From 8dfe38e06c86205e388924ceeeccb42a16fdfac9 Mon Sep 17 00:00:00 2001
From: Gregor Sturm <mail@gregor-sturm.de>
Date: Fri, 17 May 2024 08:41:15 +0200
Subject: [PATCH] Fix #517 (#518)

* Fix #517

* Update CHANGELOG
---
 CHANGELOG.md                               |  8 +++++++-
 src/scirpy/ir_dist/_clonotype_neighbors.py |  5 ++---
 src/scirpy/util/__init__.py                | 19 +++++++++++++++++++
 3 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 96ba991df..17362dd22 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,10 +8,16 @@ and this project adheres to [Semantic Versioning][].
 [keep a changelog]: https://keepachangelog.com/en/1.0.0/
 [semantic versioning]: https://semver.org/spec/v2.0.0.html
 
-## Unreleased
+## v0.17.0
+
+### Additions
 
 -   Add "TCRdist" as new metric ([#502](https://github.com/scverse/scirpy/pull/502))
 
+### Fixes
+
+-   Fix issue with detecting the number of available CPUs on MacOD ([#518](https://github.com/scverse/scirpy/pull/502))
+
 ## v0.16.1
 
 ### Fixes
diff --git a/src/scirpy/ir_dist/_clonotype_neighbors.py b/src/scirpy/ir_dist/_clonotype_neighbors.py
index b70c39e6d..a7e24a06e 100644
--- a/src/scirpy/ir_dist/_clonotype_neighbors.py
+++ b/src/scirpy/ir_dist/_clonotype_neighbors.py
@@ -1,5 +1,4 @@
 import itertools
-import os
 from collections.abc import Mapping, Sequence
 from typing import Literal, Optional, Union
 
@@ -11,7 +10,7 @@
 
 from scirpy.get import _has_ir
 from scirpy.get import airr as get_airr
-from scirpy.util import DataHandler, tqdm
+from scirpy.util import DataHandler, _get_usable_cpus, tqdm
 
 from ._util import DoubleLookupNeighborFinder, merge_coo_matrices, reduce_and, reduce_or
 
@@ -225,7 +224,7 @@ def compute_distances(self) -> sp.csr_matrix:
             dist_rows = process_map(
                 self._dist_for_clonotype,
                 range(n_clonotypes),
-                max_workers=self.n_jobs if self.n_jobs > 0 else len(os.sched_getaffinity(0)),
+                max_workers=_get_usable_cpus(self.n_jobs),
                 chunksize=2000,
                 tqdm_class=tqdm,
             )
diff --git a/src/scirpy/util/__init__.py b/src/scirpy/util/__init__.py
index caf79577c..01283b43e 100644
--- a/src/scirpy/util/__init__.py
+++ b/src/scirpy/util/__init__.py
@@ -1,4 +1,5 @@
 import contextlib
+import os
 import warnings
 from collections.abc import Mapping, Sequence
 from textwrap import dedent
@@ -582,3 +583,21 @@ def _parallelize_with_joblib(delayed_objects, *, total=None, **kwargs):
             "Consider setting verbosity in joblib.parallel_config"
         )
         return Parallel(return_as="list", **kwargs)(delayed_objects)
+
+
+def _get_usable_cpus(n_jobs: int = 0):
+    """Get the number of CPUs available to the process
+
+    If `n_jobs` is specified and > 0 that value will be returned unaltered.
+    Otherwise will try to determine the number of CPUs available to the process which
+    is not necessarily the number of CPUs available on the system.
+
+    On MacOS, `os.sched_getaffinity` is not implemented, therefore we just return the cpu count there.
+    """
+    if n_jobs > 0:
+        return n_jobs
+
+    try:
+        return os.sched_getaffinity(0)
+    except AttributeError:
+        return os.cpu_count()