Merge branch 'develop' of ssh://github.com/westpa/westpa into westpa3

jeremyleung521 · jeremyleung521 · commit 1da6ead12739 · 2025-05-05T12:05:49.000-04:00
diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml
@@ -16,6 +16,10 @@ on:
   release:
     types:
       - published
+  workflow_dispatch:
+    branches:
+      - 'westpa2'
+      - 'develop'
 
 jobs:
   build_wheels:
@@ -33,7 +37,7 @@ jobs:
         run: "brew install hdf5"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.23.0
+        uses: pypa/cibuildwheel@v2.23.3
         env:
           CIBW_SKIP: "pp* *-musllinux*"
           CIBW_BUILD: "cp3${{ matrix.python-version }}-*"
@@ -112,7 +116,7 @@ jobs:
     # alternatively, to publish when a GitHub Release is created, use the following rule:
     if: |
       github.repository == 'westpa/westpa' &&
-      (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v'))
+      (github.event_name == 'release' && github.event.action == 'published')
     steps:
       - uses: actions/download-artifact@v4
         with:
@@ -128,7 +132,7 @@ jobs:
 
   upload_pypi:
     name: PyPI
-    needs: [build_wheels, build_sdist]
+    needs: [upload_testpypi]
     runs-on: ubuntu-latest
     environment:
       name: pypi
diff --git a/.github/workflows/mirror.yaml b/.github/workflows/mirror.yaml
@@ -5,13 +5,16 @@ on:
     # Once a month on the 28th day at 4 pm UTC, which is ~11 am EST.
     - cron: "00 16 28 * *"
   workflow_dispatch:
+    branches:
+      - 'westpa2'
 
 jobs:
   mirror-develop-to-westpa2:
     runs-on: ubuntu-latest
     name: Mirror develop branch to westpa2 branch
+    if: github.repository_owner == 'westpa'
     steps:
-      - uses: actions/create-github-app-token@v1
+      - uses: actions/create-github-app-token@v2
         id: app-token
         with:
           app-id: ${{ vars.BRANCH_MIRROR_APPID }}
diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml
@@ -16,6 +16,10 @@ on:
     #   Scheduled workflows run on the latest commit on the default or base branch.
     #   (from https://help.github.com/en/actions/reference/events-that-trigger-workflows#scheduled-events-schedule)
     - cron: "30 15 * * 4"
+  workflow_dispatch:
+    branches:
+      - 'westpa2'
+      - 'develop'
 
 jobs:
   lint:
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -19,7 +19,7 @@ repos:
               | doc
           )
   - repo: https://github.com/pycqa/flake8
-    rev: 7.1.2
+    rev: 7.2.0
     hooks:
     -   id: flake8
         exclude: > 
diff --git a/src/westpa/cli/tools/w_assign.py b/src/westpa/cli/tools/w_assign.py
@@ -340,15 +340,16 @@ def load_config_from_west(self, scheme):
         from westpa.core._rc import bins_from_yaml_dict
 
         self.binning.mapper = bins_from_yaml_dict(config['analysis_schemes'][scheme]['bins'][0])
+
+        # Output file/folder wrangling
         path = os.path.join(os.getcwd(), config['directory'], scheme)
+        self.output_filename = os.path.join(path, 'assign.h5')
+
         try:
-            os.mkdir(config['directory'])
-            os.mkdir(path)
+            os.makedirs(path, exist_ok=True)
         except Exception:
             pass
 
-        self.output_filename = os.path.join(path, 'assign.h5')
-
     def load_state_file(self, state_filename):
         import yaml
 
diff --git a/src/westpa/cli/tools/w_direct.py b/src/westpa/cli/tools/w_direct.py
@@ -302,6 +302,9 @@ def w_kinavg(self):
         self.output_file.replace_dataset('target_flux_evolution', data=rate_evol, shuffle=True, compression=9)
 
     def go(self):
+        # Have class inherit user-provided self.output_filename as self.kinetics_filename
+        self.kinetics_filename = self.output_filename
+
         pi = self.progress.indicator
         with pi:
             self.w_kinavg()
@@ -474,6 +477,9 @@ def w_stateprobs(self):
         self.output_file.replace_dataset(name='state_pop_evolution', data=pop_evol, shuffle=True, compression=9)
 
     def go(self):
+        # Have class inherit user-provided self.output_filename as self.kinetics_filename
+        self.kinetics_filename = self.output_filename
+
         pi = self.progress.indicator
         with pi:
             self.w_stateprobs()
@@ -498,8 +504,9 @@ class DAll(DStateProbs, DKinAvg, DKinetics):
 '''
 
     def go(self):
-        # One minor issue; as this stands now, since it's inheriting from all the other classes, it needs
-        # a kinetics file to instantiate the other attributes.  We'll need to modify how the loading works, there.
+        # Have class inherit user-provided self.output_filename as self.kinetics_filename
+        self.kinetics_filename = self.output_filename
+
         pi = self.progress.indicator
         with pi:
             self.w_kinetics()
@@ -526,6 +533,9 @@ class DAverage(DStateProbs, DKinAvg):
 '''
 
     def go(self):
+        # Have class inherit user-provided self.output_filename as self.kinetics_filename
+        self.kinetics_filename = self.output_filename
+
         pi = self.progress.indicator
         with pi:
             self.w_kinavg()
diff --git a/src/westpa/cli/tools/w_ipa.py b/src/westpa/cli/tools/w_ipa.py
@@ -78,7 +78,6 @@ def __init__(self):
         # Well, whatever, we'll just set it to that for now.
         self.interface = 'matplotlib'
         self._scheme = None
-        global iteration
 
     def add_args(self, parser):
         self.progress.add_args(parser)
diff --git a/src/westpa/core/data_manager.py b/src/westpa/core/data_manager.py
@@ -24,6 +24,8 @@
 evolves.
 
 Version history:
+    Version 10
+        - BinMapper pickle, hash, and bin_target_count are now saved for iteration 1
     Version 9
         - Basis states are now saved as iter_segid instead of just segid as a pointer label.
         - Initial states are also saved in the iteration 0 file, with a negative sign.
@@ -66,7 +68,7 @@
 
 log = logging.getLogger(__name__)
 
-file_format_version = 9
+file_format_version = 10
 
 makepath = ExecutablePropagator.makepath
 
diff --git a/src/westpa/core/sim_manager.py b/src/westpa/core/sim_manager.py
@@ -437,6 +437,13 @@ def initialize_simulation(self, basis_states, target_states, start_states, segs_
         # Send the segments over to the data manager to commit to disk
         data_manager.current_iteration = 1
 
+        # Save BinMapper stuff for iteration 1
+        try:
+            pickled, hashed = self.we_driver.bin_mapper.pickle_and_hash()
+        except PickleError:
+            pickled = hashed = ''
+        data_manager.save_iter_binning(data_manager.current_iteration, hashed, pickled, target_counts)
+
         # Report statistics
         pstatus('Simulation prepared.')
         self.segments = {segment.seg_id: segment for segment in segments}
diff --git a/src/westpa/oldtools/aframe/plotting.py b/src/westpa/oldtools/aframe/plotting.py
@@ -1,3 +1,4 @@
+import sys
 import logging
 
 import numpy as np
@@ -76,15 +77,12 @@
 
 class PlottingMixin(AnalysisMixin):
     def __init__(self):
-        global matplotlib, pyplot
-
         super().__init__()
 
-        self.matplotlib_avail = matplotlib is not None and pyplot is not None
+        self.matplotlib_avail = 'matplotlib' in sys.modules and 'matplotlib.pyplot' in sys.modules
 
     def require_matplotlib(self):
-        global matplotlib
         if not self.matplotlib_avail:
             raise RuntimeError('matplotlib is not available')
         else:
-            return matplotlib
+            return sys.modules['matplotlib']
diff --git a/src/westpa/tools/kinetics_tool.py b/src/westpa/tools/kinetics_tool.py
@@ -91,8 +91,9 @@ class AverageCommands(WESTKineticsBase):
     def __init__(self, parent):
         # Ideally, this is stuff general to all the calculations we want to perform.
         super().__init__(parent)
-        self.kinetics_filename = None
-        self.kinetics_file = None
+        if not hasattr(self, 'kinetics_filename'):
+            self.kinetics_filename = None
+            self.kinetics_file = None
 
     def add_args(self, parser):
         iogroup = parser.add_argument_group('input/output options')
@@ -174,7 +175,9 @@ def add_args(self, parser):
         )
 
     def process_args(self, args):
-        self.kinetics_filename = args.kinetics
+        if self.kinetics_filename is None:
+            # Use default name if not inherited.
+            self.kinetics_filename = args.kinetics
 
         # Disable the bootstrap or the correlation analysis.
         self.mcbs_enable = args.bootstrap if args.bootstrap is not None else True
diff --git a/src/westpa/work_managers/processes.py b/src/westpa/work_managers/processes.py
@@ -27,11 +27,12 @@ class ProcessWorkManager(WorkManager):
     -----
 
     On MacOS, as of Python 3.8 the default start method for multiprocessing launching new processes was changed from fork to spawn.
+    On Linux, as of Python 3.14, the default start method for multiprocessing launching new processes was changed from fork to spawn.
     In general, spawn is more robust and efficient, however it requires serializability of everything being passed to the child process.
     In contrast, fork is much less memory efficient, as it makes a full copy of everything in the parent process.
     However, it does not require picklability.
 
-    So, on MacOS, the method for launching new processes is explicitly changed to fork from the (MacOS-specific) default of spawn.
+    So, on MacOS and Linux, the method for launching new processes is explicitly changed to fork from the (UNIX-specific) default of spawn.
     Unix should default to fork.
 
     See https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods and
@@ -48,7 +49,7 @@ def __init__(self, n_workers=None, shutdown_timeout=1):
         super().__init__()
 
         try:
-            if sys.platform == 'darwin':  # MacOS
+            if sys.platform in ['darwin', 'linux']:  # UNIX Platforms
                 multiprocessing.set_start_method('fork')
                 log.debug('setting multiprocessing start method to fork')
         except RuntimeError:
@@ -181,6 +182,15 @@ def shutdown(self):
                 else:
                     log.debug('worker process {:d} terminated gracefully with code {:d}'.format(worker.pid, worker.exitcode))
 
+                try:
+                    worker.close()  # Release all resources
+                except ValueError:
+                    try:
+                        if worker.is_alive():
+                            log.debug('worker process {:d} could not be closed'.format(worker.pid))
+                    except ValueError:
+                        pass  # Already closed.
+
             self._empty_queues()
             self.result_queue.put(result_shutdown_sentinel)
 
diff --git a/tests/conftest.py b/tests/conftest.py
@@ -3,8 +3,11 @@
 import glob
 from shutil import copyfile, copy
 
+import numpy as np
+
 import westpa
 
+
 REFERENCE_PATH = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'refs')
 
 H5_FILENAME = 'west.h5'
@@ -63,7 +66,11 @@ def ref_cfg(request, tmp_path):
     copy_ref(test_dir)
 
     copyfile(os.path.join(REFERENCE_PATH, 'west_init_ref.cfg'), CFG_FILENAME)
-    copyfile(os.path.join(REFERENCE_PATH, 'west_init_ref.h5'), "west_init_ref.h5")
+
+    if np.__version__ <= '2.0.0':
+        copyfile(os.path.join(REFERENCE_PATH, 'west_init_numpy1.h5'), "west_init_ref.h5")
+    else:
+        copyfile(os.path.join(REFERENCE_PATH, 'west_init_numpy2.h5'), "west_init_ref.h5")
 
     request.cls.cfg_filepath = CFG_FILENAME
     request.cls.h5_filepath = H5_FILENAME
@@ -87,7 +94,7 @@ def ref_initialized(request, tmp_path):
     os.chdir(test_dir)
     copy_ref(test_dir)
 
-    copyfile(os.path.join(REFERENCE_PATH, 'west_init_ref.h5'), H5_FILENAME)
+    copyfile(os.path.join(REFERENCE_PATH, 'west_init_numpy2.h5'), H5_FILENAME)
     copyfile(os.path.join(REFERENCE_PATH, 'west_init_ref.cfg'), CFG_FILENAME)
 
     request.cls.cfg_filepath = CFG_FILENAME
diff --git a/tests/refs/west_init_numpy1.h5 b/tests/refs/west_init_numpy1.h5
diff --git a/tests/refs/west_init_numpy2.h5 b/tests/refs/west_init_numpy2.h5
diff --git a/tests/test_oldtools/test_aframe.py b/tests/test_oldtools/test_aframe.py
@@ -0,0 +1,19 @@
+import sys
+
+import pytest
+
+from westpa.oldtools.aframe.plotting import PlottingMixin
+
+
+class TestPlotting:
+    def test_PlottingMixin(self, monkeypatch):
+        a = PlottingMixin()
+        with monkeypatch.context() as m:
+            # No matplotlib
+            m.setattr(a, 'matplotlib_avail', False)
+
+            with pytest.raises(RuntimeError):
+                a.require_matplotlib()
+
+        # With Matplotlib
+        assert a.require_matplotlib() == sys.modules['matplotlib']
diff --git a/tests/test_work_managers/test_processes.py b/tests/test_work_managers/test_processes.py

Original file line number	Diff line number	Diff line change
`@@ -19,7 +19,7 @@ repos:`
`19`	`19`	`\| doc`
`20`	`20`	`)`
`21`	`21`	`- repo: https://github.com/pycqa/flake8`
`22`		`- rev: 7.1.2`
	`22`	`+ rev: 7.2.0`
`23`	`23`	`hooks:`
`24`	`24`	`- id: flake8`
`25`	`25`	`exclude: >`