style: clean up precommit

.pre-commit-config.yaml

@@ -7,20 +7,20 @@ default_install_hook_types: [pre-commit, commit-msg]
 
 repos:
   - repo: https://github.com/compilerla/conventional-pre-commit
-    rev: v2.1.1
+    rev: v3.1.0
     hooks:
       - id: conventional-pre-commit
         stages: [commit-msg]
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.5.0
     hooks:
       - id: check-docstring-first
       - id: end-of-file-fixer
       - id: trailing-whitespace
 
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: v0.0.149
+    rev: v0.1.13
     hooks:
       - id: ruff
         args: [--fix]
@@ -31,12 +31,12 @@ repos:
       - id: black
 
   - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.10.1
+    rev: v0.15
     hooks:
       - id: validate-pyproject
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.991
+    rev: v1.8.0
     hooks:
       - id: mypy
         files: "^src/"

docs/conf.py

@@ -225,4 +225,4 @@ def linkcode_resolve(domain, info):
 
     fn = os.path.relpath(fn, start=os.path.dirname("../raman_analysis"))
 
-    return f"https://github.com/ianhi/raman-analysis/blob/main/raman_analysis/{fn}{linespec}"  # noqa
+    return f"https://github.com/ianhi/raman-analysis/blob/main/raman_analysis/{fn}{linespec}"

src/raman_analysis/baseline.py

@@ -0,0 +1,40 @@
+from typing import Any
+
+import numpy as np
+from pybaselines import Baseline
+
+__all__ = [
+    "baseline",
+]
+
+
+def baseline(spectra: np.ndarray, method: str = "arpls", **params: Any) -> np.ndarray:
+    """
+    Calculate the baseline of [many] spectra using pybaselines.
+
+    Parameters
+    ----------
+    spectra : array-like ([N], wns)
+        The spectra to calculate the baseline of.
+    method : str, default: "arpls"
+        The pybaselines method name.
+    **params:
+        Passed to pybaselines
+
+    Returns
+    -------
+    baseline : np.ndarray ([N], wns)
+        The calculated baselines
+    """
+    baseliner = Baseline(np.arange(1340))
+    baseline_func = getattr(baseliner, method)
+
+    spectra = np.atleast_2d(spectra)
+    if np.issubdtype(spectra.dtype, np.integer):
+        spectra = spectra.astype(np.float32)
+
+    baselines = np.zeros_like(spectra)
+
+    for i, spec in enumerate(spectra):
+        baselines[i], w = baseline_func(spec, **params)
+    return baselines.squeeze()

src/raman_analysis/loading.py

@@ -1,12 +1,14 @@
-from typing import Iterable, Union
+from __future__ import annotations
+
+from typing import Iterable
 
 import numpy as np
 import pandas as pd
 import xarray as xr
 
 
 def ds2df(
-    ds: xr.Dataset, fov: int, cell_index_start: int = 0, filename=None
+    ds: xr.Dataset, fov: int, cell_index_start: int = 0, filename: str | None = None
 ) -> pd.DataFrame:
     """
     Convert a single dataset into a dataframe.
@@ -39,11 +41,11 @@ def ds2df(
     df["y"] = ds["cell_points"][:, 1]
 
     cell_points = ds["cell_points"] * 2048
-    bkd_points = ds["bkd_points"] * 2048
-    cell_raman = ds["cell_raman"] - 608
-    bkd_raman = ds["bkd_raman"] - 608
+    # bkd_points = ds["bkd_points"] * 2048
+    # cell_raman = ds["cell_raman"] - 608
+    # bkd_raman = ds["bkd_raman"] - 608
 
-    thres = 140
+    # thres = 140
 
     cell_com = cell_points.to_numpy().astype(int)
     gfp_int = np.asarray([ds["img"][1, 0, x[0], x[1]].values for x in cell_com])
@@ -56,113 +58,15 @@ def ds2df(
 
 
 def glob2df(
-    files: Union[Iterable[str], str],
-    conditions,
+    files: Iterable[str] | str,
+    conditions: tuple[str, str],
     threshold: float,
     well_number: int = 0,
     cell_index_start: int = 0,
     verbose: bool = True,
 ) -> pd.DataFrame:
     """
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+    Convert a list of raman file names to a dataframe.
 
     Parameters
     ----------
@@ -188,6 +92,8 @@ def glob2df(
     images : xr.DataArray
     """
     if isinstance(files, str):
+        from glob import glob
+
         files = glob(files)
     dfs = []
     images = []