Merge pull request #34 from HiDiHlabs/update

Updates and refactors

Author: niklasmueboe

.github/workflows/cibuildwheel.yml

@@ -24,7 +24,7 @@ jobs:
       - name: set up python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
 
       - uses: actions-rust-lang/setup-rust-toolchain@v1
 

.pre-commit-config.yaml

@@ -18,20 +18,12 @@ repos:
       - id: no-commit-to-branch
         args: [--branch=main]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.4
+    rev: v0.11.12
     hooks:
-      - id: ruff
-        args: [--fix]
-  - repo: https://github.com/PyCQA/isort
-    rev: 6.0.1
-    hooks:
-      - id: isort
-  - repo: https://github.com/psf/black
-    rev: 25.1.0
-    hooks:
-      - id: black
+      - id: ruff-check
+      - id: ruff-format
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.15.0
+    rev: v1.16.0
     hooks:
       - id: mypy
         additional_dependencies:
@@ -49,7 +41,7 @@ repos:
         additional_dependencies:
           - tomli
   - repo: https://github.com/google/yamlfmt
-    rev: v0.16.0
+    rev: v0.17.0
     hooks:
       - id: yamlfmt
   - repo: https://github.com/executablebooks/mdformat

.readthedocs.yaml

@@ -2,7 +2,7 @@ version: 2
 build:
   os: ubuntu-lts-latest
   tools:
-    python: "3.10"
+    python: "3.11"
     rust: latest
 sphinx:
   configuration: docs/source/conf.py

Cargo.toml

@@ -2,7 +2,7 @@
 name         = "_utils_rust"
 version      = "0.1.0"
 edition      = "2021"
-rust-version = "1.76.0"
+rust-version = "1.85.0"
 
 [lib]
 name       = "_utils_rust"
@@ -11,14 +11,14 @@ crate-type = ["cdylib"]
 [dependencies]
 bincode       = { version = "1.3" }
 indexmap      = { version = ">= 2.1, < 2.6", features = ["rayon"] }
-itertools     = { version = "0.12.1" }
-ndarray       = { version = "0.15.6", features = ["rayon"] }
-ndarray-stats = { version = "0.5.1" }
+itertools     = { version = "0.13" }
+ndarray       = { version = "0.16", features = ["rayon"] }
+ndarray-stats = { version = "0.6" }
 num           = { version = "0.4.1" }
-numpy         = { version = "0.21" }
-polars        = { version = "0.41", features = ["partition_by", "dtype-categorical"] }
-polars-arrow  = { version = "0.41" }
-pyo3          = { version = "0.21", features = ["extension-module"] }
-pyo3-polars   = { version = "0.15" }
+numpy         = { version = "0.24" }
+polars        = { version = "0.48", features = ["partition_by", "dtype-categorical"] }
+polars-arrow  = { version = "0.48" }
+pyo3          = { version = "0.24.2", features = ["extension-module"] }
+pyo3-polars   = { version = "0.21", features = ["dtype-categorical"] }
 rayon         = { version = "1.8" }
-sprs          = { version = "= 0.11.1", features = ["serde"] }
+sprs          = { version = "0.11.2", features = ["serde"] }

README.md

@@ -1,9 +1,7 @@
 # sainsc
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Code style: Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
-[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
 [![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](http://mypy-lang.org/)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
 

docs/source/tutorials/VisiumHD_CRC.ipynb

@@ -647,7 +647,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": null,
    "id": "672b4258-dc91-4fb0-9158-eeb0870c83c9",
    "metadata": {
     "editable": true,
@@ -664,14 +664,11 @@
     "from matplotlib.colors import to_rgb\n",
     "from scipy.sparse import coo_array\n",
     "\n",
-    "from sainsc.lazykde._utils import _apply_color\n",
-    "\n",
     "background = \"black\"\n",
     "\n",
     "cmap_ls = [cmap[celltype] for celltype in adata_16um.obs[\"leiden\"].cat.categories]\n",
-    "color_map = tuple(\n",
-    "    (np.array(to_rgb(c)) * 255).round().astype(np.uint8) for c in [background] + cmap_ls\n",
-    ")\n",
+    "color_map = np.array([to_rgb(c) for c in [background] + cmap_ls])\n",
+    "\n",
     "\n",
     "celltype = adata_16um.obs[\"leiden\"].cat.codes\n",
     "x = adata_16um.obs[\"array_row\"]\n",
@@ -681,7 +678,7 @@
     "ctmap_16um = coo_array(\n",
     "    (celltype + 1, (x, y)), shape=[ceil(i / 8) for i in visium_hd.shape]\n",
     ")\n",
-    "ctmap_16um = _apply_color((ctmap_16um).toarray(), color_map)"
+    "ctmap_16um = np.take(color_map, ctmap_16um.toarray(), axis=0)"
    ]
   },
   {

pyproject.toml

@@ -1,14 +1,15 @@
 [build-system]
-requires      = ["setuptools>=61.0.0", "setuptools_scm[toml]>=6.2", "setuptools-rust>=1.7"]
+requires      = ["setuptools>=64", "setuptools-scm>=8", "setuptools-rust>=1.10"]
 build-backend = "setuptools.build_meta"
 
 
 [project]
 name            = "sainsc"
 description     = "Segmentation-free Analysis of In Situ Capture data"
 readme          = { file = "README.md", content-type = "text/markdown" }
-license         = { file = "LICENSE" }
-requires-python = ">=3.10,<3.13"
+license         = "MIT"
+license-files   = ["LICENSE"]
+requires-python = ">=3.11,<3.14"
 dynamic         = ["version"]
 
 authors = [
@@ -17,20 +18,17 @@ authors = [
 dependencies = [
     "anndata>=0.9",
     "h5py>=3",
-    "matplotlib",
+    "matplotlib>=3.7",
     "matplotlib-scalebar",
-    "numba>=0.44",
-    "numpy>=1.21",
-    "pandas",
+    "numpy>=1.24",
+    "pandas>=2.0",
     "polars[pandas]>=1",
-    "scikit-image>=0.18",
-    "scipy>=1.9",
+    "scikit-image>=0.20",
+    "scipy>=1.10",
     "seaborn>=0.11",
-    "typing-extensions>=4",
 ]
 classifiers = [
     "Intended Audience :: Science/Research",
-    "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
     "Programming Language :: Python",
     "Programming Language :: Python :: 3",
@@ -72,20 +70,21 @@ include = ["sainsc", "sainsc.io", "sainsc.lazykde", "sainsc.utils"]
 [[tool.setuptools-rust.ext-modules]]
 target = "sainsc._utils_rust"
 
-[tool.isort]
-profile = "black"
-
-[tool.black]
-target-version = ["py310", "py311", "py312"]
 
 [tool.ruff]
-target-version = "py310"
+target-version = "py311"
+
+fix        = true
+show-fixes = true
+
+[tool.ruff.lint]
+extend-select = ["I"]
 
 [tool.ruff.lint.per-file-ignores]
 "__init__.py" = ["E402"]
 
 [tool.mypy]
-python_version         = "3.10"
+python_version         = "3.11"
 ignore_missing_imports = true
 warn_no_return         = false
 packages               = "sainsc"

sainsc/_utils_rust.pyi

@@ -1,7 +1,8 @@
+from typing import Self
+
 import numpy as np
 from numpy.typing import NDArray
 from polars import DataFrame
-from typing_extensions import Self
 
 from ._typealias import _Csx, _CsxArray
 

sainsc/lazykde/_LazyKDE.py

@@ -1,6 +1,5 @@
 from collections.abc import Iterable
-from itertools import chain
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING, Any, Self, TypeVar
 
 import matplotlib.pyplot as plt
 import numpy as np
@@ -14,11 +13,9 @@
 from matplotlib.patches import Patch
 from matplotlib_scalebar.scalebar import ScaleBar
 from mpl_toolkits import axes_grid1
-from numba import njit
 from numpy.typing import NDArray
 from scipy.sparse import coo_array, csc_array, csr_array
 from skimage.feature import peak_local_max
-from typing_extensions import Self
 
 from .._typealias import _Cmap, _Csx, _CsxArray, _Local_Max, _RangeTuple2D
 from .._utils import _raise_module_load_error, _validate_n_threads, validate_threads
@@ -33,7 +30,6 @@
 from ._utils import (
     SCALEBAR_PARAMS,
     CosineCelltypeCallable,
-    _apply_color,
     _filter_blobs,
     _get_cell_dtype,
     _localmax_anndata,
@@ -358,7 +354,6 @@ def load_local_maxima(
                 }
 
                 if self.total_mRNA_KDE is not None:
-
                     sdata_dict["total_mRNA"] = Image2DModel.parse(
                         np.atleast_3d(self.total_mRNA_KDE).T, dims=("c", "y", "x")
                     )
@@ -416,7 +411,6 @@ def load_local_maxima(
             return adata
 
     def _load_KDE_maxima(self, genes: list[str]) -> csc_array | csr_array:
-
         assert self.local_maxima is not None
         if self.kernel is None:
             raise ValueError("`kernel` must be set before running KDE")
@@ -461,17 +455,13 @@ def filter_background(
             If cell type-specific thresholds do not include all cell types or if
             using cell type-specific thresholds before cell type assignment.
         """
+        T = TypeVar("T")
 
-        @njit
         def _map_celltype_to_value(
-            ct_map: NDArray[np.integer], thresholds: tuple[float, ...]
+            ct_map: NDArray[np.integer], thresholds: dict[T, float], classes: list[T]
         ) -> NDArray[np.floating]:
-            values = np.zeros(shape=ct_map.shape, dtype=float)
-            for i in range(ct_map.shape[0]):
-                for j in range(ct_map.shape[1]):
-                    if ct_map[i, j] >= 0:
-                        values[i, j] = thresholds[ct_map[i, j]]
-            return values
+            ordered_thresholds = np.array([0] + [thresholds[ct] for ct in classes])
+            return np.take(ordered_thresholds, ct_map + 1)
 
         if self.total_mRNA_KDE is None:
             raise ValueError(
@@ -485,8 +475,9 @@ def _map_celltype_to_value(
                 )
             elif not all([ct in min_norm.keys() for ct in self.celltypes]):
                 raise ValueError("'min_norm' does not contain all celltypes.")
-            idx2threshold = tuple(min_norm[ct] for ct in self.celltypes)
-            threshold = _map_celltype_to_value(self.celltype_map, idx2threshold)
+            threshold = _map_celltype_to_value(
+                self.celltype_map, min_norm, self.celltypes
+            )
             background = self.total_mRNA_KDE < threshold
         else:
             background = self.total_mRNA_KDE < min_norm
@@ -503,8 +494,9 @@ def _map_celltype_to_value(
                     )
                 elif not all([ct in min_cosine.keys() for ct in self.celltypes]):
                     raise ValueError("'min_cosine' does not contain all celltypes.")
-                idx2threshold = tuple(min_cosine[ct] for ct in self.celltypes)
-                threshold = _map_celltype_to_value(self.celltype_map, idx2threshold)
+                threshold = _map_celltype_to_value(
+                    self.celltype_map, min_cosine, self.celltypes
+                )
                 background |= self.cosine_similarity <= threshold
             else:
                 background |= self.cosine_similarity <= min_cosine
@@ -521,8 +513,9 @@ def _map_celltype_to_value(
                     )
                 elif not all([ct in min_assignment.keys() for ct in self.celltypes]):
                     raise ValueError("'min_assignment' does not contain all celltypes.")
-                idx2threshold = tuple(min_assignment[ct] for ct in self.celltypes)
-                threshold = _map_celltype_to_value(self.celltype_map, idx2threshold)
+                threshold = _map_celltype_to_value(
+                    self.celltype_map, min_assignment, self.celltypes
+                )
                 background |= self.assignment_score <= threshold
             else:
                 background |= self.assignment_score <= min_assignment
@@ -985,11 +978,11 @@ def plot_celltype_map(
             color_map = [to_rgb(c) if isinstance(c, str) else c for c in cmap]
 
         # convert to uint8 to reduce memory of final image
-        color_map_int = tuple(
-            (np.array(c) * 255).round().astype(np.uint8)
-            for c in chain([to_rgb(background)], color_map)
+        color_map_int = (
+            (np.array([to_rgb(background)] + color_map) * 255).round().astype(np.uint8)
         )
-        img = _apply_color(celltype_map.T, color_map_int)
+
+        img = np.take(color_map_int, celltype_map.T, axis=0)
 
         if return_img:
             return img

sainsc/lazykde/_utils.py

@@ -4,7 +4,6 @@
 import numpy as np
 import pandas as pd
 from anndata import AnnData
-from numba import njit
 from numpy.typing import NDArray
 from scipy.sparse import csr_matrix, sparray, spmatrix
 from skimage.measure import label, regionprops
@@ -19,17 +18,6 @@
 """Default scalebar parameters"""
 
 
-@njit
-def _apply_color(
-    img_in: NDArray[np.integer], cmap: tuple[NDArray[T], ...]
-) -> NDArray[T]:
-    img = np.empty(shape=(*img_in.shape, 3), dtype=cmap[0].dtype)
-    for i in range(img_in.shape[0]):
-        for j in range(img_in.shape[1]):
-            img[i, j, :] = cmap[img_in[i, j]]
-    return img
-
-
 def _get_cell_dtype(n: int) -> np.dtype:
     return np.result_type("int8", n)