Merge branch 'master' into pre-commit-ci-update-config

.github/workflows/ci.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest]
-        python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12" ]
+        python-version: [ "3,9", "3.10", "3.11", "3.12" ]
         include:
           - os: windows-latest
             python-version: "3.12"

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "hatchling.build"
 name = "cooler"
 version = "0.10.2"
 description = "Sparse binary format for genomic interaction matrices."
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 license = {text = "BSD-3-Clause"}
 authors = [
   {name = "Nezar Abdennur", email = "nabdennur@gmail.com"},
@@ -29,7 +29,6 @@ classifiers = [
     "Operating System :: OS Independent",
     "Programming Language :: Python",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.8",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
@@ -39,7 +38,7 @@ classifiers = [
 readme = "README.md"
 
 dependencies = [
-    "numpy>=1.9, <2",
+    "numpy>=1.26,<3",
     "scipy>=0.16",
     "pandas>1.5",
     "h5py>=2.5",
@@ -59,7 +58,7 @@ all = [
     "ipytree>=0.2.2",
     "ipywidgets>=8.0.0",
     "matplotlib",
-    "pypairix; platform_system != 'Windows'",
+#    "pypairix; platform_system != 'Windows'", # doesn't compile, see 4dn-dcic/pairix#79
     "psutil",
     "pysam; platform_system != 'Windows'",
 ]

src/cooler/_reduce.py

@@ -4,7 +4,8 @@
 import warnings
 from bisect import bisect_right
 from collections import OrderedDict, defaultdict
-from typing import Any, Iterator, Literal
+from collections.abc import Iterator
+from typing import Any, Literal
 
 import h5py
 import multiprocess as mp

src/cooler/_typing.py

@@ -1,15 +1,16 @@
 from __future__ import annotations
 
-from typing import Callable, Dict, Iterable, Optional, Tuple, TypeVar, Union
+from collections.abc import Iterable
+from typing import Callable, Optional, TypeVar, Union
 
 import numpy as np
 import pandas as pd
 
 T = TypeVar('T')
 U = TypeVar('U')
 MapFunctor = Callable[[Callable[[T], U], Iterable[T]], Iterable[U]]
-GenomicRangeSpecifier = Union[str , Tuple[str, Optional[int], Optional[int]]]
-GenomicRangeTuple = Tuple[str, int, int]
-Tabular = Union[pd.DataFrame, Dict[str, np.ndarray]]
+GenomicRangeSpecifier = Union[str , tuple[str, Optional[int], Optional[int]]]
+GenomicRangeTuple = tuple[str, int, int]
+Tabular = Union[pd.DataFrame, dict[str, np.ndarray]]
 
 __all__ = ["GenomicRangeSpecifier", "GenomicRangeTuple", "MapFunctor", "Tabular"]

src/cooler/core/_rangequery.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
-from typing import Any, Callable, Iterator
+from collections.abc import Iterator
+from typing import Any, Callable
 
 import h5py
 import numpy as np

src/cooler/core/_selectors.py

@@ -1,11 +1,11 @@
 from __future__ import annotations
 
-from typing import Any, Callable, List, Optional, Tuple, Union, overload
+from typing import Any, Callable, Optional, Union, overload
 
 import pandas as pd
 
-ColumnsArg = Optional[Union[str, List[str]]]
-GenomicRangeArg = Optional[Union[str, Tuple[str, Optional[int], Optional[int]]]]
+ColumnsArg = Optional[Union[str, list[str]]]
+GenomicRangeArg = Optional[Union[str, tuple[str, Optional[int], Optional[int]]]]
 FieldArg = Optional[str]
 
 

src/cooler/core/_tableops.py

@@ -102,7 +102,7 @@ def get(
             data[field] = pd.Categorical.from_codes(
                 dset[lo:hi], sorted(dt, key=dt.__getitem__), ordered=True
             )
-        elif dset.dtype.type == np.string_:
+        elif dset.dtype.type == np.bytes_:
             data[field] = dset[lo:hi].astype("U")
         else:
             data[field] = dset[lo:hi]

src/cooler/create/_create.py

@@ -5,8 +5,9 @@
 import posixpath
 import tempfile
 import warnings
+from collections.abc import Iterable
 from datetime import datetime
-from typing import Any, Iterable
+from typing import Any
 
 import h5py
 import numpy as np

src/cooler/create/_ingest.py

@@ -12,8 +12,9 @@
 import warnings
 from bisect import bisect_left
 from collections import Counter, OrderedDict
+from collections.abc import Iterator
 from functools import partial
-from typing import Any, Callable, Iterator
+from typing import Any, Callable
 
 import h5py
 import numpy as np
@@ -112,8 +113,8 @@ def _sanitize_records(
         return chunk
 
     # Find positional anchor columns, convert to zero-based if needed
-    anchor1 = np.array(chunk[anchor_field + suffixes[0]])
-    anchor2 = np.array(chunk[anchor_field + suffixes[1]])
+    anchor1 = chunk[anchor_field + suffixes[0]].to_numpy(copy=True)
+    anchor2 = chunk[anchor_field + suffixes[1]].to_numpy(copy=True)
     if is_one_based:
         anchor1 -= 1
         anchor2 -= 1

src/cooler/parallel.py

@@ -5,8 +5,9 @@
 """
 from __future__ import annotations
 
+from collections.abc import Iterable, Iterator, Sequence
 from functools import partial, reduce
-from typing import Any, Callable, Iterable, Iterator, Sequence
+from typing import Any, Callable
 
 from multiprocess import Lock
 

src/cooler/util.py

@@ -3,8 +3,9 @@
 import os
 import re
 from collections import OrderedDict, defaultdict
+from collections.abc import Generator, Iterable, Iterator
 from contextlib import contextmanager
-from typing import IO, Any, Generator, Iterable, Iterator
+from typing import IO, Any
 
 import h5py
 import numpy as np
@@ -627,7 +628,7 @@ def infer_meta(x, index=None):  # pragma: no cover
         "m": np.timedelta64(1),
         "S": np.str_("foo"),
         "a": np.str_("foo"),
-        "U": np.unicode_("foo"),
+        "U": np.str_("foo"),
         "O": "foo",
     }