Skip to content

fix: restore original recursion limit after dendrogram computation #1306

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

Merged
jonbrenas merged 3 commits into from
Apr 18, 2026
+216 −204
Merged

fix: restore original recursion limit after dendrogram computation #1306

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
74c5e31
fix: restore original recursion limit after dendrogram computation
kunal-10-cloud Apr 15, 2026
3dd4142
Merge branch 'master' into fix/issue-1305-recursion-limit-restore
kunal-10-cloud Apr 16, 2026
5c6a001
Merge branch 'master' into fix/issue-1305-recursion-limit-restore
jonbrenas Apr 17, 2026
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
201 changes: 103 additions & 98 deletions malariagen_data/anoph/dipclust.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,112 +88,117 @@ def plot_diplotype_clustering(
distance_sort = False

# This is needed to avoid RecursionError on some clustering analyses
# with larger numbers of nodes.
sys.setrecursionlimit(10_000)

# Load sample metadata.
df_samples = self.sample_metadata(
sample_sets=sample_sets,
sample_query=sample_query,
sample_query_options=sample_query_options,
)
# with larger numbers of nodes. Save and restore the original limit to
# avoid permanently modifying global interpreter state.
_original_limit = sys.getrecursionlimit()
try:
sys.setrecursionlimit(10_000)
Comment on lines 90 to +95
Copy link

Copilot AI Apr 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Consider adding a regression test that asserts sys.getrecursionlimit() is unchanged after calling plot_diplotype_clustering() (and ideally also when an exception is raised during clustering/plotting). This ensures the try/finally restoration behavior remains covered and prevents future regressions.

Copilot uses AI. Check for mistakes.

dist, gt_samples, n_snps_used = self.diplotype_pairwise_distances(
region=region,
site_mask=site_mask,
sample_sets=sample_sets,
sample_query=sample_query,
sample_query_options=sample_query_options,
cohort_size=cohort_size,
distance_metric=distance_metric,
random_seed=random_seed,
chunks=chunks,
inline_array=inline_array,
)
# Load sample metadata.
df_samples = self.sample_metadata(
sample_sets=sample_sets,
sample_query=sample_query,
sample_query_options=sample_query_options,
)

# Align sample metadata with genotypes.
df_samples = (
df_samples.set_index("sample_id").loc[gt_samples.tolist()].reset_index()
)
dist, gt_samples, n_snps_used = self.diplotype_pairwise_distances(
region=region,
site_mask=site_mask,
sample_sets=sample_sets,
sample_query=sample_query,
sample_query_options=sample_query_options,
cohort_size=cohort_size,
distance_metric=distance_metric,
random_seed=random_seed,
chunks=chunks,
inline_array=inline_array,
)

# Normalise color and symbol parameters.
symbol_prepped = self._setup_sample_symbol(
data=df_samples,
symbol=symbol,
)
del symbol
(
color_prepped,
color_discrete_map_prepped,
category_orders_prepped,
) = self._setup_sample_colors_plotly(
data=df_samples,
color=color,
color_discrete_map=color_discrete_map,
color_discrete_sequence=color_discrete_sequence,
category_orders=category_orders,
)
del color
del color_discrete_map
del color_discrete_sequence
# Align sample metadata with genotypes.
df_samples = (
df_samples.set_index("sample_id").loc[gt_samples.tolist()].reset_index()
)

# Configure hover data.
hover_data = self._setup_sample_hover_data_plotly(
color=color_prepped, symbol=symbol_prepped
)
# Normalise color and symbol parameters.
symbol_prepped = self._setup_sample_symbol(
data=df_samples,
symbol=symbol,
)
del symbol
(
color_prepped,
color_discrete_map_prepped,
category_orders_prepped,
) = self._setup_sample_colors_plotly(
data=df_samples,
color=color,
color_discrete_map=color_discrete_map,
color_discrete_sequence=color_discrete_sequence,
category_orders=category_orders,
)
del color
del color_discrete_map
del color_discrete_sequence

# Construct plot title.
if title is True:
title_lines = []
if sample_sets is not None:
title_lines.append(f"Sample sets: {sample_sets}")
if sample_query is not None:
title_lines.append(f"Sample query: {sample_query}")
title_lines.append(f"Genomic region: {region} ({n_snps_used:,} SNPs)")
title = "<br>".join(title_lines)

# Create the plot.
with self._spinner("Plot dendrogram"):
fig, leaf_data = _plot_dendrogram(
dist=dist,
linkage_method=linkage_method,
count_sort=count_sort,
distance_sort=distance_sort,
render_mode=render_mode,
width=width,
height=height,
title=title,
line_width=line_width,
line_color=line_color,
marker_size=marker_size,
leaf_data=df_samples,
leaf_hover_name="sample_id",
leaf_hover_data=hover_data,
leaf_color=color_prepped,
leaf_symbol=symbol_prepped,
leaf_y=leaf_y,
leaf_color_discrete_map=color_discrete_map_prepped,
leaf_category_orders=category_orders_prepped,
template="simple_white",
y_axis_title=f"Distance ({distance_metric})",
y_axis_buffer=0.1,
# Configure hover data.
hover_data = self._setup_sample_hover_data_plotly(
color=color_prepped, symbol=symbol_prepped
)

# Tidy up.
fig.update_layout(
title_font=dict(
size=title_font_size,
),
legend=dict(itemsizing=legend_sizing, tracegroupgap=0),
)
# Construct plot title.
if title is True:
title_lines = []
if sample_sets is not None:
title_lines.append(f"Sample sets: {sample_sets}")
if sample_query is not None:
title_lines.append(f"Sample query: {sample_query}")
title_lines.append(f"Genomic region: {region} ({n_snps_used:,} SNPs)")
title = "<br>".join(title_lines)

# Create the plot.
with self._spinner("Plot dendrogram"):
fig, leaf_data = _plot_dendrogram(
dist=dist,
linkage_method=linkage_method,
count_sort=count_sort,
distance_sort=distance_sort,
render_mode=render_mode,
width=width,
height=height,
title=title,
line_width=line_width,
line_color=line_color,
marker_size=marker_size,
leaf_data=df_samples,
leaf_hover_name="sample_id",
leaf_hover_data=hover_data,
leaf_color=color_prepped,
leaf_symbol=symbol_prepped,
leaf_y=leaf_y,
leaf_color_discrete_map=color_discrete_map_prepped,
leaf_category_orders=category_orders_prepped,
template="simple_white",
y_axis_title=f"Distance ({distance_metric})",
y_axis_buffer=0.1,
)

if show: # pragma: no cover
fig.show(renderer=renderer)
return {
"figure": fig,
"dendro_sample_id_order": np.asarray(leaf_data["sample_id"].to_list()),
"n_snps": n_snps_used,
}
# Tidy up.
fig.update_layout(
title_font=dict(
size=title_font_size,
),
legend=dict(itemsizing=legend_sizing, tracegroupgap=0),
)

if show: # pragma: no cover
fig.show(renderer=renderer)
return {
"figure": fig,
"dendro_sample_id_order": np.asarray(leaf_data["sample_id"].to_list()),
"n_snps": n_snps_used,
}
finally:
sys.setrecursionlimit(_original_limit)

def diplotype_pairwise_distances(
self,
Expand Down
Loading
Loading