def get_list_of_studies(self):
studies = []
h5files = fsutils.get_h5files_in_dir(self.search_path, self.trait_dir)
for h5file in h5files:
service = study_service.StudyService(h5file=h5file)
studies.extend(service.list_studies())
service.close_file()
return sorted(studies)
def get_list_of_studies_for_trait(self, trait):
h5file = fsutils.create_h5file_path(self.search_path, self.trait_dir,
trait)
if not isfile(h5file):
raise NotFoundError("Trait " + trait)
service = study_service.StudyService(h5file=h5file)
studies = service.list_studies()
service.close_file()
return sorted(studies)
def get_trait_of_study(self, study_to_find):
h5files = fsutils.get_h5files_in_dir(self.search_path, self.trait_dir)
for h5file in h5files:
service = study_service.StudyService(h5file=h5file)
for trait_study in service.list_trait_study_pairs():
if study_to_find == trait_study.split(":")[1]:
service.close_file()
return trait_study.split(":")[0]
service.close_file()
# study not found
raise NotFoundError("Study " + study_to_find)
def _find_h5file_study_group(self):
"""
Traverse all the hdf5 file and find any with the study group of interest
:return: dict of {h5file: studygroup path}
"""
hf_study_dict = {}
h5files = fsutils.get_h5files_in_dir(self.search_path, self.trait_dir)
for h5file in h5files:
service = study_service.StudyService(h5file=h5file)
for study_group in service.get_study_groups():
if self.study == study_group.get_name().split("/")[-1]:
hf_study_dict[h5file] = study_group.get_name()
service.close_file()
if any(hf_study_dict):
return hf_study_dict
else:
logger.debug("Study %s not found in any trait!", self.study)
raise NotFoundError("Study " + self.study)
def __init__(self, trait, start, size, config_properties=None):
self.trait = trait
self.start = start
self.size = size
self.properties = properties_handler.get_properties(config_properties)
self.search_path = properties_handler.get_search_path(self.properties)
self.trait_dir = self.properties.trait_dir
self.datasets = utils.create_dictionary_of_empty_dsets(TO_QUERY_DSETS)
# index marker will be returned along with the datasets
# it is the number that when added to the 'start' value that we started the query with
# will pinpoint where the next search needs to continue from
self.index_marker = 0
self.h5file = fsutils.create_h5file_path(self.search_path,
dir_name=self.trait_dir,
file_name=trait)
if not os.path.isfile(self.h5file):
raise NotFoundError("Trait " + trait)
self.service = study_service.StudyService(self.h5file)