def make_fraction_plot(hright, hwrong, plotdir, plotname, xlabel, ylabel, xbounds, only_csv=False, write_csv=False):
if 'fraction_uncertainty' not in sys.modules:
import fraction_uncertainty
# NOTE should really merge this with draw_no_root()
xvals = hright.get_bin_centers() #ignore_overflows=True)
right = hright.bin_contents
wrong = hwrong.bin_contents
yvals = [float(r) / (r + w) if r + w > 0. else 0. for r, w in zip(right, wrong)]
# remove values corresponding to bins with no entries
while yvals.count(0.) > 0:
iv = yvals.index(0.)
xvals.pop(iv)
right.pop(iv)
wrong.pop(iv)
yvals.pop(iv)
tmphilos = [sys.modules['fraction_uncertainty'].err(r, r + w) for r, w in zip(right, wrong)]
yerrs = [err[1] - err[0] for err in tmphilos]
# print '%s' % region
# for iv in range(len(xvals)):
# print ' %5.2f %5.0f / %5.0f = %5.2f +/- %.3f' % (xvals[iv], right[iv], right[iv] + wrong[iv], yvals[iv], yerrs[iv])
if write_csv:
hist_for_csv = Hist(hright.n_bins, hright.xmin, hright.xmax)
bincenters = hright.get_bin_centers()
for ibin in range(hright.n_bins):
bcenter = bincenters[ibin]
if bcenter in xvals: # if we didn't remove it
iy = xvals.index(bcenter)
hist_for_csv.set_ibin(ibin, yvals[iy], error=yerrs[iy])
hist_for_csv.write(plotdir + '/' + plotname + '.csv')
if not only_csv:
fig, ax = mpl_init()
ax.errorbar(xvals, yvals, yerr=yerrs, markersize=10, linewidth=1, marker='.')
if xlabel == 'support':
ax.plot((0, 1), (0, 1), color='black', linestyle='--', linewidth=3) # line with slope 1 and intercept 0
mpl_finish(ax, plotdir, plotname, xlabel=xlabel, ylabel=ylabel, title=plotconfig.plot_titles.get(plotname, plotname), xbounds=xbounds, ybounds=(-0.1, 1.1))
plt.close()
def make_fraction_plot(hright, hwrong, plotdir, plotname, xlabel, ylabel, xbounds, only_csv=False, write_csv=False):
if 'fraction_uncertainty' not in sys.modules:
import fraction_uncertainty
# NOTE should really merge this with draw_no_root()
xvals = hright.get_bin_centers() #ignore_overflows=True)
right = hright.bin_contents
wrong = hwrong.bin_contents
yvals = [float(r) / (r + w) if r + w > 0. else 0. for r, w in zip(right, wrong)]
# remove values corresponding to bins with no entries
while yvals.count(0.) > 0:
iv = yvals.index(0.)
xvals.pop(iv)
right.pop(iv)
wrong.pop(iv)
yvals.pop(iv)
tmphilos = [sys.modules['fraction_uncertainty'].err(r, r + w) for r, w in zip(right, wrong)]
yerrs = [err[1] - err[0] for err in tmphilos]
# print '%s' % region
# for iv in range(len(xvals)):
# print ' %5.2f %5.0f / %5.0f = %5.2f +/- %.3f' % (xvals[iv], right[iv], right[iv] + wrong[iv], yvals[iv], yerrs[iv])
if write_csv:
hist_for_csv = Hist(hright.n_bins, hright.xmin, hright.xmax)
bincenters = hright.get_bin_centers()
for ibin in range(hright.n_bins):
bcenter = bincenters[ibin]
if bcenter in xvals: # if we didn't remove it
iy = xvals.index(bcenter)
hist_for_csv.set_ibin(ibin, yvals[iy], error=yerrs[iy])
hist_for_csv.write(plotdir + '/' + plotname + '.csv')
if not only_csv:
fig, ax = mpl_init()
ax.errorbar(xvals, yvals, yerr=yerrs, markersize=10, linewidth=1, marker='.')
if xlabel == 'support':
ax.plot((0, 1), (0, 1), color='black', linestyle='--', linewidth=3) # line with slope 1 and intercept 0
mpl_finish(ax, plotdir, plotname, xlabel=xlabel, ylabel=ylabel, title=plotconfig.plot_titles.get(plotname, plotname), xbounds=xbounds, ybounds=(-0.1, 1.1))
plt.close()
import matplotlib
from matplotlib import pyplot as plt
fig, ax = plotting.mpl_init()
xvals, yvals = zip(*[(v['imax'], v['max_abs_diff']) for v in chfo.values()])
plt.scatter(xvals, yvals, alpha=0.4)
print 'writing to %s' % args.plotdir
plotting.mpl_finish(ax,
args.plotdir,
'hexbin',
title=args.title,
xlabel='break point',
ylabel='abs mfreq diff')
plotting.draw_no_root(hmaxval,
plotdir=args.plotdir,
plotname='mfreq-diff',
shift_overflows=True,
xtitle='abs mfreq diff',
ytitle='seqs')
hmaxval.write('%s/%s.csv' % (args.plotdir, 'mfreq-diff'))
plotting.draw_no_root(himax,
plotdir=args.plotdir,
plotname='imax',
shift_overflows=True,
xtitle='break point',
ytitle='seqs')
himax.write('%s/%s.csv' % (args.plotdir, 'imax'))
def gk(uids):
return ':'.join(uids)
glfo = glutils.read_glfo(args.infile.replace('.csv', '-glfo'), locus='igh')
annotations = {}
with open(args.infile) as csvfile:
reader = csv.DictReader(csvfile)
for line in reader:
if line['v_gene'] == '': # failed (i.e. couldn't find an annotation)
continue
utils.process_input_line(line) # converts strings in the csv file to floats/ints/dicts/etc.
utils.add_implicit_info(glfo, line) # add stuff to <line> that's useful, isn't written to the csv since it's redundant
annotations[gk(line['unique_ids'])] = line
chfo = {uid : utils.get_chimera_max_abs_diff(annotations[uid], iseq=0) for uid in annotations}
biggest_adiffs = sorted(chfo, key=lambda q: chfo[q][1], reverse=True)
for uid in biggest_adiffs[:10]:
print chfo[uid]
utils.print_reco_event(annotations[uid])
htmp = Hist(45, 0., 0.65)
for uid in annotations:
htmp.fill(chfo[uid][1])
utils.prep_dir(args.plotdir, wildlings=['*.svg', '*.csv'])
plotname = 'mfreq-diff'
plotting.draw_no_root(htmp, plotdir=args.plotdir, plotname=plotname, shift_overflows=True, xtitle='abs mfreq diff', ytitle='seqs')
plotting.draw_no_root(htmp, plotdir=args.plotdir, plotname=plotname + '-log', shift_overflows=True, log='y', xtitle='abs mfreq diff', ytitle='seqs')
print 'writing to %s' % args.plotdir
htmp.write('%s/%s.csv' % (args.plotdir, plotname))
