def print_groups(filename):
"""
Print the image set groups for this pipeline
This function outputs a JSON string to the console composed of a list
of the groups in the pipeline image set. Each element of the list is
a two-tuple whose first element is a key/value dictionary of the
group's key and the second is a tuple of the image numbers in the group.
"""
path = os.path.expanduser(filename)
m = Measurements(filename=path, mode="r")
metadata_tags = m.get_grouping_tags()
groupings = m.get_groupings(metadata_tags)
json.dump(groupings, sys.stdout)
def print_groups(filename):
"""
Print the image set groups for this pipeline
This function outputs a JSON string to the console composed of a list
of the groups in the pipeline image set. Each element of the list is
a two-tuple whose first element is a key/value dictionary of the
group's key and the second is a tuple of the image numbers in the group.
"""
path = os.path.expanduser(filename)
m = Measurements(filename=path, mode="r")
metadata_tags = m.get_grouping_tags()
groupings = m.get_groupings(metadata_tags)
# Groupings are np.int64 which cannot be dumped to json
groupings_export = []
for g in groupings:
groupings_export.append((g[0], [int(imgnr) for imgnr in g[1]]))
json.dump(groupings_export, sys.stdout)
def get_batch_commands(filename, n_per_job=1):
"""Print the commands needed to run the given batch data file headless
filename - the name of a Batch_data.h5 file. The file should group image sets.
The output assumes that the executable, "CellProfiler", can be used
to run the command from the shell. Alternatively, the output could be
run through a utility such as "sed":
CellProfiler --get-batch-commands Batch_data.h5 | sed s/CellProfiler/farm_job.sh/
"""
path = os.path.expanduser(filename)
m = Measurements(filename=path, mode="r")
image_numbers = m.get_image_numbers()
if m.has_feature(IMAGE, GROUP_NUMBER):
group_numbers = m[IMAGE, GROUP_NUMBER, image_numbers, ]
group_indexes = m[IMAGE, GROUP_INDEX, image_numbers, ]
if numpy.any(group_numbers != 1) and numpy.all(
(group_indexes[1:] == group_indexes[:-1] + 1)
| ((group_indexes[1:] == 1)
& (group_numbers[1:] == group_numbers[:-1] + 1))):
#
# Do -f and -l if more than one group and group numbers
# and indices are properly constructed
#
bins = numpy.bincount(group_numbers)
cumsums = numpy.cumsum(bins)
prev = 0
for i, off in enumerate(cumsums):
if off == prev:
continue
print("CellProfiler -c -r -p %s -f %d -l %d" %
(filename, prev + 1, off))
prev = off
else:
metadata_tags = m.get_grouping_tags()
if len(metadata_tags) == 1 and metadata_tags[0] == "ImageNumber":
for i in range(0, len(image_numbers), n_per_job):
first = image_numbers[i]
last = image_numbers[min(i + n_per_job - 1,
len(image_numbers) - 1)]
print("CellProfiler -c -r -p %s -f %d -l %d" %
(filename, first, last))
else:
# LoadData w/ images grouped by metadata tags
groupings = m.get_groupings(metadata_tags)
for grouping in groupings:
group_string = ",".join(
["%s=%s" % (k, v) for k, v in list(grouping[0].items())])
print("CellProfiler -c -r -p %s -g %s" %
(filename, group_string))
return