def main():
savepath = args.savepath
fastx = args.fastx
tag = args.tag
if savepath is None:
savepath = os.getcwd()
else:
savepath = misc.mkdir(savepath)
if tag is None:
tag = misc.get_fname(fastx)
if misc._getextension(fastx) == 'fastq':
fq = True
else:
fq = False
rawdata = cstats.GC_per_read(cstats.readfast(fastx), fq=fq)
# print os.path.join(savepath, '{}_summary.stats'.format(tag))
if args.raw:
rawdata.to_csv(os.path.join(savepath, '{}_raw.stats'.format(tag)))
summary = cstats.get_stats(df=rawdata)
summary.to_csv(os.path.join(savepath, '{}_summary.stats'.format(tag)))
# print summary.round(2).to_string()
if args.report:
from wub.vis import report
Plotter = report.Report(os.path.join(savepath, '{}.pdf'.format(tag)))
rawdata = rawdata.sort_values('Seqlen', ascending=True)
rawdata['cumsum'] = rawdata["Seqlen"].cumsum()
rawdata['norm'] = 100.0 * rawdata['cumsum'] / rawdata['cumsum'].max()
Plotter.plot_line(
data=rawdata,
x='Seqlen',
y='norm',
title='Normalized cumulative plot',
xlab='length (bp)',
ylab="normalized (%)",
)
# df1.sort_values('Seqlen', ascending=False)
# df1["cumsum1"] = df1['Seqlen'].cumsum()
# Plotter.plot_line(data=rawdata, x='Cumsum1', y=df1.reset_index().index, title='Ordered cumulative sum plot', xlab="contigs ordered largest to smallest", ylab='cumulative sum')
Plotter.plot_scatter(data=rawdata,
x='GC content (%)',
y='Seqlen',
title='GC content vs length plot',
xlab="GC content (%)",
ylab="length (bp)",
alpha=0.5,
ylim=0,
xlim=0)
if 'mean_q' in rawdata:
Plotter.plot_scatter(data=rawdata,
x='mean_q',
y='Seqlen',
title='Mean Q score vs length',
xlab='Mean Q',
ylab='length',
alpha=0.5,
xlim=rawdata['mean_q'].min() - 0.5,
ylim=rawdata['Seqlen'].min() - 0.5)
Plotter.close()
invert_yaxis=True,
title="",
xlab="From context",
ylab="To base")
if __name__ == '__main__':
args = parser.parse_args()
verbose = not args.Q
tag = args.t
if tag is None:
tag = os.path.basename(args.bam)
context_sizes = args.n.split(",")
context_sizes = (int(context_sizes[0]), int(context_sizes[1]))
plotter = report.Report(args.r)
references = seq_util.read_seq_records_dict(args.f)
err_read_stats = bam_stats.error_and_read_stats(
args.bam,
references,
region=args.c,
context_sizes=context_sizes,
min_aqual=args.q,
verbose=verbose)
read_stats = err_read_stats['read_stats']
error_stats = err_read_stats['events']
base_stats = err_read_stats['base_stats']
indel_stats = err_read_stats['indel_dists']
