def create_count_plot_and_array(ax: plt.Figure, data: pd.DataFrame, x: str,
palette, x_label: str) -> np.ndarray:
ax = sns.countplot(ax=ax, data=data, x=x, palette=palette)
ax.set_ylabel('Count', fontsize='xx-large')
ax.set_xlabel(x_label, fontsize='xx-large')
interval_names = data['intervals'].unique()
ax.set_xticks(range(len(interval_names)))
ax.set_xticklabels(labels=interval_names, rotation=45, size=15)
fig = ax.figure
image_as_array = from_fig_to_array(fig)
plt.close(fig)
return image_as_array
def plot(self, pars : Parameters, data : 'Data' = None, channel : Channel = None, only : list = None, exclude : list = None,
variations : list = None, residuals : bool = False, canvas : plt.Figure = None, labels : bool = True) :
"""Plot the expected event yields and optionally data as well
The plot is performed for a single model, which must be of `binned_range` type.
The event yields are plotted as a histogram, as a function of the channel
observable.
The `variations` arg allows to plot yield variations for selected NP values. The
format is { ('par1', val1), ... } , which will plot the yields for the case where
NP par1 is set to val1 (while other NPs remain at nominal), etc.
Args:
pars : parameter values for which to compute the expected yields
data : observed dataset to plot alongside the expected yields
channel : name of the channel to plot. If `None`, plot the first channel.
exclude : list of sample names to exclude from the plot
variations : list of NP variations to plot, as a list of (str, float) pairs
providing the NP name and the value to set.
residuals : if True, plot the data-model differences
canvas : a matplotlib Figure on which to plot (if None, plt.gca() is used)
labels : if True (default), add labels to the legend
"""
if canvas is None : canvas = plt.gca()
if not isinstance(only, list) and only is not None : only = [ only ]
if not isinstance(exclude, list) and exclude is not None : exclude = [ exclude ]
if channel is None :
channel = list(self.channels.values())[0]
print("Plotting channel '%s'" % channel.name)
else :
if not channel in self.channels : raise KeyError('ERROR: Channel %s is not defined.' % channel)
channel = self.channels[channel]
if isinstance(channel, BinnedRangeChannel) :
grid = [ b['lo_edge'] for b in channel.bins ]
grid.append(channel.bins[-1]['hi_edge'])
elif isinstance(channel, SingleBinChannel) :
grid = [0,1]
else :
raise ValueError("Channel '%s' is o an unsupported type" % channel.name)
xvals = [ (grid[i] + grid[i+1])/2 for i in range(0, len(grid) - 1) ]
start = self.channel_offsets[channel.name]
stop = start + channel.nbins()
nexp = self.n_exp(pars)[:, start:stop]
tot_exp = nexp.sum(axis=0)
if only is not None :
samples = []
for sample_name in only :
if not sample_name in channel.samples : raise ValueError('Sample %s is not defined.' % sample_name)
samples.append(list(channel.samples).index(sample_name))
subtract = nexp[samples,:].sum(axis=0)
subtract = tot_exp - subtract
line_style = '--'
title = ','.join(only)
elif exclude is not None :
samples = []
for sample_name in exclude :
if not sample_name in channel.samples : raise ValueError('Sample %s is not defined.' % sample_name)
samples.append(list(channel.samples).index(sample_name))
subtract = nexp[samples,:].sum(axis=0)
line_style = '--'
title = 'Model excluding ' + ','.join(exclude)
else :
subtract = np.zeros(nexp.shape[1])
line_style = '-'
title = 'Model'
yvals = tot_exp - subtract if not residuals or data is None else tot_exp - subtract - counts
canvas.hist(xvals, weights=yvals, bins=grid, histtype='step',color='b', linestyle=line_style, label=title if labels else None)
if data is not None :
counts = data.counts[start:stop]
yerrs = [ math.sqrt(n) if n > 0 else 0 for n in counts ]
yvals = counts if not residuals else np.zeros(channel.nbins())
canvas.errorbar(xvals, yvals, xerr=[0]*channel.nbins(), yerr=yerrs, fmt='ko', label='Data' if labels else None)
canvas.set_xlim(grid[0], grid[-1])
if variations is not None :
for v in variations :
vpars = pars.clone()
vpars.set(v[0], v[1])
col = 'r' if len(v) < 3 else v[2]
nexp = self.n_exp(vpars)[:, start:stop]
if only is None and exclude is None :
subtract = np.zeros(nexp.shape[1])
else :
subtract = nexp[samples,:].sum(axis=0)
if only is not None : subtract = nexp.sum(axis=0) - subtract
tot_exp = nexp.sum(axis=0) - subtract
canvas.hist(xvals, weights=tot_exp, bins=grid, histtype='step',color=col, linestyle=line_style, label='%s=%+g' %(v[0], v[1]) if labels else None)
if labels : canvas.legend()
canvas.set_title(self.name)
if isinstance(channel, BinnedRangeChannel) :
canvas.set_xlabel('$' + channel.obs_name + '$' + ((' [' + channel.obs_unit + ']') if channel.obs_unit != '' else ''))
canvas.set_ylabel('Events / bin')
elif isinstance(channel, SingleBinChannel) :
canvas.set_xlabel(channel.name)
canvas.set_ylabel('Events')
