def parse_spades_version(sample_name_): log_file = [ i for i in Utilities.scan_whole_dir( "/data1/bio/projects/vradchenko/lactobacillus_salivarius/pga-pe/log" ) if i.endswith(".log") and all(j in i for j in ["spades", sample_name_]) ][0] log_lines = Utilities.load_list(log_file) image_version_line = [ i for i in log_lines if i.strip().startswith("Status: Image is up to date for ") ][0].strip() spades_version = re.split("[\t ]+", image_version_line)[-1] return spades_version
d["is_correlation_valid"] = True return _process_out() try: print("Running on the node {}".format(os.uname()[1])) except: pass sleep(np.random.randint(90)) print("Polling the queue") remote_queue = os.path.join(ProjectDescriber.DATA_DIR, "correlation_data", "group_datasets", "tables.txt") correlation_tables = Utilities.remove_empty_values( Utilities.load_list(remote_queue)) if len(correlation_tables) == 0: print("Empty remote queue") sys.exit(0) Utilities.dump_list(correlation_tables[1:], remote_queue) correlation_table = correlation_tables[0] print("Now processing: '{}'".format(correlation_table)) group_name = os.path.splitext(os.path.basename(correlation_table))[0] out_dir = os.path.join(ProjectDescriber.DATA_DIR, "correlation_data", "group_results", group_name) correlation_df = load_tsv(correlation_table).dropna(axis=0, how="any") feature_groups = sorted(set([i.split("@")[0] for i in correlation_df.columns]))