def load_traits(self): hdf_store = fsutils.create_h5file_path(path=self.hdf_path, file_name="phen_meta", dir_name=self.trait_dir) dftrait = pd.read_csv(self.trait_file, sep="\t") self.write_traitfile_to_hdf(hdf_store, os.path.basename(self.trait_file))
def _get_traversed_size(self, retrieved_index, trait): if retrieved_index == 0: h5file = fsutils.create_h5file_path(self.search_path, dir_name=self.trait_dir, file_name=trait) service = trait_service.TraitService(h5file) trait_size = service.get_trait_size(trait) service.close_file() return trait_size return retrieved_index
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 __init__(self, chromosome, start, size, config_properties=None): self.chromosome = chromosome 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.chr_dir = self.properties.chr_dir self.datasets = utils.create_dictionary_of_empty_dsets(TO_QUERY_DSETS) self.index_marker = 0 self.h5file = fsutils.create_h5file_path(path=self.search_path, dir_name=self.chr_dir, file_name=chromosome) if not os.path.isfile(self.h5file): raise NotFoundError("Chromosome " + str(chromosome)) self.service = chromosome_service.ChromosomeService(self.h5file)
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)