cellfinder 1.1.0__tar.gz → 1.1.2__tar.gz

{cellfinder-1.1.0 → cellfinder-1.1.2}/.github/workflows/test_and_deploy.yml

@@ -35,6 +35,7 @@ jobs:
   test:
     needs: [linting, manifest]
     name: Run package tests
+    timeout-minutes: 60
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
@@ -139,11 +140,6 @@ jobs:
     if: github.event_name == 'push' && github.ref_type == 'tag'
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/download-artifact@v3
+    - uses: neuroinformatics-unit/actions/upload_pypi@v2
       with:
-        name: artifact
-        path: dist
-    - uses: pypa/gh-action-pypi-publish@v1.5.0
-      with:
-        user: __token__
-        password: ${{ secrets.TWINE_API_KEY }}
+        secret-pypi-key: ${{ secrets.TWINE_API_KEY }}

{cellfinder-1.1.0 → cellfinder-1.1.2}/.gitignore

@@ -143,3 +143,4 @@ benchmarks/env
 */_version.py
 
 .idea/
+.vscode/

cellfinder-1.1.2/CITATION.cff

@@ -0,0 +1,60 @@
+# This CITATION.cff file was generated with cffinit.
+# Visit https://bit.ly/cffinit to generate yours today!
+
+cff-version: 1.2.0
+title: cellfinder
+message: >-
+  If you use this software, please cite it using the
+  metadata from this file.
+type: software
+authors:
+  - given-names: Adam
+    family-names: Tyson
+    email: hello@brainglobe.info
+    affiliation: 'Sainsbury Wellcome Centre, University College London'
+  - given-names: Christian
+    family-names: Niedworok
+  - given-names: Charly
+    family-names: Rousseau
+  - given-names: BrainGlobe
+    family-names: Developers
+    email: hello@brainglobe.info
+repository-code: 'https://github.com/brainglobe/cellfinder'
+url: 'https://brainglobe.info'
+abstract: >-
+  Automated 3D cell detection in very large 3D images (e.g.,
+  serial two-photon or lightsheet volumes of whole mouse
+  brains).
+license: BSD-3-Clause
+date-released: '2024-01-05'
+year: 2024
+preferred-citation:
+  type: article
+  authors:
+  - given-names: Adam
+    family-names: Tyson
+    affiliation: 'Sainsbury Wellcome Centre, University College London'
+  - given-names: Charly V.
+    family-names: Rousseau
+  - given-names: Christian J.
+    family-names: Niedworok
+  - given-names: Sepiedeh
+    family-names: Keshavarzi
+  - given-names: Chryssanthi
+    family-names: Tsitoura
+  - given-names: Lee
+    family-names: Cossell
+  - given-names: Molly
+    family-names: Strom
+  - given-names: Troy W.
+    family-names: Margrie
+  doi: "10.1371/journal.pcbi.1009074"
+  url: "https://doi.org/10.1371/journal.pcbi.1009074"
+  journal: "PLOS Computational Biology"
+  month: 5
+  year: 2021
+  title: "A deep learning algorithm for 3D cell detection in whole mouse brain image datasets"
+  issue: 5
+  volume: 17
+  pages: 1-17
+citation-sentence: "This work makes use of the cellfinder detection algorithm,"

{cellfinder-1.1.0 → cellfinder-1.1.2}/MANIFEST.in

@@ -1,9 +1,8 @@
 include .napari/config.yml
+include CITATION.cff
 include LICENSE
 include README.md
 include requirements.txt
-include CF-CORE-README.md
-include CF-NAPARI-README.md
 
 exclude .pre-commit-config.yaml
 exclude .codecov.yml

{cellfinder-1.1.0 → cellfinder-1.1.2}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.1
 Name: cellfinder
-Version: 1.1.0
+Version: 1.1.2
 Summary: Automated 3D cell detection in large microscopy images
 Author-email: "Adam Tyson, Christian Niedworok, Charly Rousseau" <code@adamltyson.com>
 License: BSD-3-Clause
 Project-URL: Homepage, https://brainglobe.info/documentation/cellfinder/index.html
-Project-URL: Source Code, https://github.com/brainglobe/cellfinder-core
-Project-URL: Bug Tracker, https://github.com/brainglobe/cellfinder-core/issues
+Project-URL: Source Code, https://github.com/brainglobe/cellfinder
+Project-URL: Bug Tracker, https://github.com/brainglobe/cellfinder/issues
 Project-URL: Documentation, https://brainglobe.info/documentation/cellfinder/index.html
 Project-URL: User Support, https://forum.image.sc/tag/brainglobe
 Classifier: Development Status :: 4 - Beta
@@ -22,7 +22,8 @@ Classifier: Topic :: Scientific/Engineering :: Image Recognition
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: brainglobe-utils
+Requires-Dist: brainglobe-utils>=0.4.2
+Requires-Dist: brainglobe-napari-io>=0.3.4
 Requires-Dist: dask[array]
 Requires-Dist: fancylog>=0.0.7
 Requires-Dist: natsort
@@ -39,7 +40,6 @@ Requires-Dist: black; extra == "dev"
 Requires-Dist: pre-commit; extra == "dev"
 Requires-Dist: pyinstrument; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
-Requires-Dist: pytest-lazy-fixture; extra == "dev"
 Requires-Dist: pytest-mock; extra == "dev"
 Requires-Dist: pytest-qt; extra == "dev"
 Requires-Dist: pytest-timeout; extra == "dev"
@@ -59,7 +59,7 @@ Requires-Dist: qtpy; extra == "napari"
 [![Downloads](https://pepy.tech/badge/cellfinder-core)](https://pepy.tech/project/cellfinder)
 [![Wheel](https://img.shields.io/pypi/wheel/cellfinder-core.svg)](https://pypi.org/project/cellfinder)
 [![Development Status](https://img.shields.io/pypi/status/cellfinder-core.svg)](https://github.com/brainglobe/cellfinder)
-[![Tests](https://img.shields.io/github/workflow/status/brainglobe/cellfinder-core/tests)](https://github.com/brainglobe/cellfinder/actions)
+[![Tests](https://img.shields.io/github/actions/workflow/status/brainglobe/cellfinder/test_and_deploy.yml?branch=main)](https://github.com/brainglobe/cellfinder/actions)
 [![codecov](https://codecov.io/gh/brainglobe/cellfinder-core/branch/main/graph/badge.svg?token=nx1lhNI7ox)](https://codecov.io/gh/brainglobe/cellfinder)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black)
 [![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)

{cellfinder-1.1.0 → cellfinder-1.1.2}/README.md

@@ -3,7 +3,7 @@
 [![Downloads](https://pepy.tech/badge/cellfinder-core)](https://pepy.tech/project/cellfinder)
 [![Wheel](https://img.shields.io/pypi/wheel/cellfinder-core.svg)](https://pypi.org/project/cellfinder)
 [![Development Status](https://img.shields.io/pypi/status/cellfinder-core.svg)](https://github.com/brainglobe/cellfinder)
-[![Tests](https://img.shields.io/github/workflow/status/brainglobe/cellfinder-core/tests)](https://github.com/brainglobe/cellfinder/actions)
+[![Tests](https://img.shields.io/github/actions/workflow/status/brainglobe/cellfinder/test_and_deploy.yml?branch=main)](https://github.com/brainglobe/cellfinder/actions)
 [![codecov](https://codecov.io/gh/brainglobe/cellfinder-core/branch/main/graph/badge.svg?token=nx1lhNI7ox)](https://codecov.io/gh/brainglobe/cellfinder)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black)
 [![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/classify/cube_generator.py

@@ -197,9 +197,7 @@ class CubeGeneratorFromFile(Sequence):
         """
         return len(self.batches)
 
-    def __getitem__(
-        self, index: int
-    ) -> Union[
+    def __getitem__(self, index: int) -> Union[
         np.ndarray,
         Tuple[np.ndarray, List[Dict[str, float]]],
         Tuple[np.ndarray, Dict],
@@ -389,9 +387,7 @@ class CubeGeneratorFromDisk(Sequence):
         """
         return int(np.ceil(len(self.signal_list) / self.batch_size))
 
-    def __getitem__(
-        self, index: int
-    ) -> Union[
+    def __getitem__(self, index: int) -> Union[
         np.ndarray,
         Tuple[np.ndarray, List[Dict[str, float]]],
         Tuple[np.ndarray, Dict],

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/detect/detect.py

@@ -51,6 +51,16 @@ def calculate_parameters_in_pixels(
     ball_xy_size = int(round(ball_xy_size_um / mean_in_plane_pixel_size))
     ball_z_size = int(round(ball_z_size_um / float(voxel_sizes[0])))
 
+    if ball_z_size == 0:
+        raise ValueError(
+            "Ball z size has been calculated to be 0 voxels."
+            " This may be due to large axial spacing of your data or the "
+            "ball_z_size_um parameter being too small. "
+            "Please check input parameters are correct. "
+            "Note that cellfinder requires high resolution data in all "
+            "dimensions, so that cells can be detected in multiple "
+            "image planes."
+        )
     return soma_diameter, max_cluster_size, ball_xy_size, ball_z_size
 
 
@@ -76,11 +86,69 @@ def main(
     callback: Optional[Callable[[int], None]] = None,
 ) -> List[Cell]:
     """
+    Perform cell candidate detection on a 3D signal array.
+
     Parameters
     ----------
+    signal_array : numpy.ndarray
+        3D array representing the signal data.
+
+    start_plane : int
+        Index of the starting plane for detection.
+
+    end_plane : int
+        Index of the ending plane for detection.
+
+    voxel_sizes : Tuple[float, float, float]
+        Tuple of voxel sizes in each dimension (x, y, z).
+
+    soma_diameter : float
+        Diameter of the soma in physical units.
+
+    max_cluster_size : float
+        Maximum size of a cluster in physical units.
+
+    ball_xy_size : float
+        Size of the XY ball used for filtering in physical units.
+
+    ball_z_size : float
+        Size of the Z ball used for filtering in physical units.
+
+    ball_overlap_fraction : float
+        Fraction of overlap allowed between balls.
+
+    soma_spread_factor : float
+        Spread factor for soma size.
+
+    n_free_cpus : int
+        Number of free CPU cores available for parallel processing.
+
+    log_sigma_size : float
+        Size of the sigma for the log filter.
+
+    n_sds_above_mean_thresh : float
+        Number of standard deviations above the mean threshold.
+
+    outlier_keep : bool, optional
+        Whether to keep outliers during detection. Defaults to False.
+
+    artifact_keep : bool, optional
+        Whether to keep artifacts during detection. Defaults to False.
+
+    save_planes : bool, optional
+        Whether to save the planes during detection. Defaults to False.
+
+    plane_directory : str, optional
+        Directory path to save the planes. Defaults to None.
+
     callback : Callable[int], optional
         A callback function that is called every time a plane has finished
         being processed. Called with the plane number that has finished.
+
+    Returns
+    -------
+    List[Cell]
+        List of detected cells.
     """
     if not np.issubdtype(signal_array.dtype, np.integer):
         raise ValueError(
@@ -107,6 +175,7 @@ def main(
     if end_plane == -1:
         end_plane = len(signal_array)
     signal_array = signal_array[start_plane:end_plane]
+    signal_array = signal_array.astype(np.uint32)
 
     callback = callback or (lambda *args, **kwargs: None)
 
@@ -169,11 +238,11 @@ def main(
         # processes.
         cells = mp_3d_filter.process(async_results, locks, callback=callback)
 
-    print(
-        "Detection complete - all planes done in : {}".format(
-            datetime.now() - start_time
-        )
+    time_elapsed = datetime.now() - start_time
+    logger.debug(
+        f"All Planes done. Found {len(cells)} cells in {format(time_elapsed)}"
     )
+    print("Detection complete - all planes done in : {}".format(time_elapsed))
     return cells
 
 

cellfinder-1.1.2/cellfinder/core/detect/filters/plane/classical_filter.py

@@ -0,0 +1,45 @@
+import numpy as np
+from scipy.ndimage import gaussian_filter, laplace
+from scipy.signal import medfilt2d
+
+
+def enhance_peaks(
+    img: np.ndarray, clipping_value: float, gaussian_sigma: float = 2.5
+) -> np.ndarray:
+    """
+    Enhances the peaks (bright pixels) in an input image.
+
+    Parameters:
+    ----------
+    img : np.ndarray
+        Input image.
+    clipping_value : float
+        Maximum value for the enhanced image.
+    gaussian_sigma : float, optional
+        Standard deviation for the Gaussian filter. Default is 2.5.
+
+    Returns:
+    -------
+    np.ndarray
+        Enhanced image with peaks.
+
+    Notes:
+    ------
+    The enhancement process includes the following steps:
+    1. Applying a 2D median filter.
+    2. Applying a Laplacian of Gaussian filter (LoG).
+    3. Multiplying by -1 (bright spots respond negative in a LoG).
+    4. Rescaling image values to range from 0 to clipping value.
+    """
+    type_in = img.dtype
+    filtered_img = medfilt2d(img.astype(np.float64))
+    filtered_img = gaussian_filter(filtered_img, gaussian_sigma)
+    filtered_img = laplace(filtered_img)
+    filtered_img *= -1
+
+    filtered_img -= filtered_img.min()
+    filtered_img /= filtered_img.max()
+
+    # To leave room to label in the 3d detection.
+    filtered_img *= clipping_value
+    return filtered_img.astype(type_in)

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/detect/filters/volume/ball_filter.py

@@ -104,7 +104,7 @@ class BallFilter:
 
         # Stores the current planes that are being filtered
         self.volume = np.empty(
-            (plane_width, plane_height, ball_z_size), dtype=np.uint16
+            (plane_width, plane_height, ball_z_size), dtype=np.uint32
         )
         # Index of the middle plane in the volume
         self.middle_z_idx = int(np.floor(ball_z_size / 2))
@@ -165,7 +165,7 @@ class BallFilter:
         Get the plane in the middle of self.volume.
         """
         z = self.middle_z_idx
-        return np.array(self.volume[:, :, z], dtype=np.uint16)
+        return np.array(self.volume[:, :, z], dtype=np.uint32)
 
     def walk(self) -> None:  # Highly optimised because most time critical
         ball_radius = self.ball_xy_size // 2
@@ -327,6 +327,6 @@ def _walk(
                     THRESHOLD_VALUE,
                     kernel,
                 ):
-                    volume[
-                        ball_centre_x, ball_centre_y, middle_z
-                    ] = SOMA_CENTRE_VALUE
+                    volume[ball_centre_x, ball_centre_y, middle_z] = (
+                        SOMA_CENTRE_VALUE
+                    )

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/detect/filters/volume/structure_splitting.py

@@ -28,7 +28,7 @@ def coords_to_volume(
     expanded_shape = [
         dim_size + ball_diameter for dim_size in get_shape(xs, ys, zs)
     ]
-    volume = np.zeros(expanded_shape, dtype=np.uint16)
+    volume = np.zeros(expanded_shape, dtype=np.uint32)
 
     x_min, y_min, z_min = xs.min(), ys.min(), zs.min()
 
@@ -38,7 +38,7 @@ def coords_to_volume(
 
     # OPTIMISE: vectorize
     for rel_x, rel_y, rel_z in zip(relative_xs, relative_ys, relative_zs):
-        volume[rel_x, rel_y, rel_z] = 65534
+        volume[rel_x, rel_y, rel_z] = np.iinfo(volume.dtype).max - 1
     return volume
 
 
@@ -49,6 +49,26 @@ def ball_filter_imgs(
     ball_xy_size: int = 3,
     ball_z_size: int = 3,
 ) -> Tuple[np.ndarray, np.ndarray]:
+    """
+    Apply ball filtering to a 3D volume and detect cell centres.
+
+    Uses the `BallFilter` class to perform ball filtering on the volume
+    and the `CellDetector` class to detect cell centres.
+
+    Args:
+        volume (np.ndarray): The 3D volume to be filtered.
+        threshold_value (int): The threshold value for ball filtering.
+        soma_centre_value (int): The value representing the soma centre.
+        ball_xy_size (int, optional):
+            The size of the ball filter in the XY plane. Defaults to 3.
+        ball_z_size (int, optional):
+            The size of the ball filter in the Z plane. Defaults to 3.
+
+    Returns:
+        Tuple[np.ndarray, np.ndarray]:
+            A tuple containing the filtered volume and the cell centres.
+
+    """
     # OPTIMISE: reuse ball filter instance
 
     good_tiles_mask = np.ones((1, 1, volume.shape[2]), dtype=bool)
@@ -71,10 +91,10 @@ def ball_filter_imgs(
     )
 
     # FIXME: hard coded type
-    ball_filtered_volume = np.zeros(volume.shape, dtype=np.uint16)
+    ball_filtered_volume = np.zeros(volume.shape, dtype=np.uint32)
     previous_plane = None
     for z in range(volume.shape[2]):
-        bf.append(volume[:, :, z].astype(np.uint16), good_tiles_mask[:, :, z])
+        bf.append(volume[:, :, z].astype(np.uint32), good_tiles_mask[:, :, z])
         if bf.ready:
             bf.walk()
             middle_plane = bf.get_middle_plane()
@@ -89,11 +109,24 @@ def ball_filter_imgs(
 def iterative_ball_filter(
     volume: np.ndarray, n_iter: int = 10
 ) -> Tuple[List[int], List[np.ndarray]]:
+    """
+    Apply iterative ball filtering to the given volume.
+    The volume is eroded at each iteration, by subtracting 1 from the volume.
+
+    Parameters:
+        volume (np.ndarray): The input volume.
+        n_iter (int): The number of iterations to perform. Default is 10.
+
+    Returns:
+        Tuple[List[int], List[np.ndarray]]: A tuple containing two lists:
+            The structures found in each iteration.
+            The cell centres found in each iteration.
+    """
     ns = []
     centres = []
 
-    threshold_value = 65534
-    soma_centre_value = 65535
+    threshold_value = np.iinfo(volume.dtype).max - 1
+    soma_centre_value = np.iinfo(volume.dtype).max
 
     vol = volume.copy()  # TODO: check if required
 
@@ -131,6 +164,21 @@ def check_centre_in_cuboid(centre: np.ndarray, max_coords: np.ndarray) -> bool:
 def split_cells(
     cell_points: np.ndarray, outlier_keep: bool = False
 ) -> np.ndarray:
+    """
+    Split the given cell points into individual cell centres.
+
+    Args:
+        cell_points (np.ndarray): Array of cell points with shape (N, 3),
+            where N is the number of cell points and each point is represented
+            by its x, y, and z coordinates.
+        outlier_keep (bool, optional): Flag indicating whether to keep outliers
+            during the splitting process. Defaults to False.
+
+    Returns:
+        np.ndarray: Array of absolute cell centres with shape (M, 3),
+            where M is the number of individual cells and each centre is
+            represented by its x, y, and z coordinates.
+    """
     orig_centre = get_structure_centre(cell_points)
 
     xs = cell_points[:, 0]

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/detect/filters/volume/volume_filter.py

@@ -142,6 +142,10 @@ class VolumeFilter(object):
         )
 
         cells = []
+
+        logger.debug(
+            f"Processing {len(self.cell_detector.coords_maps.items())} cells"
+        )
         for cell_id, cell_points in self.cell_detector.coords_maps.items():
             cell_volume = len(cell_points)
 
@@ -191,6 +195,7 @@ class VolumeFilter(object):
                         )
                     )
 
+        logger.debug("Finished splitting cell clusters.")
         return cells
 
 

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/download/cli.py

@@ -3,7 +3,7 @@ from argparse import ArgumentDefaultsHelpFormatter, ArgumentParser
 from pathlib import Path
 
 from cellfinder.core.download import models
-from cellfinder.core.download.download import amend_cfg
+from cellfinder.core.download.download import amend_user_configuration
 
 home = Path.home()
 DEFAULT_DOWNLOAD_DIRECTORY = home / ".cellfinder"
@@ -65,7 +65,7 @@ def main():
         model_path = models.main(args.model, args.install_path)
 
     if not args.no_amend_config:
-        amend_cfg(new_model_path=model_path)
+        amend_user_configuration(new_model_path=model_path)
 
 
 if __name__ == "__main__":

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/download/download.py

@@ -7,8 +7,8 @@ from brainglobe_utils.general.config import get_config_obj
 from brainglobe_utils.general.system import disk_free_gb
 
 from cellfinder.core.tools.source_files import (
-    source_config_cellfinder,
-    source_custom_config_cellfinder,
+    default_configuration_path,
+    user_specific_configuration_path,
 )
 
 
@@ -75,16 +75,45 @@ def download(
         os.remove(download_path)
 
 
-def amend_cfg(new_model_path=None):
-    print("Ensuring custom config file is correct")
-
-    original_config = source_config_cellfinder()
-    new_config = source_custom_config_cellfinder()
-    if new_model_path is not None:
-        write_model_to_cfg(new_model_path, original_config, new_config)
+def amend_user_configuration(new_model_path=None) -> None:
+    """
+    Amends the user configuration to contain the configuration
+    in new_model_path, if specified.
 
+    Parameters
+    ----------
+    new_model_path : str, optional
+        The path to the new model configuration.
+    """
+    print("(Over-)writing custom user configuration")
 
-def write_model_to_cfg(new_model_path, orig_config, custom_config):
+    original_config = default_configuration_path()
+    new_config = user_specific_configuration_path()
+    if new_model_path is not None:
+        write_model_to_config(new_model_path, original_config, new_config)
+
+
+def write_model_to_config(new_model_path, orig_config, custom_config):
+    """
+    Update the model path in the custom configuration file, by
+    reading the lines in the original configuration file, replacing
+    the line starting with "model_path =" and writing these
+    lines to the custom file.
+
+    Parameters
+    ----------
+    new_model_path : str
+        The new path to the model.
+    orig_config : str
+        The path to the original configuration file.
+    custom_config : str
+        The path to the custom configuration file to be created.
+
+    Returns
+    -------
+    None
+
+    """
     config_obj = get_config_obj(orig_config)
     model_conf = config_obj["model"]
     orig_path = model_conf["model_path"]

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/main.py

@@ -2,6 +2,7 @@
 N.B imports are within functions to prevent tensorflow being imported before
 it's warnings are silenced
 """
+
 import os
 from typing import Callable, List, Optional, Tuple
 

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/tools/prep.py

@@ -3,6 +3,7 @@ prep
 ==================
 Functions to prepare files and directories needed for other functions
 """
+
 import os
 from pathlib import Path
 from typing import Optional
@@ -13,8 +14,8 @@ from brainglobe_utils.general.system import get_num_processes
 import cellfinder.core.tools.tf as tf_tools
 from cellfinder.core import logger
 from cellfinder.core.download import models as model_download
-from cellfinder.core.download.download import amend_cfg
-from cellfinder.core.tools.source_files import source_custom_config_cellfinder
+from cellfinder.core.download.download import amend_user_configuration
+from cellfinder.core.tools.source_files import user_specific_configuration_path
 
 home = Path.home()
 DEFAULT_INSTALL_PATH = home / ".cellfinder"
@@ -48,18 +49,18 @@ def prep_models(
     if model_weights_path is None:
         logger.debug("No model supplied, so using the default")
 
-        config_file = source_custom_config_cellfinder()
+        config_file = user_specific_configuration_path()
 
         if not Path(config_file).exists():
             logger.debug("Custom config does not exist, downloading models")
             model_path = model_download.main(model_name, install_path)
-            amend_cfg(new_model_path=model_path)
+            amend_user_configuration(new_model_path=model_path)
 
         model_weights = get_model_weights(config_file)
         if not model_weights.exists():
             logger.debug("Model weights do not exist, downloading")
             model_path = model_download.main(model_name, install_path)
-            amend_cfg(new_model_path=model_path)
+            amend_user_configuration(new_model_path=model_path)
             model_weights = get_model_weights(config_file)
     else:
         model_weights = Path(model_weights_path)

cellfinder-1.1.2/cellfinder/core/tools/source_files.py

@@ -0,0 +1,27 @@
+from pathlib import Path
+
+
+def default_configuration_path():
+    """
+    Returns the default configuration path for cellfinder.
+
+    Returns:
+        Path: The default configuration path.
+    """
+    return Path(__file__).parent.parent / "config" / "cellfinder.conf"
+
+
+def user_specific_configuration_path():
+    """
+    Returns the path to the user-specific configuration file for cellfinder.
+
+    This function returns the path to the user-specific configuration file
+    for cellfinder. The user-specific configuration file is located in the
+    user's home directory under the ".cellfinder" folder and is named
+    "cellfinder.conf.custom".
+
+    Returns:
+        Path: The path to the custom configuration file.
+
+    """
+    return Path.home() / ".cellfinder" / "cellfinder.conf.custom"

{cellfinder-1.1.0 → cellfinder-1.1.2}/cellfinder/core/train/train_yml.py

@@ -338,7 +338,10 @@ def run(
 
     ensure_directory_exists(output_dir)
     model_weights = prep_model_weights(
-        install_path, model_weights, model, n_free_cpus
+        model_weights=model_weights,
+        install_path=install_path,
+        model_name=model,
+        n_free_cpus=n_free_cpus,
     )
 
     yaml_contents = parse_yaml(yaml_file)