def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"-d",
"--directory",
dest="directory",
type="string",
help="supply directory where the input summaries aer located")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
infiles = glob.glob(os.path.join(options.directory, "*/*genes*summary*"))
sys.stdout.write("category\tnreads\tpreads\tsample\n")
for infile in infiles:
reformat(infile)
# write footer and output benchmark information.
E.stop()
def main(argv=None):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-r",
"--run-id",
dest="run_id",
type="int",
help="numerical identifier of a run [%default]")
parser.add_option("-d",
"--database-url",
dest="database_url",
type="string",
help="database url [%default]")
parser.add_option("-n",
"--dry-run",
dest="dry_run",
action="store_true",
help="only show statements to be executed [%default]")
parser.set_defaults(
run_id=None,
database_url="sqlite:///./csvdb",
dry_run=False,
)
(options, args) = E.start(parser, argv=argv, add_output_options=True)
purge_run_id(options.run_id, options.database_url, dry_run=options.dry_run)
E.stop()
def main(argv):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-o", "--option", dest="option", type="string")
(options, args) = E.start(parser, argv)
with IOTools.open_file(args[0]) as inf:
data = "".join(inf.readlines()).strip()
with IOTools.open_file(args[1]) as inf:
reference = "".join(inf.readlines()).strip()
data_counts = Counter(data)
ref_counts = Counter(reference)
keys = set(list(data_counts.keys()) + list(ref_counts.keys()))
options.stdout.write("key\tinput\treference\n")
for key in sorted(keys):
options.stdout.write(
"\t".join((key, str(data_counts[key]), str(ref_counts[key]))) + "\n")
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
# stop parsing options at the first argument
parser.disable_interspersed_args()
(options, args) = E.Start(parser, add_pipe_options=True)
if len(args) > 0:
cmd = args[0]
if len(args) > 1:
cmd += " '" + "' '".join(args[1:]) + "'"
s = subprocess.Popen(cmd, shell=True, cwd=os.getcwd(), close_fds=True)
(out, err) = s.communicate()
returncode = s.returncode
else:
returncode = 0
E.Stop()
sys.exit(returncode)
def main(argv=None):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"--regex-filename",
dest="regex_filename",
type="string",
help="extract column name from filename via regular expression "
"[%default]")
parser.add_option("--filter",
dest="filters",
type="choice",
action="append",
choices=("PASS", "SNP"),
help="apply filters to VCFs when reading "
"[%default]")
parser.set_defaults(
regex_filename=None,
filters=[],
)
(options, args) = E.start(parser, argv=argv, add_output_options=True)
if len(args) < 2:
raise ValueError("requiring at least 2 input filenames")
dfs = []
for filename in args:
if options.regex_filename:
try:
name = re.search(options.regex_filename, filename).groups()[0]
except AttributeError:
raise ValueError(
"regular expression '{}' does not match {}".format(
options.regex_filename, filename))
else:
name = iotools.snip(os.path.basename(filename), ".vcf.gz")
E.debug("reading data from {}".format(filename))
df = read_vcf_positions_into_dataframe(filename,
filters=options.filters)
df[name] = 1
dfs.append(df)
ndata = len(dfs)
merged_df = dfs[0]
for df in dfs[1:]:
merged_df = merged_df.merge(df, how="outer")
merged_df = merged_df.fillna(0)
ddf = merged_df.drop(["chrom", "pos"], axis=1)
set_counts = ddf.groupby(by=list(ddf.columns)).size()
set_counts = set_counts.reset_index()
set_counts.columns = list(set_counts.columns[:-1]) + ["counts"]
set_counts.to_csv(options.stdout, sep="\t", index=False)
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
dir2files = {}
for root, directory, files in os.walk("."):
dir2files[root] = files
ts = time.time()
st = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d_%H:%M:%S')
filename = "CWD_%s" % st
E.info("outputting directory state to %s" % filename)
with iotools.openFile(filename, "w") as outf:
outf.write("##contents of cwd on %s\n\n" % st)
for directory, files in dir2files.items():
for file in files:
path = os.path.join(directory, file)
outf.write(path + "\n")
# write footer and output benchmark information.
E.Stop()
def main(argv=None):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"-s", "--sample-size", dest="sample_size", type="float",
help="sample size. If less than 0, take a proportion of the chromosome size. "
"If greater than 0, take a fixed number of variants [%default]")
parser.set_defaults(
input_filename_fasta=None,
sample_size=0.001,
sample_name="NA12878"
)
(options, args) = E.start(parser,
argv=argv,
add_output_options=True)
if len(args) > 0:
options.input_filename_fasta = args[0]
if options.input_filename_fasta == "-":
options.input_filename_fasta = options.stdin
outf = options.stdout
outf.write("##fileformat=VCFv4.1\n")
outf.write("##FORMAT=<ID=GT,Number=1,Type=String,Description=\"Genotype\">\n")
outf.write("#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t{}\n".format(options.sample_name))
with pysam.FastxFile(options.input_filename_fasta) as inf:
for record in inf:
contig = record.name
sequence = record.sequence
if options.sample_size < 1.0:
nsamples = int(float(len(sequence)) * options.sample_size)
else:
nsamples = int(options.sample_size)
E.info("generating {} sampled variants for contig {}".format(nsamples, contig))
sampled_positions = set()
missing_nsamples = nsamples
while len(sampled_positions) < nsamples:
raw_positions = random.sample(list(range(len(sequence))), nsamples - len(sampled_positions))
filtered_positions = [x for x in raw_positions if sequence[x] != "N"]
sampled_positions.update(filtered_positions)
E.debug("sample update: total={}, raw={}, filtered={}".format(
len(sampled_positions),
len(raw_positions),
len(filtered_positions)))
sampled_positions = sorted(sampled_positions)
for position in sampled_positions:
base = sequence[position]
outf.write("{}\t{}\t.\t{}\t{}\t.\t.\t.\tGT\t0/0\n".format(
contig, position + 1, base, base))
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(
version=
"%prog version: $Id: cgat_script_template.py 2871 2010-03-03 10:20:44Z andreas $",
usage=globals()["__doc__"])
parser.add_option("-i",
"--test-option",
dest="test_option",
type="string",
help="test option [default=%default].")
parser.set_defaults(test_option="test")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
files = glob.glob(os.path.join(os.path.dirname(__file__), "*.pyx"))
# do sth
ninput, nskipped, noutput = 0, 0, 0
for f in files:
E.info("rebuilding %s" % f)
ninput += 1
prefix, suffix = os.path.splitext(f)
for ext in (".c", ".pyxbldc"):
try:
os.remove(prefix + ext)
except OSError:
pass
dirname, basename = os.path.split(prefix)
assert basename.startswith("_")
scriptname = os.path.join(dirname, basename[1:]) + ".py"
if not os.path.exists(scriptname):
E.warn("script %s does not exist - skipped" % scriptname)
nskipped += 1
continue
E.info("compiling %s" % scriptname)
os.system("%s %s --help > /dev/null" % (sys.executable, scriptname))
noutput += 1
E.info("ninput=%i, noutput=%i, nskipped=%i" % (ninput, noutput, nskipped))
# write footer and output benchmark information.
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(
version=
"%prog version: $Id: script_template.py 2871 2010-03-03 10:20:44Z andreas $",
usage=globals()["__doc__"])
parser.add_option("-m",
"--method",
dest="method",
type="choice",
choices=("script", "module"),
help="type of tests to create [%default].")
parser.set_defaults(method="script")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
if len(args) == 0:
raise ValueError(
"setup_test.py requires one or more command line arguments")
targetdir = os.path.dirname(__file__)
counter = E.Counter()
for arg in args:
counter.input += 1
script_dirname, basename = os.path.split(arg)
dirname = os.path.join(targetdir, basename)
if os.path.exists(dirname):
E.warn("%s already exists - skipping" % basename)
counter.skipped += 1
continue
os.mkdir(dirname)
with open(os.path.join(dirname, "tests.yaml"), "w") as outf:
outf.write(YAML_TEMPLATE)
counter.created += 1
E.info("%s" % str(counter))
# write footer and output benchmark information.
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(
version="%prog version: $Id$", usage=globals()["__doc__"])
(options, args) = E.start(parser, argv=argv)
if len(args) == 0:
args.append("-")
E.info(options.stdin)
infile = IOTools.open_file(options.stdin.name)
iterator = FastaIterator.FastaIterator(infile)
# outfile_info = IOTools.open_file(options.info_file, "w")
d = collections.OrderedDict()
cluster_dict = dict()
# first iterate over the fasta file and generate a dict
# with the name (title) as the key and the sequence as the value
# Remove any pseudo sequences
for cur_record in iterator:
# This is a temp fix because bedtools getfasta --name seems to have
# changed the way it names the fasta titles. This may be temp but This
# will fix this issue for the time being.
m = re.match("(chr\d+.tRNA\d+-\S+-(pseudo)?)::\S+([+|-])", cur_record.title.replace("(","").replace(")",""))
if m == None:
continue
if m.group(2) == "pseudo":
pass
else:
key = str(m.group(1) + m.group(3))
d[key] = cur_record.sequence
# next iterate of over the dict give the cluster a number
# this will be used to then map back for the info name
for key, value in d.items():
# Add CCA tail
options.stdout.write((">%s\n%scca\n")%(key, value))
E.stop()
def main(argv):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
(options, args) = E.start(parser, argv)
data = "".join(open(args[0]).readlines())
print(data[::-1])
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: fastas2fasta.py 2782 2009-09-10 11:40:29Z andreas $",
usage=globals()["__doc__"])
(options, args) = E.start(parser)
if len(args) < 2:
raise ValueError(
"please supply at least two filenames to concatenate.")
iterators = []
for a in args:
iterators.append(FastaIterator.FastaIterator(iotools.open_file(a,
"r")))
ninput, noutput, nerrors = 0, 0, 0
while 1:
sequences = []
ids = []
for iterator in iterators:
try:
cur_record = next(iterator)
except StopIteration:
break
sequences.append(re.sub(" ", "", cur_record.sequence))
ids.append(cur_record.title)
if not sequences:
break
ninput += 1
if len(sequences) != len(iterators):
raise ValueError("unequal number of sequences in files")
noutput += 1
options.stdout.write(">%s\n%s\n" % (ids[0], "".join(sequences)))
E.info("ninput=%i, noutput=%i, nerrors=%i" % (ninput, noutput, nerrors))
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(
version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"-a", "--first-fastq-file", dest="fastq1", type="string",
help="supply read1 fastq file")
parser.add_option(
"-b", "--second-fastq-file", dest="fastq2", type="string",
help="supply read2 fastq file")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
if args and len(args) == 2:
options.fastq1, options.fastq2 = args
fastq1 = iotools.open_file(options.fastq1)
fastq2 = iotools.open_file(options.fastq2)
E.info("iterating over fastq files")
f1_count = 0
for f1, f2 in zip_longest(Fastq.iterate(fastq1),
Fastq.iterate(fastq2)):
if not (f1 and f2) or (not f2 and f1):
try:
raise PairedReadError(
"unpaired reads detected. Are files sorted? are "
"files of equal length?")
except PairedReadError as e:
raise PairedReadError(e).with_traceback(sys.exc_info()[2])
else:
assert f1.identifier.endswith("/1") and \
f2.identifier.endswith("/2"), \
"Reads in file 1 must end with /1 and reads in file 2 with /2"
options.stdout.write(
">%s\n%s\n>%s\n%s\n" %
(f1.identifier, f1.seq, f2.identifier, f2.seq))
f1_count += 1
E.info("output: %i pairs" % f1_count)
# write footer and output benchmark information.
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv == None: argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-o",
"--ontology",
dest="ontology",
type="string",
help="ontology label")
parser.add_option("-f",
"--filter",
dest="filter",
action="store_true",
help="filter out genesets")
parser.add_option("-l",
"--filter-list",
dest="filter_list",
type="string",
help="list of pathways to keep")
parser.set_defaults(ontology=None, filter=False, filter_list=None)
## add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
if options.filter:
assert options.filter_list, "must specify a list of pathways to keep"
filter_set = set()
for line in open(options.filter_list).readlines():
filter_set.add(line[:-1])
inf = options.stdin
for line in inf.readlines():
data = line[:-1].split("\t")
name, description, evidence = data[0], data[0], data[1]
if options.filter:
if name not in filter_set: continue
genes = data[2:]
for gene in genes:
options.stdout.write("\t".join(
[options.ontology, gene, name, description, evidence]) + "\n")
## write footer and output benchmark information.
E.stop()
def main(argv=None):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-d",
"--delimiter",
dest="delimiter",
type="string",
help="delimiter to separate columns [%default]")
parser.add_option("-m",
"--method",
dest="methods",
type="choice",
action="append",
choices=["row-describe", "column-describe"],
help="additional methods to apply [%default]")
parser.set_defaults(
delimiter="\t",
methods=[],
)
(options, args) = E.start(parser, argv=argv, add_output_options=True)
if not options.methods:
options.methods = ["summary"]
table = pandas.read_csv(options.stdin, options.delimiter)
options.stdout.write("metric\tcount\tpercent\tinfo\n")
for method in options.methods:
label = re.sub("-", "_", method)
if method == "summary":
for category, count, denominator, info in compute_table_summary(
table):
options.stdout.write("\t".join(
map(str, (category, count,
iotools.pretty_percent(count, denominator,
na=""), info))) + "\n")
elif method == "column-describe":
df = table.describe().T.stack()
with E.open_output_file(label) as outf:
outf.write("label\tcategory\tvalue\n")
df.to_csv(outf, sep="\t")
elif method == "row-describe":
df = table.T.describe().stack()
with E.open_output_file(label) as outf:
outf.write("label\tcategory\tvalue\n")
df.to_csv(outf, sep="\t")
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
(options, args) = E.start(parser, argv=argv)
if len(args) == 0:
args.append("-")
E.info(options.stdin)
infile = IOTools.open_file(options.stdin.name)
lines = infile.readlines()
for line in lines:
column = line.split()
new_columns = [
column[0],
str(int(column[1]) - 50),
str(int(column[2]) + 50), column[3], column[4], column[5],
str(int(column[1]) - 50),
str(int(column[2]) + 50), column[8], column[9]
]
if "pseudo" not in column[3]:
if int(column[9]) == 2:
[c, d] = column[10].split(",")
block = int(column[2]) - int(column[1]) - int(d) + 50
new_10 = ''.join(str(int(c) + 50) + ',' + str(int(d) + 50))
new_11 = ''.join('0' + ',' + str(block))
new_columns = new_columns + [new_10, new_11]
else:
new_columns = new_columns + [
str(int(column[10]) + 100), column[11]
]
options.stdout.write('\t'.join(new_columns[0:]) + '\n')
E.stop()
def main(argv):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-o", "--option", dest="option", type="string")
(options, args) = E.start(parser, argv)
data = "".join(open(args[0]).readlines())
print(re.sub("o", "a", data))
E.stop()
def main(argv=sys.argv):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-i",
"--input-fastq-file",
dest="input_fastq_file",
type="string",
help="input fastq file. "
"[%default]")
parser.add_option("-m",
"--method",
dest="methods",
action="append",
type="choice",
choices=("length", ),
help="methods to apply [%default]")
parser.set_defaults(
methods=[],
input_fastq_file=None,
)
(options, args) = E.start(parser, argv)
if len(args) == 1:
options.input_fastq_file = args[0]
if options.input_fastq_file is None:
raise ValueError("missing input fastq file")
counter = E.Counter()
# note: complete rewrite with Counters, currently only length
if options.methods != ["length"]:
raise NotImplementedError()
with pysam.FastqFile(options.input_fastq_file) as inf:
for read in inf:
counter.input += 1
options.stdout.write(
"\t".join(map(str, (read.name, len(read.sequence)))) + "\n")
counter.output += 1
E.info(counter)
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-n",
"--dry-run",
dest="dry_run",
action="store_true",
help="dry run, do not delete any files [%default]")
parser.set_defaults(dry_run=False)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
filenames = args
c = E.Counter()
for filename in filenames:
c.checked += 1
if os.path.exists(filename + ".log"):
if iotools.isComplete(filename + ".log"):
c.complete += 1
continue
if iotools.isComplete(filename):
c.complete += 1
continue
c.incomplete += 1
E.info('deleting %s' % filename)
if options.dry_run:
continue
os.unlink(filename)
c.deleted += 1
E.info(c)
# write footer and output benchmark information.
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
(options, args) = E.start(parser, argv=argv)
if len(args) == 0:
args.append("-")
E.info(options.stdin)
infile = IOTools.open_file(options.stdin.name)
iterator = FastaIterator.FastaIterator(infile)
# outfile_info = IOTools.open_file(options.info_file, "w")
d = collections.OrderedDict()
cluster_dict = dict()
# first iterate over the fasta file and generate a dict
# with the name (title) as the key and the sequence as the value
# Remove any pseudo sequences
for cur_record in iterator:
key = cur_record.title
if "pseudo" in key:
pass
else:
d[key] = cur_record.sequence
# next iterate of over the dict give the cluster a number
# this will be used to then map back for the info name
for key, value in d.items():
# Add CCA tail
options.stdout.write((">%s\n%scca\n") % (key, value))
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(
version=
"%prog version: $Id: cgat_script_template.py 2781 2009-09-10 11:33:14Z andreas $",
usage=globals()["__doc__"])
parser.set_defaults()
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
if len(args) == 0 or (len(args) == 1 and args[0] == "-"):
infile = options.stdin
else:
infile = fileinput.FileInput(args)
# do sth
ninput, nskipped, noutput = 0, 0, 0
header = False
for line in infile:
ninput += 1
if line.startswith("#"):
pass
elif not header:
header = line
elif line == header:
nskipped += 1
continue
options.stdout.write(line)
noutput += 1
E.info("ninput=%i, noutput=%i, nskipped=%i" % (ninput, noutput, nskipped))
# write footer and output benchmark information.
E.stop()
def main(argv=None):
if argv is None:
argv = sys.argv
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("--fastq1", dest="fastq1")
parser.add_option("--to-drop-single", dest='to_remove_singletons')
parser.add_option("--fastq-out1", dest="fq_out1")
parser.add_option("--fastq-drop1", dest="fq_dropped1")
(options, args) = E.start(parser)
reads_to_remove = IOTools.open_file(
options.to_remove_singletons).readlines()
reads_to_remove = set([x.strip() for x in reads_to_remove])
fastq_out = IOTools.open_file(options.fq_out1, 'w')
fastq_host = IOTools.open_file(options.fq_dropped1, 'w')
reads = 0
dropped_reads = 0
for read in Fastq.iterate(IOTools.open_file(fastq1)):
reads += 1
if read.identifier.split()[0] in reads_to_remove:
fastq_host.write("@%s\n%s\n+\n%s\n" %
(read.identifier, read.seq, read.quals))
dropped_reads += 1
else:
fastq_out.write("@%s\n%s\n+\n%s\n" %
(read.identifier, read.seq, read.quals))
fastq_out.close()
fastq_host.close()
try:
percent_dropped = dropped_reads / float(reads) * 100
except ZeroDivisionError:
percent_dropped = 0.0
E.info('Dropped %i of %i reads (%f percent)' \
% (dropped_reads, reads, percent_dropped))
def main(argv=sys.argv):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option(
"-i", "--input-fastq", dest="input_fastq_file", type="string",
help="input fastq file")
parser.add_option(
"-m", "--method", dest="method", type="choice",
choices=["ont2pacbio"],
help="methods to apply [%default]")
parser.set_defaults(
input_fastq_file=None,
line_width=80,
method=None,
)
(options, args) = E.start(parser, argv, add_output_options=True)
if len(args) == 1:
options.input_fastq_file = args[0]
if options.input_fastq_file == "-":
options.input_fastq_file = options.stdin
outf = options.stdout
line_width = options.line_width
well_no = 0
for record in pysam.FastqFile(options.input_fastq_file):
well_no += 1
quals = record.get_quality_array()
seq = record.sequence
qv = int(math.floor(sum(quals) / len(quals)))
outf.write(">{}/{}/{}_{} RQ=0.{}\n".format(
"test", well_no, 1, len(seq) + 1, qv))
for x in range(0, len(seq), line_width):
outf.write(seq[x:x + line_width] + "\n")
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-k",
"--keep-header",
dest="keep_header",
type="int",
help="randomize, but keep header in place [%default]")
parser.set_defaults(keep_header=0)
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
inf = options.stdin
outf = options.stdout
c = E.Counter()
for x in range(options.keep_header):
c.header += 1
outf.write(inf.readline())
lines = inf.readlines()
c.lines_input = len(lines)
random.shuffle(lines)
for line in lines:
outf.write(line)
c.lines_output = len(lines)
E.info(c)
# write footer and output benchmark information.
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
infile = argv[-1]
for record in makeSplicedFasta(infile):
options.stdout.write(record)
# write footer and output benchmark information.
E.stop()
def main(argv=None):
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
(options, args) = E.start(parser, argv=argv, add_output_options=True)
total_counter = E.Counter()
table = []
for section, map_task2runner in [("tool", map_tool_to_runner),
("metric", map_metric_to_runner),
("split", map_split_to_runner),
("collate", map_collate_to_runner)]:
E.debug("processing section: {}".format(section))
counter = E.Counter()
for task, taskf in sorted(map_task2runner.items()):
counter.ntasks += 1
comments = []
try:
version = taskf().get_version()
counter.version_ok += 1
except Exception:
version = ""
comments.append("unavailable")
counter.version_fail += 1
comments = "; ".join(comments)
table.append((section, task, version, comments))
E.info("{}: {}".format(section, counter))
total_counter += counter
options.stdout.write("section\ttask\tversion\tcomments\n")
for row in table:
options.stdout.write("\t".join(map(str, row)) + "\n")
E.info("{}: {}".format("total", counter))
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(version="%prog version: $Id$")
parser.add_option("-s",
"--method=sort --sort-order",
dest="sort",
type="string",
help="fields to take (in sorted order).")
(options, args) = E.start(parser, add_csv_options=True)
reader = csv.DictReader(E.stdin, dialect=options.csv_dialect)
if options.sort:
fields = options.sort.split(",")
else:
fields = None
writer = csv.DictWriter(E.stdout,
fields,
dialect=options.csv_dialect,
lineterminator=options.csv_lineterminator,
extrasaction='ignore')
E.stdout.write("\t".join(fields) + "\n")
for row in reader:
row = iotools.convertDictionary(row)
writer.writerow(row)
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("--task", dest="task", type="choice",
choices=["extract_table", "get_coverage",
"clean_table"],
help="task to perform")
parser.add_option("-t", "--table-name", dest="table", type="string",
help="table in SQLite DB to extract")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv, add_database_options=True)
if options.task == "extract_table":
out_df = getTableFromDb(options.database_url, options.table)
elif options.task == "get_coverage":
out_df = getModelCoverage(options.database_url,
table_regex="(\S+)_transcript_counts")
elif options.task == "clean_table":
infile = argv[-1]
out_df = cleanStatsTable(infile)
out_df.to_csv(options.stdout,
sep="\t", index_label="track")
# write footer and output benchmark information.
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-t",
"--test",
dest="test",
type="string",
help="supply help")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
# write footer and output benchmark information.
E.stop()
def main(argv=None):
# Parse the options
parser = E.OptionParser(
version=
"%prog version: $Id: cgat_script_template.py 2871 2010-03-03 10:20:44Z andreas $",
usage=globals()["__doc__"])
parser.add_option(
"-p",
"--params",
"--args",
dest="params",
type="string",
help="comma separated list of addtional parameter strings")
parser.add_option("-m",
"--module",
dest="module",
type="string",
help="the full path to the module file",
default=None)
parser.add_option("-i",
"--input",
dest="input_filenames",
type="string",
action="append",
help="input filename")
parser.add_option("-o",
"--output-section",
dest="output_filenames",
type="string",
action="append",
help="output filename")
parser.add_option("-f",
"--function",
dest="function",
type="string",
help="the module function",
default=None)
parser.set_defaults(input_filenames=[], output_filenames=[], params=None)
(options, args) = E.start(parser)
# Check a module and function have been specified
if not options.module or not options.function:
raise ValueError("Both a function and Module must be specified")
# initialize defaults
P.get_parameters()
# If a full path was given, add this path to the system path
location = os.path.dirname(options.module)
if location != "":
sys.path.append(location)
# Establish the module name, accomodating cases where the
# .py extension has been included in the module name
module_name = os.path.basename(options.module)
if module_name.endswith(".py"):
module_base_name = module_name[:-3]
else:
module_base_name = module_name
# Import the specified module and map the specified fuction
E.info("importing module '%s' " % module_base_name)
E.debug("sys.path is: %s" % sys.path)
module = importlib.import_module(module_base_name)
try:
function = getattr(module, options.function)
except AttributeError as msg:
raise AttributeError(
msg.message + "unknown function, available functions are: %s" %
",".join([x for x in dir(module) if not x.startswith("_")]))
if options.input_filenames and not options.input_filenames == ["None"]:
infiles = options.input_filenames
else:
infiles = False
if options.output_filenames and not options.output_filenames == ["None"]:
outfiles = options.output_filenames
else:
outfiles = False
# Parse the parameters into an array
if options.params:
params = [param.strip() for param in options.params.split(",")]
else:
params = False
# deal with single file case
if infiles and len(infiles) == 1:
infiles = infiles[0]
if outfiles and len(outfiles) == 1:
outfiles = outfiles[0]
# Make the function call
if infiles and outfiles and params:
function(infiles, outfiles, params)
elif infiles and outfiles and not params:
function(infiles, outfiles)
elif params:
function(params)
else:
raise ValueError(
"Expecting infile+outfile+params or infile+outfile or params")
E.stop()
