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):
utils.prep_dir(plotdir + '/plots', 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(hist, 'bool', plotname=column, plotdir=plotdir, write_csv=True)
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:
hist.GetXaxis().SetTitle('hamming distance')
else:
hist.GetXaxis().SetTitle('inferred - true')
plotting.draw(hist, 'int', plotname=column, plotdir=plotdir, write_csv=True, log=log)
for column in self.hists:
hist = plotting.make_hist_from_my_hist_class(self.hists[column], column)
plotting.draw(hist, 'float', plotname=column, plotdir=plotdir, write_csv=True, log=log)
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(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):
for column in self.values:
if column in bool_columns:
right = self.values[column]['right']
wrong = self.values[column]['wrong']
print ' %s\n correct up to allele: %4d / %-4d = %4.2f' % (column, right, right+wrong, float(right) / (right + wrong))
hist = plotting.make_bool_hist(right, wrong, self.name + '-' + column)
plotting.draw(hist, 'bool', plotname=column, plotdir=self.plotdir, write_csv=True)
else:
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:
hist.GetXaxis().SetTitle('hamming distance')
else:
hist.GetXaxis().SetTitle('inferred - true')
plotting.draw(hist, 'int', plotname=column, plotdir=self.plotdir, write_csv=True, log=log)
for column in self.hists:
hist = plotting.make_hist_from_my_hist_class(self.hists[column], 'mute_freqs')
plotting.draw(hist, 'float', plotname=column, plotdir=self.plotdir, write_csv=True, log=log)
check_call(['./bin/makeHtml', self.plotdir, '3', 'null', 'svg'])
check_call(['./bin/permissify-www', self.plotdir]) # NOTE this should really permissify starting a few directories higher up
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)
