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, partition=None, infiles=None, annotations=None, only_csv=None):
print ' plotting partitions'
sys.stdout.flush()
start = time.time()
for subdir in self.subplotdirs:
utils.prep_dir(plotdir + '/' + subdir, wildlings=['*.csv', '*.svg'])
if partition is not None: # one partition
assert infiles is None
assert annotations is not None
csize_hists = {'best' : plotting.get_cluster_size_hist(partition)}
self.plot_within_vs_between_hists(partition, annotations, plotdir)
elif infiles is not None: # plot the mean of a partition from each file
subset_hists = []
for fname in infiles:
cp = ClusterPath()
cp.readfile(fname)
subset_hists.append(plotting.get_cluster_size_hist(cp.partitions[cp.i_best]))
csize_hists = {'best' : plotting.make_mean_hist(subset_hists)}
for ih in range(len(subset_hists)):
subset_hists[ih].write(plotdir + ('/subset-%d-cluster-sizes.csv' % ih))
else:
assert False
plotting.plot_cluster_size_hists(plotdir + '/overall/cluster-sizes.svg', csize_hists, title='', log='x')
if not only_csv:
for subdir in self.subplotdirs:
plotting.make_html(plotdir + '/' + subdir)
print '(%.1f sec)' % (time.time()-start)
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,
plotdir,
partition=None,
infiles=None,
annotations=None,
only_csv=None):
import plotting
print ' plotting partitions'
sys.stdout.flush()
start = time.time()
for subdir in self.subplotdirs:
utils.prep_dir(plotdir + '/' + subdir,
wildlings=['*.csv', '*.svg'])
fnames = []
if partition is not None: # one partition
assert infiles is None
assert annotations is not None
csize_hists = {'best': plotting.get_cluster_size_hist(partition)}
# self.plot_within_vs_between_hists(partition, annotations, plotdir)
fnames += self.plot_size_vs_shm(partition, annotations, plotdir)
elif infiles is not None: # plot the mean of a partition from each file
subset_hists = []
for fname in infiles:
cp = ClusterPath()
cp.readfile(fname)
subset_hists.append(
plotting.get_cluster_size_hist(cp.partitions[cp.i_best]))
csize_hists = {'best': plotting.make_mean_hist(subset_hists)}
for ih in range(len(subset_hists)):
subset_hists[ih].write(plotdir +
('/subset-%d-cluster-sizes.csv' % ih))
else:
assert False
plotting.plot_cluster_size_hists(plotdir +
'/overall/cluster-sizes.svg',
csize_hists,
title='',
log='x')
fnames.append(['cluster-sizes.svg'])
if not only_csv:
for subdir in self.subplotdirs:
plotting.make_html(plotdir + '/' + subdir,
fnames=fnames,
new_table_each_row=True)
print '(%.1f sec)' % (time.time() - start)
def plot(self, plotdir, only_csv=False, only_overall=False):
import plotting
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 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 compare_directories(args, plotdirlist, outdir):
utils.prep_dir(outdir, wildlings=['*.png', '*.svg', '*.csv'])
# read hists from <plotdirlist>
allhists = OrderedDict()
allvars = set() # all variables that appeared in any dir
for idir in range(len(plotdirlist)):
dirhists = get_hists_from_dir(plotdirlist[idir], args.names[idir])
allvars |= set(dirhists.keys())
allhists[args.names[idir]] = dirhists
# then loop over all the <varname>s we found
for varname in allvars:
hlist = [allhists[dname].get(varname, Hist(1, 0, 1, title='null')) for dname in allhists]
plot_single_variable(args, varname, hlist, outdir, pathnameclues=plotdirlist[0])
plotting.make_html(outdir, n_columns=4)
def compare_directories(args, plotdirlist, outdir):
utils.prep_dir(outdir, wildlings=['*.png', '*.svg', '*.csv'])
# read hists from <plotdirlist>
allhists = OrderedDict()
allvars = set() # all variables that appeared in any dir
for idir in range(len(plotdirlist)):
dirhists = get_hists_from_dir(plotdirlist[idir], args.names[idir])
allvars |= set(dirhists.keys())
allhists[args.names[idir]] = dirhists
# then loop over all the <varname>s we found
for varname in allvars:
hlist = [allhists[dname].get(varname, Hist(1, 0, 1, title='null')) for dname in allhists]
plot_single_variable(args, varname, hlist, outdir, pathnameclues=plotdirlist[0])
plotting.make_html(outdir, n_columns=4)
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, 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 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):
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)
args.glfo = tmpglfo
else:
args.glfo = glutils.get_merged_glfo(args.glfo, tmpglfo)
listof_plotdirlists, listof_outdirs = [], []
# first add the main/parent dir, if it has csvs
firstdir = args.plotdirs[0]
if len(glob.glob(firstdir + '/*.csv')) > 0:
listof_plotdirlists.append(args.plotdirs)
listof_outdirs.append(args.outdir)
else:
print ' no csvs in main/parent dir %s' % firstdir
# then figure out if there's subdirs we need to deal with
added_subds = []
for subdir in [
d for d in os.listdir(firstdir) if os.path.isdir(firstdir + '/' + d)
]:
listof_plotdirlists.append([d + '/' + subdir for d in args.plotdirs])
listof_outdirs.append(args.outdir + '/' + subdir)
added_subds.append(subdir)
if len(added_subds) > 0:
print ' added %d subdirs: %s' % (len(added_subds), ' '.join(added_subds))
for dlist, outdir in zip(listof_plotdirlists, listof_outdirs):
compare_directories(args, dlist, outdir)
if args.make_parent_html: # didn't really test this very well
fnoutstr, _ = utils.simplerun('find %s -type f -name *.svg' % args.outdir,
return_out_err=True)
plotting.make_html(args.outdir, fnames=[fnoutstr.strip().split('\n')])