def _make_input_for_exclude_tests(exclude_images=True):
"""Generate input data, that upon exclusion should leave only the first
reflection."""
if exclude_images:
exclude_images = [["0:360:720"], ["1:360:720"]]
expt1 = Experiment(scan=Scan(image_range=(0, 720), oscillation=(0.0, 1.0)))
expt2 = Experiment(scan=Scan(image_range=(0, 720), oscillation=(0.0,
-1.0)))
refls1 = flex.reflection_table()
refls2 = flex.reflection_table()
refls1["xyzobs.mm.value"] = flex.vec3_double([
(0.0, 0.0, 10.0 * math.pi / 180.0), (0.0, 0.0, 370.0 * math.pi / 180.0)
])
refls1["xyzobs.px.value"] = flex.vec3_double([(0.0, 0.0, 10.0),
(0.0, 0.0, 370.0)])
refls1["i"] = flex.int([0, 1])
refls2["xyzobs.mm.value"] = flex.vec3_double([
(0.0, 0.0, -10.0 * math.pi / 180.0),
(0.0, 0.0, -370.0 * math.pi / 180.0)
])
refls2["xyzobs.px.value"] = flex.vec3_double([(0.0, 0.0, 10.0),
(0.0, 0.0, 370.0)])
refls2["i"] = flex.int([0, 1])
expts = ExperimentList([expt1, expt2])
tables = [refls1, refls2]
expts, tables = assign_unique_identifiers(expts, tables)
return exclude_images, expts, tables
def test_assigning_specified_identifiers(experiments, reflections):
reflections[0].experiment_identifiers()[0] = "5"
reflections[1].experiment_identifiers()[1] = "6"
reflections[1].experiment_identifiers()[4] = "7"
input_identifiers = ["0", "1", "10"]
exp, rts = assign_unique_identifiers(experiments, reflections, input_identifiers)
assert list(exp.identifiers()) == input_identifiers
assert rts[0].experiment_identifiers()[0] == "0"
assert rts[0]["id"][0] == 0
assert rts[1].experiment_identifiers()[1] == "1"
assert rts[1]["id"][0] == 1
assert rts[2].experiment_identifiers()[2] == "10"
assert rts[2]["id"][0] == 2
# Test raises ValueError when wrong number of identifiers given
with pytest.raises(ValueError):
exp, rts = assign_unique_identifiers(experiments, reflections, ["0", "1"])
def test_assign_identifiers_where_none_are_set_but_refl_table_ids_have_duplicates(
experiments, reflections):
reflections[2]["id"] = flex.int([0, 0])
expts, rts = assign_unique_identifiers(experiments, reflections)
for i, (expt, refl) in enumerate(zip(expts, rts)):
assert set(refl["id"]) == {i}
assert expt.identifier != ""
assert refl.experiment_identifiers()[i] == expt.identifier
def test_assignment_of_unique_identifiers_when_refl_table_ids_are_present(
experiments, reflections):
assert list(experiments.identifiers()) == ["", "", ""]
expts, rts = assign_unique_identifiers(experiments, reflections)
for i, (expt, refl) in enumerate(zip(expts, rts)):
assert set(refl["id"]) == {i}
assert expt.identifier != ""
assert refl.experiment_identifiers()[i] == expt.identifier
def run(args=None):
usage = "dials.cosym [options] models.expt observations.refl"
parser = OptionParser(
usage=usage,
phil=phil_scope,
read_reflections=True,
read_experiments=True,
check_format=False,
epilog=help_message,
)
params, options, args = parser.parse_args(args=args,
show_diff_phil=False,
return_unhandled=True)
# Configure the logging
log.config(verbosity=options.verbose, logfile=params.output.log)
logger.info(dials_version())
# Log the diff phil
diff_phil = parser.diff_phil.as_str()
if diff_phil != "":
logger.info("The following parameters have been modified:\n")
logger.info(diff_phil)
if params.seed is not None:
flex.set_random_seed(params.seed)
np.random.seed(params.seed)
random.seed(params.seed)
if not params.input.experiments or not params.input.reflections:
parser.print_help()
sys.exit()
reflections, experiments = reflections_and_experiments_from_files(
params.input.reflections, params.input.experiments)
reflections = parse_multiple_datasets(reflections)
if len(experiments) != len(reflections):
raise Sorry(
"Mismatched number of experiments and reflection tables found: %s & %s."
% (len(experiments), len(reflections)))
try:
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
cosym_instance = cosym(experiments=experiments,
reflections=reflections,
params=params)
except ValueError as e:
raise Sorry(e)
if params.output.html or params.output.json:
register_default_cosym_observers(cosym_instance)
cosym_instance.run()
cosym_instance.export()
def test_raise_exception_if_unequal_experiments_and_reflections(experiments_024):
reflections_multi = [flex.reflection_table()]
reflections_multi[0]["id"] = flex.int([0, 1, 4])
reflections_multi[0].experiment_identifiers()[0] = "0"
reflections_multi[0].experiment_identifiers()[1] = "2"
reflections_multi[0].experiment_identifiers()[4] = "4"
del reflections_multi[0].experiment_identifiers()[4]
del reflections_multi[0]["id"][2]
with pytest.raises(ValueError):
exp, rts = assign_unique_identifiers(experiments_024, reflections_multi)
def run(args):
usage = "dials.symmetry [options] models.expt observations.refl"
parser = OptionParser(
usage=usage,
phil=phil_scope,
read_reflections=True,
read_experiments=True,
check_format=False,
epilog=help_message,
)
params, _, args = parser.parse_args(args=args,
show_diff_phil=False,
return_unhandled=True)
# Configure the logging
log.config(params.verbosity,
info=params.output.log,
debug=params.output.debug_log)
from dials.util.version import dials_version
logger.info(dials_version())
# Log the diff phil
diff_phil = parser.diff_phil.as_str()
if diff_phil != "":
logger.info("The following parameters have been modified:\n")
logger.info(diff_phil)
if params.seed is not None:
import random
flex.set_random_seed(params.seed)
random.seed(params.seed)
if not params.input.experiments or not params.input.reflections:
parser.print_help()
sys.exit()
experiments = flatten_experiments(params.input.experiments)
reflections = flatten_reflections(params.input.reflections)
reflections = parse_multiple_datasets(reflections)
if len(experiments) != len(reflections):
raise Sorry(
"Mismatched number of experiments and reflection tables found: %s & %s."
% (len(experiments), len(reflections)))
try:
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
symmetry(experiments, reflections, params=params)
except ValueError as e:
raise Sorry(e)
def test_assigned_identifiers_are_kept_when_assigning_rest(
experiments, reflections):
# Now test that if some are set, these are maintained and unique ids are
# set for the rest
experiments[0].identifier = "1"
reflections[0].experiment_identifiers()[0] = "1"
expts, rts = assign_unique_identifiers(experiments, reflections)
assert expts.identifiers()[0] == "1"
for i, (expt, refl) in enumerate(zip(expts, rts)):
assert set(refl["id"]) == {i}
assert expt.identifier != ""
assert refl.experiment_identifiers()[i] == expt.identifier
def test_assign_identifiers_where_none_are_set_but_refl_table_ids_have_duplicates(
experiments, reflections
):
reflections[2]["id"] = flex.int([0, 0])
exp, rts = assign_unique_identifiers(experiments, reflections)
expected_identifiers = ["0", "1", "2"]
# Check that identifiers are set in experiments and reflection table.
assert list(exp.identifiers()) == expected_identifiers
expected_ids = [0, 1, 2]
for i, refl in enumerate(rts):
assert refl.experiment_identifiers()[i] == expected_identifiers[i]
assert set(refl["id"]) == {i}
assert i == expected_ids[i]
def test_assignment_of_unique_identifiers_when_refl_table_ids_are_present(
experiments, reflections
):
assert list(experiments.identifiers()) == ["", "", ""]
exp, rts = assign_unique_identifiers(experiments, reflections)
expected_identifiers = ["0", "1", "2"]
expected_ids = [0, 1, 2]
# Check that identifiers are set in experiments and reflection table.
assert list(exp.identifiers()) == expected_identifiers
for i, refl in enumerate(rts):
assert refl.experiment_identifiers()[i] == expected_identifiers[i]
assert set(refl["id"]) == {i}
assert i == expected_ids[i]
def test_mtz_multi_wavelength(dials_data, run_in_tmpdir):
"""Test multi-wavelength mtz export"""
# First make suitable input - multi datasets experiment list and reflection
# table with different wavelengths
mcp = dials_data("multi_crystal_proteinase_k")
exp_1 = load.experiment_list(
mcp.join("experiments_1.json").strpath, check_format=False
)
exp_2 = load.experiment_list(
mcp.join("experiments_2.json").strpath, check_format=False
)
refl_1 = flex.reflection_table.from_file(mcp.join("reflections_1.pickle").strpath)
refl_2 = flex.reflection_table.from_file(mcp.join("reflections_2.pickle").strpath)
exp_1[0].beam.set_wavelength(0.5)
exp_2[0].beam.set_wavelength(1.0)
exp_1.extend(exp_2)
reflection_list = [refl_1, refl_2]
exps, refls = assign_unique_identifiers(exp_1, reflection_list)
joint_refl = flex.reflection_table()
for r in refls:
joint_refl.extend(r)
exps.as_json("tmp_exp.expt")
joint_refl.as_file("tmp_refl.refl")
# Now run
result = procrunner.run(
[
"dials.export",
"experiments=tmp_exp.expt",
"reflections=tmp_refl.refl",
"format=mtz",
"mtz.hklout=unmerged.mtz",
],
environment_override={"DIALS_EXPORT_DO_NOT_CHECK_FORMAT": "True"},
working_directory=run_in_tmpdir.strpath,
)
assert not result.returncode and not result.stderr
assert os.path.exists("unmerged.mtz")
# Inspect output
m = mtz.object("unmerged.mtz").crystals()
n_batches = []
wavelengths = []
for crystal in m:
for dataset in crystal.datasets():
wavelengths.append(dataset.wavelength())
n_batches.append(dataset.n_batches())
assert n_batches == [0, 25, 25] # base, dataset1, dataset2
assert wavelengths == [0, 0.5, 1.0] # base, dataset1, dataset2
def run(args=None):
"""Run symmetry analysis from the command-line."""
usage = "dials.symmetry [options] models.expt observations.refl"
parser = ArgumentParser(
usage=usage,
phil=phil_scope,
read_reflections=True,
read_experiments=True,
check_format=False,
epilog=help_message,
)
params, options, args = parser.parse_args(args=args,
show_diff_phil=False,
return_unhandled=True)
# Configure the logging
log.config(verbosity=options.verbose, logfile=params.output.log)
logger.info(dials_version())
# Log the diff phil
diff_phil = parser.diff_phil.as_str()
if diff_phil != "":
logger.info("The following parameters have been modified:\n")
logger.info(diff_phil)
if params.seed is not None:
flex.set_random_seed(params.seed)
random.seed(params.seed)
if not params.input.experiments or not params.input.reflections:
parser.print_help()
sys.exit()
reflections, experiments = reflections_and_experiments_from_files(
params.input.reflections, params.input.experiments)
reflections = parse_multiple_datasets(reflections)
if len(experiments) != len(reflections):
sys.exit(
"Mismatched number of experiments and reflection tables found: %s & %s."
% (len(experiments), len(reflections)))
try:
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
symmetry(experiments, reflections, params=params)
except ValueError as e:
sys.exit(e)
def test_assigned_identifiers_are_kept_when_assigning_rest(experiments, reflections):
# Now test that if some are set, these are maintained and unique ids are
# set for the rest
experiments[0].identifier = "1"
reflections[0].experiment_identifiers()[0] = "1"
exp, rts = assign_unique_identifiers(experiments, reflections)
expected_identifiers = ["1", "0", "2"]
assert list(exp.identifiers()) == expected_identifiers
expected_ids = [0, 1, 2]
for i, refl in enumerate(rts):
id_ = refl["id"][0]
assert refl.experiment_identifiers()[id_] == expected_identifiers[i]
assert set(refl["id"]) == {id_}
assert id_ == expected_ids[i]
def test_cases_where_all_set_whether_reflection_table_is_split_or_not(
experiments_024, reflections_024):
# should pass experiments back if identifiers all already set
exp, rts = assign_unique_identifiers(experiments_024, reflections_024)
expected_identifiers = ["0", "2", "4"]
# Check that identifiers are set in experiments and reflection table.
assert exp is experiments_024
assert list(exp.identifiers()) == expected_identifiers
expected_ids = [0, 1, 4]
for i, refl in enumerate(rts):
id_ = refl["id"][0]
assert refl.experiment_identifiers()[id_] == expected_identifiers[i]
assert set(refl["id"]) == {id_}
assert id_ == expected_ids[i]
def test_synthetic(
space_group,
unit_cell,
dimensions,
sample_size,
use_known_space_group,
use_known_lattice_group,
tmpdir,
):
os.chdir(tmpdir.strpath)
space_group = sgtbx.space_group_info(space_group).group()
if unit_cell is not None:
unit_cell = uctbx.unit_cell(unit_cell)
experiments, reflections, reindexing_ops = generate_experiments_reflections(
space_group=space_group,
unit_cell=unit_cell,
unit_cell_volume=10000,
sample_size=sample_size,
map_to_p1=True,
d_min=1.5,
)
params = phil_scope.extract()
if use_known_space_group:
params.space_group = space_group.info()
if use_known_lattice_group:
params.lattice_group = space_group.info()
if dimensions is not None:
params.dimensions = dimensions
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
cosym_instance = cosym(experiments, reflections, params=params)
register_default_cosym_observers(cosym_instance)
cosym_instance.run()
cosym_instance.export()
assert os.path.exists(params.output.experiments)
assert os.path.exists(params.output.reflections)
assert os.path.exists(params.output.html)
assert os.path.exists(params.output.json)
cosym_expts = load.experiment_list(params.output.experiments,
check_format=False)
assert len(cosym_expts) == len(experiments)
for expt in cosym_expts:
if unit_cell is not None:
assert expt.crystal.get_unit_cell().parameters() == pytest.approx(
unit_cell.parameters())
assert str(expt.crystal.get_space_group().info()) == str(
space_group.info())
assert expt.crystal.get_space_group() == space_group
def run(args=None):
"""Run assign experiment identifiers from the command line."""
usage = (
"""Usage: dials.assign_experiment_identifiers observations.refl models.expt"""
)
parser = ArgumentParser(
usage=usage,
read_experiments=True,
read_reflections=True,
phil=phil_scope,
check_format=False,
epilog=help_message,
)
params, _ = parser.parse_args(args=args, show_diff_phil=False)
if not params.input.experiments or not params.input.reflections:
parser.print_help()
sys.exit()
reflections, experiments = reflections_and_experiments_from_files(
params.input.reflections, params.input.experiments)
reflections = parse_multiple_datasets(reflections)
if len(experiments) != len(reflections):
raise Sorry(
"Mismatched number of experiments and reflection tables found: %s & %s."
% (len(experiments), len(reflections)))
try:
experiments, reflections = assign_unique_identifiers(
experiments, reflections, params.identifiers)
except ValueError as e:
raise Sorry(e)
print(f"assigned identifiers: {list(experiments.identifiers())}")
experiments.as_file(params.output.experiments)
joint_table = flex.reflection_table()
for reflection_table in reflections:
joint_table.extend(reflection_table)
joint_table.as_file(params.output.reflections)
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 run(args):
usage = ("xia2.multiplex [options] [param.phil] "
"models1.expt models2.expt observations1.refl "
"observations2.refl...")
# Create the parser
parser = OptionParser(
usage=usage,
phil=phil_scope,
read_reflections=True,
read_experiments=True,
check_format=False,
epilog=help_message,
)
# Parse the command line
params, options = parser.parse_args(args=args, show_diff_phil=False)
# Configure the logging
xia2.Handlers.Streams.setup_logging(logfile=params.output.log,
verbose=options.verbose)
logger.info(dials_version())
# Log the diff phil
diff_phil = parser.diff_phil.as_str()
if diff_phil != "":
logger.info("The following parameters have been modified:\n")
logger.info(diff_phil)
# Try to load the models and data
if len(params.input.experiments) == 0:
logger.info("No Experiments found in the input")
parser.print_help()
return
if len(params.input.reflections) == 0:
logger.info("No reflection data found in the input")
parser.print_help()
return
try:
assert len(params.input.reflections) == len(params.input.experiments)
except AssertionError:
raise sys.exit(
"The number of input reflections files does not match the "
"number of input experiments")
if params.seed is not None:
flex.set_random_seed(params.seed)
random.seed(params.seed)
experiments = flatten_experiments(params.input.experiments)
reflections = flatten_reflections(params.input.reflections)
if len(experiments) < 2:
sys.exit("xia2.multiplex requires a minimum of two experiments")
reflections = parse_multiple_datasets(reflections)
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
reflections, experiments = exclude_image_ranges_for_scaling(
reflections, experiments, params.exclude_images)
reflections_all = flex.reflection_table()
assert len(reflections) == 1 or len(reflections) == len(experiments)
for i, (expt, refl) in enumerate(zip(experiments, reflections)):
reflections_all.extend(refl)
reflections_all.assert_experiment_identifiers_are_consistent(experiments)
if params.identifiers is not None:
identifiers = []
for identifier in params.identifiers:
identifiers.extend(identifier.split(","))
params.identifiers = identifiers
try:
ScaleAndMerge.MultiCrystalScale(experiments, reflections_all, params)
except ValueError as e:
sys.exit(str(e))
def prepare_input(params, experiments, reflections):
"""Perform checks on the data and prepare the data for scaling.
Raises:
ValueError - a range of checks are made, a ValueError may be raised
for a number of reasons.
"""
#### First exclude any datasets, before the dataset is split into
#### individual reflection tables and expids set.
if (params.dataset_selection.exclude_datasets
or params.dataset_selection.use_datasets):
experiments, reflections = select_datasets_on_ids(
experiments,
reflections,
params.dataset_selection.exclude_datasets,
params.dataset_selection.use_datasets,
)
ids = flex.size_t()
for r in reflections:
ids.extend(r.experiment_identifiers().keys())
logger.info(
"\nDataset ids for retained datasets are: %s \n",
",".join(str(i) for i in ids),
)
#### Split the reflections tables into a list of reflection tables,
#### with one table per experiment.
logger.info("Checking for the existence of a reflection table \n"
"containing multiple datasets \n")
reflections = parse_multiple_datasets(reflections)
logger.info(
"Found %s reflection tables & %s experiments in total.",
len(reflections),
len(experiments),
)
if len(experiments) != len(reflections):
raise ValueError(
"Mismatched number of experiments and reflection tables found.")
#### Assign experiment identifiers.
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
ids = itertools.chain.from_iterable(r.experiment_identifiers().keys()
for r in reflections)
logger.info("\nDataset ids are: %s \n", ",".join(str(i) for i in ids))
for r in reflections:
r.unset_flags(flex.bool(len(r), True), r.flags.bad_for_scaling)
r.unset_flags(flex.bool(r.size(), True), r.flags.scaled)
reflections, experiments = exclude_image_ranges_for_scaling(
reflections, experiments, params.exclude_images)
#### Allow checking of consistent indexing, useful for
#### targeted / incremental scaling.
if params.scaling_options.check_consistent_indexing:
logger.info("Running dials.cosym to check consistent indexing:\n")
cosym_params = cosym_phil_scope.extract()
cosym_params.nproc = params.scaling_options.nproc
cosym_instance = cosym(experiments, reflections, cosym_params)
cosym_instance.run()
experiments = cosym_instance.experiments
reflections = cosym_instance.reflections
logger.info("Finished running dials.cosym, continuing with scaling.\n")
#### Make sure all experiments in same space group
sgs = [
expt.crystal.get_space_group().type().number() for expt in experiments
]
if len(set(sgs)) > 1:
raise ValueError("""The experiments have different space groups:
space group numbers found: %s
Please reanalyse the data so that space groups are consistent,
(consider using dials.reindex, dials.symmetry or dials.cosym) or
remove incompatible experiments (using the option exclude_datasets=)"""
% ", ".join(map(str, set(sgs))))
logger.info(
"Space group being used during scaling is %s",
experiments[0].crystal.get_space_group().info(),
)
#### If doing targeted scaling, extract data and append an experiment
#### and reflection table to the lists
if params.scaling_options.target_model:
logger.info("Extracting data from structural model.")
exp, reflection_table = create_datastructures_for_structural_model(
reflections, experiments, params.scaling_options.target_model)
experiments.append(exp)
reflections.append(reflection_table)
elif params.scaling_options.target_mtz:
logger.info("Extracting data from merged mtz.")
exp, reflection_table = create_datastructures_for_target_mtz(
experiments, params.scaling_options.target_mtz)
experiments.append(exp)
reflections.append(reflection_table)
#### Perform any non-batch cutting of the datasets, including the target dataset
best_unit_cell = params.reflection_selection.best_unit_cell
if best_unit_cell is None:
best_unit_cell = determine_best_unit_cell(experiments)
for reflection in reflections:
if params.cut_data.d_min or params.cut_data.d_max:
d = best_unit_cell.d(reflection["miller_index"])
if params.cut_data.d_min:
sel = d < params.cut_data.d_min
reflection.set_flags(sel,
reflection.flags.user_excluded_in_scaling)
if params.cut_data.d_max:
sel = d > params.cut_data.d_max
reflection.set_flags(sel,
reflection.flags.user_excluded_in_scaling)
if params.cut_data.partiality_cutoff and "partiality" in reflection:
reflection.set_flags(
reflection["partiality"] < params.cut_data.partiality_cutoff,
reflection.flags.user_excluded_in_scaling,
)
return params, experiments, reflections
def run(args=None,
phil=phil_scope): # type: (List[str], libtbx.phil.scope) -> None
usage = "dials.missing_reflections [options] scaled.expt scaled.refl"
parser = OptionParser(
usage=usage,
phil=phil,
read_reflections=True,
read_experiments=True,
check_format=False,
epilog=__doc__,
)
params, options = parser.parse_args(args=args, show_diff_phil=False)
# Configure the logging.
dials.util.log.config(options.verbose)
logger.info(dials_version())
# Log the difference between the PHIL scope definition and the active PHIL scope,
# which will include the parsed user inputs.
diff_phil = parser.diff_phil.as_str()
if diff_phil:
logger.info("The following parameters have been modified:\n%s",
diff_phil)
experiments = flatten_experiments(params.input.experiments)
reflections = flatten_reflections(params.input.reflections)
if not experiments or not reflections:
parser.print_help()
return
if len(reflections) != 1 and len(experiments) != len(reflections):
sys.exit(
"Number of experiments must equal the number of reflection tables")
from dials.util.multi_dataset_handling import (
assign_unique_identifiers,
parse_multiple_datasets,
)
reflections = parse_multiple_datasets(reflections)
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
if all("inverse_scale_factor" in refl for refl in reflections):
# Assume all arrays have been scaled
miller_array = scaled_data_as_miller_array(reflections,
experiments,
anomalous_flag=False)
else:
# Else get the integrated intensities
miller_arrays = filtered_arrays_from_experiments_reflections(
experiments,
reflections,
)
miller_array = miller_arrays[0]
for ma in miller_arrays[1:]:
miller_array = miller_array.concatenate(ma)
if params.d_min or params.d_max:
miller_array = miller_array.resolution_filter(d_min=params.d_min,
d_max=params.d_max)
# Print overall summary of input miller array
s = io.StringIO()
ma_unique = miller_array.unique_under_symmetry()
ma_unique.show_comprehensive_summary(f=s)
logger.info(f"\n{s.getvalue()}")
# Get the regions of missing reflections
complete_set, unique_ms = missing_reflections.connected_components(
miller_array)
unique_ms = [
ms for ms in unique_ms if ms.size() >= params.min_component_size
]
# Print some output for user
if len(unique_ms):
logger.info(
"The following connected regions of missing reflections have been identified:"
)
n_expected = complete_set.size()
rows = []
for ms in unique_ms:
d_max, d_min = (uctbx.d_star_sq_as_d(ds2)
for ds2 in ms.min_max_d_star_sq())
rows.append([
ms.size(),
f"{100 * ms.size() / n_expected:.1f}",
f"{d_max:.2f}-{d_min:.2f}",
])
logger.info(
tabulate(
rows,
headers=["# reflections", "% missing",
"Resolution range (Å)"]))
else:
logger.info("No connected regions of missing reflections identified")
def run(args=sys.argv[1:]):
# Create the parser
parser = OptionParser(
# usage=usage,
phil=phil_scope,
read_reflections=True,
read_experiments=True,
check_format=False,
# epilog=help_message,
)
# Parse the command line
params, options, args = parser.parse_args(args=args,
show_diff_phil=False,
return_unhandled=True)
# Configure the logging
xia2.Handlers.Streams.setup_logging(logfile=params.output.log,
verbose=options.verbose)
logger.info(dials_version())
# Log the diff phil
diff_phil = parser.diff_phil.as_str()
if diff_phil != "":
logger.info("The following parameters have been modified:\n")
logger.info(diff_phil)
if params.unit_cell is not None:
unit_cell = params.unit_cell
crystal_symmetry = crystal.symmetry(unit_cell=unit_cell)
else:
crystal_symmetry = None
if len(params.input.experiments):
experiments = flatten_experiments(params.input.experiments)
reflections = flatten_reflections(params.input.reflections)
reflections = parse_multiple_datasets(reflections)
if len(experiments) != len(reflections):
raise sys.exit(
"Mismatched number of experiments and reflection tables found: %s & %s."
% (len(experiments), len(reflections)))
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
# transform models into miller arrays
intensities, batches = filtered_arrays_from_experiments_reflections(
experiments,
reflections,
outlier_rejection_after_filter=False,
partiality_threshold=0.99,
return_batches=True,
)
if args and os.path.isfile(args[0]):
result = any_reflection_file(args[0])
unmerged_intensities = None
batches_all = None
for ma in result.as_miller_arrays(merge_equivalents=False,
crystal_symmetry=crystal_symmetry):
if ma.info().labels == ["I(+)", "SIGI(+)", "I(-)", "SIGI(-)"]:
assert ma.anomalous_flag()
unmerged_intensities = ma
elif ma.info().labels == ["I", "SIGI"]:
assert not ma.anomalous_flag()
unmerged_intensities = ma
elif ma.info().labels == ["BATCH"]:
batches_all = ma
assert batches_all is not None
assert unmerged_intensities is not None
sel = unmerged_intensities.sigmas() > 0
unmerged_intensities = unmerged_intensities.select(sel).set_info(
unmerged_intensities.info())
batches_all = batches_all.select(sel)
id_to_batches = None
if len(params.batch) > 0:
id_to_batches = {}
for b in params.batch:
assert b.id is not None
assert b.range is not None
assert b.id not in id_to_batches, "Duplicate batch id: %s" % b.id
id_to_batches[b.id] = b.range
separate = separate_unmerged(unmerged_intensities,
batches_all,
id_to_batches=id_to_batches)
batches = list(separate.batches.values())
intensities = list(separate.intensities.values())
result = DeltaCcHalf(
intensities,
batches,
n_bins=params.n_bins,
d_min=params.d_min,
cc_one_half_method=params.cc_one_half_method,
group_size=params.group_size,
)
logger.info(tabulate(result.get_table(), headers="firstrow"))
hist_filename = "delta_cc_hist.png"
logger.info("Saving histogram to %s" % hist_filename)
result.plot_histogram(hist_filename)
normalised_scores_filename = "normalised_scores.png"
logger.info("Saving normalised scores to %s" % normalised_scores_filename)
result.plot_normalised_scores(normalised_scores_filename)
Citations.cite("delta_cc_half")
for citation in Citations.get_citations_acta():
logger.info(citation)
def test_raise_exception_when_existing_identifiers_are_inconsistent(
experiments_024, reflections):
reflections[1].experiment_identifiers()[0] = "5"
# should raise an assertion error for inconsistent identifiers
with pytest.raises(ValueError):
_, __ = assign_unique_identifiers(experiments_024, reflections)
def run(args=None,
phil=phil_scope): # type: (List[str], libtbx.phil.scope) -> None
"""
Check command-line input and call other functions to do the legwork.
Run the script, parsing arguments found in 'args' and using the PHIL scope
defined in 'phil'.
Args:
args: The arguments supplied by the user (default: sys.argv[1:])
phil: The PHIL scope definition (default: phil_scope, the master PHIL scope
for this program).
"""
usage = "dials.command_name [options] imported.expt strong.refl"
parser = OptionParser(
usage=usage,
phil=phil,
read_reflections=True,
read_experiments=True,
check_format=False,
epilog=__doc__,
)
params, options = parser.parse_args(args=args, show_diff_phil=False)
# Configure the logging.
dials.util.log.config(options.verbose)
# Log the difference between the PHIL scope definition and the active PHIL scope,
# which will include the parsed user inputs.
diff_phil = parser.diff_phil.as_str()
if diff_phil:
logger.info("The following parameters have been modified:\n%s",
diff_phil)
experiments = flatten_experiments(params.input.experiments)
reflections = flatten_reflections(params.input.reflections)
if not experiments or not reflections:
parser.print_help()
return
if len(reflections) != 1 and len(experiments) != len(reflections):
sys.exit(
"Number of experiments must equal the number of reflection tables")
from dials.util.multi_dataset_handling import (
assign_unique_identifiers,
parse_multiple_datasets,
)
reflections = parse_multiple_datasets(reflections)
experiments, reflections = assign_unique_identifiers(
experiments, reflections)
# Do whatever this program is supposed to do.
do_connected_components(
experiments,
reflections,
min_component_size=params.min_component_size,
)
