use flake8 and pre-commit

.flake8

@@ -0,0 +1,20 @@
+[flake8]
+max-line-length = 100
+ignore =
+    # line break before a binary operator -> black does not adhere to PEP8
+    W503
+    # line break occured after a binary operator -> black does not adhere to PEP8
+    W504
+    # line too long -> we accept long comment lines; black gets rid of long code lines
+    E501
+    # whitespace before : -> black does not adhere to PEP8
+    E203
+    # leading '#' are fine if not used too often
+    E266
+    # it can be more convenient to use a bare 'except'
+    E722
+exclude = .git,__pycache__
+per-file-ignores =
+    tests/*: D
+    */__init__.py: F401
+    sopa/main.py: F401

.pre-commit-config.yaml

@@ -0,0 +1,30 @@
+fail_fast: false
+default_language_version:
+    python: python3
+default_stages:
+    - commit
+    - push
+minimum_pre_commit_version: 2.16.0
+repos:
+    - repo: https://github.com/psf/black
+      rev: 24.1.1
+      hooks:
+          - id: black
+    - repo: https://github.com/PyCQA/isort
+      rev: 5.13.2
+      hooks:
+          - id: isort
+    - repo: https://github.com/PyCQA/flake8
+      rev: 7.0.0
+      hooks:
+          - id: flake8
+    - repo: https://github.com/pre-commit/pre-commit-hooks
+      rev: v4.5.0
+      hooks:
+          - id: trailing-whitespace
+          - id: end-of-file-fixer
+          - id: check-yaml
+          - id: debug-statements
+          - id: double-quote-string-fixer
+          - id: name-tests-test
+          - id: requirements-txt-fixer

pyproject.toml

@@ -49,6 +49,7 @@ tangram-sc = { version = "^1.0.4", optional = true }
 
 snakemake = { version = "^7.32.4,<8.1.3", optional = true }
 pulp = { version = ">=2.3.1,<2.8", optional = true }
+flake8 = {version = "^7.0.0", extras = ["dev"]}
 
 [tool.poetry.extras]
 cellpose = ["cellpose", "opencv-python", "torch"]

sopa/annotation/tangram/run.py

@@ -166,7 +166,7 @@ def pp_adata(self, ad_sp_: AnnData, ad_sc_: AnnData, split: np.ndarray) -> AnnDa
 
         assert len(
             selection
-        ), f"No gene in common between the reference and the spatial adata object. Have you run transcript aggregation?"
+        ), "No gene in common between the reference and the spatial adata object. Have you run transcript aggregation?"
         log.info(f"Keeping {len(selection)} shared genes")
 
         for ad_ in [ad_sp_split, ad_sc_]:

sopa/cli/annotate.py

@@ -26,7 +26,7 @@ def fluorescence(
 
     sdata = read_zarr_standardized(sdata_path)
 
-    assert sdata.table is not None, f"Annotation requires `sdata.table` to be not None"
+    assert sdata.table is not None, "Annotation requires `sdata.table` to be not None"
 
     higher_z_score(sdata.table, marker_cell_dict, cell_type_key)
     sdata.table.write_zarr(Path(sdata_path) / "table" / "table")

sopa/cli/check.py

@@ -77,15 +77,15 @@ def reference(
 
 def _get(config, *args):
     for arg in args:
-        if not arg in config:
+        if arg not in config:
             return False
         config = config[arg]
     return config
 
 
 def _check_dict(config: dict, d: dict, log, prefix: str = "config"):
     for key, values in d.items():
-        if not key in config:
+        if key not in config:
             log.warn(f"Required config key {prefix}['{key}'] not found")
         elif isinstance(values, dict):
             _check_dict(config[key], values, log, f"{prefix}['{key}']")

sopa/cli/patchify.py

@@ -69,8 +69,6 @@ def baysor(
     ),
 ):
     """Prepare the patches for Baysor segmentation"""
-    from pathlib import Path
-
     from sopa._constants import SopaFiles, SopaKeys
     from sopa._sdata import get_key
     from sopa.io.standardize import read_zarr_standardized, sanity_check

sopa/cli/utils.py

@@ -1,7 +1,7 @@
 def _check_zip(names: list[str]):
     for name in names:
         if isinstance(name, str):
-            assert name.endswith(".zip"), f"Intermediate files names must end with .zip"
+            assert name.endswith(".zip"), "Intermediate files names must end with .zip"
 
 
 def _default_boundary_dir(sdata_path: str, directory_name: str):

sopa/io/explorer/_constants.py

@@ -97,7 +97,6 @@ def experiment_dict(run_name: str, region_name: str, num_cells: int, pixel_size:
         "instrument_sn": "N/A",
         "instrument_sw_version": "N/A",
         "analysis_sw_version": "xenium-1.3.0.5",
-        "experiment_uuid": "",
         "cassette_uuid": "",
         "roi_uuid": "",
         "z_step_size": 3.0,

sopa/io/explorer/converter.py

@@ -22,7 +22,7 @@
 def _check_explorer_directory(path: Path):
     assert (
         not path.exists() or path.is_dir()
-    ), f"A path to an existing file was provided. It should be a path to a directory."
+    ), "A path to an existing file was provided. It should be a path to a directory."
     path.mkdir(parents=True, exist_ok=True)
 
 
@@ -33,7 +33,7 @@ def _should_save(mode: str | None, character: str):
     assert len(mode) and mode[0] in [
         "-",
         "+",
-    ], f"Mode should be a string that starts with '+' or '-'"
+    ], "Mode should be a string that starts with '+' or '-'"
 
     return character in mode if mode[0] == "+" else character not in mode
 

sopa/io/explorer/images.py

@@ -144,7 +144,7 @@ def _set_colors(channel_names: list[str]) -> list[str]:
     ]
     valid_colors = [c for c in ExplorerConstants.COLORS if c != ExplorerConstants.NUCLEUS_COLOR]
     n_missing = sum(
-        not is_wavelength and not c in ExplorerConstants.KNOWN_CHANNELS
+        not is_wavelength and c not in ExplorerConstants.KNOWN_CHANNELS
         for c, is_wavelength in zip(channel_names, existing_wavelength)
     )
     colors_iterator: list = np.repeat(valid_colors, ceil(n_missing / len(valid_colors))).tolist()

sopa/io/explorer/shapes.py

@@ -7,7 +7,7 @@
 import zarr
 from shapely.geometry import Polygon
 
-from ._constants import ExplorerConstants, FileNames, cell_summary_attrs, group_attrs
+from ._constants import FileNames, cell_summary_attrs, group_attrs
 from .utils import explorer_file_path
 
 log = logging.getLogger(__name__)

sopa/io/imaging.py

@@ -272,7 +272,7 @@ def ome_tif(path: Path, as_image: bool = False) -> SpatialImage | SpatialData:
     image: da.Array = imread(path)
 
     if image.ndim == 4:
-        assert image.shape[0] == 1, f"4D images not supported"
+        assert image.shape[0] == 1, "4D images not supported"
         image = da.moveaxis(image[0], 2, 0)
         log.info(f"Transformed 4D image into a 3D image of shape (c, y, x) = {image.shape}")
     elif image.ndim != 3:

sopa/io/report/generate.py

@@ -56,7 +56,7 @@ def __init__(self, sdata: SpatialData):
         self.sdata = sdata
 
     def _table_has(self, key, default=False):
-        if not SopaKeys.UNS_KEY in self.sdata.table.uns:
+        if SopaKeys.UNS_KEY not in self.sdata.table.uns:
             return default
         return self.sdata.table.uns[SopaKeys.UNS_KEY].get(key, default)
 
@@ -70,7 +70,7 @@ def general_section(self):
                     "SpatialData information",
                     [
                         Paragraph(
-                            f"Sopa is using <a href='https://spatialdata.scverse.org/en/latest/'>SpatialData</a> under the hood. This is how the object looks like:"
+                            "Sopa is using <a href='https://spatialdata.scverse.org/en/latest/'>SpatialData</a> under the hood. This is how the object looks like:"
                         ),
                         CodeBlock(str(self.sdata)),
                     ],

sopa/io/standardize.py

@@ -14,7 +14,7 @@
 def sanity_check(sdata: SpatialData, delete_table: bool = False, warn: bool = False):
     assert (
         len(sdata.images) > 0
-    ), f"The spatialdata object has no image. Sopa is not designed for this."
+    ), "The spatialdata object has no image. Sopa is not designed for this."
 
     if len(sdata.images) != 1:
         message = f"The spatialdata object has {len(sdata.images)} images. We advise to run sopa on one image (which can have multiple channels and multiple scales)"

sopa/io/transcriptomics.py

@@ -21,8 +21,7 @@
 from spatialdata import SpatialData
 from spatialdata._logging import logger
 from spatialdata.models import Image2DModel, PointsModel, ShapesModel, TableModel
-from spatialdata.transformations import Affine, Identity
-from spatialdata.transformations.transformations import Identity, Scale
+from spatialdata.transformations import Affine, Identity, Scale
 from spatialdata_io._constants._constants import MerscopeKeys, XeniumKeys
 
 

sopa/segmentation/aggregate.py

@@ -130,7 +130,7 @@ def update_table(
 
         assert (
             average_intensities or does_count
-        ), f"You must choose at least one aggregation: transcripts or fluorescence intensities"
+        ), "You must choose at least one aggregation: transcripts or fluorescence intensities"
 
         if gene_column is not None:
             if self.table is not None:

sopa/segmentation/shapes.py

@@ -31,7 +31,7 @@ def solve_conflicts(
     n_cells = len(cells)
     resolved_indices = np.arange(n_cells)
 
-    assert n_cells > 0, f"No cells was segmented, cannot continue"
+    assert n_cells > 0, "No cells was segmented, cannot continue"
 
     tree = shapely.STRtree(cells)
     conflicts = tree.query(cells, predicate="intersects")

sopa/segmentation/stainings.py

@@ -4,7 +4,6 @@
 
 import geopandas as gpd
 import numpy as np
-import zarr
 from scipy.ndimage import gaussian_filter
 from shapely import affinity
 from shapely.geometry import Polygon, box

sopa/spatial/_build.py

@@ -42,7 +42,7 @@ def spatial_neighbors(
 
     assert (
         radius is None or len(radius) == 2
-    ), f"Radius is expected to be a tuple (min_radius, max_radius)"
+    ), "Radius is expected to be a tuple (min_radius, max_radius)"
 
     log.info("Computing delaunay graph")
 

sopa/spatial/morpho.py

@@ -141,7 +141,7 @@ def niches_geometry_stats(
     gdf = geometrize_niches(adata, niche_key, **geometrize_niches_kwargs)
     value_counts = gdf[niche_key].value_counts()
 
-    assert len(gdf), f"No niche geometry found, stats can't be computed"
+    assert len(gdf), "No niche geometry found, stats can't be computed"
 
     log.info(f"Computing pairwise distances between {len(gdf)} components")
     pairwise_distances: pd.DataFrame = gdf.geometry.apply(lambda g: gdf.distance(g))