def gen_upset_plot(self, className=None):
# total_peps = len([pep for s in self.results.samples for pep in s.peptides])
total_peps = np.sum([len(s.peptides) for s in self.results.samples])
data = from_contents({s.sample_name: set(s.peptides)
for s in self.results.samples})
for intersection in data.index.unique():
if len(data.loc[intersection, :])/total_peps < 0.005:
data.drop(index=intersection, inplace=True)
data['peptide_length'] = np.vectorize(len)(data['id'])
n_sets = len(data.index.unique())
if n_sets <= 100: # Plot horizontal
upset = UpSet(data,
sort_by='cardinality',
#sort_categories_by=None,
show_counts=True,)
#totals_plot_elements=4,
#intersection_plot_elements=10)
upset.add_catplot(value='peptide_length', kind='boxen', color='gray')
plot = upset.plot()
plot['totals'].grid(False)
ylim = plot['intersections'].get_ylim()[1]
plot['intersections'].set_ylim((0, ylim * 1.1))
for c in plot['intersections'].get_children():
if isinstance(c, plotText):
text = c.get_text()
text = text.replace('\n', ' ')
c.set_text(text)
c.set_rotation('vertical')
pos = c.get_position()
pos = (pos[0], pos[1] + 0.02 * ylim)
c.set_position(pos)
else: # plot vertical
upset = UpSet(data, subset_size='count',
orientation='vertical',
sort_by='cardinality',
sort_categories_by=None,
show_counts=True)
upset.add_catplot(value='peptide_length', kind='boxen', color='gray')
plot = upset.plot()
lim = plot['intersections'].get_xlim()
plot['intersections'].set_xlim([0, lim[1] * 1.6])
plot['totals'].grid(False)
ylim = plot['totals'].get_ylim()[1]
for c in plot['totals'].get_children():
if isinstance(c, plotText):
text = c.get_text()
text = text.replace('\n', ' ')
c.set_text(text)
c.set_rotation('vertical')
pos = c.get_position()
pos = (pos[0], pos[1] + 0.1 * ylim)
c.set_position(pos)
plt.draw()
upset_fig = f'{self.fig_dir / "upsetplot.svg"}'
plt.savefig(upset_fig, bbox_inches="tight")
encoded_upset_fig = base64.b64encode(open(upset_fig, 'rb').read()).decode()
card = div(className='card', style="height: 100%")
card.add(div([b('UpSet Plot'), p('Only intersections > 0.5% are displayed')], className='card-header'))
plot_body = div(img(src=f'data:image/svg+xml;base64,{encoded_upset_fig}',
className='img-fluid',
style=f'width: 100%; height: auto'),
className='card-body')
card.add(plot_body)
return div(card, className=className)
def test_add_catplot():
pytest.importorskip('seaborn')
X = generate_data(n_samples=100)
upset = UpSet(X)
# smoke test
upset.add_catplot('violin')
fig = matplotlib.figure.Figure()
upset.plot(fig)
# can't provide value with Series
with pytest.raises(ValueError):
upset.add_catplot('violin', value='foo')
# check the above add_catplot did not break the state
upset.plot(fig)
X = generate_data(n_samples=100)
X.name = 'foo'
X = X.to_frame()
upset = UpSet(X, sum_over=False)
# must provide value with DataFrame
with pytest.raises(ValueError):
upset.add_catplot('violin')
upset.add_catplot('violin', value='foo')
with pytest.raises(ValueError):
# not a known column
upset.add_catplot('violin', value='bar')
upset.plot(fig)
# invalid plot kind raises error when plotting
upset.add_catplot('foobar', value='foo')
with pytest.raises(AttributeError):
upset.plot(fig)
# Get a binary indicator of whether each top feature is above average
boston_above_avg = boston_df > boston_df.median(axis=0)
boston_above_avg = boston_above_avg[top_features]
boston_above_avg = boston_above_avg.rename(columns=lambda x: x + '>')
# Make this indicator mask an index of boston_df
boston_df = pd.concat([boston_df, boston_above_avg], axis=1)
boston_df = boston_df.set_index(list(boston_above_avg.columns))
# Also give us access to the target (median house value)
boston_df = boston_df.assign(median_value=boston.target)
# UpSet plot it!
upset = UpSet(boston_df, subset_size='count', intersection_plot_elements=3)
upset.add_catplot(value='median_value', kind='strip', color='blue')
upset.add_catplot(value='AGE', kind='strip', color='black')
upset.plot()
plt.title("UpSet with catplots, for orientation='horizontal'")
plt.show()
# And again in vertical orientation
upset = UpSet(boston_df,
subset_size='count',
intersection_plot_elements=3,
orientation='vertical')
upset.add_catplot(value='median_value', kind='strip', color='blue')
upset.add_catplot(value='AGE', kind='strip', color='black')
upset.plot()
plt.title("UpSet with catplots, for orientation='vertical'")