Update to numpy v2

.github/workflows/tests.yml

@@ -28,9 +28,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          python -m pip install flake8 pytest pytest-cov coveralls
-          pip install -r requirements.txt
-          pip install .
+          pip install -e ".[dev]"
       - name: Lint with flake8
         run: |
           # stop the build if there are Python syntax errors or undefined names
@@ -49,6 +47,6 @@ jobs:
           pyensembl install --release 93 --species mouse --custom-mirror https://github.com/openvax/ensembl-data/releases/download/GRCm38.93/
       - name: Run unit tests
         run: |
-          ./test.sh
+          pytest --cov=pyensembl/ --cov-report=term-missing tests/
       - name: Publish coverage to Coveralls
         uses: coverallsapp/github-action@v2.2.3

.gitignore

@@ -1,3 +1,6 @@
+# cursor
+.cursor/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

README.md

@@ -4,7 +4,8 @@
 <img src="https://img.shields.io/pypi/v/pyensembl.svg?maxAge=1000" alt="PyPI" />
 </a>
 
-# PyEnsembl
+PyEnsembl
+=========
 
 PyEnsembl is a Python interface to [Ensembl](http://www.ensembl.org) reference genome metadata such as exons and transcripts. PyEnsembl downloads [GTF](https://en.wikipedia.org/wiki/Gene_transfer_format) and [FASTA](https://en.wikipedia.org/wiki/FASTA_format) files from the [Ensembl FTP server](ftp://ftp.ensembl.org) and loads them into a local database. PyEnsembl can also work with custom reference data specified using user-supplied GTF and FASTA files.
 
@@ -138,6 +139,60 @@ data.index()
 gene_names = data.gene_names_at_locus(contig=6, position=29945884)
 ```
 
+# Development and Testing
+
+## Installation for Development
+
+To install PyEnsembl for development with testing dependencies:
+
+```sh
+pip install -e ".[dev]"
+```
+
+This installs PyEnsembl in editable mode along with development dependencies including `pytest`, `pytest-cov`, `flake8`, and `coveralls`.
+
+## Running Tests
+
+PyEnsembl uses pytest for testing. Before running tests, you'll need to install some Ensembl data:
+
+```sh
+# Install required Ensembl releases for testing
+pyensembl install --release 75 --species human \
+  && pyensembl install --release 77 --species human \
+  && pyensembl install --release 93 --species human \
+  && pyensembl install --release 111 --species homo_sapiens
+```
+
+### Run all tests:
+
+```sh
+pytest tests/
+```
+
+### Run tests with coverage:
+
+```sh
+pytest --cov=pyensembl/ --cov-report=term-missing tests/
+```
+
+### Run a specific test file:
+
+```sh
+pytest tests/test_gene_names.py
+```
+
+### Run a specific test function:
+
+```sh
+pytest tests/test_gene_names.py::test_all_gene_names
+```
+
+### Run tests with verbose output:
+
+```sh
+pytest -v tests/
+```
+
 # API
 
 The `EnsemblRelease` object has methods to let you access all possible

pyensembl/__init__.py

@@ -10,6 +10,16 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+"""pyensembl public API and compatibility helpers."""
+
+import numpy as np
+
+# ``numpy.typeDict`` was removed in NumPy 2.0.  Some of ``pyensembl``'s
+# dependencies still rely on this old attribute, so provide it when
+# running under newer versions of NumPy.
+if not hasattr(np, "typeDict"):
+    np.typeDict = np.sctypeDict
+
 from .database import Database
 from .download_cache import DownloadCache
 from .ensembl_release import EnsemblRelease, cached_release

pyensembl/shell.py

@@ -40,7 +40,10 @@
 
 import argparse
 import logging.config
-import pkg_resources
+try:
+    from importlib import resources as importlib_resources
+except ImportError:  # pragma: no cover - Python <3.9 fallback
+    import importlib_resources  # type: ignore
 import os
 
 from .ensembl_release import EnsemblRelease
@@ -49,7 +52,9 @@
 from .species import Species
 from .version import __version__
 
-logging.config.fileConfig(pkg_resources.resource_filename(__name__, "logging.conf"))
+logging.config.fileConfig(
+    importlib_resources.files(__package__).joinpath("logging.conf")
+)
 logger = logging.getLogger(__name__)
 
 

pyproject.toml

@@ -0,0 +1,50 @@
+[build-system]
+requires = ["setuptools>=64", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pyensembl"
+dynamic = ["version"]
+description = "Python interface to Ensembl reference genome metadata"
+readme = "README.md"
+requires-python = ">=3.8"
+license = {file = "LICENSE"}
+authors = [{name = "Alex Rubinsteyn", email = "alex.rubinsteyn@unc.edu"}]
+keywords = ["ensembl", "genomics", "bioinformatics"]
+
+dependencies = [
+    "typechecks>=0.0.2,<1.0.0",
+    "datacache>=1.4.0,<2.0.0",
+    "memoized-property>=1.0.2",
+    "tinytimer>=0.0.0,<1.0.0",
+    #"gtfparse>=2.5.0",
+    "gtfparse @ git+https://github.com/nick-youngblut/gtfparse.git@pyarrow_update",
+    "serializable>=0.2.1,<1.0.0",
+    "pyarrow>=16.0.0",
+    "pandas>=2.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=6.0",
+    "pytest-cov>=2.0",
+    "flake8>=3.8",
+    "coveralls>=3.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/openvax/pyensembl"
+Source = "https://github.com/openvax/pyensembl"
+
+[project.scripts]
+pyensembl = "pyensembl.shell:run"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["pyensembl*"]
+
+[tool.setuptools.package-data]
+pyensembl = ["logging.conf"]
+
+[tool.setuptools.dynamic]
+version = {attr = "pyensembl.version.__version__"}