applied 'prettier' to reformat code, and pre-commit as dependency

.devcontainer/devcontainer.json

@@ -14,10 +14,7 @@
     // Configure tool-specific properties.
     "customizations": {
         "vscode": {
-            "extensions": [
-                "ms-python.python",
-                "editorconfig.editorconfig",
-            ],
+            "extensions": ["ms-python.python", "editorconfig.editorconfig"],
             "settings": {
                 "python.testing.pytestArgs": ["tests"],
                 "python.testing.unittestEnabled": false,

.github/actions/setup-poetry-env/action.yml

@@ -2,10 +2,10 @@ name: "setup-poetry-env"
 description: "Composite action to setup the Python and poetry environment."
 
 inputs:
-   python-version:
-     required: false
-     description: "The python version to use"
-     default: "3.11"
+  python-version:
+    required: false
+    description: "The python version to use"
+    default: "3.11"
 
 runs:
   using: "composite"

.github/workflows/main.yml

@@ -49,7 +49,6 @@ jobs:
       - name: Check typing
         run: poetry run mypy
 
-
       - name: Upload coverage reports to Codecov with GitHub Action on Python 3.11
         uses: codecov/codecov-action@v4
         if: ${{ matrix.python-version == '3.11' }}

.github/workflows/on-release-main.yml

@@ -6,7 +6,6 @@ on:
     branches: [main]
 
 jobs:
-
   publish:
     runs-on: ubuntu-latest
     steps:
@@ -28,7 +27,7 @@ jobs:
         env:
           PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
           RELEASE_VERSION: ${{ steps.vars.outputs.tag }}
-  
+
   deploy-docs:
     needs: publish
     runs-on: ubuntu-latest
@@ -41,4 +40,3 @@ jobs:
 
       - name: Deploy documentation
         run: poetry run mkdocs gh-deploy --force
-

LICENSE

@@ -19,4 +19,3 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
-

mkdocs.yml

@@ -15,9 +15,9 @@ plugins:
   - mkdocstrings:
       handlers:
         python:
-            setup_commands:
-                - import sys
-                - sys.path.append('../')
+          setup_commands:
+            - import sys
+            - sys.path.append('../')
 theme:
   name: material
   feature:

pyproject.toml

@@ -22,6 +22,7 @@ vtk = "^9.3.1"
 pyvcell-fvsolver = "^0.0.4"
 typer = "^0.12.3"
 h5py-stubs = "^0.1.1"
+pre-commit = "^3.8.0"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.2.0"

pyvcell/simdata/main.py

@@ -3,18 +3,18 @@
 import typer
 
 from pyvcell.simdata.mesh import CartesianMesh
-from pyvcell.simdata.simdata_models import PdeDataSet, DataFunctions
+from pyvcell.simdata.simdata_models import DataFunctions, PdeDataSet
 from pyvcell.simdata.zarr_writer import write_zarr
 
 app = typer.Typer()
 
 
 @app.command(name="vc_to_zarr", help="Convert a VCell FiniteVolume simulation dataset to Zarr")
 def n5_to_zarr(
-        sim_data_dir: Path = typer.Argument(..., help="path to vcell dataset directory"),
-        sim_id: int = typer.Argument(..., help="simulation id (e.g. 946368938)"),
-        job_id: int = typer.Argument(..., help="job id (e.g. 0"),
-        zarr_path: Path = typer.Argument(..., help="path to zarr dataset to write to")
+    sim_data_dir: Path = typer.Argument(..., help="path to vcell dataset directory"),
+    sim_id: int = typer.Argument(..., help="simulation id (e.g. 946368938)"),
+    job_id: int = typer.Argument(..., help="job id (e.g. 0"),
+    zarr_path: Path = typer.Argument(..., help="path to zarr dataset to write to"),
 ) -> None:
     pde_dataset = PdeDataSet(base_dir=sim_data_dir, log_filename=f"SimID_{sim_id}_{job_id}_.log")
     pde_dataset.read()

pyvcell/simdata/mesh.py

@@ -69,6 +69,7 @@ class CartesianMesh:
         }
     }
     """
+
     mesh_file: Path
     size: list[int]  # [x, y, z]
     extent: list[float]  # [x, y, z]
@@ -103,7 +104,7 @@ def dimension(self) -> int:
 
     def read(self) -> None:
         # read file as lines and parse
-        with (self.mesh_file.open('r') as f):
+        with self.mesh_file.open("r") as f:
             # get line enumerator from f
 
             iter_lines = iter(f.readlines())
@@ -157,7 +158,7 @@ def read(self) -> None:
             compressed_bytes = bytes.fromhex(hex_string)
             # assert len(compressed_bytes) == num_compressed_bytes
             uncompressed_bytes: bytes = zlib.decompress(compressed_bytes)
-            self.volume_region_map = np.frombuffer(uncompressed_bytes, dtype='<u2')  # unsigned 2-byte integers
+            self.volume_region_map = np.frombuffer(uncompressed_bytes, dtype="<u2")  # unsigned 2-byte integers
             assert self.volume_region_map.shape[0] == self.size[0] * self.size[1] * self.size[2]
             assert num_volume_elements == self.volume_region_map.shape[0]
             assert set(np.unique(self.volume_region_map)) == set([v[0] for v in self.volume_regions])
@@ -199,10 +200,16 @@ def get_membrane_region_index(self, mem_element_index: int) -> int:
         return int(self.membrane_elements[mem_element_index, 7])
 
     def get_membrane_region_ids(self, volume_domain_name: str) -> set[int]:
-        return set([mem_reg_id for mem_reg_id, vol_reg1, vol_reg2, surface in self.membrane_regions
-                    if self.volume_regions[vol_reg1][3] == volume_domain_name or
-                    self.volume_regions[vol_reg2][3] == volume_domain_name])
+        return set([
+            mem_reg_id
+            for mem_reg_id, vol_reg1, vol_reg2, surface in self.membrane_regions
+            if self.volume_regions[vol_reg1][3] == volume_domain_name
+            or self.volume_regions[vol_reg2][3] == volume_domain_name
+        ])
 
     def get_volume_region_ids(self, volume_domain_name: str) -> set[int]:
-        return set([vol_reg_id for vol_reg_id, subvol_id, volume, domain_name in self.volume_regions
-                    if domain_name == volume_domain_name])
+        return set([
+            vol_reg_id
+            for vol_reg_id, subvol_id, volume, domain_name in self.volume_regions
+            if domain_name == volume_domain_name
+        ])

pyvcell/simdata/postprocessing.py

@@ -2,7 +2,8 @@
 from pathlib import Path
 
 import numpy as np
-from h5py import Dataset, File as H5File, Group
+from h5py import Dataset, Group
+from h5py import File as H5File
 
 
 class StatisticType(IntEnum):
@@ -28,10 +29,11 @@ def get_dataset(self, hdf5_file: H5File, time_index: int) -> Dataset:
         if not isinstance(group_path_object, Group):
             raise ValueError(f"Expected a group at {self.group_path} but found {type(group_path_object)}")
         image_group: Group = group_path_object
-        dataset_path_object = image_group[f'time{time_index:06d}']
+        dataset_path_object = image_group[f"time{time_index:06d}"]
         if not isinstance(dataset_path_object, Dataset):
             raise ValueError(
-                f"Expected a dataset at {self.group_path}/time{time_index:06d} but found {type(dataset_path_object)}")
+                f"Expected a dataset at {self.group_path}/time{time_index:06d} but found {type(dataset_path_object)}"
+            )
         image_ds: Dataset = dataset_path_object
         return image_ds
 
@@ -45,17 +47,17 @@ def read(self, f: H5File) -> None:
         extents_list = []
         origin_list = []
         if "ExtentX" in image_group.attrs:
-            extents_list.append(image_group.attrs['ExtentX'])
+            extents_list.append(image_group.attrs["ExtentX"])
         if "ExtentY" in image_group.attrs:
-            extents_list.append(image_group.attrs['ExtentY'])
+            extents_list.append(image_group.attrs["ExtentY"])
         if "ExtentZ" in image_group.attrs:
-            extents_list.append(image_group.attrs['ExtentZ'])
+            extents_list.append(image_group.attrs["ExtentZ"])
         if "OriginX" in image_group.attrs:
-            origin_list.append(image_group.attrs['OriginX'])
+            origin_list.append(image_group.attrs["OriginX"])
         if "OriginY" in image_group.attrs:
-            origin_list.append(image_group.attrs['OriginY'])
+            origin_list.append(image_group.attrs["OriginY"])
         if "OriginZ" in image_group.attrs:
-            origin_list.append(image_group.attrs['OriginZ'])
+            origin_list.append(image_group.attrs["OriginZ"])
         self.extents = np.array(extents_list)
         self.origin = np.array(origin_list)
         self.shape = self.get_dataset(f, 0).shape
@@ -94,12 +96,13 @@ def __init__(self, postprocessing_hdf5_path: Path):
 
     def read(self) -> None:
         # read the file as hdf5
-        with H5File(name=self.postprocessing_hdf5_path, mode='r') as file:  # type: ignore
+        with H5File(name=self.postprocessing_hdf5_path, mode="r") as file:  # type: ignore
             # read dataset with path /PostProcessing/Times
-            postprocessing_times_object = file['/PostProcessing/Times']
+            postprocessing_times_object = file["/PostProcessing/Times"]
             if not isinstance(postprocessing_times_object, Dataset):
                 raise ValueError(
-                    f"Expected a dataset at /PostProcessing/Times but found {type(postprocessing_times_object)}")
+                    f"Expected a dataset at /PostProcessing/Times but found {type(postprocessing_times_object)}"
+                )
             times_ds: Dataset = postprocessing_times_object
             # read array from times dataset into a ndarray
             self.times = times_ds[()]
@@ -116,30 +119,35 @@ def read(self) -> None:
             # key=comp_3_name, value=b'C_cyt_max'
             # key=comp_3_unit, value=b'uM'
             #
-            var_stats_grp_object = file['/PostProcessing/VariableStatistics']
+            var_stats_grp_object = file["/PostProcessing/VariableStatistics"]
             if not isinstance(var_stats_grp_object, Group):
                 raise ValueError(
-                    f"Expected a group at /PostProcessing/VariableStatistics but found {type(var_stats_grp_object)}")
+                    f"Expected a group at /PostProcessing/VariableStatistics but found {type(var_stats_grp_object)}"
+                )
             var_stats_grp: Group = var_stats_grp_object
             # gather stat_var_name and stat_var_unit for each channel into dictionaries by channel
             var_name_by_channel: dict[int, str] = {}
             var_unit_by_channel: dict[int, str] = {}
             for k, v in var_stats_grp.attrs.items():
-                parts = k.split('_')
+                parts = k.split("_")
                 channel = int(parts[1])
                 if not isinstance(v, bytes):
                     raise ValueError(f"Expected a bytes object for attribute {k} but found {type(v)}")
-                value = v.decode('utf-8')
+                value = v.decode("utf-8")
                 if parts[2] == "name":
                     var_name_by_channel[channel] = value
                 elif parts[2] == "unit":
                     var_unit_by_channel[channel] = value
             # combine into a single list of VariableInfo objects, one for each channel
-            self.variables = [VariableInfo(stat_var_name=var_name_by_channel[i],
-                                           stat_var_unit=var_unit_by_channel[i],
-                                           stat_channel=i,
-                                           var_index=i // 4)
-                              for i in range(len(var_name_by_channel))]
+            self.variables = [
+                VariableInfo(
+                    stat_var_name=var_name_by_channel[i],
+                    stat_var_unit=var_unit_by_channel[i],
+                    stat_channel=i,
+                    var_index=i // 4,
+                )
+                for i in range(len(var_name_by_channel))
+            ]
 
             # within /PostProcessing/VariableStatistics, there are datasets for each time point
             # PostProcessing/VariableStatistics
@@ -152,11 +160,12 @@ def read(self) -> None:
             # we can read the data for each time point into a list of ndarrays
             statistics_raw: np.ndarray = np.zeros((len(self.times), len(self.variables)))
             for time_index in range(len(self.times)):
-                time_ds_object = var_stats_grp[f'time{time_index:06d}']
+                time_ds_object = var_stats_grp[f"time{time_index:06d}"]
                 if not isinstance(time_ds_object, Dataset):
                     raise ValueError(
                         f"Expected a dataset at /PostProcessing/VariableStatistics/time{time_index:06d} "
-                        f"but found {type(time_ds_object)}")
+                        f"but found {type(time_ds_object)}"
+                    )
                 time_ds: Dataset = time_ds_object
                 statistics_raw[time_index, :] = time_ds[()]
 
@@ -165,10 +174,10 @@ def read(self) -> None:
 
             # get list of child groups from /PostProcessing which are not Times or VariableStatistics
             # e.g. /PostProcessing/fluor
-            postprocessing_dataset = file['/PostProcessing']
+            postprocessing_dataset = file["/PostProcessing"]
             if not isinstance(postprocessing_dataset, Group):
                 raise ValueError(f"Expected a group at /PostProcessing but found {type(postprocessing_dataset)}")
-            image_groups = [k for k in postprocessing_dataset.keys() if k not in ['Times', 'VariableStatistics']]
+            image_groups = [k for k in postprocessing_dataset.keys() if k not in ["Times", "VariableStatistics"]]
 
             # for each image group, read the metadata to allow reading later
             for image_group in image_groups:
@@ -177,6 +186,6 @@ def read(self) -> None:
                 self.image_metadata.append(metadata)
 
     def read_image_data(self, image_metadata: ImageMetadata, time_index: int) -> np.ndarray:
-        with H5File(self.postprocessing_hdf5_path, 'r') as file:  # type: ignore
+        with H5File(self.postprocessing_hdf5_path, "r") as file:  # type: ignore
             image_ds = image_metadata.get_dataset(hdf5_file=file, time_index=time_index)
             return image_ds[()]  # type: ignore