More type hinting for the codebase

.gitignore

@@ -81,6 +81,7 @@ venv/
 ENV/
 env.bak/
 venv.bak/
+.vscode/
 
 dclab/_version.py
 *.bib.bak

CHANGELOG

@@ -1,4 +1,5 @@
 0.67.1
+ - docs: type hinted the features sub-module
  - enh: add mass density feature, deprecate some qpi features (#284)
 0.67.0
  - BREAKING CHANGE: make it difficult to export the "contour" feature

README.rst

@@ -88,6 +88,22 @@ We use flake8 to enforce coding style::
     flake8 tests
 
 
+Type Hinting
+~~~~~~~~~~~~
+For type hinting and docstring styling, try to keep the 
+Code Reference readable in the documentation website.
+If in doubt just ask, or look at the examples in the codebase.
+
+* Simple type combintions such as ``float`` or ``str | pathlib.Path``
+  should be included as type hints, but do not need to be included
+  in the docstring parameter description.
+* More involved type hints can have extra information in the 
+  docstring. For example for numpy arrays, ``npt.NDArray[np.bool]`` doesn't
+  render in a readable way in the Code Reference, and doesn't include shape.
+  Therefore, you can also keep the docstring parameter description with 
+  the shape and dtype information e.g., ``binary ndarray of shape (M, N)``.
+
+
 Incrementing version
 ~~~~~~~~~~~~~~~~~~~~
 Dclab gets its version from the latest git tag.

dclab/features/bright.py

@@ -2,10 +2,19 @@
 Computation of mean and standard deviation of grayscale values inside the
 RT-DC event image mask.
 """
+from __future__ import annotations
+
 import numpy as np
+import numpy.typing as npt
 
 
-def get_bright(mask, image, ret_data="avg,sd"):
+def get_bright(mask: npt.NDArray[bool] | list[npt.NDArray[bool]],
+               image: npt.NDArray | list[npt.NDArray],
+               ret_data: str = "avg,sd"
+               ) -> (float |
+                     npt.NDArray |
+                     tuple[float, float] |
+                     tuple[npt.NDArray, npt.NDArray]):
     """Compute avg and/or std of the event brightness
 
     The event brightness is defined by the gray-scale values of the
@@ -18,7 +27,7 @@ def get_bright(mask, image, ret_data="avg,sd"):
     image: ndarray or list of ndarrays of shape (M,N)
         A 2D array that holds the image in form of grayscale values
         of an event.
-    ret_data: str
+    ret_data
         A comma-separated list of metrices to compute
         - "avg": compute the average
         - "sd": compute the standard deviation

dclab/features/bright_bc.py

@@ -2,10 +2,21 @@
 Computation of mean and standard deviation of grayscale values inside the
 RT-DC event image mask with background-correction taken into account.
 """
+from __future__ import annotations
+
 import numpy as np
+import numpy.typing as npt
 
 
-def get_bright_bc(mask, image, image_bg, bg_off=None, ret_data="avg,sd"):
+def get_bright_bc(mask: npt.NDArray[bool] | list[npt.NDArray[bool]],
+                  image: npt.NDArray | list[npt.NDArray],
+                  image_bg: npt.NDArray | list[npt.NDArray],
+                  bg_off: float | npt.NDArray = None,
+                  ret_data: str = "avg,sd"
+                  ) -> (float |
+                        npt.NDArray |
+                        tuple[float, float] |
+                        tuple[npt.NDArray, npt.NDArray]):
     """Compute avg and/or std of the background-corrected event brightness
 
     The background-corrected event brightness is defined by the
@@ -24,7 +35,7 @@ def get_bright_bc(mask, image, image_bg, bg_off=None, ret_data="avg,sd"):
     bg_off: float or 1D ndarray
         Additional offset value that is added to `image_bg` before
         background correction
-    ret_data: str
+    ret_data
         A comma-separated list of metrices to compute
         - "avg": compute the average
         - "sd": compute the standard deviation

dclab/features/bright_perc.py

@@ -2,10 +2,18 @@
 Computation of the 10th and 90th percentile of grayscale values inside the
 RT-DC event image mask with background-correction taken into account.
 """
+from __future__ import annotations
+
 import numpy as np
+import numpy.typing as npt
 
 
-def get_bright_perc(mask, image, image_bg, bg_off=None):
+def get_bright_perc(mask: npt.NDArray[bool] | list[npt.NDArray[bool]],
+                    image: npt.NDArray | list[npt.NDArray],
+                    image_bg: npt.NDArray | list[npt.NDArray],
+                    bg_off: float | npt.NDArray = None
+                    ) -> (tuple[float, float] |
+                          tuple[npt.NDArray, npt.NDArray]):
     """Compute 10th and 90th percentile of the bg-corrected event brightness
 
     The background-corrected event brightness is defined by the
@@ -29,7 +37,7 @@ def get_bright_perc(mask, image, image_bg, bg_off=None):
     -------
     bright_perc_10: float or ndarray of size N
         10th percentile of brightness
-    bright_perc_10: float or ndarray of size N
+    bright_perc_90: float or ndarray of size N
         90th percentile of brightness
     """
     if isinstance(mask, np.ndarray) and len(mask.shape) == 2:

dclab/features/contour.py

@@ -1,8 +1,11 @@
 """Computation of event contour from event mask"""
+from __future__ import annotations
+
 from collections import deque
 import numbers
 
 import numpy as np
+import numpy.typing as npt
 
 # equivalent to
 # from skimage.measure import find_contours
@@ -14,15 +17,15 @@ class NoValidContourFoundError(BaseException):
 
 
 class LazyContourList(object):
-    def __init__(self, masks, max_events=1000):
+    def __init__(self, masks: npt.ArrayLike, max_events: int = 1000) -> None:
         """A list-like object that computes contours upon indexing
 
         Parameters
         ----------
-        masks: array-like
+        masks
             3D array of masks, may be an HDF5 dataset or any other
             structure that supports indexing
-        max_events: int
+        max_events
             maximum number of contours to keep in the contour list;
             set to 0/False/None to cache all contours
 
@@ -40,7 +43,7 @@ def __init__(self, masks, max_events=1000):
         self.identifier = str(masks[0][:].tobytes())
         self.shape = len(masks), np.nan, 2
 
-    def __getitem__(self, idx):
+    def __getitem__(self, idx) -> npt.NDArray:
         """Compute contour(s) if not already in self.contours"""
         if not isinstance(idx, numbers.Integral):
             # slicing!
@@ -74,7 +77,8 @@ def __len__(self):
         return len(self.masks)
 
 
-def get_contour(mask):
+def get_contour(mask: npt.NDArray[np.bool | np.int]
+                ) -> npt.NDArray | list[npt.NDArray]:
     """Compute the image contour from a mask
 
     The contour is computed in a very inefficient way using scikit-image
@@ -127,7 +131,8 @@ def get_contour(mask):
         return contours[0]
 
 
-def get_contour_lazily(mask):
+def get_contour_lazily(mask: npt.NDArray[np.bool | np.int]
+                       ) -> npt.NDArray | LazyContourList:
     """Like :func:`get_contour`, but computes contours on demand
 
     Parameters
@@ -153,7 +158,7 @@ def get_contour_lazily(mask):
     return cont
 
 
-def remove_duplicates(cont):
+def remove_duplicates(cont: npt.NDArray) -> npt.NDArray:
     """Remove duplicates in a circular contour"""
     x = np.resize(cont, (len(cont) + 1, 2))
     selection = np.ones(len(x), dtype=bool)

dclab/features/emodulus/__init__.py

@@ -7,6 +7,7 @@
 import warnings
 
 import numpy as np
+import numpy.typing as npt
 import scipy.interpolate as spint
 
 from ...warn import PipelineWarning
@@ -18,7 +19,6 @@
 from .scale_linear import scale_emodulus, scale_feature
 from .viscosity import get_viscosity
 
-
 #: Set this to True to globally enable spline extrapolation when the
 #: `area_um`/`deform` data are outside the LUT. This is discouraged and
 #: a :class:`KnowWhatYouAreDoingWarning` warning will be issued.
@@ -33,8 +33,13 @@ class YoungsModulusLookupTableExceededWarning(PipelineWarning):
     pass
 
 
-def extrapolate_emodulus(lut, datax, deform, emod, deform_norm,
-                         deform_thresh=.05, inplace=True):
+def extrapolate_emodulus(lut: npt.NDArray,
+                         datax: npt.NDArray,
+                         deform: npt.NDArray,
+                         emod: npt.NDArray,
+                         deform_norm: float,
+                         deform_thresh: float = .05,
+                         inplace: bool = True) -> npt.NDArray:
     """Use spline interpolation to fill in nan-values
 
     When points (`datax`, `deform`) are outside the convex
@@ -61,16 +66,16 @@ def extrapolate_emodulus(lut, datax, deform, emod, deform_norm,
     emod: ndarray of size N
         The emodulus (corresponding to `lut[:, 2]`); If `emod`
         does not contain nan-values, there is nothing to do here.
-    deform_norm: float
+    deform_norm
         The normalization value used to normalize `lut[:, 1]` and
         `deform`.
-    deform_thresh: float
+    deform_thresh
         Not the entire LUT is used for bivariate spline interpolation.
         Only the points where `lut[:, 1] > deform_thresh/deform_norm`
         are used. This is necessary, because for small deformations,
         the LUT has an extreme slope that kills any meaningful
         spline interpolation.
-    inplace: bool
+    inplace
         If True (default), replaces nan values in `emod` in-place.
         If False, `emod` is not modified.
     """
@@ -99,65 +104,66 @@ def extrapolate_emodulus(lut, datax, deform, emod, deform_norm,
     return emod
 
 
-def get_emodulus(deform: float | np.array,
-                 area_um: float | np.array | None = None,
-                 volume: float | np.array | None = None,
+def get_emodulus(deform: float | npt.NDArray,
+                 area_um: float | npt.NDArray | None = None,
+                 volume: float | npt.NDArray | None = None,
                  medium: float | str = "0.49% MC-PBS",
                  channel_width: float = 20.0,
                  flow_rate: float = 0.16,
                  px_um: float = 0.34,
-                 temperature: float | np.ndarray | None = 23.0,
-                 lut_data: str | pathlib.Path | np.ndarray = "LE-2D-FEM-19",
+                 temperature: float | npt.NDArray | None = 23.0,
+                 lut_data: (str | pathlib.Path |
+                            tuple[npt.NDArray, dict]) = "LE-2D-FEM-19",
                  visc_model: Literal['herold-2017',
                                      'herold-2017-fallback',
                                      'buyukurganci-2022',
                                      'kestin-1978',
                                      None] = "herold-2017-fallback",
                  extrapolate: bool = INACCURATE_SPLINE_EXTRAPOLATION,
-                 copy: bool = True):
+                 copy: bool = True) -> npt.NDArray:
     """Compute apparent Young's modulus using a look-up table
 
     Parameters
     ----------
-    area_um: float or ndarray
-        Apparent (2D image) area [µm²] of the event(s)
-    deform: float or ndarray
+    deform
         Deformation (1-circularity) of the event(s)
-    volume: float or ndarray
+    area_um
+        Apparent (2D image) area [µm²] of the event(s)
+    volume
         Apparent volume of the event(s). It is not possible to define
         `volume` and `area_um` at the same time (makes no sense).
 
         .. versionadded:: 0.25.0
-    medium: str or float
+    medium
         The medium to compute the viscosity for. If a string
         is given, the viscosity is computed. If a float is given,
         this value is used as the viscosity in mPa*s (Note that
         `temperature` and `visc_model` must be set to None in this case).
-    channel_width: float
+    channel_width
         The channel width [µm]
-    flow_rate: float
+    flow_rate
         Flow rate [µL/s]
-    px_um: float
+    px_um
         The detector pixel size [µm] used for pixelation correction.
         Set to zero to disable.
-    temperature: float, ndarray, or None
+    temperature
         Temperature [°C] of the event(s)
-    lut_data: path, str, or tuple of (np.ndarray of shape (N, 3), dict)
+    lut_data: str, path, or tuple of (np.ndarray of shape (N, 3), dict)
         The LUT data to use. If it is a built-in identifier,
         then the respective LUT will be used. Otherwise, a path to a
         file on disk or a tuple (LUT array, metadata) is possible.
         The LUT metadata is used to check whether the given features
         (e.g. `area_um` and `deform`) are valid interpolation choices.
 
         .. versionadded:: 0.25.0
-    visc_model: str
+    visc_model
         The viscosity model to use,
         see :func:`dclab.features.emodulus.viscosity.get_viscosity`
-    extrapolate: bool
+    extrapolate
         Perform extrapolation using :func:`extrapolate_emodulus`. This
         is discouraged!
-    copy: bool
-        Copy input arrays. If set to false, input arrays are
+    copy
+        Copy input arrays. If set to False, input arrays are
         overridden.
 
     Returns
@@ -326,7 +332,7 @@ def get_emodulus(deform: float | np.array,
     return emod
 
 
-def normalize(data, dmax):
+def normalize(data: npt.NDArray, dmax: float) -> npt.NDArray:
     """Perform normalization in-place for interpolation
 
     Note that :func:`scipy.interpolate.griddata` has a `rescale`