Skip to content

fix: expose cohort size parameters in diversity_stats #1290

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
adilraza99 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix: expose cohort size parameters in diversity_stats #1290

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
53a028f
fix: correct misleading cohort downsampling warning in diversity_stats
adilraza99 Apr 28, 2026
b2f763f
Merge branch 'master' into GH1288-diversity-stats-cohort-params
adilraza99 Apr 28, 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
41 changes: 28 additions & 13 deletions malariagen_data/anopheles.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import warnings
from typing import Any, Dict, Mapping, Optional, Tuple, Sequence

import allel # type: ignore
Expand Down Expand Up @@ -444,19 +445,33 @@ def cohort_diversity_stats(

except CacheMiss:
debug("access allele counts")
ac = self.snp_allele_counts(
region=region,
site_mask=site_mask,
site_class=site_class,
sample_query=cohort_query,
sample_sets=sample_sets,
cohort_size=cohort_size,
min_cohort_size=min_cohort_size,
max_cohort_size=max_cohort_size,
random_seed=random_seed,
chunks=chunks,
inline_array=inline_array,
)
with warnings.catch_warnings(record=True) as caught_warnings:
warnings.simplefilter("always")
ac = self.snp_allele_counts(
region=region,
site_mask=site_mask,
site_class=site_class,
sample_query=cohort_query,
sample_sets=sample_sets,
cohort_size=cohort_size,
min_cohort_size=min_cohort_size,
max_cohort_size=max_cohort_size,
random_seed=random_seed,
chunks=chunks,
inline_array=inline_array,
)
for w in caught_warnings:
if "Cohort downsampled" in str(w.message):
msg = str(w.message).split(". Set")[0] + "."
warnings.warn(msg, w.category, stacklevel=2)
else:
warnings.warn_explicit(
message=w.message,
category=w.category,
filename=w.filename,
lineno=w.lineno,
source=w.source,
)

debug("compute diversity stats")
stats = self._block_jackknife_cohort_diversity_stats(
Expand Down
Loading