def plot(self, plotdir, subset_by_gene=False, cyst_positions=None, tryp_positions=None, only_csv=False):
print ' plotting parameters'
# start = time.time()
utils.prep_dir(plotdir + '/plots') #, multilings=('*.csv', '*.svg'))
for column in self.counts:
if column == 'all':
continue
values, gene_values = {}, {}
if len(self.counts[column]) == 0:
print 'ERROR no counts in %s' % column
assert False
for index, count in self.counts[column].iteritems():
gene = None
if subset_by_gene and ('_del' in column or column == 'vd_insertion' or column == 'dj_insertion'): # option to subset deletion and (real) insertion plots by gene
if '_del' in column:
region = column[0]
else:
region = column[1]
assert region in utils.regions
assert 'IGH' + region.upper() in index[1] # NOTE this is hackey, but it works find now and will fail obviously
gene = index[1] # if I ever change the correlations to be incompatible. so screw it
if gene not in gene_values:
gene_values[gene] = {}
column_val = index[0]
if gene is not None:
if column_val not in gene_values[gene]:
gene_values[gene][column_val] = 0.0
gene_values[gene][column_val] += count
if column_val not in values:
values[column_val] = 0.0
values[column_val] += count
try: # figure out whether this is an integer or string (only used outside this loop when we make the plots)
int(column_val)
var_type = 'int'
except:
var_type = 'string'
if subset_by_gene and ('_del' in column or column == 'vd_insertion' or column == 'dj_insertion'): # option to subset deletion and (real) insertion plots by gene
thisplotdir = plotdir + '/' + column
utils.prep_dir(thisplotdir + '/plots', multilings=['*.csv', '*.svg'])
for gene in gene_values:
plotname = utils.sanitize_name(gene) + '-' + column
hist = plotting.make_hist_from_dict_of_counts(gene_values[gene], var_type, plotname, sort=True)
plotting.draw_no_root(hist, plotname=plotname, plotdir=thisplotdir, errors=True, write_csv=True, only_csv=only_csv)
if not only_csv:
check_call(['./bin/makeHtml', thisplotdir, '3', 'null', 'svg'])
check_call(['./bin/permissify-www', thisplotdir]) # NOTE this should really permissify starting a few directories higher up
plotname = column
hist = plotting.make_hist_from_dict_of_counts(values, var_type, plotname, sort=True)
plotting.draw_no_root(hist, plotname=plotname, plotdir=plotdir, errors=True, write_csv=True, only_csv=only_csv)
self.mutefreqer.plot(plotdir, cyst_positions, tryp_positions, only_csv=only_csv) #, mean_freq_outfname=base_outdir + '/REGION-mean-mute-freqs.csv') # REGION is replace by each region in the three output files
if not only_csv:
check_call(['./bin/makeHtml', plotdir, '3', 'null', 'svg'])
check_call(['./bin/permissify-www', plotdir]) # NOTE this should really permissify starting a few directories higher up
def plot_each_within_vs_between_hist(self, distances, plotdir, plotname, plottitle):
xmax = 1.2 * max([d for dtype in distances for d in distances[dtype]])
hists = {}
for dtype in distances:
hists[dtype] = Hist(self.n_bins, 0., xmax, title=dtype)
for mut_freq in distances[dtype]:
hists[dtype].fill(mut_freq)
plotting.draw_no_root(hists['within'], plotname=plotname, plotdir=plotdir, more_hists=[hists['between']], plottitle=plottitle, xtitle='hamming distance', errors=True)
def plot(self, plotdir, only_csv=False):
utils.prep_dir(plotdir, wildling=None, multilings=['*.csv', '*.svg', '*.root'])
for column in self.values:
if self.only_correct_gene_fractions and column not in bool_columns:
continue
if column in bool_columns:
right = self.values[column]['right']
wrong = self.values[column]['wrong']
errs = fraction_uncertainty.err(right, right+wrong)
print ' %s\n correct up to allele: %4d / %-4d = %4.4f (-%.3f, +%.3f)' % (column, right, right+wrong, float(right) / (right + wrong), errs[0], errs[1])
hist = plotting.make_bool_hist(right, wrong, self.name + '-' + column)
plotting.draw_no_root(hist, plotname=column, plotdir=plotdir, write_csv=True, stats='0-bin', only_csv=only_csv)
else:
# TODO this is dumb... I should make the integer-valued ones histograms as well
hist = plotting.make_hist_from_dict_of_counts(self.values[column], 'int', self.name + '-' + column, normalize=True)
log = ''
if column.find('hamming_to_true_naive') >= 0: # TODO why doesn't this just use the config dicts in plotheaders or wherever?
hist.title = 'hamming distance'
else:
hist.title = 'inferred - true'
plotting.draw_no_root(hist, plotname=column, plotdir=plotdir, write_csv=True, log=log, only_csv=only_csv)
for column in self.hists:
plotting.draw_no_root(self.hists[column], plotname=column, plotdir=plotdir, write_csv=True, log=log, only_csv=only_csv)
if not only_csv:
plotting.make_html(plotdir)
def plot(self, plotdir, only_csv=False, only_overall=False):
if not self.finalized:
self.finalize()
overall_plotdir = plotdir + '/overall'
for gene in self.freqs:
if only_overall:
continue
freqs = self.freqs[gene]
if len(freqs) == 0:
if gene not in glutils.dummy_d_genes.values():
print ' %s no mutefreqer obs for %s' % (utils.color('red', 'warning'), utils.color_gene(gene))
continue
sorted_positions = sorted(freqs.keys())
genehist = Hist(sorted_positions[-1] - sorted_positions[0] + 1, sorted_positions[0] - 0.5, sorted_positions[-1] + 0.5, xtitle='position', ytitle='mut freq', title=gene)
for position in sorted_positions:
hi_diff = abs(freqs[position]['freq'] - freqs[position]['freq_hi_err'])
lo_diff = abs(freqs[position]['freq'] - freqs[position]['freq_lo_err'])
err = 0.5*(hi_diff + lo_diff)
genehist.set_ibin(genehist.find_bin(position), freqs[position]['freq'], error=err)
xline = None
figsize = [7, 4]
if utils.get_region(gene) in utils.conserved_codons[self.glfo['chain']]:
codon = utils.conserved_codons[self.glfo['chain']][utils.get_region(gene)]
xline = self.glfo[codon + '-positions'][gene]
if utils.get_region(gene) == 'v':
figsize[0] *= 3.5
elif utils.get_region(gene) == 'j':
figsize[0] *= 2
plotting.draw_no_root(self.per_gene_mean_rates[gene], plotdir=plotdir + '/per-gene/' + utils.get_region(gene), plotname=utils.sanitize_name(gene), errors=True, write_csv=True, only_csv=only_csv, shift_overflows=True)
# per-position plots:
plotting.draw_no_root(genehist, plotdir=plotdir + '/per-gene-per-position/' + utils.get_region(gene), plotname=utils.sanitize_name(gene), errors=True, write_csv=True, xline=xline, figsize=figsize, only_csv=only_csv, shift_overflows=True)
# # per-position, per-base plots:
# paramutils.make_mutefreq_plot(plotdir + '/' + utils.get_region(gene) + '-per-base', utils.sanitize_name(gene), plotting_info) # needs translation to mpl UPDATE fcn is fixed, but I can't be bothered uncommenting this at the moment
# make mean mute freq hists
for rstr in ['all', 'cdr3'] + utils.regions:
if rstr == 'all':
bounds = (0.0, 0.4)
else:
bounds = (0.0, 0.6 if rstr == 'd' else 0.4)
plotting.draw_no_root(self.mean_rates[rstr], plotname=rstr+'_mean-freq', plotdir=overall_plotdir, stats='mean', bounds=bounds, write_csv=True, only_csv=only_csv, shift_overflows=True)
plotting.draw_no_root(self.mean_n_muted[rstr], plotname=rstr+'_mean-n-muted', plotdir=overall_plotdir, stats='mean', write_csv=True, only_csv=only_csv, shift_overflows=True)
if not only_csv: # write html file and fix permissiions
for substr in self.subplotdirs:
plotting.make_html(plotdir + '/' + substr)
def plot(self, plotdir, only_csv=False):
print ' plotting performance',
import fraction_uncertainty
import plotting
start = time.time()
for substr in self.subplotdirs:
utils.prep_dir(plotdir + '/' + substr, wildlings=('*.csv', '*.svg'))
for column in self.values:
if column in plotconfig.gene_usage_columns:
right = self.values[column]['right']
wrong = self.values[column]['wrong']
lo, hi = fraction_uncertainty.err(right, right + wrong)
hist = plotting.make_bool_hist(right, wrong, self.name + '-' + column)
plotting.draw_no_root(hist, plotname=column, plotdir=plotdir + '/gene-call', write_csv=True, stats='0-bin', only_csv=only_csv)
else:
hist = plotting.make_hist_from_dict_of_counts(self.values[column], 'int', self.name + '-' + column, normalize=False)
if 'hamming_to_true_naive' in column:
xtitle = 'hamming distance'
tmpplotdir = plotdir + '/mutation'
else:
xtitle = 'inferred - true'
if 'muted' in column:
tmpplotdir = plotdir + '/mutation'
else:
tmpplotdir = plotdir + '/boundaries'
plotting.draw_no_root(hist, plotname=column, plotdir=tmpplotdir, write_csv=True, only_csv=only_csv, xtitle=xtitle, shift_overflows=True)
for column in self.hists:
if '_vs_mute_freq' in column or '_vs_per_gene_support' in column: # only really care about the fraction, which we plot below
continue
plotting.draw_no_root(self.hists[column], plotname=column, plotdir=plotdir + '/mutation', write_csv=True, only_csv=only_csv, ytitle='counts', xtitle='inferred - true', shift_overflows=True)
# fraction correct vs mute freq
for region in utils.regions:
hright = self.hists[region + '_gene_right_vs_mute_freq']
hwrong = self.hists[region + '_gene_wrong_vs_mute_freq']
if hright.integral(include_overflows=True) == 0:
continue
plotting.make_fraction_plot(hright, hwrong, plotdir + '/gene-call', region + '_fraction_correct_vs_mute_freq', xlabel='mut freq', ylabel='fraction correct up to allele', xbounds=(0., 0.5), only_csv=only_csv, write_csv=True)
# per-gene support stuff
for region in utils.regions:
if self.hists[region + '_allele_right_vs_per_gene_support'].integral(include_overflows=True) == 0:
continue
hright = self.hists[region + '_allele_right_vs_per_gene_support']
hwrong = self.hists[region + '_allele_wrong_vs_per_gene_support']
plotting.make_fraction_plot(hright, hwrong, plotdir + '/gene-call', region + '_allele_fraction_correct_vs_per_gene_support', xlabel='support', ylabel='fraction with correct allele', xbounds=(-0.1, 1.1), only_csv=only_csv, write_csv=True)
if not only_csv: # write html file and fix permissiions
for substr in self.subplotdirs:
plotting.make_html(plotdir + '/' + substr, n_columns=4)
print '(%.1f sec)' % (time.time()-start)
def plot(self, plotdir, only_csv=False):
print ' plotting performance',
start = time.time()
for substr in self.subplotdirs:
utils.prep_dir(plotdir + '/' + substr, wildlings=('*.csv', '*.svg'))
for column in self.values:
if column in bool_columns:
right = self.values[column]['right']
wrong = self.values[column]['wrong']
lo, hi, _ = fraction_uncertainty.err(right, right + wrong)
hist = plotting.make_bool_hist(right, wrong, self.name + '-' + column)
plotting.draw_no_root(hist, plotname=column, plotdir=plotdir + '/gene-call', write_csv=True, stats='0-bin', only_csv=only_csv)
else:
hist = plotting.make_hist_from_dict_of_counts(self.values[column], 'int', self.name + '-' + column, normalize=False)
if 'hamming_to_true_naive' in column:
xtitle = 'hamming distance'
tmpplotdir = plotdir + '/mutation'
else:
xtitle = 'inferred - true'
if 'muted' in column:
tmpplotdir = plotdir + '/mutation'
else:
tmpplotdir = plotdir + '/boundaries'
plotting.draw_no_root(hist, plotname=column, plotdir=tmpplotdir, write_csv=True, only_csv=only_csv, xtitle=xtitle, shift_overflows=True)
for column in self.hists:
if '_vs_mute_freq' in column or '_vs_per_gene_support' in column: # only really care about the fraction, which we plot below
continue
plotting.draw_no_root(self.hists[column], plotname=column, plotdir=plotdir + '/mutation', write_csv=True, only_csv=only_csv, ytitle='counts', xtitle='inferred - true', shift_overflows=True)
# fraction correct vs mute freq
for region in utils.regions:
hright = self.hists[region + '_gene_right_vs_mute_freq']
hwrong = self.hists[region + '_gene_wrong_vs_mute_freq']
if hright.integral(include_overflows=True) == 0:
continue
plotting.make_fraction_plot(hright, hwrong, plotdir + '/gene-call', region + '_fraction_correct_vs_mute_freq', xlabel='mut freq', ylabel='fraction correct up to allele', xbounds=(0., 0.5), only_csv=only_csv, write_csv=True)
# per-gene support stuff
for region in utils.regions:
if self.hists[region + '_allele_right_vs_per_gene_support'].integral(include_overflows=True) == 0:
continue
hright = self.hists[region + '_allele_right_vs_per_gene_support']
hwrong = self.hists[region + '_allele_wrong_vs_per_gene_support']
plotting.make_fraction_plot(hright, hwrong, plotdir + '/gene-call', region + '_allele_fraction_correct_vs_per_gene_support', xlabel='support', ylabel='fraction with correct allele', xbounds=(-0.1, 1.1), only_csv=only_csv, write_csv=True)
if not only_csv: # write html file and fix permissiions
for substr in self.subplotdirs:
plotting.make_html(plotdir + '/' + substr, n_columns=4)
print '(%.1f sec)' % (time.time()-start)
def plot(self, base_plotdir, cyst_positions=None, tryp_positions=None, only_csv=False):
if not self.finalized:
self.finalize()
plotdir = base_plotdir + '/mute-freqs'
overall_plotdir = plotdir + '/overall'
utils.prep_dir(overall_plotdir, multilings=('*.csv', '*.svg'))
for region in utils.regions:
utils.prep_dir(plotdir + '/' + region, multilings=('*.csv', '*.svg'))
# utils.prep_dir(plotdir + '/' + region + '-per-base/plots', multilings=('*.csv', '*.png'))
if self.tigger:
utils.prep_dir(plotdir + '/tigger', multilings=('*.csv', '*.svg'))
for gene in self.freqs:
freqs = self.freqs[gene]
sorted_positions = sorted(freqs.keys())
genehist = Hist(sorted_positions[-1] - sorted_positions[0] + 1, sorted_positions[0] - 0.5, sorted_positions[-1] + 0.5, xtitle='fixme', ytitle='fixme') #, title=utils.sanitize_name(gene))
for position in sorted_positions:
hi_diff = abs(freqs[position]['freq'] - freqs[position]['freq_hi_err'])
lo_diff = abs(freqs[position]['freq'] - freqs[position]['freq_lo_err'])
err = 0.5*(hi_diff + lo_diff)
genehist.set_ibin(genehist.find_bin(position), freqs[position]['freq'], error=err)
xline = None
figsize = [3, 3]
if utils.get_region(gene) == 'v' and cyst_positions is not None:
xline = cyst_positions[gene]
figsize[0] *= 3.5
elif utils.get_region(gene) == 'j' and tryp_positions is not None:
xline = tryp_positions[gene]
figsize[0] *= 2
plotting.draw_no_root(genehist, plotdir=plotdir + '/' + utils.get_region(gene), plotname=utils.sanitize_name(gene), errors=True, write_csv=True, xline=xline, figsize=figsize, only_csv=only_csv)
# paramutils.make_mutefreq_plot(plotdir + '/' + utils.get_region(gene) + '-per-base', utils.sanitize_name(gene), plotting_info) # needs translation to mpl
# make mean mute freq hists
plotting.draw_no_root(self.mean_rates['all'], plotname='all-mean-freq', plotdir=overall_plotdir, stats='mean', bounds=(0.0, 0.4), write_csv=True, only_csv=only_csv)
for region in utils.regions:
plotting.draw_no_root(self.mean_rates[region], plotname=region+'-mean-freq', plotdir=overall_plotdir, stats='mean', bounds=(0.0, 0.4), write_csv=True, only_csv=only_csv)
if self.tigger:
self.tigger_plot(only_csv)
if not only_csv: # write html file and fix permissiions
plotting.make_html(overall_plotdir)
for region in utils.regions:
plotting.make_html(plotdir + '/' + region, n_columns=1)
def plot(self, base_plotdir, cyst_positions=None, tryp_positions=None, only_csv=False):
if not self.finalized:
self.finalize()
plotdir = base_plotdir + '/mute-freqs'
utils.prep_dir(plotdir + '/plots', multilings=('*.csv', '*.svg'))
for region in utils.regions:
utils.prep_dir(plotdir + '/' + region + '/plots', multilings=('*.csv', '*.svg'))
# utils.prep_dir(plotdir + '/' + region + '-per-base/plots', multilings=('*.csv', '*.png'))
for gene in self.counts:
counts, plotting_info = self.counts[gene], self.plotting_info[gene]
sorted_positions = sorted(counts)
genehist = Hist(sorted_positions[-1] - sorted_positions[0] + 1, sorted_positions[0] - 0.5, sorted_positions[-1] + 0.5, xtitle='fixme', ytitle='fixme') #, title=utils.sanitize_name(gene))
for position in sorted_positions:
hi_diff = abs(counts[position]['freq'] - counts[position]['freq_hi_err'])
lo_diff = abs(counts[position]['freq'] - counts[position]['freq_lo_err'])
err = 0.5*(hi_diff + lo_diff)
genehist.set_ibin(genehist.find_bin(position), counts[position]['freq'], error=err)
xline = None
figsize = [3, 3]
if utils.get_region(gene) == 'v' and cyst_positions is not None:
xline = cyst_positions[gene]['cysteine-position']
figsize[0] *= 3.5
elif utils.get_region(gene) == 'j' and tryp_positions is not None:
xline = int(tryp_positions[gene])
figsize[0] *= 2
plotting.draw_no_root(genehist, plotdir=plotdir + '/' + utils.get_region(gene), plotname=utils.sanitize_name(gene), errors=True, write_csv=True, xline=xline, figsize=figsize, only_csv=only_csv)
# paramutils.make_mutefreq_plot(plotdir + '/' + utils.get_region(gene) + '-per-base', utils.sanitize_name(gene), plotting_info) # needs translation to mpl
# make mean mute freq hists
plotting.draw_no_root(self.mean_rates['all'], plotname='all-mean-freq', plotdir=plotdir, stats='mean', bounds=(0.0, 0.4), write_csv=True, only_csv=only_csv)
for region in utils.regions:
plotting.draw_no_root(self.mean_rates[region], plotname=region+'-mean-freq', plotdir=plotdir, stats='mean', bounds=(0.0, 0.4), write_csv=True, only_csv=only_csv)
if not only_csv: # write html file and fix permissiions
check_call(['./bin/makeHtml', plotdir, '3', 'null', 'svg'])
for region in utils.regions:
check_call(['./bin/makeHtml', plotdir + '/' + region, '1', 'null', 'svg'])
# check_call(['./bin/makeHtml', plotdir + '/' + region + '-per-base', '1', 'null', 'png'])
check_call(['./bin/permissify-www', plotdir]) # NOTE this should really permissify starting a few directories higher up
def plot(self, plotdir, subset_by_gene=False, cyst_positions=None, tryp_positions=None, only_csv=False):
print ' plotting parameters',
sys.stdout.flush()
start = time.time()
self.clean_plots(plotdir, subset_by_gene)
self.mfreqer.plot(plotdir + '/mute-freqs', cyst_positions, tryp_positions, only_csv=only_csv) #, mean_freq_outfname=base_outdir + '/REGION-mean-mute-freqs.csv') # REGION is replace by each region in the three output files
overall_plotdir = plotdir + '/overall'
for column in self.counts:
if column == 'all':
continue
values, gene_values = {}, {}
if len(self.counts[column]) == 0:
raise Exception('no counts in %s' % column)
for index, count in self.counts[column].iteritems():
gene = None
if subset_by_gene and ('_del' in column or column == 'vd_insertion' or column == 'dj_insertion'): # option to subset deletion and (real) insertion plots by gene
if '_del' in column:
region = column[0]
else:
region = column[1]
assert region in utils.regions
assert 'IGH' + region.upper() in index[1] # NOTE this is hackey, but it works find now and will fail obviously
gene = index[1] # if I ever change the correlations to be incompatible. so screw it
if gene not in gene_values:
gene_values[gene] = {}
column_val = index[0]
if gene is not None:
if column_val not in gene_values[gene]:
gene_values[gene][column_val] = 0.0
gene_values[gene][column_val] += count
if column_val not in values:
values[column_val] = 0.0
values[column_val] += count
try: # figure out whether this is an integer or string (only used outside this loop when we make the plots)
int(column_val)
var_type = 'int'
except:
var_type = 'string'
if subset_by_gene and ('_del' in column or column == 'vd_insertion' or column == 'dj_insertion'): # option to subset deletion and (real) insertion plots by gene
thisplotdir = plotdir + '/' + column
for gene in gene_values:
plotname = utils.sanitize_name(gene) + '-' + column
hist = plotting.make_hist_from_dict_of_counts(gene_values[gene], var_type, plotname, sort=True)
plotting.draw_no_root(hist, plotname=plotname, plotdir=thisplotdir, errors=True, write_csv=True, only_csv=only_csv)
if not only_csv:
plotting.make_html(thisplotdir)
plotname = column
hist = plotting.make_hist_from_dict_of_counts(values, var_type, plotname, sort=True)
plotting.draw_no_root(hist, plotname=plotname, plotdir=overall_plotdir, errors=True, write_csv=True, only_csv=only_csv)
if not only_csv:
plotting.make_html(overall_plotdir)
print '(%.1f sec)' % (time.time()-start)
def get_gls_gen_annotation_performance_plots(args, region, baseoutdir):
assert region == 'v' # needs to be implemented
import plotting
import plotconfig
methcolors = { # NOTE started from scolors in bin/plot-gl-set-trees.py htmlcolorcods.com, and slide each one a little rightward
'tigger-default' : '#dd4d39',
'igdiscover' : '#55ab7a', #60ac84',
'partis' : '#6b83ca', #758bcd',
'full' : '#858585',
}
lstyledict = {} # 'tigger-default' : '--'}
lwdict = {'full' : 9, 'igdiscover' : 8, 'partis' : 5, 'tigger-default' : 2} # methods are sorted below, so it's always [full, igdiscover, partis, tigger]
linewidths = [lwdict[m] for m in args.methods]
colors = [methcolors[meth] for meth in args.methods]
linestyles = [lstyledict.get(m, '-') for m in args.methods]
alphas = [0.8 if m in ['full', 'igdiscover'] else 1 for m in args.methods]
varname = args.action
varval = 'simu'
plotnames = ['v_hamming_to_true_naive', 'v_muted_bases']
xtitles = ['V distance to true naive', 'inferred - true']
meanvals = {pn : {m : [] for m in args.methods} for pn in plotnames}
print ' annotations: %s' % get_outdir(args, baseoutdir, varname, varval, n_events=args.gls_gen_events)
all_hists = {pn : [] for pn in plotnames}
for iproc in range(args.iteststart, args.n_tests):
outdir = get_outdir(args, baseoutdir, varname, varval, n_events=args.gls_gen_events) + '/' + str(iproc) # duplicates code in bin/test-germline-inference.py
plotdir = outdir + '/annotation-performance-plots'
print ' %s' % plotdir
if not args.only_print:
utils.prep_dir(plotdir, wildlings=['*.png', '*.svg', '*.csv'])
# shenanigans for the six (three easy and thre hard) of 'em that go in the paper pdf
make_legend = (iproc > 2) or (iproc == 0) # and args.gls_gen_difficulty == 'easy')
make_xtitle = (iproc > 2) or (iproc == 2)
make_ytitle = (iproc > 2) or (args.gls_gen_difficulty == 'easy')
for plotname in plotnames:
hfnames = {meth : get_gls_fname(region, outdir, meth, args.locus, annotation_performance_plots=True) for meth in args.methods}
for hfn in hfnames.values():
if not os.path.exists(hfn):
raise Exception('%s d.n.e.: need to first run non-plotting (without --plot) --annotation-performance-plots (which involves re-running partis, I think the difference being partis is now running with --plot-annotation-performance' % hfn)
hists = {meth : Hist(fname=hfnames[meth] + '/' + plotname + '.csv', title=methstr(meth) if make_legend else None) for meth in args.methods}
for meth in args.methods:
if hists[meth].overflow_contents() != 0.0:
print ' %s %s non-zero under/overflow %f' % (utils.color('red', 'error'), methstr(meth), hists[meth].overflow_contents())
meanvals[plotname][meth].append(hists[meth].get_mean())
if args.only_print:
continue
plotting.draw_no_root(hists[args.methods[0]], log='y', plotdir=plotdir, plotname=plotname, more_hists=[hists[m] for m in args.methods[1:]], colors=colors, ytitle='sequences' if make_ytitle else None,
xtitle=xtitles[plotnames.index(plotname)] if make_xtitle else '',
plottitle=gls_sim_str(args.gls_gen_difficulty, iproc),
linewidths=linewidths, linestyles=linestyles, alphas=alphas, remove_empty_bins=True, square_bins=True)
all_hists[plotname].append(hists)
print ' total plots'
plotdir = get_outdir(args, baseoutdir, varname, varval, n_events=args.gls_gen_events) + '/annotation-performance-plots'
print ' %s' % plotdir
if not args.only_print:
utils.prep_dir(plotdir, wildlings=['*.png', '*.svg', '*.csv'])
for plotname in plotnames:
total_hists = {}
for meth in args.methods:
xmin = min([hdict[meth].xmin for hdict in all_hists[plotname]])
xmax = max([hdict[meth].xmax for hdict in all_hists[plotname]])
total_hists[meth] = Hist(xmax - xmin, xmin, xmax, title=all_hists[plotname][0][meth].title)
for hdict in all_hists[plotname]:
assert hdict[meth].integral(include_overflows=True) > 100 # make sure it isn't normalized (this is a shitty way to do this)
bin_centers = hdict[meth].get_bin_centers()
for ibin in range(len(hdict[meth].low_edges)):
xval = bin_centers[ibin]
for _ in range(int(hdict[meth].bin_contents[ibin])):
total_hists[meth].fill(xval)
plotting.draw_no_root(total_hists[args.methods[0]], log='y', plotdir=plotdir, plotname='total-' + plotname, more_hists=[total_hists[m] for m in args.methods[1:]], colors=colors, ytitle='sequences' if make_ytitle else None,
xtitle=xtitles[plotnames.index(plotname)],
plottitle=gls_sim_str(args.gls_gen_difficulty, iproc=''),
linewidths=linewidths, linestyles=linestyles, alphas=alphas, remove_empty_bins=True, square_bins=True)
for plotname in plotnames:
if 'muted_bases' in plotname: # mean value isn't meaningful
continue
print plotname
for meth in args.methods:
mean = float(sum(meanvals[plotname][meth])) / len(meanvals[plotname][meth])
err = numpy.std(meanvals[plotname][meth], ddof=1) / math.sqrt(len(meanvals[plotname][meth]))
print ' %15s %6.3f / %d = %6.2f +/- %6.2f' % (methstr(meth), sum(meanvals[plotname][meth]), len(meanvals[plotname][meth]), mean, err)
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))
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 plot(self, plotdir, only_csv=False, only_overall=False):
import plotting
if not self.finalized:
self.finalize()
overall_plotdir = plotdir + '/overall'
for gene in self.freqs:
if only_overall:
continue
freqs = self.freqs[gene]
if len(freqs) == 0:
if gene not in glutils.dummy_d_genes.values():
print ' %s no mutefreqer obs for %s' % (utils.color(
'red', 'warning'), utils.color_gene(gene))
continue
sorted_positions = sorted(freqs.keys())
genehist = Hist(sorted_positions[-1] - sorted_positions[0] + 1,
sorted_positions[0] - 0.5,
sorted_positions[-1] + 0.5,
xtitle='position',
ytitle='mut freq',
title=gene)
for position in sorted_positions:
hi_diff = abs(freqs[position]['freq'] -
freqs[position]['freq_hi_err'])
lo_diff = abs(freqs[position]['freq'] -
freqs[position]['freq_lo_err'])
err = 0.5 * (hi_diff + lo_diff)
genehist.set_ibin(genehist.find_bin(position),
freqs[position]['freq'],
error=err)
xline = None
figsize = [7, 4]
if utils.get_region(gene) in utils.conserved_codons[
self.glfo['locus']]:
xline = utils.cdn_pos(self.glfo, utils.get_region(gene), gene)
if utils.get_region(gene) == 'v':
figsize[0] *= 3.5
elif utils.get_region(gene) == 'j':
figsize[0] *= 2
plotting.draw_no_root(self.per_gene_mean_rates[gene],
plotdir=plotdir + '/per-gene/' +
utils.get_region(gene),
plotname=utils.sanitize_name(gene),
errors=True,
write_csv=True,
only_csv=only_csv,
shift_overflows=True)
# per-position plots:
plotting.draw_no_root(genehist,
plotdir=plotdir + '/per-gene-per-position/' +
utils.get_region(gene),
plotname=utils.sanitize_name(gene),
errors=True,
write_csv=True,
xline=xline,
figsize=figsize,
only_csv=only_csv,
shift_overflows=True)
# # per-position, per-base plots:
# paramutils.make_mutefreq_plot(plotdir + '/' + utils.get_region(gene) + '-per-base', utils.sanitize_name(gene), plotting_info) # needs translation to mpl UPDATE fcn is fixed, but I can't be bothered uncommenting this at the moment
# make mean mute freq hists
for rstr in ['all', 'cdr3'] + utils.regions:
if rstr == 'all':
bounds = (0.0, 0.4)
else:
bounds = (0.0, 0.6 if rstr == 'd' else 0.4)
plotting.draw_no_root(self.mean_rates[rstr],
plotname=rstr + '_mean-freq',
plotdir=overall_plotdir,
stats='mean',
bounds=bounds,
write_csv=True,
only_csv=only_csv,
shift_overflows=True)
plotting.draw_no_root(self.mean_n_muted[rstr],
plotname=rstr + '_mean-n-muted',
plotdir=overall_plotdir,
stats='mean',
write_csv=True,
only_csv=only_csv,
shift_overflows=True)
if not only_csv: # write html file and fix permissiions
for substr in self.subplotdirs:
plotting.make_html(plotdir + '/' + substr)
def plot(self, plotdir, only_csv=False):
utils.prep_dir(plotdir, wildling=None, multilings=['*.csv', '*.svg', '*.root'])
for column in self.values:
if self.only_correct_gene_fractions and column not in bool_columns:
continue
if column in bool_columns:
right = self.values[column]['right']
wrong = self.values[column]['wrong']
errs = fraction_uncertainty.err(right, right+wrong)
print ' %s\n correct up to allele: %4d / %-4d = %4.4f (-%.3f, +%.3f)' % (column, right, right+wrong, float(right) / (right + wrong), errs[0], errs[1])
hist = plotting.make_bool_hist(right, wrong, self.name + '-' + column)
plotting.draw_no_root(hist, plotname=column, plotdir=plotdir, write_csv=True, stats='0-bin', only_csv=only_csv)
else:
# TODO this is dumb... I should make the integer-valued ones histograms as well
hist = plotting.make_hist_from_dict_of_counts(self.values[column], 'int', self.name + '-' + column, normalize=True)
log = ''
if column.find('hamming_to_true_naive') >= 0: # TODO why doesn't this just use the config dicts in plotheaders or wherever?
hist.title = 'hamming distance'
else:
hist.title = 'inferred - true'
plotting.draw_no_root(hist, plotname=column, plotdir=plotdir, write_csv=True, log=log, only_csv=only_csv)
for column in self.hists:
plotting.draw_no_root(self.hists[column], plotname=column, plotdir=plotdir, write_csv=True, log=log, only_csv=only_csv)
# per-gene support crap
for region in utils.regions:
if self.hists[region + '_allele_right_vs_per_gene_support'].integral(include_overflows=True) == 0:
continue
xvals = self.hists[region + '_allele_right_vs_per_gene_support'].get_bin_centers() #ignore_overflows=True)
right = self.hists[region + '_allele_right_vs_per_gene_support'].bin_contents
wrong = self.hists[region + '_allele_wrong_vs_per_gene_support'].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 = [fraction_uncertainty.err(r, r + w) for r, w in zip(right, wrong)]
yerrs = [err[1] - err[0] for err in tmphilos]
# fitting a line isn't particularly informative, actually
# params, cov = numpy.polyfit(xvals, yvals, 1, w=[1./(e*e) if e > 0. else 0. for e in yerrs], cov=True)
# slope, slope_err = params[0], math.sqrt(cov[0][0])
# y_icpt, y_icpt_err = params[1], math.sqrt(cov[1][1])
# print '%s slope: %5.2f +/- %5.2f y-intercept: %5.2f +/- %5.2f' % (region, slope, slope_err, y_icpt, y_icpt_err)
# 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])
fig, ax = plotting.mpl_init()
ax.errorbar(xvals, yvals, yerr=yerrs, markersize=10, linewidth=1, marker='.')
ax.plot((0, 1), (0, 1), color='black', linestyle='--', linewidth=3) # line with slope 1 and intercept 0
# linevals = [slope*x + y_icpt for x in [0] + xvals] # fitted line
# ax.plot([0] + xvals, linevals)
plotting.mpl_finish(ax, plotdir, region + '_allele_fraction_correct_vs_per_gene_support', xlabel='support', ylabel='fraction correct', xbounds=(-0.1, 1.1), ybounds=(-0.1, 1.1))
if not only_csv:
plotting.make_html(plotdir)
def plot(
self,
plotdir,
only_csv=False,
only_overall=False,
make_per_base_plots=False
): # NOTE most of the time in here is taken up by mutefrequer.finalize() (if it write() wasn't called first, that is)
import plotting
print ' plotting parameters in %s' % plotdir,
sys.stdout.flush()
start = time.time()
self.clean_plots(plotdir)
self.mfreqer.plot(plotdir + '/mute-freqs',
only_csv=only_csv,
only_overall=only_overall,
make_per_base_plots=make_per_base_plots)
overall_plotdir = plotdir + '/overall'
for column in self.counts:
if column == 'all':
continue
values, gene_values = {}, {}
for index, count in self.counts[column].iteritems():
column_val = index[0]
if column_val not in values:
values[column_val] = 0.0
values[column_val] += count
if column in self.columns_to_subset_by_gene:
gene = index[
1] # NOTE this is hackey, but it works find now and will fail obviously if I ever change the correlations to be incompatible. so screw it
utils.split_gene(gene) # checks validity of gene
if gene not in gene_values:
gene_values[gene] = {}
if column_val not in gene_values[gene]:
gene_values[gene][column_val] = 0.0
gene_values[gene][column_val] += count
var_type = 'string' if column in self.string_columns else 'int'
hist = hutils.make_hist_from_dict_of_counts(
values, var_type, column)
plotting.draw_no_root(
hist,
plotname=column,
plotdir=overall_plotdir,
xtitle=plotconfig.xtitles.get(column, column),
plottitle=plotconfig.plot_titles.get(column, column),
errors=True,
write_csv=True,
only_csv=only_csv,
stats='mean' if column in self.mean_columns else None,
normalize=True)
if column in self.columns_to_subset_by_gene and not only_overall:
thisplotdir = plotdir + '/' + column
for gene in gene_values:
plotname = utils.sanitize_name(gene) + '-' + column
hist = hutils.make_hist_from_dict_of_counts(
gene_values[gene], var_type, plotname)
plotting.draw_no_root(hist,
plotname=plotname,
plotdir=thisplotdir,
xtitle=plotconfig.plot_titles.get(
column, column),
plottitle=gene,
errors=True,
write_csv=True,
only_csv=only_csv)
if not only_csv:
plotting.make_html(thisplotdir)
if not only_csv:
plotting.make_html(overall_plotdir)
print '(%.1f sec)' % (time.time() - start)
def plot(self, plotdir, only_csv=False, only_overall=False):
print " plotting parameters",
sys.stdout.flush()
start = time.time()
self.clean_plots(plotdir)
self.mfreqer.plot(plotdir + "/mute-freqs", only_csv=only_csv, only_overall=only_overall)
overall_plotdir = plotdir + "/overall"
for column in self.counts:
if column == "all":
continue
values, gene_values = {}, {}
for index, count in self.counts[column].iteritems():
column_val = index[0]
if column_val not in values:
values[column_val] = 0.0
values[column_val] += count
if column in self.columns_to_subset_by_gene:
gene = index[
1
] # NOTE this is hackey, but it works find now and will fail obviously if I ever change the correlations to be incompatible. so screw it
utils.split_gene(gene) # checks validity of gene
if gene not in gene_values:
gene_values[gene] = {}
if column_val not in gene_values[gene]:
gene_values[gene][column_val] = 0.0
gene_values[gene][column_val] += count
var_type = "string" if column in self.string_columns else "int"
hist = plotting.make_hist_from_dict_of_counts(values, var_type, column, sort=True)
plotting.draw_no_root(
hist,
plotname=column,
plotdir=overall_plotdir,
xtitle=plotconfig.xtitles.get(column, column),
plottitle=plotconfig.plot_titles.get(column, column),
errors=True,
write_csv=True,
only_csv=only_csv,
)
if column in self.columns_to_subset_by_gene and not only_overall:
thisplotdir = plotdir + "/" + column
for gene in gene_values:
plotname = utils.sanitize_name(gene) + "-" + column
hist = plotting.make_hist_from_dict_of_counts(gene_values[gene], var_type, plotname, sort=True)
plotting.draw_no_root(
hist,
plotname=plotname,
plotdir=thisplotdir,
xtitle=plotconfig.plot_titles.get(column, column),
plottitle=gene,
errors=True,
write_csv=True,
only_csv=only_csv,
)
if not only_csv:
plotting.make_html(thisplotdir)
if not only_csv:
plotting.make_html(overall_plotdir)
print "(%.1f sec)" % (time.time() - start)
def get_gls_gen_annotation_performance_plots(args, baseoutdir):
import plotting
import plotconfig
methcolors = { # NOTE started from scolors in bin/plot-gl-set-trees.py htmlcolorcods.com, and slide each one a little rightward
'tigger-default' : '#dd4d39',
'igdiscover' : '#55ab7a', #60ac84',
'partis' : '#6b83ca', #758bcd',
'full' : '#858585',
}
varname = args.action
varval = 'simu'
plotnames = ['v_hamming_to_true_naive', 'v_muted_bases']
xtitles = ['V distance to true naive', 'inferred - true']
meanvals = {pn: {m: [] for m in args.methods} for pn in plotnames}
print ' annotations: %s' % get_outdir(
args, baseoutdir, varname, varval, n_events=args.gls_gen_events)
for iproc in range(args.iteststart, args.n_tests):
outdir = get_outdir(
args, baseoutdir, varname, varval,
n_events=args.gls_gen_events) + '/' + str(
iproc) # duplicates code in bin/test-germline-inference.py
plotdir = outdir + '/annotation-performance-plots'
print ' %s' % plotdir
if not args.only_print:
utils.prep_dir(plotdir, wildlings=['*.png', '*.svg', '*.csv'])
# shenanigans for the six (three easy and thre hard) of 'em that go in the paper pdf
make_legend = (iproc > 2) or (
iproc == 0) # and args.gls_gen_difficulty == 'easy')
make_xtitle = (iproc > 2) or (iproc == 2)
make_ytitle = (iproc > 2) or (args.gls_gen_difficulty == 'easy')
for plotname in plotnames:
hists = {
meth: Hist(fname=get_gls_fname(
outdir, meth, sim_locus, annotation_performance_plots=True)
+ '/' + plotname + '.csv',
title=methstr(meth) if make_legend else None)
for meth in args.methods
}
for meth in args.methods:
if hists[meth].overflow_contents() != 0.0:
print ' %s %s non-zero under/overflow %f' % (
utils.color('red', 'error'), methstr(meth),
hists[meth].overflow_contents())
meanvals[plotname][meth].append(hists[meth].get_mean())
if args.only_print:
continue
colors = [methcolors[meth] for meth in args.methods]
linewidths = [
9, 8, 4, 3
] # methods are sorted below, so it's always [full, igdiscover, partis, tigger]
plotting.draw_no_root(
hists[args.methods[0]],
log='y',
plotdir=plotdir,
plotname=plotname,
more_hists=[hists[m] for m in args.methods[1:]],
colors=colors,
ytitle='sequences' if make_ytitle else None,
xtitle=xtitles[plotnames.index(plotname)]
if make_xtitle else '',
plottitle=gls_sim_str(args.gls_gen_difficulty, iproc),
linewidths=linewidths)
for plotname in plotnames:
if 'muted_bases' in plotname: # mean value isn't meaningful
continue
print plotname
for meth in args.methods:
mean = float(sum(meanvals[plotname][meth])) / len(
meanvals[plotname][meth])
err = numpy.std(meanvals[plotname][meth], ddof=1) / math.sqrt(
len(meanvals[plotname][meth]))
print ' %15s %6.3f / %d = %6.2f +/- %6.2f' % (
methstr(meth), sum(meanvals[plotname][meth]),
len(meanvals[plotname][meth]), mean, err)
def plot_single_variable(args, varname, hlist, outdir, pathnameclues):
if varname in plotconfig.gene_usage_columns:
hlist = plotting.add_bin_labels_not_in_all_hists(hlist)
no_labels = False
xline, bounds, figsize = None, None, None
stats = args.extra_stats
translegend = [0.0, -0.2]
xtitle, ytitle = hlist[0].xtitle, hlist[0].ytitle
if xtitle == '': # arg, plotting.py thinks default should be None, hist.py thinks it's ''
xtitle = None
if '-mean-bins' in varname:
raise Exception(
'darn, I was hoping I wasn\'t making these plots any more')
plottitle = plotconfig.plot_titles[
varname] if varname in plotconfig.plot_titles else varname
ytitle = 'frequency' if args.normalize else 'counts'
if 'mute-freqs/v' in pathnameclues or 'mute-freqs/d' in pathnameclues or 'mute-freqs/j' in pathnameclues:
assert not args.normalize
ytitle = 'mutation freq'
if varname in plotconfig.gene_usage_columns:
xtitle = 'allele'
if hlist[0].n_bins == 2:
stats = ' 0-bin' # print the fraction of entries in the zero bin into the legend (i.e. the fraction correct)
# elif hlist[0].bin_labels.count('') == hlist[0].n_bins + 2:
# xtitle = '???'
line_width_override = None
if args.performance_plots:
if 'hamming_to_true_naive' in varname:
xtitle = 'hamming distance'
if '_normed' in varname:
xtitle = 'fractional ' + xtitle
elif '_vs_mute_freq' in varname:
xtitle = 'mutation freq'
ytitle = 'fraction correct'
if varname[0] == 'v' or varname[0] == 'j':
translegend = [-0.4, -0.4]
elif varname.find('_gene') == 1:
xtitle = ''
ytitle = 'fraction correct'
else:
xtitle = 'inferred - true'
bounds = plotconfig.true_vs_inferred_hard_bounds.setdefault(
varname, None)
else:
bounds = plotconfig.default_hard_bounds.setdefault(varname, None)
if bounds is None and 'insertion' in varname:
bounds = plotconfig.default_hard_bounds.setdefault(
'all_insertions', None)
if varname in plotconfig.gene_usage_columns:
no_labels = True
if 'j_' not in varname:
figsize = (10, 5)
line_width_override = 1
elif 'per-gene-per-position/v' in pathnameclues:
figsize = (20, 5)
bounds = plotconfig.default_hard_bounds.setdefault(
utils.unsanitize_name(varname), None)
if 'IG' in varname or 'TR' in varname:
if 'mute-freqs' in pathnameclues:
gene = utils.unsanitize_name(varname)
plottitle = gene # + ' -- mutation frequency'
xtitle = 'position'
if utils.get_region(gene) == 'j':
translegend = [0.1, 0.] #(-0.35, -0.02)
else:
translegend = [0.15, -0.02]
xline = None
if args.glfo is not None:
if utils.get_region(gene) in utils.conserved_codons[
args.locus]:
xline = args.glfo[utils.conserved_codons[args.locus][
utils.get_region(gene)] + '-positions'][gene]
else:
ilastdash = varname.rfind('-')
gene = utils.unsanitize_name(varname[:ilastdash])
base_varname = varname[ilastdash + 1:]
base_plottitle = plotconfig.plot_titles[
base_varname] if base_varname in plotconfig.plot_titles else ''
plottitle = gene + ' -- ' + base_plottitle
if len(hlist) > 9: # skootch it down so they (maybe) all fit
translegend[1] -= 0.5
if args.translegend is not None: # override with the command line
translegend = args.translegend
if args.extra_stats == 'auto': # kind of hackey
if xtitle == 'inferred - true':
stats = 'absmean'
else:
stats = 'mean'
# draw that little #$*(!
linewidths = [
line_width_override,
] if line_width_override is not None else args.linewidths
alphas = [0.6 for _ in range(len(hlist))]
plotting.draw_no_root(
hlist[0],
plotname=varname,
plotdir=outdir,
more_hists=hlist[1:],
write_csv=False,
stats=stats,
bounds=bounds,
shift_overflows=(os.path.basename(outdir) != 'gene-call'),
plottitle=plottitle,
colors=args.colors,
xtitle=xtitle,
ytitle=ytitle,
xline=xline,
normalize=(args.normalize and '_vs_mute_freq' not in varname),
linewidths=linewidths,
alphas=alphas,
errors=True,
figsize=figsize,
no_labels=no_labels,
log=args.log,
translegend=translegend)
def plot_single_variable(args, varname, hlist, outdir, pathnameclues):
if varname in plotconfig.gene_usage_columns:
hlist = plotting.add_bin_labels_not_in_all_hists(hlist)
no_labels = False
xline, bounds, figsize = None, None, None
translegend = (0.0, -0.2)
extrastats, log = '', ''
xtitle, ytitle = hlist[0].xtitle, hlist[0].ytitle
if xtitle == '': # arg, plotting.py thinks default should be None, hist.py thinks it's ''
xtitle = None
if '-mean-bins' in varname:
raise Exception('darn, I was hoping I wasn\'t making these plots any more')
plottitle = plotconfig.plot_titles[varname] if varname in plotconfig.plot_titles else varname
ytitle = 'frequency' if args.normalize else 'counts'
if 'mute-freqs/v' in pathnameclues or 'mute-freqs/d' in pathnameclues or 'mute-freqs/j' in pathnameclues:
assert not args.normalize
ytitle = 'mutation freq'
if varname in plotconfig.gene_usage_columns:
xtitle = 'allele'
if hlist[0].n_bins == 2:
extrastats = ' 0-bin' # print the fraction of entries in the zero bin into the legend (i.e. the fraction correct)
# elif hlist[0].bin_labels.count('') == hlist[0].n_bins + 2:
# xtitle = '???'
line_width_override = None
if args.performance_plots:
if 'hamming_to_true_naive' in varname:
xtitle = 'hamming distance'
if '_normed' in varname:
xtitle = 'fractional ' + xtitle
elif '_vs_mute_freq' in varname:
xtitle = 'mutation freq'
ytitle = 'fraction correct'
if varname[0] == 'v' or varname[0] == 'j':
translegend = (-0.4, -0.4)
elif varname.find('_gene') == 1:
xtitle = ''
ytitle = 'fraction correct'
else:
xtitle = 'inferred - true'
bounds = plotconfig.true_vs_inferred_hard_bounds.setdefault(varname, None)
else:
bounds = plotconfig.default_hard_bounds.setdefault(varname, None)
if bounds is None and 'insertion' in varname:
bounds = plotconfig.default_hard_bounds.setdefault('all_insertions', None)
if varname in plotconfig.gene_usage_columns:
no_labels = True
if 'j_' not in varname:
figsize = (10, 5)
line_width_override = 1
elif 'per-gene-per-position/v' in pathnameclues:
figsize = (20, 5)
bounds = plotconfig.default_hard_bounds.setdefault(utils.unsanitize_name(varname), None)
if 'IG' in varname:
if 'mute-freqs' in pathnameclues:
gene = utils.unsanitize_name(varname)
plottitle = gene # + ' -- mutation frequency'
xtitle = 'position'
if utils.get_region(gene) == 'j':
translegend = (0.1, 0.) #(-0.35, -0.02)
else:
translegend = (0.15, -0.02)
xline = None
if args.glfo is not None:
if utils.get_region(gene) in utils.conserved_codons[args.chain]:
xline = args.glfo[utils.conserved_codons[args.chain][utils.get_region(gene)] + '-positions'][gene]
else:
ilastdash = varname.rfind('-')
gene = utils.unsanitize_name(varname[:ilastdash])
base_varname = varname[ilastdash + 1 :]
base_plottitle = plotconfig.plot_titles[base_varname] if base_varname in plotconfig.plot_titles else ''
plottitle = gene + ' -- ' + base_plottitle
# draw that little #$*(!
linewidths = [line_width_override, ] if line_width_override is not None else args.linewidths
alphas = [0.6 for _ in range(len(hlist))]
plotting.draw_no_root(hlist[0], plotname=varname, plotdir=outdir, more_hists=hlist[1:], write_csv=False, stats=extrastats, bounds=bounds,
shift_overflows=(os.path.basename(outdir) != 'gene-call'), plottitle=plottitle, colors=args.colors,
xtitle=xtitle, ytitle=ytitle, xline=xline, normalize=(args.normalize and '_vs_mute_freq' not in varname),
linewidths=linewidths, alphas=alphas, errors=True,
figsize=figsize, no_labels=no_labels, log=log, translegend=translegend)
