def main():
fig, ax = plt.subplots(2, 2, figsize=(10, 10))
fig.tight_layout()
data = -25 * make_test_data('hills',
noise_factor=0.025) # secretly swapped :-)
#data = -25 * make_test_data('circles', noise_factor=0.025) # secretly swapped :-)
terrain = data
assert terrain.shape == data.shape, "{} != {}".format(
terrain.shape, data.shape)
if '--bw' in sys.argv:
# Only intensities
blend_function = no_blending
cmap = INTENSITY_CMAP
# Don't auto scale the intensities, it gives the wrong impression
norm = mpl.colors.Normalize(vmin=0.0, vmax=1.0)
else:
blend_function = rgb_blending
cmap = plt.cm.get_cmap('gist_earth')
norm = mpl.colors.Normalize()
azimuths = [45, 135, 270] # North-East, North-West and South.
elevations = [60] * len(azimuths)
# Draw shading by separate light sources
for idx, (azim, elev) in enumerate(zip(azimuths, elevations)):
row = idx // 2
col = idx % 2
draw(ax[row, col],
cmap=cmap,
norm=norm,
title='azim = {}, elev = {}'.format(azim, elev),
image_data=hill_shade(data,
terrain,
blend_function=blend_function,
ambient_weight=1,
lamp_weight=5,
cmap=cmap,
norm=norm,
azimuth=azim,
elevation=elev))
# Draw shading by all light sources combined
draw(ax[1, 1],
cmap=cmap,
norm=norm,
title='combined'.format(azim, elev),
image_data=hill_shade(data,
terrain,
blend_function=blend_function,
ambient_weight=1,
lamp_weight=[5, 5, 5],
cmap=cmap,
norm=norm,
azimuth=azimuths,
elevation=elevations))
plt.show()
def plot(self, plotdir, subset_by_gene=False, cyst_positions=None, tryp_positions=None):
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(hist, var_type, plotname=plotname, plotdir=thisplotdir, errors=True, write_csv=True)
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(hist, var_type, plotname=plotname, plotdir=plotdir, errors=True, write_csv=True)
self.mutefreqer.plot(plotdir, cyst_positions, tryp_positions) #, mean_freq_outfname=base_outdir + '/REGION-mean-mute-freqs.csv') # REGION is replace by each region in the three output files
if has_root:
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
print ' parameter plot time: %.3f' % (time.time()-start)
def plot(self, plotdir, subset_by_gene=False, cyst_positions=None, tryp_positions=None):
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(hist, var_type, plotname=plotname, plotdir=thisplotdir, errors=True, write_csv=True)
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(hist, var_type, plotname=plotname, plotdir=plotdir, errors=True, write_csv=True)
self.mutefreqer.plot(plotdir, cyst_positions, tryp_positions) #, mean_freq_outfname=base_outdir + '/REGION-mean-mute-freqs.csv') # REGION is replace by each region in the three output files
if has_root:
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 main():
fig, ax = plt.subplots(2, 2, figsize=(10, 10))
fig.tight_layout()
data = -25 * make_test_data('hills', noise_factor=0.025) # secretly swapped :-)
#data = -25 * make_test_data('circles', noise_factor=0.025) # secretly swapped :-)
terrain = data
assert terrain.shape == data.shape, "{} != {}".format(terrain.shape, data.shape)
if '--bw' in sys.argv:
# Only intensities
blend_function = no_blending
cmap=INTENSITY_CMAP
# Don't auto scale the intensities, it gives the wrong impression
norm = mpl.colors.Normalize(vmin=0.0, vmax=1.0)
else:
blend_function = rgb_blending
cmap = plt.cm.get_cmap('gist_earth')
norm = mpl.colors.Normalize()
azimuths = [45, 135, 270] # North-East, North-West and South.
elevations = [60] * len(azimuths)
# Draw shading by separate light sources
for idx, (azim, elev) in enumerate(zip(azimuths, elevations)):
row = idx // 2
col = idx % 2
draw(ax[row, col], cmap=cmap, norm=norm,
title='azim = {}, elev = {}'.format(azim, elev),
image_data = hill_shade(data, terrain, blend_function=blend_function,
ambient_weight = 1, lamp_weight = 5,
cmap=cmap, norm=norm,
azimuth=azim, elevation=elev))
# Draw shading by all light sources combined
draw(ax[1, 1], cmap=cmap, norm=norm,
title='combined'.format(azim, elev),
image_data = hill_shade(data, terrain, blend_function=blend_function,
ambient_weight = 1, lamp_weight = [5, 5, 5],
cmap=cmap, norm=norm,
azimuth=azimuths, elevation=elevations))
plt.show()
def main():
fig, ax = plt.subplots(2, 2, figsize=(10, 10))
fig.tight_layout()
data = make_test_data('circles')
terrain = 10 * make_test_data('hills', noise_factor=0.05)
assert terrain.shape == data.shape, "{} != {}".format(terrain.shape, data.shape)
print("min data: {}".format(np.min(data)))
print("max data: {}".format(np.max(data)))
# Some color maps to try.
#cmap = plt.cm.get_cmap('bwr')
#cmap = plt.cm.get_cmap('CMRmap')
#cmap = plt.cm.get_cmap('rainbow')
#cmap = plt.cm.get_cmap('cool_r')
cmap = plt.cm.get_cmap('Set1')
# Optionally set the over and under flow colors.
#cmap.set_bad('yellow')
#cmap.set_over('cyan')
#cmap.set_under('magenta')
if ['--autoscale'] in sys.argv:
print ("Auto scale legend")
dnorm = mpl.colors.Normalize()
else:
dmin = 0
dmax = 10
print ("clip legend at ({}, {})".format(dmin, dmax))
dnorm = mpl.colors.Normalize(vmin=dmin, vmax=dmax)
# Don't auto scale the intensities, it gives the wrong impression
inorm = mpl.colors.Normalize(vmin=0.0, vmax=1.0)
azimuth = DEF_AZIMUTH
elevation = DEF_ELEVATION
draw(ax[0, 0], cmap=plt.cm.gist_earth, title='Terrain height',
image_data = terrain)
draw(ax[0, 1], cmap=INTENSITY_CMAP, norm=inorm,
title='Shaded terrain (azim = {}, elev = {})'.format(azimuth, elevation),
image_data = hill_shade(terrain, blend_function=no_blending,
azimuth=azimuth, elevation=elevation))
draw(ax[1, 0], cmap=cmap, norm=dnorm, title='Surface properties',
image_data = data)
draw(ax[1, 1], cmap=cmap, norm=dnorm, title='Shaded terrain with surface properties',
image_data = hill_shade(data, terrain=terrain,
azimuth=azimuth, elevation=elevation,
cmap=cmap, norm=dnorm))
plt.show()
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 main():
fig, ax = plt.subplots(3, 4, figsize=(15, 10))
fig.tight_layout()
#terrain = make_test_data('circles', noise_factor=0.0)
terrain = make_test_data('hills', noise_factor=0.1)
# Scale terrain.
terrain *= 5
# Don't auto scale the intensities, it gives the wrong impression
inorm = mpl.colors.Normalize(vmin=0.0, vmax=1.0)
# Draw the terrain as color map
draw(ax[0, 0], cmap=plt.cm.gist_earth, title='No shading', ticks=True,
image_data = terrain)
# Draw empty space
ax[1, 0].set_axis_off()
ax[2, 0].set_axis_off()
cmap = INTENSITY_CMAP
azim0_is_east = True # If true, azimuth 0 will correspond to east just as in our implementation
azimuths = [45, 90, 135]
#elev = 50
# At low elevation you will see still noise bumps in places that are completely in the shadows.
# This may seem nice but it is incorrect.
elev = 15
for idx, azim in enumerate(azimuths):
col = idx + 1
draw(ax[0, col], cmap=cmap, norm=inorm,
title="MPL normalized (azim = {}, elev = {})".format(azim, elev),
image_data = mpl_surface_intensity(terrain, azimuth=azim, elevation=elev,
azim0_is_east=azim0_is_east, normalize=True))
draw(ax[1, col], cmap=cmap, norm=inorm,
title="MPL (azim = {}, elev = {})".format(azim, elev),
image_data = mpl_surface_intensity(terrain, azimuth=azim, elevation=elev,
azim0_is_east=azim0_is_east, normalize=False))
draw(ax[2, col], cmap=cmap, norm=inorm,
title="Diffuse (azim = {}, elev = {})".format(azim, elev),
image_data = relative_surface_intensity(terrain, azimuth=azim, elevation=elev))
plt.show()
def plot(self, base_plotdir, cyst_positions=None, tryp_positions=None):
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)
hist = TH1D('hist_' + utils.sanitize_name(gene), '',
sorted_positions[-1] - sorted_positions[0] + 1,
sorted_positions[0] - 0.5, sorted_positions[-1] + 0.5)
for position in sorted_positions:
hist.SetBinContent(hist.FindBin(position), counts[position]['freq'])
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)
hist.SetBinError(hist.FindBin(position), err)
plotfname = plotdir + '/' + utils.get_region(gene) + '/plots/' + utils.sanitize_name(gene) + '.svg'
xline = None
if utils.get_region(gene) == 'v' and cyst_positions is not None:
xline = cyst_positions[gene]['cysteine-position']
elif utils.get_region(gene) == 'j' and tryp_positions is not None:
xline = int(tryp_positions[gene])
plotting.draw(hist, 'int', plotdir=plotdir + '/' + utils.get_region(gene), plotname=utils.sanitize_name(gene), errors=True, write_csv=True, xline=xline, draw_str='e') #, cwidth=4000, cheight=1000)
paramutils.make_mutefreq_plot(plotdir + '/' + utils.get_region(gene) + '-per-base', utils.sanitize_name(gene), plotting_info)
# for region in utils.regions:
# utils.prep_dir(plotdir + '/' + region + '/tmp/plots', multilings=('*.csv', '*.svg'))
# for gene in self.tmpcounts:
# for position in self.tmpcounts[gene]:
# roothist = plotting.make_hist_from_my_hist_class(self.tmpcounts[gene][position]['muted'], gene + '_' + str(position))
# plotting.draw(roothist, 'int', plotdir=plotdir + '/' + utils.get_region(gene) + '/tmp', plotname=utils.sanitize_name(gene) + '_' + str(position), errors=True, write_csv=True) #, cwidth=4000, cheight=1000)
# make mean mute freq hists
hist = plotting.make_hist_from_my_hist_class(self.mean_rates['all'], 'all-mean-freq')
plotting.draw(hist, 'float', plotname='all-mean-freq', plotdir=plotdir, stats='mean', bounds=(0.0, 0.4), write_csv=True)
for region in utils.regions:
hist = plotting.make_hist_from_my_hist_class(self.mean_rates[region], region+'-mean-freq')
plotting.draw(hist, 'float', plotname=region+'-mean-freq', plotdir=plotdir, stats='mean', bounds=(0.0, 0.4), write_csv=True)
check_call(['./bin/makeHtml', plotdir, '3', 'null', 'svg'])
# then write html file and fix permissiions
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):
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 main():
fig, ax = plt.subplots(3, 2, figsize=(7, 10))
fig.tight_layout()
if 1:
# Same terrain and data.
data = make_test_data('circles', noise_factor=0.05) * 2 - 7
terrain = data
else:
# Different terrain and data. Matplotlib hill shading can only show the data.
data = make_test_data('hills') * -1
terrain = make_test_data('circles', noise_factor=0.05) * 2
assert terrain.shape == data.shape, "{} != {}".format(terrain.shape, data.shape)
print("data range: {} {}".format(np.min(data), np.max(data)))
if len(sys.argv) > 1:
cmap_name = sys.argv[1]
else:
#cmap_name = 'copper' # from http://matplotlib.org/examples/pylab_examples/shading_example.html?highlight=codex%20shade
#cmap_name = 'gist_earth' # works reasonably fine with all of them
cmap_name = 'bwr' # shows that mpl & pegtop don't work when there is no increasing intensity
#cmap_name = 'cubehelix' # shows that HSV blending does not work were color is black
#cmap_name = 'rainbow' # shows that mpl & pegtop don't work when there is no increasing intensity
#cmap_name = 'Paired_r' # is nice to inspect when the data is different from the terrain
print ("Using colormap: {!r}".format(cmap_name))
cmap = plt.cm.get_cmap(cmap_name)
cmap.set_bad('cyan')
cmap.set_over('cyan')
cmap.set_under('cyan')
abs_max = np.max(np.abs(data)) # force color bar to be symmetrical.
norm = mpl.colors.Normalize(vmin=-abs_max, vmax=abs_max)
#norm = mpl.colors.Normalize(vmin=-2, vmax=3)
draw(ax[0, 0], cmap=cmap, norm=norm, title='No shading',
image_data = data)
draw(ax[0, 1], cmap=plt.cm.gray, title='Matplotlib intensity',
image_data = mpl_surface_intensity(terrain))
ls = LightSource(azdeg=DEF_AZIMUTH, altdeg=DEF_ELEVATION)
draw(ax[1, 0], cmap=cmap, norm=norm, title='Matplotlib hill shading',
image_data = ls.shade(data, cmap=cmap, norm=norm))
draw(ax[1, 1], cmap=cmap, norm=norm, title='Pegtop blending',
image_data = mpl_hill_shade(data, terrain=terrain,
cmap=cmap, norm=norm, blend_function=pegtop_blending))
draw(ax[2, 0], cmap=cmap, norm=norm, title='RGB blending',
image_data = mpl_hill_shade(data, terrain=terrain,
cmap=cmap, norm=norm, blend_function=rgb_blending))
draw(ax[2, 1], cmap=cmap, norm=norm, title='HSV blending',
image_data = mpl_hill_shade(data, terrain=terrain,
cmap=cmap, norm=norm, blend_function=hsv_blending))
plt.show()
def main():
fig, ax = plt.subplots(3, 2, figsize=(7, 10))
fig.tight_layout()
if 1:
# Same terrain and data.
data = make_test_data('circles', noise_factor=0.05) * 2 - 7
terrain = data
else:
# Different terrain and data. Matplotlib hill shading can only show the data.
data = make_test_data('hills') * -1
terrain = make_test_data('circles', noise_factor=0.05) * 2
assert terrain.shape == data.shape, "{} != {}".format(
terrain.shape, data.shape)
print("data range: {} {}".format(np.min(data), np.max(data)))
if len(sys.argv) > 1:
cmap_name = sys.argv[1]
else:
#cmap_name = 'copper' # from http://matplotlib.org/examples/pylab_examples/shading_example.html?highlight=codex%20shade
#cmap_name = 'gist_earth' # works reasonably fine with all of them
cmap_name = 'bwr' # shows that mpl & pegtop don't work when there is no increasing intensity
#cmap_name = 'cubehelix' # shows that HSV blending does not work were color is black
#cmap_name = 'rainbow' # shows that mpl & pegtop don't work when there is no increasing intensity
#cmap_name = 'Paired_r' # is nice to inspect when the data is different from the terrain
print("Using colormap: {!r}".format(cmap_name))
cmap = plt.cm.get_cmap(cmap_name)
cmap.set_bad('cyan')
cmap.set_over('cyan')
cmap.set_under('cyan')
abs_max = np.max(np.abs(data)) # force color bar to be symmetrical.
norm = mpl.colors.Normalize(vmin=-abs_max, vmax=abs_max)
#norm = mpl.colors.Normalize(vmin=-2, vmax=3)
draw(ax[0, 0], cmap=cmap, norm=norm, title='No shading', image_data=data)
draw(ax[0, 1],
cmap=plt.cm.gray,
title='Matplotlib intensity',
image_data=mpl_surface_intensity(terrain))
ls = LightSource(azdeg=DEF_AZIMUTH, altdeg=DEF_ELEVATION)
draw(ax[1, 0],
cmap=cmap,
norm=norm,
title='Matplotlib hill shading',
image_data=ls.shade(data, cmap=cmap, norm=norm))
draw(ax[1, 1],
cmap=cmap,
norm=norm,
title='Pegtop blending',
image_data=mpl_hill_shade(data,
terrain=terrain,
cmap=cmap,
norm=norm,
blend_function=pegtop_blending))
draw(ax[2, 0],
cmap=cmap,
norm=norm,
title='RGB blending',
image_data=mpl_hill_shade(data,
terrain=terrain,
cmap=cmap,
norm=norm,
blend_function=rgb_blending))
draw(ax[2, 1],
cmap=cmap,
norm=norm,
title='HSV blending',
image_data=mpl_hill_shade(data,
terrain=terrain,
cmap=cmap,
norm=norm,
blend_function=hsv_blending))
plt.show()
def cluster(self, input_scores=None, infname=None, debug=False, reco_info=None, outfile=None, plotdir=''):
if infname is None:
assert input_scores is not None
else:
assert input_scores is None # should only specify <input_scores> *or* <infname>
input_scores = []
with opener('r')(infname) as infile:
reader = csv.DictReader(infile)
for line in reader:
input_scores.append(line)
sorted_lines = sorted(input_scores, key=lambda k: float(k['score']))
for line in sorted_lines:
a_name = line['id_a']
b_name = line['id_b']
score = float(line['score'])
from_same_event = -1 if (reco_info == None or a_name not in reco_info or b_name not in reco_info) else reco_info[a_name]['reco_id'] == reco_info[b_name]['reco_id']
dbg_str_list = ['%22s %22s %8.3f %d' % (a_name, b_name, score, from_same_event), ]
self.incorporate_into_clusters(a_name, b_name, score, dbg_str_list)
self.pairscores[(utils.get_key((a_name, b_name)))] = score
self.plotscores['all'].append(score)
if reco_info != None:
if from_same_event:
self.plotscores['same'].append(score)
else:
self.plotscores['diff'].append(score)
# if reco_info != None and reco_info[a_name]['reco_id'] == reco_info[b_name]['reco_id']:
# for query,score in {a_name:score, b_name:score}.iteritems():
# if query not in self.nearest_true_mate:
# self.nearest_true_mate[query] = score
# elif self.greater_than and score > self.nearest_true_mate[query]:
# self.nearest_true_mate[query] = score
# elif not self.greater_than and score < self.nearest_true_mate[query]:
# self.nearest_true_mate[query] = score
if debug:
outstr = ''.join(dbg_str_list)
if outfile == None:
print outstr
else:
outfile.write(outstr + '\n')
if plotdir != '':
utils.prep_dir(plotdir + '/plots', '*.svg')
hists = {}
for htype in ['all', 'same', 'diff']:
hists[htype] = plotting.make_hist_from_list(self.plotscores[htype], htype + '_pairscores')
hists[htype].SetTitle(htype)
plotting.draw(hists['all'], 'float', plotdir=plotdir, plotname='pairscores', more_hists=[hists['same'], hists['diff']])
check_call(['./bin/makeHtml', plotdir, '3', 'null', 'svg'])
check_call(['./bin/permissify-www', plotdir])
for query, cluster_id in self.query_clusters.iteritems():
if cluster_id not in self.id_clusters:
self.id_clusters[cluster_id] = []
self.id_clusters[cluster_id].append(query)
for cluster_id, queries in self.id_clusters.items():
if len(queries) == 1:
self.singletons.append(queries[0])
# print 'nearest',self.nearest_true_mate
out_str_list = [' %d clusters:\n'%len(self.id_clusters), ]
for cluster_id in self.id_clusters:
out_str_list.append(' ' + ' '.join([str(x) for x in self.id_clusters[cluster_id]]) + '\n')
if outfile == None:
print ''.join(out_str_list)
else:
outfile.write(''.join(out_str_list))
def main():
fig, ax = plt.subplots(3, 4, figsize=(15, 10))
fig.tight_layout()
#terrain = make_test_data('circles', noise_factor=0.0)
terrain = make_test_data('hills', noise_factor=0.1)
# Scale terrain.
terrain *= 5
# Don't auto scale the intensities, it gives the wrong impression
inorm = mpl.colors.Normalize(vmin=0.0, vmax=1.0)
# Draw the terrain as color map
draw(ax[0, 0],
cmap=plt.cm.gist_earth,
title='No shading',
ticks=True,
image_data=terrain)
# Draw empty space
ax[1, 0].set_axis_off()
ax[2, 0].set_axis_off()
cmap = INTENSITY_CMAP
azim0_is_east = True # If true, azimuth 0 will correspond to east just as in our implementation
azimuths = [45, 90, 135]
#elev = 50
# At low elevation you will see still noise bumps in places that are completely in the shadows.
# This may seem nice but it is incorrect.
elev = 15
for idx, azim in enumerate(azimuths):
col = idx + 1
draw(ax[0, col],
cmap=cmap,
norm=inorm,
title="MPL normalized (azim = {}, elev = {})".format(azim, elev),
image_data=mpl_surface_intensity(terrain,
azimuth=azim,
elevation=elev,
azim0_is_east=azim0_is_east,
normalize=True))
draw(ax[1, col],
cmap=cmap,
norm=inorm,
title="MPL (azim = {}, elev = {})".format(azim, elev),
image_data=mpl_surface_intensity(terrain,
azimuth=azim,
elevation=elev,
azim0_is_east=azim0_is_east,
normalize=False))
draw(ax[2, col],
cmap=cmap,
norm=inorm,
title="Diffuse (azim = {}, elev = {})".format(azim, elev),
image_data=relative_surface_intensity(terrain,
azimuth=azim,
elevation=elev))
plt.show()
def main():
fig, ax = plt.subplots(2, 2, figsize=(10, 10))
fig.tight_layout()
data = make_test_data('circles')
terrain = 10 * make_test_data('hills', noise_factor=0.05)
assert terrain.shape == data.shape, "{} != {}".format(
terrain.shape, data.shape)
print("min data: {}".format(np.min(data)))
print("max data: {}".format(np.max(data)))
# Some color maps to try.
#cmap = plt.cm.get_cmap('bwr')
#cmap = plt.cm.get_cmap('CMRmap')
#cmap = plt.cm.get_cmap('rainbow')
#cmap = plt.cm.get_cmap('cool_r')
cmap = plt.cm.get_cmap('Set1')
# Optionally set the over and under flow colors.
#cmap.set_bad('yellow')
#cmap.set_over('cyan')
#cmap.set_under('magenta')
if ['--autoscale'] in sys.argv:
print("Auto scale legend")
dnorm = mpl.colors.Normalize()
else:
dmin = 0
dmax = 10
print("clip legend at ({}, {})".format(dmin, dmax))
dnorm = mpl.colors.Normalize(vmin=dmin, vmax=dmax)
# Don't auto scale the intensities, it gives the wrong impression
inorm = mpl.colors.Normalize(vmin=0.0, vmax=1.0)
azimuth = DEF_AZIMUTH
elevation = DEF_ELEVATION
draw(ax[0, 0],
cmap=plt.cm.gist_earth,
title='Terrain height',
image_data=terrain)
draw(ax[0, 1],
cmap=INTENSITY_CMAP,
norm=inorm,
title='Shaded terrain (azim = {}, elev = {})'.format(
azimuth, elevation),
image_data=hill_shade(terrain,
blend_function=no_blending,
azimuth=azimuth,
elevation=elevation))
draw(ax[1, 0],
cmap=cmap,
norm=dnorm,
title='Surface properties',
image_data=data)
draw(ax[1, 1],
cmap=cmap,
norm=dnorm,
title='Shaded terrain with surface properties',
image_data=hill_shade(data,
terrain=terrain,
azimuth=azimuth,
elevation=elevation,
cmap=cmap,
norm=dnorm))
plt.show()
def plot(self, base_plotdir, cyst_positions=None, tryp_positions=None):
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)
hist = TH1D('hist_' + utils.sanitize_name(gene), '',
sorted_positions[-1] - sorted_positions[0] + 1,
sorted_positions[0] - 0.5, sorted_positions[-1] + 0.5)
for position in sorted_positions:
hist.SetBinContent(hist.FindBin(position),
counts[position]['freq'])
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)
hist.SetBinError(hist.FindBin(position), err)
plotfname = plotdir + '/' + utils.get_region(
gene) + '/plots/' + utils.sanitize_name(gene) + '.svg'
xline = None
if utils.get_region(gene) == 'v' and cyst_positions is not None:
xline = cyst_positions[gene]['cysteine-position']
elif utils.get_region(gene) == 'j' and tryp_positions is not None:
xline = int(tryp_positions[gene])
plotting.draw(hist,
'int',
plotdir=plotdir + '/' + utils.get_region(gene),
plotname=utils.sanitize_name(gene),
errors=True,
write_csv=True,
xline=xline,
draw_str='e') #, cwidth=4000, cheight=1000)
paramutils.make_mutefreq_plot(
plotdir + '/' + utils.get_region(gene) + '-per-base',
utils.sanitize_name(gene), plotting_info)
# make mean mute freq hists
hist = plotting.make_hist_from_my_hist_class(self.mean_rates['all'],
'all-mean-freq')
plotting.draw(hist,
'float',
plotname='all-mean-freq',
plotdir=plotdir,
stats='mean',
bounds=(0.0, 0.4),
write_csv=True)
for region in utils.regions:
hist = plotting.make_hist_from_my_hist_class(
self.mean_rates[region], region + '-mean-freq')
plotting.draw(hist,
'float',
plotname=region + '-mean-freq',
plotdir=plotdir,
stats='mean',
bounds=(0.0, 0.4),
write_csv=True)
check_call(['./bin/makeHtml', plotdir, '3', 'null', 'svg'])
# then write html file and fix permissiions
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
