Skip to content

Histogram facet plot #328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ying39purdue wants to merge 10 commits into
base: dev
Choose a base branch
from
Open

Histogram facet plot #328

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
6ce438c
histogram rebase to dev
ying39purdue Apr 15, 2025
88dd59c
add facet plots on histogram group by
ying39purdue Apr 2, 2025
193a666
add unittest for facet output
ying39purdue Apr 2, 2025
ae848f3
formatting of facet plot, and unittest
ying39purdue Apr 2, 2025
40572f0
formatting of facet plot, and unittest
ying39purdue Apr 2, 2025
78c15f6
remove axis rotation and formatting
ying39purdue Apr 8, 2025
157902e
Unittest addition of element numbers, title, and axis labels check
ying39purdue Apr 11, 2025
a143bd2
unittest rebase with dev
ying39purdue Apr 15, 2025
f3ad951
correct facet function return
ying39purdue Apr 16, 2025
773a616
Merge branch 'dev' into histogram_facet_plot
ying39purdue May 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
172 changes: 102 additions & 70 deletions src/spac/visualization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -400,7 +400,7 @@ def tsne_plot(adata, color_column=None, ax=None, **kwargs):

def histogram(adata, feature=None, annotation=None, layer=None,
group_by=None, together=False, ax=None,
x_log_scale=False, y_log_scale=False, **kwargs):
x_log_scale=False, y_log_scale=False, facet=False, **kwargs):
"""
Plot the histogram of cells based on a specific feature from adata.X
or annotation from adata.obs.
Expand Down Expand Up @@ -442,6 +442,9 @@ def histogram(adata, feature=None, annotation=None, layer=None,
y_log_scale : bool, default False
If True, the y-axis will be set to log scale.

facet : bool, default False
If True, group by function outputs facet plots

**kwargs
Additional keyword arguments passed to seaborn histplot function.
Key arguments include:
Expand Down Expand Up @@ -562,7 +565,8 @@ def cal_bin_num(
):
bins = max(int(2*(num_rows ** (1/3))), 1)
print(f'Automatically calculated number of bins is: {bins}')
return(bins)

return (bins)

num_rows = plot_data.shape[0]

Expand Down Expand Up @@ -624,6 +628,7 @@ def calculate_histogram(data, bins, bin_edges=None):
if group_by:
groups = df[group_by].dropna().unique().tolist()
n_groups = len(groups)

if n_groups == 0:
raise ValueError("There must be at least one group to create a"
" histogram.")
Expand Down Expand Up @@ -660,62 +665,86 @@ def calculate_histogram(data, bins, bin_edges=None):
if feature:
ax.set_title(f'Layer: {layer}')
axs.append(ax)

else:
fig, ax_array = plt.subplots(
n_groups, 1, figsize=(5, 5 * n_groups)
)
if not facet:
fig, ax_array = plt.subplots(
n_groups, 1, figsize=(5, 5 * n_groups)
)

# Convert a single Axes object to a list
# Ensure ax_array is always iterable
if n_groups == 1:
ax_array = [ax_array]

# Convert a single Axes object to a list
# Ensure ax_array is always iterable
if n_groups == 1:
ax_array = [ax_array]
else:
ax_array = ax_array.flatten()

for i, ax_i in enumerate(ax_array):
group_data = plot_data[plot_data[group_by] ==
groups[i]][data_column]
hist_data = calculate_histogram(group_data, kwargs['bins'])

sns.histplot(data=hist_data, x="bin_center", ax=ax_i,
weights='count', **kwargs)
# If plotting feature specify which layer
if feature:
ax_i.set_title(f'{groups[i]} with Layer: {layer}')
else:
ax_i.set_title(f'{groups[i]}')
ax_array = ax_array.flatten()

for i, ax_i in enumerate(ax_array):
group_data = plot_data[plot_data[group_by] ==
groups[i]][data_column]
hist_data = calculate_histogram(group_data, kwargs['bins'])

sns.histplot(data=hist_data, x="bin_center", ax=ax_i,
weights='count', **kwargs)
# If plotting feature specify which layer
if feature:
ax_i.set_title(f'{groups[i]} with Layer: {layer}')
else:
ax_array = ax_array.flatten()

# Set axis scales if y_log_scale is True
if y_log_scale:
ax_i.set_yscale('log')

# Adjust x-axis label if x_log_scale is True
if x_log_scale:
xlabel = f'log({data_column})'
else:
xlabel = data_column
ax_i.set_xlabel(xlabel)

# Adjust y-axis label based on 'stat' parameter
stat = kwargs.get('stat', 'count')
ylabel_map = {
'count': 'Count',
'frequency': 'Frequency',
'density': 'Density',
'probability': 'Probability'
}
ylabel = ylabel_map.get(stat, 'Count')
if y_log_scale:
ylabel = f'log({ylabel})'
ax_i.set_ylabel(ylabel)
axs.append(ax_i)
else:
hist = sns.FacetGrid(plot_data, col=group_by)
# Map the histogram function to the grid
hist.map(sns.histplot, data_column, **kwargs)

# Set axis scales if y_log_scale is True
if y_log_scale:
ax_i.set_yscale('log')
# Set rotation of label
hist.set_xticklabels(rotation=20, ha='right')

# Titles for each facet
hist.set_titles("{col_name}")

# Ajust top margin
hist.figure.subplots_adjust(left=.1,
top=0.85,
bottom=0.15,
hspace=0.3)

fig = hist.figure
axs.extend(hist.axes.flat)
hist_data = plot_data

# Adjust x-axis label if x_log_scale is True
if x_log_scale:
xlabel = f'log({data_column})'
else:
xlabel = data_column
ax_i.set_xlabel(xlabel)

# Adjust y-axis label based on 'stat' parameter
stat = kwargs.get('stat', 'count')
ylabel_map = {
'count': 'Count',
'frequency': 'Frequency',
'density': 'Density',
'probability': 'Probability'
}
ylabel = ylabel_map.get(stat, 'Count')
if y_log_scale:
ylabel = f'log({ylabel})'
ax_i.set_ylabel(ylabel)

axs.append(ax_i)
else:
# Precompute histogram data for single plot
hist_data = calculate_histogram(plot_data[data_column], kwargs['bins'])
if pd.api.types.is_numeric_dtype(plot_data[data_column]):
ax.set_xlim(hist_data['bin_left'].min(),
hist_data['bin_right'].max())
hist_data['bin_right'].max())


sns.histplot(
data=hist_data,
Expand All @@ -730,35 +759,38 @@ def calculate_histogram(data, bins, bin_edges=None):
ax.set_title(f'Layer: {layer}')
axs.append(ax)

# Set axis scales if y_log_scale is True
if y_log_scale:
ax.set_yscale('log')
axes = axs if isinstance(axs, (list, np.ndarray)) else [axs]
for ax in axes:
# Set axis scales if y_log_scale is True
if y_log_scale:
ax.set_yscale('log')

# Adjust x-axis label if x_log_scale is True
if x_log_scale:
xlabel = f'log({data_column})'
else:
xlabel = data_column
ax.set_xlabel(xlabel)

# Adjust y-axis label based on 'stat' parameter
stat = kwargs.get('stat', 'count')
ylabel_map = {
'count': 'Count',
'frequency': 'Frequency',
'density': 'Density',
'probability': 'Probability'
}
ylabel = ylabel_map.get(stat, 'Count')
if y_log_scale:
ylabel = f'log({ylabel})'
ax.set_ylabel(ylabel)
# Adjust x-axis label if x_log_scale is True
if x_log_scale:
xlabel = f'log({data_column})'
else:
xlabel = data_column
ax.set_xlabel(xlabel)

# Adjust y-axis label based on 'stat' parameter
stat = kwargs.get('stat', 'count')
ylabel_map = {
'count': 'Count',
'frequency': 'Frequency',
'density': 'Density',
'probability': 'Probability'
}
ylabel = ylabel_map.get(stat, 'Count')
if y_log_scale:
ylabel = f'log({ylabel})'
ax.set_ylabel(ylabel)

if len(axs) == 1:
return {"fig": fig, "axs": axs[0], "df": hist_data}
else:
return {"fig": fig, "axs": axs, "df": hist_data}


def heatmap(adata, column, layer=None, **kwargs):
"""
Plot the heatmap of the mean feature of cells that belong to a `column`.
Expand Down
40 changes: 39 additions & 1 deletion tests/test_visualization/test_histogram.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,7 +222,7 @@ def test_y_log_scale_axis(self):

def test_y_log_scale_label(self):
"""Test that y-axis label is updated when y_log_scale is True."""
fig, ax, dfd = histogram(
fig, ax, df = histogram(
self.adata,
feature='marker1',
y_log_scale=True
Expand Down Expand Up @@ -413,6 +413,44 @@ def test_default_bins_calculation(self):
expected_bins = max(int(2 * (self.adata.shape[0] ** (1 / 3))), 1)
self.assertEqual(n_bins, expected_bins)

def test_facet_plot(self):
"""Test that facet plot works."""
fig, ax, df = histogram(
self.adata,
feature='marker1',
group_by='annotation2',
facet=True,
).values()

# Check if axs is a collection (list/array of Axes)
self.assertIsInstance(ax, (list, np.ndarray),
"Output is not a multi-axis grid")

# Check number of facets equals number of unique groups
unique_groups = self.adata.obs['annotation2'].dropna().unique()
self.assertEqual(len(ax), len(unique_groups),
f"Expected {len(unique_groups)}"
f" facet plots, got {len(ax)}.")

# Validate each axis: title, xlabel, and ylabel
for i, axis in enumerate(ax):
# Check that title is set and matches the group
title = axis.get_title()
self.assertTrue(title, f"Facet {i} is missing a title.")
self.assertTrue(any(str(group) in title
for group in unique_groups),
f"Title '{title}' does not contain"
f"any expected group names.")

# Check X and Y labels
self.assertIn('marker1', axis.get_xlabel(),
f"Facet {i} X-axis label"
f" '{axis.get_xlabel()}' is incorrect.")
self.assertIn(axis.get_ylabel(),
['Count', 'Frequency', 'Density', 'Probability'],
f"Facet {i} Y-axis label"
f" '{axis.get_ylabel()}' is not a valid stat.")


if __name__ == '__main__':
unittest.main()