def print_scaling_summary(self, scaling_script):
"""Log summary information after scaling."""
if ScalingModelObserver().data:
logger.info(ScalingModelObserver().return_model_error_summary())
valid_ranges = get_valid_image_ranges(scaling_script.experiments)
image_ranges = get_image_ranges(scaling_script.experiments)
msg = []
for (img, valid, refl) in zip(image_ranges, valid_ranges,
scaling_script.reflections):
if valid:
if len(valid) > 1 or valid[0][0] != img[0] or valid[-1][
1] != img[1]:
msg.append(
"Excluded images for experiment id: %s, image range: %s, limited range: %s"
% (
refl.experiment_identifiers().keys()[0],
list(img),
list(valid),
))
if msg:
msg = ["Summary of image ranges removed:"] + msg
logger.info("\n".join(msg))
# report on partiality of dataset
partials = flex.double()
for r in scaling_script.reflections:
if "partiality" in r:
partials.extend(r["partiality"])
not_full_sel = partials < 0.99
not_zero_sel = partials > 0.01
gt_half = partials > 0.5
lt_half = partials < 0.5
partial_gt_half_sel = not_full_sel & gt_half
partial_lt_half_sel = not_zero_sel & lt_half
logger.info("Summary of dataset partialities")
header = ["Partiality (p)", "n_refl"]
rows = [
["all reflections", str(partials.size())],
["p > 0.99", str(not_full_sel.count(False))],
["0.5 < p < 0.99",
str(partial_gt_half_sel.count(True))],
["0.01 < p < 0.5",
str(partial_lt_half_sel.count(True))],
["p < 0.01", str(not_zero_sel.count(False))],
]
logger.info(tabulate(rows, header))
logger.info(
"""
Reflections below a partiality_cutoff of %s are not considered for any
part of the scaling analysis or for the reporting of merging statistics.
Additionally, if applicable, only reflections with a min_partiality > %s
were considered for use when refining the scaling model.
""",
scaling_script.params.cut_data.partiality_cutoff,
scaling_script.params.reflection_selection.min_partiality,
)
if MergingStatisticsObserver().data:
logger.info(
make_merging_statistics_summary(
MergingStatisticsObserver().data["statistics"]))
def test_get_image_ranges():
"""Test for namesake function"""
scan = Scan(image_range=[1, 200], oscillation=[0.0, 1.0])
exp1 = Experiment(scan=scan)
exp2 = Experiment()
experiments = [exp1, exp2]
image_ranges = get_image_ranges(experiments)
assert image_ranges == [(1, 200), (0, 0)]
def export_mtz(integrated_data, experiment_list, params):
"""Export data from integrated_data corresponding to experiment_list to an
MTZ file hklout."""
# if mtz filename is auto, then choose scaled.mtz or integrated.mtz
if params.mtz.hklout in (None, Auto, "auto"):
if ("intensity.scale.value"
in integrated_data) and ("intensity.scale.variance"
in integrated_data):
params.mtz.hklout = "scaled.mtz"
logger.info(
"Data appears to be scaled, setting mtz.hklout = 'scaled.mtz'")
else:
params.mtz.hklout = "integrated.mtz"
logger.info(
"Data appears to be unscaled, setting mtz.hklout = 'integrated.mtz'"
)
# First get the experiment identifier information out of the data
expids_in_table = integrated_data.experiment_identifiers()
if not list(expids_in_table.keys()):
reflection_tables = parse_multiple_datasets([integrated_data])
experiment_list, refl_list = assign_unique_identifiers(
experiment_list, reflection_tables)
integrated_data = flex.reflection_table()
for reflections in refl_list:
integrated_data.extend(reflections)
expids_in_table = integrated_data.experiment_identifiers()
integrated_data.assert_experiment_identifiers_are_consistent(
experiment_list)
expids_in_list = list(experiment_list.identifiers())
# Convert experiment_list to a real python list or else identity assumptions
# fail like:
# assert experiment_list[0] is experiment_list[0]
# And assumptions about added attributes break
experiment_list = list(experiment_list)
# Validate multi-experiment assumptions
if len(experiment_list) > 1:
# All experiments should match crystals, or else we need multiple crystals/datasets
if not all(x.crystal == experiment_list[0].crystal
for x in experiment_list[1:]):
logger.warning(
"Experiment crystals differ. Using first experiment crystal for file-level data."
)
wavelengths = match_wavelengths(experiment_list)
if len(wavelengths.keys()) > 1:
logger.info(
"Multiple wavelengths found: \n%s",
"\n".join(" Wavlength: %.5f, experiment numbers: %s " %
(k, ",".join(map(str, v)))
for k, v in wavelengths.items()),
)
else:
wavelengths = OrderedDict(
{experiment_list[0].beam.get_wavelength(): [0]})
# also only work correctly with one panel (for the moment)
if any(len(experiment.detector) != 1 for experiment in experiment_list):
logger.warning("Ignoring multiple panels in output MTZ")
best_unit_cell = params.mtz.best_unit_cell
if best_unit_cell is None:
best_unit_cell = determine_best_unit_cell(experiment_list)
integrated_data["d"] = best_unit_cell.d(integrated_data["miller_index"])
# Clean up the data with the passed in options
integrated_data = filter_reflection_table(
integrated_data,
intensity_choice=params.intensity,
partiality_threshold=params.mtz.partiality_threshold,
combine_partials=params.mtz.combine_partials,
min_isigi=params.mtz.min_isigi,
filter_ice_rings=params.mtz.filter_ice_rings,
d_min=params.mtz.d_min,
)
# get batch offsets and image ranges - even for scanless experiments
batch_offsets = [
expt.scan.get_batch_offset() for expt in experiment_list
if expt.scan is not None
]
unique_offsets = set(batch_offsets)
if len(set(unique_offsets)) <= 1:
logger.debug("Calculating new batches")
batch_offsets = calculate_batch_offsets(experiment_list)
batch_starts = [
e.scan.get_image_range()[0] if e.scan else 0
for e in experiment_list
]
effective_offsets = [
o + s for o, s in zip(batch_offsets, batch_starts)
]
unique_offsets = set(effective_offsets)
else:
logger.debug("Keeping existing batches")
image_ranges = get_image_ranges(experiment_list)
if len(unique_offsets) != len(batch_offsets):
raise ValueError("Duplicate batch offsets detected: %s" % ", ".join(
str(item)
for item, count in Counter(batch_offsets).items() if count > 1))
# Create the mtz file
mtz_writer = UnmergedMTZWriter(
experiment_list[0].crystal.get_space_group())
# FIXME TODO for more than one experiment into an MTZ file:
#
# - add an epoch (or recover an epoch) from the scan and add this as an extra
# column to the MTZ file for scaling, so we know that the two lattices were
# integrated at the same time
# ✓ decide a sensible BATCH increment to apply to the BATCH value between
# experiments and add this
for id_ in expids_in_table.keys():
# Grab our subset of the data
loc = expids_in_list.index(
expids_in_table[id_]) # get strid and use to find loc in list
experiment = experiment_list[loc]
if len(list(wavelengths.keys())) > 1:
for i, (wl, exps) in enumerate(wavelengths.items()):
if loc in exps:
wavelength = wl
dataset_id = i + 1
break
else:
wavelength = list(wavelengths.keys())[0]
dataset_id = 1
reflections = integrated_data.select(integrated_data["id"] == id_)
batch_offset = batch_offsets[loc]
image_range = image_ranges[loc]
reflections = assign_batches_to_reflections([reflections],
[batch_offset])[0]
experiment.data = dict(reflections)
s0n = matrix.col(experiment.beam.get_s0()).normalize().elems
logger.debug("Beam vector: %.4f %.4f %.4f" % s0n)
mtz_writer.add_batch_list(
image_range,
experiment,
wavelength,
dataset_id,
batch_offset=batch_offset,
force_static_model=params.mtz.force_static_model,
)
# Create the batch offset array. This gives us an experiment (id)-dependent
# batch offset to calculate the correct batch from image number.
experiment.data["batch_offset"] = flex.int(len(experiment.data["id"]),
batch_offset)
# Calculate whether we have a ROT value for this experiment, and set the column
_, _, z = experiment.data["xyzcal.px"].parts()
if experiment.scan:
experiment.data[
"ROT"] = experiment.scan.get_angle_from_array_index(z)
else:
experiment.data["ROT"] = z
mtz_writer.add_crystal(
crystal_name=params.mtz.crystal_name,
project_name=params.mtz.project_name,
unit_cell=best_unit_cell,
)
# Note: add unit cell here as may have changed basis since creating mtz.
# For multi-wave unmerged mtz, we add an empty dataset for each wavelength,
# but only write the data into the final dataset (for unmerged the batches
# link the unmerged data to the individual wavelengths).
for wavelength in wavelengths:
mtz_writer.add_empty_dataset(wavelength)
# Combine all of the experiment data columns before writing
combined_data = {
k: v.deep_copy()
for k, v in experiment_list[0].data.items()
}
for experiment in experiment_list[1:]:
for k, v in experiment.data.items():
combined_data[k].extend(v)
# ALL columns must be the same length
assert len({len(v)
for v in combined_data.values()
}) == 1, "Column length mismatch"
assert len(combined_data["id"]) == len(
integrated_data["id"]), "Lost rows in split/combine"
# Write all the data and columns to the mtz file
mtz_writer.write_columns(combined_data)
logger.info("Saving {} integrated reflections to {}".format(
len(combined_data["id"]), params.mtz.hklout))
mtz_file = mtz_writer.mtz_file
mtz_file.write(params.mtz.hklout)
return mtz_file
def print_scaling_summary(script):
"""Log summary information after scaling."""
logger.info(print_scaling_model_error_summary(script.experiments))
valid_ranges = get_valid_image_ranges(script.experiments)
image_ranges = get_image_ranges(script.experiments)
msg = []
for (img, valid, refl) in zip(image_ranges, valid_ranges,
script.reflections):
if valid:
if len(valid
) > 1 or valid[0][0] != img[0] or valid[-1][1] != img[1]:
msg.append(
"Excluded images for experiment id: %s, image range: %s, limited range: %s"
% (
refl.experiment_identifiers().keys()[0],
list(img),
list(valid),
))
if msg:
msg = ["Summary of image ranges removed:"] + msg
logger.info("\n".join(msg))
# report on partiality of dataset
partials = flex.double()
for r in script.reflections:
if "partiality" in r:
partials.extend(r["partiality"])
not_full_sel = partials < 0.99
not_zero_sel = partials > 0.01
gt_half = partials > 0.5
lt_half = partials < 0.5
partial_gt_half_sel = not_full_sel & gt_half
partial_lt_half_sel = not_zero_sel & lt_half
logger.info("Summary of dataset partialities")
header = ["Partiality (p)", "n_refl"]
rows = [
["all reflections", str(partials.size())],
["p > 0.99", str(not_full_sel.count(False))],
["0.5 < p < 0.99",
str(partial_gt_half_sel.count(True))],
["0.01 < p < 0.5",
str(partial_lt_half_sel.count(True))],
["p < 0.01", str(not_zero_sel.count(False))],
]
logger.info(tabulate(rows, header))
logger.info(
"""
Reflections below a partiality_cutoff of %s are not considered for any
part of the scaling analysis or for the reporting of merging statistics.
Additionally, if applicable, only reflections with a min_partiality > %s
were considered for use when refining the scaling model.
""",
script.params.cut_data.partiality_cutoff,
script.params.reflection_selection.min_partiality,
)
stats = script.merging_statistics_result
if stats:
anom_stats, cut_stats, cut_anom_stats = (None, None, None)
if not script.scaled_miller_array.space_group().is_centric():
anom_stats = script.anom_merging_statistics_result
logger.info(make_merging_statistics_summary(stats))
try:
d_min = resolution_cc_half(stats, limit=0.3).d_min
except RuntimeError as e:
logger.debug(f"Resolution fit failed: {e}")
else:
max_current_res = stats.bins[-1].d_min
if d_min and d_min - max_current_res > 0.005:
logger.info(
"Resolution limit suggested from CC" + "\u00BD" +
" fit (limit CC" + "\u00BD" + "=0.3): %.2f",
d_min,
)
try:
cut_stats, cut_anom_stats = merging_stats_from_scaled_array(
script.scaled_miller_array.resolution_filter(
d_min=d_min),
script.params.output.merging.nbins,
script.params.output.use_internal_variance,
)
except DialsMergingStatisticsError:
pass
else:
if script.scaled_miller_array.space_group().is_centric():
cut_anom_stats = None
logger.info(
table_1_summary(stats, anom_stats, cut_stats, cut_anom_stats))
