def out_put(self):
TEMPLATE = '{workdir}/face_tracking/{corpus}/{show}.txt'
video = self.in_video().task
corpus = video.corpus
show = video.show
path = TEMPLATE.format(workdir=self.workdir, corpus=corpus, show=show)
return sciluigi.TargetInfo(self, path)
def out_bed(self):
basename1 = os.path.splitext(os.path.basename(
self.in_regions().path))[0]
return sciluigi.TargetInfo(
self,
os.path.join(self.outdir,
'%s.random_%.0e.bed' % (basename1, self.num_random)))
def out_rnafold(self, ):
basename = os.path.splitext(os.path.basename(self.in_fasta().path))[0]
if self.constraint:
outfile = os.path.join(self.outdir, basename + '.constraint.dG.dat' )
else:
outfile = os.path.join(self.outdir, basename + '.dG.dat' )
return sciluigi.TargetInfo(self, outfile)
def out_file(self):
return sciluigi.TargetInfo(
self,
os.path.join(
self.outdir,
os.path.splitext(os.path.basename(self.in_filename().path))[0]
+ '_muts.dat'))
def out_bed(self):
basename1 = os.path.splitext(os.path.basename(
self.in_regions().path))[0]
basename2 = os.path.splitext(os.path.basename(self.motif))[0]
return sciluigi.TargetInfo(
self,
os.path.join(self.outdir, '%s.%s.bed' % (basename1, basename2)))
def out_data(self, ):
filenames = [target().path for target in self.in_data.values()]
return sciluigi.TargetInfo(
self,
os.path.join(
self.outdir,
processing.combine_filenames_split(filenames) +
'.combined_data.gz'))
def out_table(self, ):
filenames = [target().path for target in self.in_counts.values()]
return sciluigi.TargetInfo(
self,
os.path.join(
self.outdir,
processing.combine_filenames_split(filenames) +
'.temp%d.combined_data.gz' % self.temperature))
def out_bed(self):
basenames = processing.combine_filenames(
[target().path for target in self.in_beds])
basename = '.'.join(basenames)
return sciluigi.TargetInfo(
self, os.path.join(self.outdir, basename + '.bed'))
def out_fastq2(self):
path = self._output_from_hash()
target = sl.TargetInfo(
self,
os.path.join(os.path.dirname(path),
os.path.basename(self.in_fastq2().path)))
target.target.makedirs()
return target
def out_table(self, ):
filenames = [
os.path.basename(subdict.values()[0]().path)
for windowsize, subdict in self.in_secstructure.items()
]
#filenames = [os.path.basename(target().path) for target in self.in_secstructure.values()]
filename = processing.combine_filenames_split(
filenames, avoid_elements=['dat', 'constraint'])
return sciluigi.TargetInfo(
self, os.path.join(self.outdir, filename + '.combined_data.gz'))
class Foo2Bar(sl.Task):
'''
Another dummy task
'''
replacement = luigi.Parameter()
in_foo = sl.TargetInfo(None, 'None')
def out_bar(self):
return sl.TargetInfo(
self,
self.in_foo().path + '.{r}.txt'.format(r=self.replacement))
def run(self):
self.ex('sed "s/foo/{r}/g" {inf} > {outf}'.format(
r=self.replacement,
inf=self.in_foo().path,
outf=self.out_bar().path))
def out_put(self):
INA_TEMPLATE = '{corpus_dir}/INA/LAffaireSnowden/medias_reencoded/tv/{show}.mp4'
UPC_TEMPLATE = '{corpus_dir}/3-24/media/{show}.mp4'
DW_TEMPLATE = '{corpus_dir}/DW/{show}.mp4'
TRAILER_TEMPLATE = '{corpus_dir}/{show}.mp4'
TVD_TEMPLATE = '{corpus_dir}/{corpus}/dvd/rip/video/{show}.mkv'
EASTENDERS_TEMPLATE = '{corpus_dir}/{show}.mp4'
if self.corpus == 'INA':
path = INA_TEMPLATE.format(corpus_dir=self.corpus_dir,
show=self.show)
elif self.corpus == 'UPC':
path = UPC_TEMPLATE.format(corpus_dir=self.corpus_dir,
show=self.show)
elif self.corpus == 'DW':
path = DW_TEMPLATE.format(corpus_dir=self.corpus_dir,
show=self.show)
elif self.corpus == 'TRAILER':
path = TRAILER_TEMPLATE.format(corpus_dir=self.corpus_dir,
show=self.show)
elif self.corpus == 'TheBigBangTheory':
path = TVD_TEMPLATE.format(corpus=self.corpus,
corpus_dir=self.corpus_dir,
show=self.show)
elif self.corpus == 'GameOfThrones':
path = TVD_TEMPLATE.format(corpus=self.corpus,
corpus_dir=self.corpus_dir,
show=self.show)
elif self.corpus == 'EastEnders':
path = EASTENDERS_TEMPLATE.format(corpus_dir=self.corpus_dir,
show=self.show)
else:
raise NotImplementedError('')
return sciluigi.TargetInfo(self, path)
def out_put(self):
INA_TEMPLATE = '{corpus_dir}/INA/LAffaireSnowden/medias_reencoded/tv/{show}.wav'
UPC_TEMPLATE = '{corpus_dir}/3-24/{show}.wav'
# DW_TEMPLATE = '{corpus_dir}/DW/{show}.wav'
if self.corpus == 'INA':
path = INA_TEMPLATE.format(corpus_dir=self.corpus_dir,
show=self.show)
elif self.corpus == 'UPC':
path = UPC_TEMPLATE.format(corpus_dir=self.corpus_dir,
show=self.show)
elif self.corpus == 'DW':
raise NotImplementedError('')
else:
raise NotImplementedError('')
return sciluigi.TargetInfo(self, path)
def out_trimmo(self):
outp_name = 'trimmed_seq'
adapter_full_path = self.adapters_path + self.adapter
self.default_trimmo_args = OrderedDict()
args = [
'SE', 'PE', '-basein', '-baseout', 'ILLUMINACLIP:', 'MAXINFO:',
'SLIDINGWINDOW:', 'LEADING:', 'CROP:', 'TRAILING:', 'HEADCROP:',
'MINLEN:'
]
vals = [
None, True, None, None, adapter_full_path + ':2:30:10', None, None,
30, None, 30, 15, 20
]
# "leading": head_qual, "trailing": 30, "headcrop": 15}
for arg, vals in zip_longest(args, vals):
self.default_trimmo_args[arg] = vals
# TODO move this constants to config file
# print(self.default_trimmo_args)
# print(self.tool_path)
print(self.outp_path + 'trimmo_res.txt')
return sl.TargetInfo(self, self.outp_path + 'trimmo_res.txt')
def out_report(self):
outf_path = 'data/' + self.run_id + '/testrun_dataset_liblinear_datareport.csv'
return sl.TargetInfo(
self, outf_path
) # We manually re-create the filename that this should have
def out_replatot(self):
return sl.TargetInfo(self, self.in_data().path + '.atot')
def out_rawdata(self):
return sl.TargetInfo(self, 'data/acgt.txt')
def out_multi(self):
return [
sl.TargetInfo(self, itgt.path + '.daa.txt')
for itgt in self.in_multi()
]
def out_done(self):
return sl.TargetInfo(self, self.in_lowestrmsd().path + '.mainwf_done')
def out_merged(self):
return sl.TargetInfo(self, self.in_data1().path + '.merged.txt')
def out_data1(self):
return sl.TargetInfo(self, 'data/' + self.text + '.txt')
def out_put(self):
TEMPLATE = '{workdir}/external/gregory/lists/{episode}.txt'
path = TEMPLATE.format(
workdir=self.workdir,
episode=pyannote_workflows.tasks.tvd_dataset.get_episode(self))
return sciluigi.TargetInfo(self, path)
def out_sequences(self):
return sciluigi.TargetInfo(
self,
os.path.join(self.outdir, 'library_%s' % self.lib_name + '.dat'))
def out_file(self):
return sciluigi.TargetInfo(self, self.filename)
def out_put(self):
TEMPLATE = '{workdir}/_models/dlib.face.landmarks.dat'
path = TEMPLATE.format(workdir=self.workdir)
return sciluigi.TargetInfo(self, path)
def out_fastq(self):
return [
sl.TargetInfo(self, fastqc_res)
for fastqc_res in glob.glob(self.outp_path + '*')
]
def out_put(self):
TEMPLATE = '{workdir}/_models/openface.nn4.small2.v1.t7'
path = TEMPLATE.format(workdir=self.workdir)
return sciluigi.TargetInfo(self, path)
def out_trimmo(self):
return [
sl.TargetInfo(self, trimmo_res)
for trimmo_res in glob.glob(self.outp_path + '*')
]
def out_data(self):
return sl.TargetInfo(self, self.outp_path)
def out_multi(self):
return [
sl.TargetInfo(self, '/tmp/out_%s_%d.txt' % (self.an_id, i))
for i in xrange(10)
]
