Release phylib 2.7.1 (#65)

* style: fix existing flake8 violations

* ci: enforce flake8 checks

* release: prepare phylib 2.7.1

* Ensure dataset is writable

* release: refresh 2.7.1 documentation and package metadata

* release: date phylib 2.7.1 changelog

---------

Co-authored-by: Ghislain Vaillant <ghisvail@users.noreply.github.com>

Author: rossant

.github/workflows/ci.yml

@@ -15,6 +15,26 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Set up Python
+        uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
+        with:
+          python-version: "3.12"
+          cache: pip
+          cache-dependency-path: requirements-dev.txt
+
+      - name: Install lint dependencies
+        run: python -m pip install flake8
+
+      - name: Run lint
+        run: python -m flake8 phylib
+
   test:
     name: ${{ matrix.scope }} (${{ matrix.os }}, Python ${{ matrix.python-version }})
     runs-on: ${{ matrix.os }}
@@ -66,7 +86,7 @@ jobs:
   build:
     name: Build package
     runs-on: ubuntu-latest
-    needs: test
+    needs: [lint, test]
 
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1

CHANGELOG.md

@@ -5,20 +5,34 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [2.7.1] - 2026-10-08
 
 ### Added
-- Code of Conduct for project participation and incident reporting.
+- Added a Code of Conduct for project participation and incident reporting.
+
+### Changed
+- Optimized spike selection and stored sparse-waveform extraction for large datasets,
+  including bounded display sampling and batched memory-mapped reads.
+- Unknown raw-data file extensions now emit a warning instead of preventing the dataset
+  from loading.
 
 ### Fixed
+- Prevented geometry range searches from hanging with `float32` input.
 - Development checkouts now report a development version with a Git commit suffix.
-- Template datasets without waveform templates can be reloaded after cluster assignments change,
-  and stored spike-waveform subsets provide their waveform sample count.
-- Cluster assignments are written atomically, so a crash during a save no longer truncates `spike_clusters.npy`.
-- TSV, JSON, text and `params.py` files are written atomically, so a crash during a save no longer
-  truncates the file it was replacing, for instance `cluster_group.tsv`.
-- #57 a blank `dat_path` in `params.py` is now read as "no raw data file" instead of resolving to
-  the dataset directory.
+- Fixed reloading curated template-less datasets after cluster assignments change.
+- Derived the waveform sample count from stored spike-waveform subsets when templates are
+  unavailable.
+- Treated a blank `dat_path` in `params.py` as no raw-data file instead of the dataset
+  directory (#57).
+- Made cluster-assignment, TSV, JSON, text, and `params.py` writes atomic to prevent
+  truncation if saving is interrupted.
+- Corrected wheel metadata to advertise Python 3 only.
+- Included the changelog and test dependency list in source distributions.
+
+### Development
+- Enforced flake8 checks in CI and fixed existing lint violations.
+- Made copied test datasets writable when the source cache is read-only, supporting
+  sandboxed distribution builds (#66).
 
 ## [2.7.0] 2025-12-10
 

MANIFEST.in

@@ -1,8 +1,9 @@
 include LICENSE.md
 include README.md
+include CHANGELOG.md
 include requirements.txt
+include requirements-dev.txt
 
-recursive-include tests *
 recursive-include phylib/electrode/probes *.prb
 recursive-exclude * __pycache__
 recursive-exclude * *.py[co]

README.md

@@ -1,25 +1,54 @@
-# phylib
-[![Build Status](https://img.shields.io/travis/cortex-lab/phylib.svg)](https://travis-ci.org/cortex-lab/phylib)
-[![codecov.io](https://img.shields.io/codecov/c/github/cortex-lab/phylib.svg)](http://codecov.io/github/cortex-lab/phylib?branch=master)
-
-Electrophysiological data analysis library used by [phy](https://github.com/kwikteam/phy/), a spike sorting visualization software, and [ibllib](https://github.com/int-brain-lab/ibllib/).
-
-
+# phylib
+[![CI](https://github.com/cortex-lab/phylib/actions/workflows/ci.yml/badge.svg)](https://github.com/cortex-lab/phylib/actions/workflows/ci.yml)
+[![codecov.io](https://img.shields.io/codecov/c/github/cortex-lab/phylib.svg)](http://codecov.io/github/cortex-lab/phylib?branch=master)
+
+Electrophysiological data analysis library used by [phy](https://github.com/kwikteam/phy/), a spike sorting visualization software, and [ibllib](https://github.com/int-brain-lab/ibllib/).
+
+
 ## Contribution
 
 - participation in phylib is governed by the project [Code of Conduct](CODE_OF_CONDUCT.md)
 - run all tests using pytest `pytest phylib`
 - PR to master
 - keep `phylib/__init__.py` on the next development version (for example,
   `2.7.1.dev0`)
-- for a release, update `CHANGELOG.md`, remove the `.dev0` suffix, run the
-  tests, and tag the exact release commit
+- for a release, follow the steps below
 - after publishing, immediately bump `phylib/__init__.py` to the next
   `.dev0` version
-- publish to pypi:
-```shell
-rm -R dist
-rm -R build 
-python setup.py sdist bdist_wheel
-twine upload dist/*
+
+## Release
+
+Before merging the release PR, confirm maintainer approval and green CI. Update
+`CHANGELOG.md` with all changes since the previous release, replace the pending
+release date with the actual release date, and remove the `.dev0` suffix from
+`phylib/__init__.py`.
+
+Validate the final release checkout in a dedicated environment:
+
+```shell
+uv venv --python 3.12 .venv-release
+uv pip install --python .venv-release -r requirements-dev.txt -e . setuptools build twine
+.venv-release/bin/python -m flake8 phylib
+.venv-release/bin/python -m pytest phylib
 ```
+
+After the approved PR is merged, create an annotated tag from the merged release
+commit (for example, `git tag -a 2.7.1 -m "phylib 2.7.1"`). Build fresh artifacts
+from that tagged checkout into an empty output directory:
+
+```shell
+.venv-release/bin/python -m build --outdir dist/2.7.1
+.venv-release/bin/python -m twine check dist/2.7.1/*
+```
+
+Install the wheel in a separate clean environment and verify its version and
+imports. Verify the downstream phy template-less waveform regression against
+this wheel before publishing. Upload only the artifacts just checked:
+
+```shell
+.venv-release/bin/python -m twine upload dist/2.7.1/*
+```
+
+Verify installation of the published version from PyPI in another clean
+environment. Then bump `master` to `2.7.2.dev0` and add an `Unreleased` changelog
+section. Substitute the appropriate version numbers for subsequent releases.

phylib/__init__.py

@@ -22,7 +22,7 @@
 
 __author__ = 'Cyrille Rossant'
 __email__ = 'cyrille.rossant at gmail.com'
-__version__ = '2.7.1.dev0'
+__version__ = '2.7.1'
 __version_git__ = __version__ + _git_version()
 
 

phylib/io/alf.py

@@ -373,10 +373,11 @@ def get_waveforms_amp(templates):
         cha = np.max(templates, axis=1) - np.min(templates, axis=1)
         return np.max(cha, axis=1)
 
-    # we unwhiten the templates waveforms, this will expand the templates to the original non-sparse size
+    # Unwhitening expands the template waveforms to the original non-sparse size.
     templates_phy = np.zeros([nclu, templates['waveforms'].shape[1], nch], dtype=np.float32)
     for i in np.arange(templates_phy.shape[0]):
-        templates_phy[i] = np.matmul(templates['waveforms'][i], wm[templates['waveformsChannels'][i], :])
+        templates_phy[i] = np.matmul(
+            templates['waveforms'][i], wm[templates['waveformsChannels'][i], :])
 
     # the original templates have a rms of 1.0, so here we just need to normalize by rms
     rms_templates = np.sum(np.sum(templates['waveforms'] ** 2, axis=1), axis=1) ** 0.5
@@ -390,7 +391,8 @@ def get_waveforms_amp(templates):
     np.save(target_path.joinpath('channel_map.npy'), np.arange(nch))
     np.save(target_path.joinpath('templates.npy'), templates_phy)
 
-    np.save(target_path.joinpath('templates_ind.npy'), np.tile(np.arange(nclu)[np.newaxis, :], reps=[nch, 1]))
+    template_indices = np.tile(np.arange(nclu)[np.newaxis, :], reps=[nch, 1])
+    np.save(target_path.joinpath('templates_ind.npy'), template_indices)
 
     # if we have metrics information, output the ks2_label information
     if alf_path.joinpath('cluster.metrics.pqt').exists():

phylib/io/model.py

@@ -994,14 +994,14 @@ def get_waveforms(self, spike_ids, channel_ids=None):
             # Load from precomputed spikes.
             try:
                 return get_spike_waveforms(
-                spike_ids, channel_ids, spike_waveforms=self.spike_waveforms,
-                n_samples_waveforms=nsw)
+                    spike_ids, channel_ids, spike_waveforms=self.spike_waveforms,
+                    n_samples_waveforms=nsw)
             except AssertionError:
-              logger.warning(
-                  "Error when loading waveforms from precomputed waveforms, trying to load the raw data.")
-              spike_samples = self.spike_samples[spike_ids]
-              return extract_waveforms(
-                  self.traces, spike_samples, channel_ids, n_samples_waveforms=nsw)
+                logger.warning(
+                    "Error when loading precomputed waveforms; trying the raw data instead.")
+                spike_samples = self.spike_samples[spike_ids]
+                return extract_waveforms(
+                    self.traces, spike_samples, channel_ids, n_samples_waveforms=nsw)
         else:
             # Or load directly from raw data (slower).
             spike_samples = self.spike_samples[spike_ids]

phylib/io/tests/test_alf.py

@@ -41,7 +41,8 @@ def __init__(self, tempdir):
         np.save(p / 'amplitudes.npy', nr.uniform(low=0.5, high=1.5, size=self.ns))
         np.save(p / 'channel_positions.npy', np.c_[np.arange(self.nc), np.zeros(self.nc)])
         templates = np.random.normal(size=(self.nt, 50, self.nc))
-        templates = templates / (np.sum(np.sum(templates ** 2, axis=1), axis=1) ** .5)[:, np.newaxis, np.newaxis]
+        template_norms = np.sum(np.sum(templates ** 2, axis=1), axis=1) ** .5
+        templates = templates / template_norms[:, np.newaxis, np.newaxis]
         np.save(p / 'templates.npy', templates)
         np.save(p / 'similar_templates.npy', np.tile(np.arange(self.nt), (self.nt, 1)))
         np.save(p / 'channel_map.npy', np.c_[np.arange(self.nc)])

phylib/io/tests/test_array.py

@@ -425,6 +425,7 @@ def __getitem__(self, indices):
     sampled = _sample_spikes_evenly(SortedSpikeIDs(), 10)
     ae(sampled, np.linspace(0, 999_999, 10, dtype=np.int64))
 
+
 def test_select_spikes_1():
     spike_times = np.array([0., 1., 2., 3.3, 4.4])
     spike_clusters = np.array([1, 2, 1, 2, 4])

phylib/io/tests/test_datasets.py

@@ -141,10 +141,10 @@ def test_download_file(tempdir, mock_urls):
 
     assert_succeeds = (data_here and data_valid and
                        ((checksum_here == checksum_valid) or
-                        (not(checksum_here) and checksum_valid)))
+                        (not checksum_here and checksum_valid)))
 
     download_succeeds = (assert_succeeds or (data_here and
-                                             (not(data_valid) and not(checksum_here))))
+                                             (not data_valid and not checksum_here)))
 
     if download_succeeds:
         data = _dl(path)