG and MG per pixel per mem cell used
             # for rel gain calculation
             frac_high_med_pix = pc_high_m / pc_med_m
-            # avarage ration between HG and MG as a function of 
+            # avarage ration between HG and MG as a function of
             # mem cell (needed for bls_stripes)
             # TODO: Per pixel would be more optimal correction
             frac_high_med = pc_high_med / pc_med_med
             # calculate additional medium-gain offset
             md_additional_offset = pc_high_l - pc_med_l * pc_high_m / pc_med_m
 
+            # Calculate relative gain. If FF constants are available,
+            # use them for high gain
+            # if not rel_gain is calculated using PC data only
+            # if self.corr_bools.get("xray_corr"):
+            #     rel_gain[..., :self.max_cells, 0] /= xray_corr
+
             # PC data should be 'calibrated with X-ray data,
             # if it is not done, it is better to use 1 instead of bias
             # the results with PC arteffacts.
@@ -1078,17 +1068,35 @@ class AgipdCorrections:
         dname = device.device_name
         cons_data = dict()
         when = dict()
+
         for cname, mdata in const_yaml[dname].items():
             when[cname] = mdata["creation-time"]
             if when[cname]:
-                cf = h5py.File(mdata["file-path"], "r")
-                cons_data[cname] = np.copy(cf[f"{dname}/{cname}/0/data"])
-                cf.close()
+                # This path is only used when testing new flat fields from
+                # file during development: it takes ages to test using all
+                # cells. Consequently, the shape needs to be fixed when less
+                # cells are used.
+                with h5py.File(mdata["file-path"], "r") as cf:
+                    cons_data[cname] = np.copy(cf[f"{dname}/{cname}/0/data"])
+                    shape = cons_data[cname].shape  # (128, 512, mem_cells)
+                    extra_dims = shape[:2] + (self.max_cells-shape[2], )
+
+                    if extra_dims[-1] != 0 and cname == "BadPixelsFF":
+                        extra_temp = np.zeros(extra_dims, dtype=np.int32)
+                        cons_data[cname] = np.concatenate(
+                            (cons_data[cname], extra_temp), axis=2)
+                        print('An extra dimension was added to the constants '
+                              'for the benefit of BadPixelsFF')
+
+                    if extra_dims[-1] != 0 and cname == "SlopesFF":
+                        extra_temp = np.ones(extra_dims, dtype=np.float32)
+                        cons_data[cname] = np.concatenate(
+                            (cons_data[cname], extra_temp), axis=2)
+                        print('An extra dimension was added to the constants '
+                              'for the benefit of SlopesFF')
             else:
                 # Create empty constant using the list elements
-                cons_data[cname] = \
-                    getattr(np, mdata["file-path"][0])(mdata["file-path"][1])
-
+                cons_data[cname] = getattr(np, mdata["file-path"][0])(mdata["file-path"][1])  # noqa
         self.init_constants(cons_data, module_idx)
 
         return when
@@ -1191,7 +1199,7 @@ class AgipdCorrections:
                                                              dtype='f4')
 
             self.mask[module_idx] = sharedmem.empty(constant_shape, dtype='i4')
-            self.xray_cor[module_idx] = sharedmem.empty(constant_shape[2:],
+            self.xray_cor[module_idx] = sharedmem.empty(constant_shape[1:],
                                                         dtype='f4')
 
     def allocate_images(self, shape, n_cores_files):

cal_tools/cal_tools/agipdutils.py

@@ -43,7 +43,7 @@ def assemble_constant_dict(corr_bools, pc_bools, memory_cells, bias_voltage,
     const_dict = {
         "Offset": ["zeros", (128, 512, memory_cells, 3), darkcond],
         "Noise": ["zeros", (128, 512, memory_cells, 3), darkcond],
-        "ThresholdsDark": ["ones", (128, 512, memory_cells, 2), darkcond],
+        "ThresholdsDark": ["ones", (128, 512, memory_cells, 5), darkcond],
         "BadPixelsDark": ["zeros", (128, 512, memory_cells, 3), darkcond],
     }
 

cal_tools/cal_tools/agipdutils_ff.py

+from typing import Any, Dict, List, Optional, Tuple
+
+from iminuit import Minuit
+import numpy as np
+
+from cal_tools.enums import BadPixelsFF
+
+
+def any_in(mask: np.ndarray, bits: int) -> bool:
+    return mask.astype(np.uint) & bits > 0
+
+
+def gaussian(x: np.ndarray, norm: int = 1, mean: int = 0, sigma: int = 1) -> float:  # noqa
+    """
+    Return value of Gaussian function
+
+    :param x: Argument (float of 1D array) of Gaussian function
+    :param norm: Normalization of Gaussian function
+    :param mean: Mean parameter
+    :param sigma: Sigma parameter
+    :return: Value of gaussian function.
+    """
+    return norm * np.exp(-1 / 2 * ((x - mean) / sigma) ** 2) / (sigma * np.sqrt(2 * np.pi))  # noqa
+
+
+def gaussian_sum(x: np.ndarray, ng: int = 4, *p: Tuple[Any]) -> float:
+    """Sum of ng Gaussian functions
+
+    :param x: Argument (float of 1D array) of the function
+    :param ng: Number of Gaussian functions
+    :param p: List of parameters (norm1,mean1,sigma1,norm2,mean2,sigma2,...)
+    """
+    r = 0.
+    for i in range(ng):
+        r += gaussian(x, *p[i * 3:(i + 1) * 3])
+    return r
+
+
+def get_statistical_parameters(x: np.ndarray,
+                               y: np.ndarray,
+                               x_range: List) -> Tuple[np.uint64, np.float64, np.float64, np.ndarray]:  # noqa
+    """Return statistical parameters of selected part of a histogram.
+
+    :param x: Center of bins of the histogram
+    :param y: Value of bins of the histogram
+    :param x_range: x range to be considered
+    :return: Sum of histogram, Mean value, Standard deviation,
+             List of selected bins
+    """
+    # TODO: Check if wq.median works better than mean
+    sel = (x >= x_range[0]) & (x < x_range[1])
+    h_sum = np.sum(y[sel])
+    h_norm = y[sel] / h_sum
+    h_mean = np.sum(h_norm * x[sel])
+    h_sqr = (x[sel] - h_mean) ** 2
+    h_std = np.sqrt(np.sum(h_norm * h_sqr))
+
+    return h_sum, h_mean, h_std, sel
+
+
+def get_starting_parameters(xe: np.ndarray,
+                            ye: np.ndarray,
+                            limits: np.ndarray,
+                            n_peaks: int = 3,
+                            f_lim: int = 2) -> Tuple[Dict[str, Any], List[Tuple]]:  # noqa
+    """
+    Estimate starting parameters for Gaussian fit of several peaks.
+
+    :param xe: Center of bins of the histogram
+    :param ye: Value of bins of the histogram
+    :param limits: Position of each peak ((left1, right1),
+    (left2, right2), ...) to be considered.
+    :param n_peaks: Number of peaks
+    :param f_lim: Limits in units of standard deviation to consider
+    """
+    parameters = {}
+    shapes = []
+    for peak in range(n_peaks):
+        n, m, rms, idx = get_statistical_parameters(xe, ye, limits[peak])
+        limits2 = [m - f_lim * rms, m + f_lim * rms]
+        n, m, rms, idx = get_statistical_parameters(xe, ye, limits2)
+        shapes.append((n, m, rms, idx))
+
+        parameters.update({f'g{peak}sigma': rms,
+                           f'g{peak}n': float(n),
+                           f'g{peak}mean': m})
+    return parameters, shapes
+
+
+def fit_n_peaks(x: np.ndarray,
+                y: np.ndarray,
+                pars: Dict[str, Any],
+                x_range: Tuple[float, float],
+                do_minos: Optional[bool] = False,
+                n_peaks: Optional[int] = 4,
+                fix_d01: Optional[bool] = True) -> Minuit:
+    """
+    Fit histogram with n-Gaussian function.
+
+    :param x: Center of bins of the histogram
+    :param y: Value of bins of the histogram
+    :param pars: Dictionary of initial parameters for fitting
+    :param x_range: x Range to be considered for the fitting
+    :param do_minos: Run Minos if True
+    :param n_peaks: Number of Gaussian peaks to fit (min 2, max 4)
+    :param fix_d01: Fix position of peaks to the distance between noise and
+    first photon peak.
+    :return: minuit object
+    """
+    sel = (x >= x_range[0]) & (x < x_range[1])
+
+    # Square of bin errors
+    yrr2 = np.copy(y[sel])
+    yrr2[yrr2 == 0] = 1  # bins with zero events have error=1
+
+    if fix_d01:
+        pars['fix_g2mean'] = True
+        pars['fix_g3mean'] = True
+
+    if n_peaks < 4:
+        pars['g3n'] = 0
+        pars['fix_g3n'] = True
+        pars['g3sigma'] = 1
+        pars['fix_g3sigma'] = True
+        pars['fix_g3mean'] = True
+
+    if n_peaks < 3:
+        pars['g2n'] = 0
+        pars['fix_g2n'] = True
+        pars['g2sigma'] = 1
+        pars['fix_g2sigma'] = True
+        pars['fix_g2mean'] = True
+
+    def chi2_f(g0n, g0mean, g0sigma,
+               g1n, g1mean, g1sigma,
+               g2n, g2mean, g2sigma,
+               g3n, g3mean, g3sigma, ):
+
+        d01 = (g1mean - g0mean)
+
+        if 'fix_g2mean' in pars and pars['fix_g2mean']:
+            g2mean = g0mean + d01 * 2
+
+        if 'fix_g3mean' in pars and pars['fix_g3mean']:
+            g3mean = g0mean + d01 * 3
+
+        if g3n == 0:
+            n_peaks = 3
+        elif g2n == 0:
+            n_peaks = 2
+        else:
+            n_peaks = 4
+
+        yt = gaussian_sum(x[sel], n_peaks,
+                          g0n, g0mean, g0sigma,
+                          g1n, g1mean, g1sigma,
+                          g2n, g2mean, g2sigma,
+                          g3n, g3mean, g3sigma)
+        return np.nansum((yt - y[sel]) ** 2 / yrr2)
+
+    minuit = Minuit(chi2_f, **pars, pedantic=False)
+    minuit.migrad()
+
+    if do_minos:
+        if minuit.get_fmin().is_valid:
+            minuit.minos()
+
+    return minuit
+
+
+def set_par_limits(pars: Dict[str, Any],
+                   peak_range: np.ndarray,
+                   peak_norm_range: np.ndarray,
+                   peak_width_range: np.ndarray,
+                   n_peaks: Optional[int] = 4):
+    """
+    Set limits on initial fit parameters based on given values
+
+    :param pars: Dictionary of initial fit parameters
+    :param peak_range: Limits on peak positions
+    :param peak_norm_range: Limits on normalization of Gaussian peaks
+    :param peak_width_range: Limits on width of Gaussian peaks
+    :param n_peaks: Number of Gaussian peaks
+    """
+    for peak in range(n_peaks):
+        pars.update({f'limit_g{peak}n': peak_norm_range[peak],
+                     f'limit_g{peak}mean': peak_range[peak],
+                     f'limit_g{peak}sigma': peak_width_range[peak],
+                     })
+
+
+def get_mask(fit_summary: Dict[str, Any],
+             peak_lim: List,
+             d0_lim: List,
+             chi2_lim: List,
+             peak_width_lim: np.array) -> int:
+    """
+    Calculate Bad pixels mask based on fit results and given limits
+
+    :param fit_summary: Dictionary of the fit output from Multi-Gaussian fit
+    :param peak_lim: Limits on noise peak position
+    :param d0_lim: Limits on distance between noise and first photon peak
+    :param chi2_lim: Limits on reduced chi^2 value
+    :param peak_width_lim: Limits on noise peak width
+    :return: Bad pixel mask
+    """
+    if not fit_summary['is_valid']:
+        return BadPixelsFF.FIT_FAILED.value
+
+    m0 = fit_summary['g0mean']
+    s0 = fit_summary['g0sigma']
+    s1 = fit_summary['g1sigma']
+    s2 = fit_summary['g2sigma']
+    chi2_ndof = fit_summary['chi2_ndof']
+    d01 = fit_summary['g1mean'] - m0
+
+    mask = 0
+    if not fit_summary['is_valid']:
+        mask |= BadPixelsFF.FIT_FAILED.value
+
+    if not fit_summary['has_accurate_covar']:
+        mask |= BadPixelsFF.ACCURATE_COVAR.value
+
+    if not peak_lim[0] <= m0 <= peak_lim[1]:
+        mask |= BadPixelsFF.NOISE_PEAK_THRESHOLD.value
+
+    if not d0_lim[0] <= d01 <= d0_lim[1]:
+        mask |= BadPixelsFF.GAIN_THRESHOLD.value
+
+    if not chi2_lim[0] <= chi2_ndof <= chi2_lim[1]:
+        mask |= BadPixelsFF.CHI2_THRESHOLD.value
+
+    width_lim = peak_width_lim[0] * s0
+    inside_s1 = width_lim[0] <= s1 <= width_lim[1]
+
+    width_lim = peak_width_lim[1] * s0
+    inside_s2 = width_lim[0] <= s2 <= width_lim[1]
+
+    if not inside_s1 and inside_s2:
+        mask |= BadPixelsFF.PEAK_WIDTH_THRESHOLD.value
+
+    return mask

cal_tools/cal_tools/enums.py

@@ -28,6 +28,21 @@ class BadPixels(Enum):
     NON_LIN_RESPONSE_REGION  = 0b100000000000000000000 # bit 21
     
     
+class BadPixelsFF(Enum):
+    """ The SLopesFF Bad Pixel Encoding
+    """
+        
+    FIT_FAILED               = 0b000000000000000000001 # bit 1
+    CHI2_THRESHOLD           = 0b000000000000000000010 # bit 2
+    NOISE_PEAK_THRESHOLD     = 0b000000000000000000100 # bit 3
+    GAIN_THRESHOLD           = 0b000000000000000001000 # bit 4
+    PEAK_WIDTH_THRESHOLD     = 0b000000000000000010000 # bit 5
+    ACCURATE_COVAR           = 0b000000000000000100000 # bit 6
+    BAD_DARK                 = 0b000000000000001000000 # bit 6
+    NO_ENTRY                 = 0b000000000000010000000 # bit 7
+    GAIN_DEVIATION           = 0b000000000000100000000 # bit 8
+    
+    
 class SnowResolution(Enum):
     """ An Enum specifying how to resolve snowy pixels
     """

cal_tools/cal_tools/tools.py

@@ -264,13 +264,15 @@ def get_dir_creation_date(directory: str, run: int,
     ntries = 100
     while ntries > 0:
         try:
-            dates = []
-            for f in directory.glob('*.h5'):
-                with h5py.File(f, 'r') as fin:
-                    cdate = fin['METADATA/creationDate'][0].decode()
-                    cdate = datetime.datetime.strptime(cdate, "%Y%m%dT%H%M%SZ")
-                    dates.append(cdate)
-            return min(dates)
+            rfiles = list(directory.glob('*.h5'))
+            rfiles.sort(key=path.getmtime)
+            # get creation time for oldest file,
+            # as creation time between run files
+            # should be different only within few seconds
+            with h5py.File(rfiles[0], 'r') as fin:
+                cdate = fin['METADATA/creationDate'][0].decode()
+                cdate = datetime.datetime.strptime(cdate, "%Y%m%dT%H%M%SZ")
+            return cdate
         except (IOError, ValueError):
             ntries -= 1
         except KeyError:  # The files are here, but it's an older dataset

notebooks/AGIPD/AGIPD_Correct_and_Verify.ipynb

 %% Cell type:markdown id: tags:
 
 # AGIPD Offline Correction #
 
 Author: European XFEL Detector Group, Version: 2.0
 
 Offline Calibration for the AGIPD Detector
 
 %% Cell type:code id: tags:
 
 ``` python
 in_folder = "/gpfs/exfel/exp/HED/202031/p900174/raw" # the folder to read data from, required
 out_folder = "/gpfs/exfel/data/scratch/ahmedk/test/hibef_agipd2"  # the folder to output to, required
 sequences = [-1] # sequences to correct, set to -1 for all, range allowed
 modules = [-1] # modules to correct, set to -1 for all, range allowed
 run = 155 # runs to process, required
 
 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_id = "{}CH0" # inset for receiver devices
 path_template = 'RAW-R{:04d}-{}-S{:05d}.h5' # the template to use to access data
 h5path = 'INSTRUMENT/{}/DET/{}:xtdf/' # path in the HDF5 file to images
 h5path_idx = 'INDEX/{}/DET/{}:xtdf/' # path in the HDF5 file to images
 h5path_ctrl = '/CONTROL/{}/MDL/FPGA_COMP' # path to control information
 karabo_id_control = "HED_EXP_AGIPD500K2G" # karabo-id for control device
 karabo_da_control = 'AGIPD500K2G00' # karabo DA for control infromation
 
+slopes_ff_from_files = "" # Path to locally stored SlopesFF and BadPixelsFF constants
+
 use_dir_creation_date = True # use the creation data of the input dir for database queries
 cal_db_interface = "tcp://max-exfl016:8015#8045" # the database interface to use
 cal_db_timeout = 30000 # in milli seconds
 creation_date_offset = "00:00:00" # add an offset to creation date, e.g. to get different constants
 
 max_cells = 0 # number of memory cells used, set to 0 to automatically infer
 bias_voltage = 300 # Bias voltage
 acq_rate = 0. # the detector acquisition rate, use 0 to try to auto-determine
 gain_setting = 0.1 # the gain setting, use 0.1 to try to auto-determine
 photon_energy = 9.2 # photon energy in keV
 overwrite = True # set to True if existing data should be overwritten
 max_pulses = [0, 500, 1] # range list [st, end, step] of maximum pulse indices within a train. 3 allowed maximum list input elements.
 mem_cells_db = 0 # set to a value different than 0 to use this value for DB queries
 cell_id_preview = 1 # cell Id used for preview in single-shot plots
 
 # Correction parameters
 blc_noise_threshold = 5000 # above this mean signal intensity now baseline correction via noise is attempted
 cm_dark_fraction = 0.66 # threshold for fraction of  empty pixels to consider module enough dark to perform CM correction
 cm_dark_range = [-50.,30] # range for signal value ADU for pixel to be consider as a dark pixel
 cm_n_itr = 4 # number of iterations for common mode correction
 hg_hard_threshold = 1000 # threshold to force medium gain offset subtracted pixel to high gain
 mg_hard_threshold = 1000 # threshold to force medium gain offset subtracted pixel from low to medium gain
 noisy_adc_threshold = 0.25 # threshold to mask complete adc
 
 # Correction Booleans
 only_offset = False # Apply only Offset correction. if False, Offset is applied by Default. if True, Offset is only applied.
 rel_gain = False # do relative gain correction based on PC data
 xray_gain = False # do relative gain correction based on xray data
 blc_noise = False # if set, baseline correction via noise peak location is attempted
 blc_stripes = False # if set, baseline corrected via stripes
 blc_hmatch = False # if set, base line correction via histogram matching is attempted
 match_asics = False # if set, inner ASIC borders are matched to the same signal level
 adjust_mg_baseline = False # adjust medium gain baseline to match highest high gain value
 zero_nans = False # set NaN values in corrected data to 0
 zero_orange = False # set to 0 very negative and very large values in corrected data
 blc_set_min = False # Shift to 0 negative medium gain pixels after offset corr
 corr_asic_diag = False # if set, diagonal drop offs on ASICs are correted
 force_hg_if_below = False # set high gain if mg offset subtracted value is below hg_hard_threshold
 force_mg_if_below = False # set medium gain if mg offset subtracted value is below mg_hard_threshold
 mask_noisy_adc = False # Mask entire ADC if they are noise above a relative threshold
 common_mode = False # Common mode correction
 melt_snow = False # Identify (and optionally interpolate) 'snowy' pixels
 mask_zero_std = False # Mask pixels with zero standard deviation across train
 low_medium_gap = False # 5 sigma separation in thresholding between low and medium gain
 
 # Paralellization parameters
 chunk_size = 1000 # Size of chunk for image-weise correction
 chunk_size_idim = 1  # chunking size of imaging dimension, adjust if user software is sensitive to this.
 n_cores_correct = 16 # Number of chunks to be processed in parallel
 n_cores_files = 4 # Number of files to be processed in parallel
 sequences_per_node = 2 # number of sequence files per cluster node if run as slurm job, set to 0 to not run SLURM parallel
 
 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
 import copy
 from datetime import timedelta
 from dateutil import parser
 import gc
 import glob
 import itertools
 from IPython.display import HTML, display, Markdown, Latex
 import math
 from multiprocessing import Pool
 import os
 import re
 import sys
 import traceback
 from time import time, sleep, perf_counter
 import tabulate
 import warnings
 warnings.filterwarnings('ignore')
 import yaml
 
 from extra_geom import AGIPD_1MGeometry, AGIPD_500K2GGeometry
 from extra_data import RunDirectory, stack_detector_data
 from iCalibrationDB import Detectors
 from mpl_toolkits.mplot3d import Axes3D
 from matplotlib.ticker import LinearLocator, FormatStrFormatter
 from matplotlib.colors import LogNorm
 from matplotlib import cm as colormap
 import matplotlib.pyplot as plt
 import matplotlib
 matplotlib.use("agg")
 %matplotlib inline
 import numpy as np
 import seaborn as sns
 sns.set()
 sns.set_context("paper", font_scale=1.4)
 sns.set_style("ticks")
 
 from cal_tools.agipdlib import (AgipdCorrections, get_acq_rate,
                                 get_gain_setting, get_num_cells)
 from cal_tools.cython import agipdalgs as calgs
 from cal_tools.ana_tools import get_range
 from cal_tools.enums import BadPixels
 from cal_tools.tools import get_dir_creation_date, map_modules_from_folder
 from cal_tools.step_timing import StepTimer
 
 import seaborn as sns
 sns.set()
 sns.set_context("paper", font_scale=1.4)
 sns.set_style("ticks")
 ```
 
 %% Cell type:markdown id: tags:
 
 ## Evaluated parameters ##
 
 %% Cell type:code id: tags:
 
 ``` python
 # Fill dictionaries comprising bools and arguments for correction and data analysis
 
 # Here the herarichy and dependability for correction booleans are defined
 corr_bools = {}
 
 # offset is at the bottom of AGIPD correction pyramid.
 corr_bools["only_offset"] = only_offset
 
 # Dont apply any corrections if only_offset is requested
 if not only_offset:
     corr_bools["adjust_mg_baseline"] = adjust_mg_baseline
     corr_bools["rel_gain"] = rel_gain
     corr_bools["xray_corr"] = xray_gain
     corr_bools["blc_noise"] = blc_noise
     corr_bools["blc_stripes"] = blc_stripes
     corr_bools["blc_hmatch"] = blc_hmatch
     corr_bools["blc_set_min"] = blc_set_min
     corr_bools["match_asics"] = match_asics
     corr_bools["corr_asic_diag"] = corr_asic_diag
     corr_bools["zero_nans"] = zero_nans
     corr_bools["zero_orange"] = zero_orange
     corr_bools["mask_noisy_adc"] = mask_noisy_adc
     corr_bools["force_hg_if_below"] = force_hg_if_below
     corr_bools["force_mg_if_below"] = force_mg_if_below
     corr_bools["common_mode"] = common_mode
     corr_bools["melt_snow"] = melt_snow
     corr_bools["mask_zero_std"] = mask_zero_std
     corr_bools["low_medium_gap"] = low_medium_gap
 
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 if in_folder[-1] == "/":
     in_folder = in_folder[:-1]
 if sequences[0] == -1:
     sequences = None
 
 control_fname = f'{in_folder}/r{run:04d}/RAW-R{run:04d}-{karabo_da_control}-S00000.h5'
 h5path_ctrl = h5path_ctrl.format(karabo_id_control)
 h5path = h5path.format(karabo_id, receiver_id)
 h5path_idx = h5path_idx.format(karabo_id, receiver_id)
 
 print(f'Path to control file {control_fname}')
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # Create output folder
 os.makedirs(out_folder, exist_ok=overwrite)
 
 # Evaluate detector instance for mapping
 instrument = karabo_id.split("_")[0]
 if instrument == "SPB":
     dinstance = "AGIPD1M1"
     nmods = 16
 elif instrument == "MID":
     dinstance = "AGIPD1M2"
     nmods = 16
 # TODO: Remove DETLAB
 elif instrument == "HED" or instrument == "DETLAB":
     dinstance = "AGIPD500K"
     nmods = 8
 
 # Evaluate requested modules
 if karabo_da[0] == '-1':
     if modules[0] == -1:
         modules = list(range(nmods))
     karabo_da = ["AGIPD{:02d}".format(i) for i in modules]
 else:
     modules = [int(x[-2:]) for x in karabo_da]
 
 def mod_name(modno):
     return f"Q{modno // 4 + 1}M{modno % 4 + 1}"
 
 print("Process modules: ", ', '.join(
     [mod_name(x) for x in modules]))
 print(f"Detector in use is {karabo_id}")
 print(f"Instrument {instrument}")
 print(f"Detector instance {dinstance}")
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # Display Information about the selected pulses indices for correction.
 pulses_lst = list(range(*max_pulses)) if not (len(max_pulses)==1 and max_pulses[0]==0) else max_pulses
 
 try:
     if len(pulses_lst) > 1:
         print("A range of {} pulse indices is selected: from {} to {} with a step of {}"
                .format(len(pulses_lst), pulses_lst[0] , pulses_lst[-1] + (pulses_lst[1] - pulses_lst[0]),
                        pulses_lst[1] - pulses_lst[0]))
     else:
         print("one pulse is selected: a pulse of idx {}".format(pulses_lst[0]))
 except Exception as e:
     raise ValueError('max_pulses input Error: {}'.format(e))
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # set everything up filewise
 mmf = map_modules_from_folder(in_folder, run, path_template,
                               karabo_da, sequences)
 mapped_files, mod_ids, total_sequences, sequences_qm, _ = mmf
 file_list = []
 
 # ToDo: Split table over pages
 print(f"Processing a total of {total_sequences} sequence files in chunks of {n_cores_files}")
 table = []
 ti = 0
 for k, files in mapped_files.items():
     i = 0
     for f in list(files.queue):
         file_list.append(f)
         if i == 0:
             table.append((ti, k, i, f))
         else:
             table.append((ti, "", i,  f))
         i += 1
         ti += 1
 md = display(Latex(tabulate.tabulate(table, tablefmt='latex',
                                      headers=["#", "module", "# module", "file"])))
 file_list = sorted(file_list, key=lambda name: name[-10:])
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 filename = file_list[0]
 channel = int(re.findall(r".*-AGIPD([0-9]+)-.*", filename)[0])
 
 # Evaluate number of memory cells
 mem_cells = get_num_cells(filename, karabo_id, channel)
 if mem_cells is None:
     raise ValueError(f"No raw images found in {filename}")
 
 mem_cells_db = mem_cells if mem_cells_db == 0 else mem_cells_db
 max_cells = mem_cells if max_cells == 0 else max_cells
 
 # Evaluate aquisition rate
 if acq_rate == 0:
     acq_rate = get_acq_rate((filename, karabo_id, channel))
 
 print(f"Maximum memory cells to calibrate: {max_cells}")
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # Evaluate creation time
 creation_time = None
 if use_dir_creation_date:
     creation_time = get_dir_creation_date(in_folder, run)
     offset = parser.parse(creation_date_offset)
     delta = timedelta(hours=offset.hour,
                       minutes=offset.minute, seconds=offset.second)
     creation_time += delta
 
 # Evaluate gain setting
 if gain_setting == 0.1:
     if creation_time.replace(tzinfo=None) < parser.parse('2020-01-31'):
         print("Set gain-setting to None for runs taken before 2020-01-31")
         gain_setting = None
     else:
         try:
             gain_setting = get_gain_setting(control_fname, h5path_ctrl)
         except Exception as e:
             print(f'ERROR: while reading gain setting from: \n{control_fname}')
             print(e)
             print("Set gain setting to 0")
             gain_setting = 0
 
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 print(f"Using {creation_time} as creation time")
 print(f"Operating conditions are:\n• Bias voltage: {bias_voltage}\n• Memory cells: {mem_cells_db}\n"
               f"• Acquisition rate: {acq_rate}\n• Gain setting: {gain_setting}\n• Photon Energy: {photon_energy}\n")
 ```
 
 %% Cell type:markdown id: tags:
 
 ## Data processing ##
 
 %% Cell type:code id: tags:
 
 ``` python
 agipd_corr = AgipdCorrections(max_cells, max_pulses,
                               h5_data_path=h5path,
                               h5_index_path=h5path_idx,
                               corr_bools=corr_bools)
 
 agipd_corr.baseline_corr_noise_threshold = -blc_noise_threshold
 agipd_corr.hg_hard_threshold = hg_hard_threshold
 agipd_corr.mg_hard_threshold = mg_hard_threshold
 
 agipd_corr.cm_dark_min = cm_dark_range[0]
 agipd_corr.cm_dark_max = cm_dark_range[1]
 agipd_corr.cm_dark_fraction = cm_dark_fraction
 agipd_corr.cm_n_itr = cm_n_itr
 agipd_corr.noisy_adc_threshold = noisy_adc_threshold
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # Retrieve calibration constants to RAM
 agipd_corr.allocate_constants(modules, (3, mem_cells_db, 512, 128))
 
 const_yaml = None
 if os.path.isfile(f'{out_folder}/retrieved_constants.yml'):
     with open(f'{out_folder}/retrieved_constants.yml', "r") as f:
         const_yaml = yaml.safe_load(f.read())
 
 # retrive constants
 def retrieve_constants(mod):
     """
     Retrieve calibration constants and load them to shared memory
 
     Metadata for constants is taken from yml file or retrieved from the DB
     """
     device = getattr(getattr(Detectors, dinstance), mod_name(mod))
     err = ''
     try:
         # check if there is a yaml file in out_folder that has the device constants.
         if const_yaml and device.device_name in const_yaml:
             when = agipd_corr.initialize_from_yaml(const_yaml, mod, device)
         else:
             when = agipd_corr.initialize_from_db(cal_db_interface, creation_time, mem_cells_db, bias_voltage,
                                                  photon_energy, gain_setting, acq_rate, mod, device, False)
     except Exception as e:
         err = f"Error: {e}\nError traceback: {traceback.format_exc()}"
         when = None
     return err, mod, when, device.device_name
 
 
 ts = perf_counter()
 with Pool(processes=len(modules)) as pool:
     const_out = pool.map(retrieve_constants, modules)
 print(f"Constants were loaded in {perf_counter()-ts:.01f}s")
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # allocate memory for images and hists
 n_images_max = max_cells*256
 data_shape = (n_images_max, 512, 128)
 agipd_corr.allocate_images(data_shape, n_cores_files)
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 def batches(l, batch_size):
     """Group a list into batches of (up to) batch_size elements"""
     start = 0
     while start < len(l):
         yield l[start:start + batch_size]
         start += batch_size
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 def imagewise_chunks(img_counts):
     """Break up the loaded data into chunks of up to chunk_size
 
     Yields (file data slot, start index, stop index)
     """
     for i_proc, n_img in enumerate(img_counts):
         n_chunks = math.ceil(n_img / chunk_size)
         for i in range(n_chunks):
             yield i_proc, i * n_img // n_chunks, (i+1) * n_img // n_chunks
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 step_timer = StepTimer()
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 with Pool() as pool:
     for file_batch in batches(file_list, n_cores_files):
         # TODO: Move some printed output to logging or similar
         print(f"Processing next {len(file_batch)} files:")
         for file_name in file_batch:
             print(" ", file_name)
         step_timer.start()
 
         img_counts = pool.starmap(agipd_corr.read_file, enumerate(file_batch))
         step_timer.done_step('Loading data from files')
 
         # Evaluate zero-data-std mask
         pool.starmap(agipd_corr.mask_zero_std, itertools.product(
             range(len(file_batch)), np.array_split(np.arange(agipd_corr.max_cells), n_cores_correct)
         ))
         step_timer.done_step('Mask 0 std')
 
         # Perform offset image-wise correction
         pool.starmap(agipd_corr.offset_correction, imagewise_chunks(img_counts))
         step_timer.done_step("Offset correction")
 
 
         if blc_noise or blc_stripes or blc_hmatch:
             # Perform image-wise correction
             pool.starmap(agipd_corr.baseline_correction, imagewise_chunks(img_counts))
             step_timer.done_step("Base-line shift correction")
 
         if common_mode:
             # Perform cross-file correction parallel over asics
             pool.starmap(agipd_corr.cm_correction, itertools.product(
                 range(len(file_batch)), range(16)  # 16 ASICs per module
             ))
             step_timer.done_step("Common-mode correction")
 
         # Perform image-wise correction
         pool.starmap(agipd_corr.gain_correction, imagewise_chunks(img_counts))
         step_timer.done_step("Image-wise correction")
 
         # Save corrected data
         pool.starmap(agipd_corr.write_file, [
             (i_proc, file_name, os.path.join(out_folder, os.path.basename(file_name).replace("RAW", "CORR")))
             for i_proc, file_name in enumerate(file_batch)
         ])
         step_timer.done_step("Save")
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 print(f"Correction of {len(file_list)} files is finished")
 print(f"Total processing time {step_timer.timespan():.01f} s")
 print(f"Timing summary per batch of {n_cores_files} files:")
 step_timer.print_summary()
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # if there is a yml file that means a leading notebook got processed
 # and the reporting would be generated from it.
 fst_print = True
 
 to_store = []
 line = []
 for i, (error, modno, when, mod_dev) in enumerate(const_out):
     qm = mod_name(modno)
     # expose errors while applying correction
     if error:
         print("Error: {}".format(error) )
 
     if not const_yaml or mod_dev not in const_yaml:
         if fst_print:
             print("Constants are retrieved with creation time: ")
             fst_print = False
 
         line = [qm]
 
         # If correction is crashed
         if not error:
             print(f"{qm}:")
             for key, item in when.items():
                 if hasattr(item, 'strftime'):
                     item = item.strftime('%y-%m-%d %H:%M')
                 when[key] = item
                 print('{:.<12s}'.format(key), item)
 
         # Store few time stamps if exists
         # Add NA to keep array structure
         for key in ['Offset', 'SlopesPC', 'SlopesFF']:
             if when and key in when and when[key]:
                 line.append(when[key])
             else:
                 if error is not None:
                     line.append('Err')
                 else:
                     line.append('NA')
 
         if len(line) > 0:
             to_store.append(line)
 
 seq = sequences[0] if sequences else 0
 
 if len(to_store) > 0:
     with open(f"{out_folder}/retrieved_constants_s{seq}.yml","w") as fyml:
         yaml.safe_dump({"time-summary": {f"S{seq}":to_store}}, fyml)
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 def do_3d_plot(data, edges, x_axis, y_axis):
     fig = plt.figure(figsize=(10, 10))
     ax = fig.gca(projection='3d')
 
     # Make data.
     X = edges[0][:-1]
     Y = edges[1][:-1]
     X, Y = np.meshgrid(X, Y)
     Z = data.T
 
     # Plot the surface.
     surf = ax.plot_surface(X, Y, Z, cmap=colormap.coolwarm,
                            linewidth=0, antialiased=False)
     ax.set_xlabel(x_axis)
     ax.set_ylabel(y_axis)
     ax.set_zlabel("Counts")
 
 
 def do_2d_plot(data, edges, y_axis, x_axis):
     fig = plt.figure(figsize=(10, 10))
     ax = fig.add_subplot(111)
     extent = [np.min(edges[1]), np.max(edges[1]),
               np.min(edges[0]), np.max(edges[0])]
     im = ax.imshow(data[::-1, :], extent=extent, aspect="auto",
                    norm=LogNorm(vmin=1, vmax=max(10, np.max(data))))
     ax.set_xlabel(x_axis)
     ax.set_ylabel(y_axis)
     cb = fig.colorbar(im)
     cb.set_label("Counts")
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 def get_trains_data(run_folder, source, include, tid=None, path='*/DET/*', modules=16, fillvalue=np.nan):
     """
     Load single train for all module
 
     :param run_folder: Path to folder with data
     :param source: Data source to be loaded
     :param include: Inset of file name to be considered
     :param tid: Train Id to be loaded. First train is considered if None is given
     :param path: Path to find image data inside h5 file
 
     """
     run_data = RunDirectory(run_folder, include)
     if tid:
         tid, data = run_data.select('*/DET/*', source).train_from_id(tid)
         return tid, stack_detector_data(train=data, data=source, fillvalue=fillvalue, modules=modules)
     else:
         for tid, data in run_data.select('*/DET/*', source).trains(require_all=True):
             return tid, stack_detector_data(train=data, data=source, fillvalue=fillvalue, modules=modules)
     return None, None
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 if dinstance == "AGIPD500K":
     geom = AGIPD_500K2GGeometry.from_origin()
 else:
     geom = AGIPD_1MGeometry.from_quad_positions(quad_pos=[
         (-525, 625),
         (-550, -10),
         (520, -160),
         (542.5, 475),
     ])
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 include = '*S00000*' if sequences is None else f'*S{sequences[0]:05d}*'
 tid, corrected = get_trains_data(f'{out_folder}/', 'image.data', include, modules=nmods)
 _, gains = get_trains_data(f'{out_folder}/', 'image.gain', include, tid, modules=nmods)
 _, mask = get_trains_data(f'{out_folder}/', 'image.mask', include, tid, modules=nmods)
 _, blshift = get_trains_data(f'{out_folder}/', 'image.blShift', include, tid, modules=nmods)
 _, cellId = get_trains_data(f'{out_folder}/', 'image.cellId', include, tid, modules=nmods)
 _, pulseId = get_trains_data(f'{out_folder}/', 'image.pulseId', include, tid,
                              modules=nmods, fillvalue=0)
 _, raw = get_trains_data(f'{in_folder}/r{run:04d}/', 'image.data', include, tid, modules=nmods)
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 display(Markdown(f'## Preview and statistics for {gains.shape[0]} images of the train {tid} ##\n'))
 ```
 
 %% Cell type:markdown id: tags:
 
 ### Signal vs. Analogue Gain ###
 
 %% Cell type:code id: tags:
 
 ``` python
 hist, bins_x, bins_y = calgs.histogram2d(raw[:,0,...].flatten().astype(np.float32),
                                          raw[:,1,...].flatten().astype(np.float32),
                                          bins=(100, 100),
                                          range=[[4000, 8192], [4000, 8192]])
 do_2d_plot(hist, (bins_x, bins_y), "Signal (ADU)", "Analogue gain (ADU)")
 do_3d_plot(hist, (bins_x, bins_y), "Signal (ADU)", "Analogue gain (ADU)")
 ```
 
 %% Cell type:markdown id: tags:
 
 ### Signal vs. Digitized Gain ###
 
 The following plot shows plots signal vs. digitized gain
 
 %% Cell type:code id: tags:
 
 ``` python
 hist, bins_x, bins_y = calgs.histogram2d(corrected.flatten().astype(np.float32),
                                          gains.flatten().astype(np.float32), bins=(100, 3),
                                          range=[[-50, 8192], [0, 3]])
 do_2d_plot(hist, (bins_x, bins_y), "Signal (ADU)", "Gain bit value")
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 print(f"Gain statistics in %")
 table = [[f'{gains[gains==0].size/gains.size*100:.02f}',
           f'{gains[gains==1].size/gains.size*100:.03f}',
           f'{gains[gains==2].size/gains.size*100:.03f}']]
 md = display(Latex(tabulate.tabulate(table, tablefmt='latex',
                                      headers=["High", "Medium", "Low"])))
 ```
 
 %% Cell type:markdown id: tags:
 
 ### Intensity per Pulse ###
 
 %% Cell type:code id: tags:
 
 ``` python
 pulse_range = [np.min(pulseId[pulseId>=0]), np.max(pulseId[pulseId>=0])]
 
 mean_data = np.nanmean(corrected, axis=(2, 3))
 hist, bins_x, bins_y = calgs.histogram2d(mean_data.flatten().astype(np.float32),
                                       pulseId.flatten().astype(np.float32),
                                       bins=(100, int(pulse_range[1])),
                                       range=[[-50, 1000], pulse_range])
 
 do_2d_plot(hist, (bins_x, bins_y), "Signal (ADU)", "Pulse id")
 do_3d_plot(hist, (bins_x, bins_y), "Signal (ADU)", "Pulse id")
 
 hist, bins_x, bins_y = calgs.histogram2d(mean_data.flatten().astype(np.float32),
                                       pulseId.flatten().astype(np.float32),
                                       bins=(100,  int(pulse_range[1])),
                                       range=[[-50, 200000], pulse_range])
 
 do_2d_plot(hist, (bins_x, bins_y), "Signal (ADU)", "Pulse id")
 do_3d_plot(hist, (bins_x, bins_y), "Signal (ADU)", "Pulse id")
 ```
 
 %% Cell type:markdown id: tags:
 
 ### Baseline shift ###
 
 Estimated base-line shift with respect to the total ADU counts of corrected image.
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 h = ax.hist(blshift.flatten(), bins=100, log=True)
 _ = plt.xlabel('Baseline shift [ADU]')
 _ = plt.ylabel('Counts')
 _ = ax.grid()
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(10, 10))
 corrected_ave = np.nansum(corrected, axis=(2, 3))
 plt.scatter(corrected_ave.flatten()/10**6, blshift.flatten(), s=0.9)
 plt.xlim(-1, 1000)
 plt.grid()
 plt.xlabel('Illuminated corrected [MADU] ')
 _ = plt.ylabel('Estimated baseline shift [ADU]')
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 display(Markdown('### Raw preview ###\n'))
 display(Markdown(f'Mean over images of the RAW data\n'))
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 data = np.mean(raw[:, 0, ...], axis=0)
 vmin, vmax = get_range(data, 5)
 ax = geom.plot_data_fast(data, ax=ax, cmap="jet", vmin=vmin, vmax=vmax)
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 display(Markdown(f'Single shot of the RAW data from cell {np.max(cellId[cell_id_preview])} \n'))
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 vmin, vmax = get_range(raw[cell_id_preview, 0, ...], 5)
 ax = geom.plot_data_fast(raw[cell_id_preview, 0, ...], ax=ax, cmap="jet", vmin=vmin, vmax=vmax)
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 display(Markdown('### Corrected preview ###\n'))
 display(Markdown(f'A single shot image from cell {np.max(cellId[cell_id_preview])} \n'))
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 vmin, vmax = get_range(corrected[cell_id_preview], 7, -50)
 vmin = - 50
 ax = geom.plot_data_fast(corrected[cell_id_preview], ax=ax, cmap="jet", vmin=vmin, vmax=vmax)
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 vmin, vmax = get_range(corrected[cell_id_preview], 5, -50)
 nbins = np.int((vmax + 50) / 2)
 h = ax.hist(corrected[cell_id_preview].flatten(),
             bins=nbins, range=(-50, vmax),
             histtype='stepfilled', log=True)
 _ = plt.xlabel('[ADU]')
 _ = plt.ylabel('Counts')
 _ = ax.grid()
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 display(Markdown('### Mean CORRECTED Preview ###\n'))
 display(Markdown(f'A mean across one train \n'))
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 data = np.mean(corrected, axis=0)
 vmin, vmax = get_range(data, 7)
 ax = geom.plot_data_fast(data, ax=ax, cmap="jet", vmin=-50, vmax=vmax)
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 vmin, vmax = get_range(corrected, 10, -100)
 vmax = np.nanmax(corrected)
 if vmax > 50000:
     vmax=50000
 nbins = np.int((vmax + 100) / 5)
 h = ax.hist(corrected.flatten(), bins=nbins,
             range=(-100, vmax), histtype='step', log=True, label = 'All')
 _ = ax.hist(corrected[gains == 0].flatten(), bins=nbins, range=(-100, vmax),
             alpha=0.5, log=True, label='High gain', color='green')
 _ = ax.hist(corrected[gains == 1].flatten(), bins=nbins, range=(-100, vmax),
             alpha=0.5, log=True, label='Medium gain', color='red')
 _ = ax.hist(corrected[gains == 2].flatten(), bins=nbins,
             range=(-100, vmax), alpha=0.5, log=True, label='Low gain', color='yellow')
 _ = ax.legend()
 _ = ax.grid()
 _ = plt.xlabel('[ADU]')
 _ = plt.ylabel('Counts')
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 display(Markdown('### Maximum GAIN Preview ###\n'))
 display(Markdown(f'The per pixel maximum across one train for the digitized gain'))
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 ax = geom.plot_data_fast(np.max(gains, axis=0), ax=ax,
                          cmap="jet", vmin=-1, vmax=3)
 ```
 
 %% Cell type:markdown id: tags:
 
 ## Bad Pixels ##
 The mask contains dedicated entries for all pixels and memory cells as well as all three gains stages. Each mask entry is encoded in 32 bits as:
 
 %% Cell type:code id: tags:
 
 ``` python
 table = []
 for item in BadPixels:
     table.append((item.name, "{:016b}".format(item.value)))
 md = display(Latex(tabulate.tabulate(table, tablefmt='latex',
                                      headers=["Bad pixel type", "Bit mask"])))
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 display(Markdown(f'### Single Shot Bad Pixels ### \n'))
 display(Markdown(f'A single shot bad pixel map from cell {np.max(cellId[cell_id_preview])} \n'))
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 ax = geom.plot_data_fast(np.log2(mask[cell_id_preview]), ax=ax, vmin=0, vmax=32, cmap="jet")
 ```
 
 %% Cell type:markdown id: tags:
 
 ### Percentage of Bad Pixels across one train  ###
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 ax = geom.plot_data_fast(np.mean(mask>0, axis=0),
                          vmin=0, ax=ax, vmax=1, cmap="jet")
 ```
 
 %% Cell type:markdown id: tags:
 
 ### Percentage of Bad Pixels across one train. Only Dark Related ###
 
 %% Cell type:code id: tags:
 
 ``` python
 fig = plt.figure(figsize=(20, 10))
 ax = fig.add_subplot(111)
 cm = np.copy(mask)
 cm[cm > BadPixels.NO_DARK_DATA.value] = 0
 ax = geom.plot_data_fast(np.mean(cm>0, axis=0),
                          vmin=0, ax=ax, vmax=1, cmap="jet")
 ```

notebooks/AGIPD/AGIPD_Retrieve_Constants_Precorrection.ipynb

 %% Cell type:markdown id: tags:
 
 # AGIPD Retrieving Constants Pre-correction #
 
 Author: European XFEL Detector Group, Version: 1.0
 
 Retrieving Required Constants for Offline Calibration of the AGIPD Detector
 
 %% Cell type:code id: tags:
 
 ``` python
 cluster_profile = "noDB"
 in_folder = "/gpfs/exfel/exp/SPB/202030/p900119/raw" # the folder to read data from, required
 out_folder =  "/gpfs/exfel/data/scratch/ahmedk/test/AGIPD_"  # the folder to output to, required
 sequences =  [-1] # sequences to correct, set to -1 for all, range allowed
 modules = [-1] # modules to correct, set to -1 for all, range allowed
 run = 80 # runs to process, required
 
 karabo_id = "SPB_DET_AGIPD1M-1" # karabo karabo_id
 karabo_da = ['-1']  # a list of data aggregators names, Default [-1] for selecting all data aggregators
 path_template = 'RAW-R{:04d}-{}-S{:05d}.h5' # the template to use to access data
 h5path_ctrl = '/CONTROL/{}/MDL/FPGA_COMP_TEST' # path to control information
 karabo_id_control = "SPB_IRU_AGIPD1M1" # karabo-id for control device
 karabo_da_control = 'AGIPD1MCTRL00' # karabo DA for control infromation
 
 use_dir_creation_date = True # use the creation data of the input dir for database queries
 cal_db_interface = "tcp://max-exfl016:8015#8045" # the database interface to use
 creation_date_offset = "00:00:00" # add an offset to creation date, e.g. to get different constants
 
+slopes_ff_from_files = "" # Path to locally stored SlopesFF and BadPixelsFF constants
 calfile =  "" # path to calibration file. Leave empty if all data should come from DB
 nodb = False # if set only file-based constants will be used
 mem_cells = 0 # number of memory cells used, set to 0 to automatically infer
 bias_voltage = 300
 acq_rate = 0. # the detector acquisition rate, use 0 to try to auto-determine
 gain_setting = 0.1 # the gain setting, use 0.1 to try to auto-determine
 photon_energy = 9.2 # photon energy in keV
 max_cells_db_dark = 0  # set to a value different than 0 to use this value for dark data DB queries
 max_cells_db = 0 # set to a value different than 0 to use this value for DB queries
 
 # Correction Booleans
 only_offset = False # Apply only Offset correction. if False, Offset is applied by Default. if True, Offset is only applied.
 rel_gain = False # do relative gain correction based on PC data
 xray_gain = True # do relative gain correction based on xray data
 blc_noise = False # if set, baseline correction via noise peak location is attempted
 blc_stripes = False # if set, baseline corrected via stripes
 blc_hmatch = False # if set, base line correction via histogram matching is attempted
 match_asics = False # if set, inner ASIC borders are matched to the same signal level
 adjust_mg_baseline = False # adjust medium gain baseline to match highest high gain value
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # Fill dictionaries comprising bools and arguments for correction and data analysis
 
 # Here the herarichy and dependability for correction booleans are defined
 corr_bools = {}
 
 # offset is at the bottom of AGIPD correction pyramid.
 corr_bools["only_offset"] = only_offset
 
 # Dont apply any corrections if only_offset is requested
 if not only_offset:
     corr_bools["adjust_mg_baseline"] = adjust_mg_baseline
     corr_bools["rel_gain"] = rel_gain
     corr_bools["xray_corr"] = xray_gain
     corr_bools["blc_noise"] = blc_noise
     corr_bools["blc_hmatch"] = blc_hmatch
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 import sys
 from collections import OrderedDict
 
-# make sure a cluster is running with ipcluster start --n=32, give it a while to start
 import os
 import h5py
 import numpy as np
 import matplotlib
 matplotlib.use("agg")
 import matplotlib.pyplot as plt
-from ipyparallel import Client
-print(f"Connecting to profile {cluster_profile}")
-view = Client(profile=cluster_profile)[:]
-view.use_dill()
+import multiprocessing as mp
 
 from iCalibrationDB import Constants, Conditions, Detectors
 from cal_tools.tools import (map_modules_from_folder, get_dir_creation_date)
 from cal_tools.agipdlib import get_gain_setting
 from dateutil import parser
 from datetime import timedelta
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 max_cells = mem_cells
 
 creation_time = None
 if use_dir_creation_date:
     creation_time = get_dir_creation_date(in_folder, run)
     offset = parser.parse(creation_date_offset)
     delta = timedelta(hours=offset.hour, minutes=offset.minute, seconds=offset.second)
     creation_time += delta
     print(f"Using {creation_time} as creation time")
 
 if sequences[0] == -1:
     sequences = None
 
 if in_folder[-1] == "/":
     in_folder = in_folder[:-1]
 print(f"Outputting to {out_folder}")
 
 os.makedirs(out_folder, exist_ok=True)
 
 import warnings
 warnings.filterwarnings('ignore')
 
 from cal_tools.agipdlib import SnowResolution
 
 melt_snow = False if corr_bools["only_offset"] else SnowResolution.NONE
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 control_fname = f'{in_folder}/r{run:04d}/RAW-R{run:04d}-{karabo_da_control}-S00000.h5'
 h5path_ctrl = h5path_ctrl.format(karabo_id_control)
 
 if gain_setting == 0.1:
     if creation_time.replace(tzinfo=None) < parser.parse('2020-01-31'):
         print("Set gain-setting to None for runs taken before 2020-01-31")
         gain_setting = None
     else:
         try:
             gain_setting = get_gain_setting(control_fname, h5path_ctrl)
         except Exception as e:
             print(f'ERROR: while reading gain setting from: \n{control_fname}')
             print(e)
             print("Set gain setting to 0")
             gain_setting = 0
 
 print(f"Gain setting: {gain_setting}")
 print(f"Detector in use is {karabo_id}")
 
 
 # Extracting Instrument string
 instrument = karabo_id.split("_")[0]
 # Evaluate detector instance for mapping
 if instrument == "SPB":
     dinstance = "AGIPD1M1"
     nmods = 16
 elif instrument == "MID":
     dinstance = "AGIPD1M2"
     nmods = 16
 # TODO: Remove DETLAB
 elif instrument == "HED" or instrument == "DETLAB":
     dinstance = "AGIPD500K"
     nmods = 8
 
 print(f"Instrument {instrument}")
 print(f"Detector instance {dinstance}")
 
 
 if karabo_da[0] == '-1':
     if modules[0] == -1:
         modules = list(range(nmods))
     karabo_da = ["AGIPD{:02d}".format(i) for i in modules]
 else:
     modules = [int(x[-2:]) for x in karabo_da]
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 # set everything up filewise
 print(f"Checking the files before retrieving constants")
 mmf = map_modules_from_folder(in_folder, run, path_template, karabo_da, sequences)
 
 mapped_files, mod_ids, total_sequences, sequences_qm, _ = mmf
 ```
 
 %% Cell type:markdown id: tags:
 
 ## Retrieve Constants ##
 
 %% Cell type:code id: tags:
 
 ``` python
 from functools import partial
 import yaml
 
+
 def retrieve_constants(karabo_id, bias_voltage, max_cells, acq_rate,
                        gain_setting, photon_energy, only_dark, nodb_with_dark,
                        cal_db_interface, creation_time,
                        corr_bools, pc_bools, inp):
     """
     Retreive constant for each module in parallel and produce a dictionary
     with the creation-time and constant file path.
 
     :param karabo_id: (STR) Karabo ID
     :param bias_voltage: (FLOAT) Bias Voltage
     :param max_cells: (INT) Memory cells
     :param acq_rate: (FLOAT) Acquisition Rate
     :param gain_setting: (FLOAT) Gain setting
     :param photon_energy: (FLOAT) Photon Energy
     :param only_dark: (BOOL) only retrieve dark constants
     :param nodb_with_dark: (BOOL) no constant retrieval even for dark
     :param cal_db_interface: (STR) the database interface port
     :param creation_time: (STR) raw data creation time
     :param corr_bools: (DICT) A dictionary with bools for applying requested corrections
     :param pc_bools: (LIST) list of bools to retrieve pulse capacitor constants
     :param inp: (LIST) input for the parallel cluster of the partial function
     :return:
             mdata_dict: (DICT) dictionary with the metadata for the retrieved constants
             dev.device_name: (STR) device name
     """
 
     import numpy as np
     import sys
     import traceback
 
     from cal_tools.agipdlib import get_num_cells, get_acq_rate
     from cal_tools.agipdutils import assemble_constant_dict
     from cal_tools.tools import get_from_db
 
     from iCalibrationDB import Constants, Conditions, Detectors
 
     err = None
 
     qm_files, qm, dev, idx = inp
     # get number of memory cells from a sequence file with image data
     for f in qm_files:
         if not max_cells:
             max_cells = get_num_cells(f, karabo_id, idx)
             if max_cells is None:
                 if f != qm_files[-1]:
                     continue
                 else:
                     raise ValueError(f"No raw images found for {qm} for all sequences")
             else:
                 cells = np.arange(max_cells)
                 # get out of the loop,
                 # if max_cells is successfully calculated.
                 break
 
     if acq_rate == 0.:
         acq_rate = get_acq_rate((f, karabo_id, idx))
 
-    print(f"Set memory cells to {max_cells}")
-    print(f"Set acquistion rate cells to {acq_rate} MHz")
-
     # avoid creating retireving constant, if requested.
     if not nodb_with_dark:
         const_dict = assemble_constant_dict(corr_bools, pc_bools, max_cells, bias_voltage,
                                             gain_setting, acq_rate, photon_energy,
                                             beam_energy=None, only_dark=only_dark)
 
         # Retrieve multiple constants through an input dictionary
         # to return a dict of useful metadata.
         mdata_dict = dict()
         for cname, cval in const_dict.items():
-            try:
-                condition = getattr(Conditions, cval[2][0]).AGIPD(**cval[2][1])
-                co, mdata = \
-                    get_from_db(dev, getattr(Constants.AGIPD, cname)(),
-                                condition, getattr(np, cval[0])(cval[1]),
-                                cal_db_interface, creation_time, meta_only=True)
-                mdata_const = mdata.calibration_constant_version
-                # saving metadata in a dict
-                mdata_dict[cname] = dict()
-                # check if constant was sucessfully retrieved.
-                if mdata.comm_db_success:
-                    mdata_dict[cname]["file-path"] = f"{mdata_const.hdf5path}" \
-                                                     f"{mdata_const.filename}"
-                    mdata_dict[cname]["creation-time"] = f"{mdata_const.begin_at}"
-                else:
-                    mdata_dict[cname]["file-path"] = const_dict[cname][:2]
-                    mdata_dict[cname]["creation-time"] = None
-            except Exception as e:
-                err = f"Error: {e}, Traceback: {traceback.format_exc()}"
-                print(err)
+            # saving metadata in a dict
+            mdata_dict[cname] = dict()
+
+            if slopes_ff_from_files and cname in ["SlopesFF", "BadPixelsFF"]:
+                mdata_dict[cname]["file-path"] = f"{slopes_ff_from_files}/slopesff_bpmask_module_{qm}.h5"
+                mdata_dict[cname]["creation-time"] = "00:00:00"
+            else:
+                try:
+                    condition = getattr(Conditions, cval[2][0]).AGIPD(**cval[2][1])
+                    co, mdata = \
+                        get_from_db(dev, getattr(Constants.AGIPD, cname)(),
+                                    condition, getattr(np, cval[0])(cval[1]),
+                                    cal_db_interface, creation_time, meta_only=True, verbosity=0)
+                    mdata_const = mdata.calibration_constant_version
+
+                    # check if constant was sucessfully retrieved.
+                    if mdata.comm_db_success:
+                        mdata_dict[cname]["file-path"] = f"{mdata_const.hdf5path}" \
+                                                         f"{mdata_const.filename}"
+                        mdata_dict[cname]["creation-time"] = f"{mdata_const.begin_at}"
+                    else:
+                        mdata_dict[cname]["file-path"] = const_dict[cname][:2]
+                        mdata_dict[cname]["creation-time"] = None
+                except Exception as e:
+                    err = f"Error: {e}, Traceback: {traceback.format_exc()}"
+                    print(err)
 
     return qm, mdata_dict, dev.device_name, acq_rate, max_cells, err
 
 pc_bools = [corr_bools.get("rel_gain"),
             corr_bools.get("adjust_mg_baseline"),
             corr_bools.get('blc_noise'),
             corr_bools.get('blc_hmatch'),
             corr_bools.get('blc_stripes'),
             melt_snow]
 
 inp = []
 only_dark = False
 nodb_with_dark = False
 if not nodb:
     only_dark=(calfile != "")
 if calfile != "" and not corr_bools["only_offset"]:
     nodb_with_dark = nodb
 
 # A dict to connect virtual device
 # to actual device name.
 for i in modules:
     qm = f"Q{i//4+1}M{i%4+1}"
     if qm in mapped_files and not mapped_files[qm].empty():
         device = getattr(getattr(Detectors, dinstance), qm)
         qm_files = [str(mapped_files[qm].get()) for _ in range(mapped_files[qm].qsize())]
 
     else:
         print(f"Skipping {qm}")
         continue
 
     inp.append((qm_files, qm, device, i))
 
 p = partial(retrieve_constants, karabo_id, bias_voltage, max_cells,
             acq_rate, gain_setting, photon_energy, only_dark, nodb_with_dark,
             cal_db_interface, creation_time,
             corr_bools, pc_bools)
 
-results = view.map_sync(p, inp)
-#results = list(map(p, inp))
+with mp.Pool(processes=16) as pool:
+    results = pool.map(p, inp)
+
 mod_dev = dict()
 mdata_dict = dict()
 for r in results:
     if r:
         qm, md_dict, dname, acq_rate, max_cells, err = r
         mod_dev[dname] = {"mod": qm, "err": err}
         if err:
             print(f"Error for module {qm}: {err}")
         mdata_dict[dname] = md_dict
 # check if it is requested not to retrieve any constants from the database
 if not nodb_with_dark:
     with open(f"{out_folder}/retrieved_constants.yml", "w") as outfile:
         yaml.safe_dump(mdata_dict, outfile)
     print("\nRetrieved constants for modules: ",
           f"{[', '.join([f'Q{x//4+1}M{x%4+1}' for x in modules])]}")
     print(f"Operating conditions are:\n• Bias voltage: {bias_voltage}\n• Memory cells: {max_cells}\n"
           f"• Acquisition rate: {acq_rate}\n• Gain setting: {gain_setting}\n• Photon Energy: {photon_energy}\n")
     print(f"Constant metadata is saved in retrieved_constants.yml\n")
 else:
     print("No constants were retrieved as calibrated files will be used.")
 ```
 
 %% Cell type:code id: tags:
 
 ``` python
 print("Constants are retrieved with creation time: ")
 i = 0
 when = dict()
 to_store = []
 
 for dname, dinfo in mod_dev.items():
     print(dinfo["mod"], ":")
     line = [dinfo["mod"]]
     if dname in mdata_dict:
         for cname, mdata in mdata_dict[dname].items():
             if hasattr(mdata["creation-time"], 'strftime'):
                 mdata["creation-time"] = mdata["creation-time"].strftime('%y-%m-%d %H:%M')
             print(f'{cname:.<12s}', mdata["creation-time"])
         # Store few time stamps if exists
         # Add NA to keep array structure
     for cname in ['Offset', 'SlopesPC', 'SlopesFF']:
         if not dname in mdata_dict or dinfo["err"]:
             line.append('Err')
         else:
             if cname in mdata_dict[dname]:
                 if mdata_dict[dname][cname]["creation-time"]:
                     line.append(mdata_dict[dname][cname]["creation-time"])
                 else:
                     line.append('NA')
             else:
                 line.append('NA')
     to_store.append(line)
 
     i += 1
     if sequences:
         seq_num = sequences[0]
     else:
         # if sequences[0] changed to None as it was -1
         seq_num = 0
 
 with open(f"{out_folder}/retrieved_constants.yml","r") as fyml:
     time_summary = yaml.safe_load(fyml)
     time_summary.update({"time-summary": {
                                           "SAll":to_store
                                         }})
 with open(f"{out_folder}/retrieved_constants.yml","w") as fyml:
         yaml.safe_dump(time_summary, fyml)
 ```
-
-%% Cell type:code id: tags:
-
-``` python
-```

xfel_calibrate/notebooks.py

@@ -21,6 +21,8 @@ notebooks = {
         "FF": {
             "notebook":
                 "notebooks/AGIPD/Characterize_AGIPD_Gain_FlatFields_NBC.ipynb",
+            "dep_notebooks": [
+                "notebooks/AGIPD/Characterize_AGIPD_Gain_FlatFields_Summary.ipynb"],
             "concurrency": {"parameter": "modules",
                             "default concurrency": 16,
                             "cluster cores": 16},