def checkArgs(args):
# Checks input for errors
args.o = checkDir(args.o, True)
if os.path.isdir(args.i) == True:
args.i = checkDir(args.i)
elif os.path.isfile(args.i) == False:
print("\n\t[Error] Please specify valid xls/xlsx file or directory. Exiting.")
quit()
return args
def __init__(self, indir, outfile):
self.columns = None
self.records = {}
self.species = {}
self.indir = unixpath.checkDir(indir)
self.outfile = outfile
self.ext = unixpath.getExt(self.outfile)
self.delim = self.__setDelim__()
self.totalsfile = self.__setTotalsFile__()
self.header = "Accession,CommonName,Species,Pathology#,DateOfDeath,MannerOfDeath,\
CauseOfDeath,Tumor,Location,Type,CancerDiagnosis,Malignant,MorphologicalDiagnosis\n"
# Make sure input directory exists
unixpath.checkDir(self.indir)
def __init__(self, args):
self.commands = []
self.config = "config.txt"
self.outdir = unixpath.checkDir(args.o, True)
self.password = getpass(prompt="\n\tEnter MySQL password: ")
self.user = args.u
self.__setConfig__()
def main():
parser = ArgumentParser("This script will check the output logs from \
mutect2parallel to identify any samples which were not successful.")
parser.add_argument("outdir",
help="Path to output directory of mutect2 parallel.")
args = parser.parse_args()
outdir = checkDir(args.outdir)
identifyFails(outdir)
def __init__(self, args):
unixpath.checkFile(args.d)
self.indir = unixpath.checkDir(args.p)
self.infile = args.d
self.outfile = args.o
self.species = {}
self.__readDeathBooks__()
self.__readPopulationFiles__()
self.__write__()
def __setInfiles__(self, infiles):
# Stores input file(s) in list
print("\n\tLocating input file(s)...")
if os.path.isfile(infiles):
self.infiles = [infiles]
else:
infiles = unixpath.checkDir(infiles)
for i in ["*.csv", "*.tsv", "*.txt"]:
self.infiles.extend(glob(infiles + i))
def main():
start = datetime.now()
parser = ArgumentParser("This script will merge Smithsonian National Zoo data, remove dupliates, and calcultate species totals.")
parser.add_argument("-i", required = True, help = "Path to input directory")
parser.add_argument("-t", required = True, help = "Path to species total directory.")
parser.add_argument("-o", required = True, help = "Path to output file (species total file will be written to same directory).")
args = parser.parse_args()
p = SmithsonianParser(args.i, args.o)
p.setSpecies(unixpath.checkDir(args.t))
p.parseInputDirectory()
p.getSpeciesTotals()
p.writeRecords()
print(("\tFinished. Run time: {}\n").format(datetime.now()-start))
def __init__(self, args):
pyplot.style.use("seaborn-deep")
self.approved ="Approved"
self.columns = [["Infant", "Castrated"], ["Masspresent", "Necropsy", "Metastasis"], ["Approved", "Zoo"]]
self.fields = ["Infant", "Castrated", "Masspresent", "Necropsy", "Metastasis", "Zoo"]
self.id = "ID"
self.label = [self.approved, "All"]
self.legend = "upper left"
self.outdir = unixpath.checkDir(args.o, True)
self.records = {}
print()
for idx, i in enumerate([args.p, args.d, args.s]):
self.__setTable__(i, self.columns[idx])
self.__barPlot__()
def __init__(self, args):
print("\n\tReading input file...")
d = ","
if "anage" in args.i:
d = "\t"
self.x = "Birth weight (g)"
self.y = "Weaning weight (g)"
elif "Amniote" in args.i:
self.x = "birth_or_hatching_weight_g"
self.y = "weaning_weight_g"
else:
self.x = args.x
self.y = args.y
self.df = read_csv(args.i, delimiter = d, header = 0, index_col = 0)
self.outdir = unixpath.checkDir(args.o, True)
self.fields = [["female_maturity", "male_maturity", "Gestation", "Weaning", "Infancy"],
["litter_size", "litters_year", "interbirth_interval", "max_longevity", "metabolic_rate", "adult_weight"],
["birth_weight", "weaning_weight", "adult_weight", "growth_rate"]]
def main():
starttime = datetime.now()
parser = ArgumentParser("This script will filter mutect2 output files.")
parser.add_argument("-t", type = int, default = 1, help = "Number of threads.")
parser.add_argument("-c", help = "Path to config file containing reference genome, java jars \
(if using), and mutect options (required; input files are read from sub-directories in output_directory \
and output will be written to same sub-directory).")
parser.add_argument("-o", help = "Output directory (if different from directory in config file).")
parser.add_argument("--cleanup", action = "store_true", default = False,
help = "Remove intermediary files (default is to keep them).")
parser.add_argument("--force", action = "store_true", default = False,
help = "Force script to re-run filtering (resumes from last complete step by default).")
args = parser.parse_args()
checkBin()
if args.t > cpu_count():
args.t = cpu_count()
# Load config file and discard batch template
conf, _ = getConf(args.c)
conf["cleanup"] = args.cleanup
conf["force"] = args.force
if args.o:
args.o = checkDir(args.o, True)
done, flog, blog, ulog = getComplete(args.o, args.force)
else:
args.o = conf["outpath"]
done, flog, blog, ulog = getComplete(conf["outpath"], args.force)
variants = getOutdir(conf, args.o, done, flog, blog, ulog)
l = len(variants)
pool = Pool(processes = args.t)
print(("\tComparing samples from {} sets with {} threads...\n").format(l, args.t))
for x in pool.imap_unordered(filterPair, variants):
l -= 1
if x[0] == False:
print(("\t[Warning] Some files from {} failed comparison.").format(x[1]), flush = True)
else:
print(("\tAll comparisons for {} run successfully. {} samples remaining.").format(x[1], l), flush = True)
pool.close()
pool.join()
print(("\n\tFinished. Runtime: {}\n").format(datetime.now()-starttime))
def __setTotalsFile__(self): # Stores name of species total file and makes sure output directory exists path = os.path.split(self.outfile)[0] path = unixpath.checkDir(path, True) return os.path.join(path, "smithsonianSpeciesTotals." + self.ext)
