fix:

- switched from gdf to ndarray for point iteration
- removed rasterio as dep
- added kernels
- finished docstrings

to do:
- tests
- CICD
- README

pre-commit-config.yaml → .pre-commit-config.yaml

@@ -10,4 +10,10 @@ repos:
 -   repo: https://github.com/PyCQA/bandit
     rev: 1.7.7
     hooks:
-    -   id: bandit
+    -   id: bandit
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.971
+  hooks:
+    - id: mypy
+      types: [python]
+      args: [--strict]

README.md

@@ -0,0 +1,6 @@
+## Roadmap
+-------
+- Add more kernels.
+- Implement other methods of distance measurement, e.g. haversine, manhattan.
+- Investigate possible alternatives to iterating over points.
+- Enable use of single radius and weight values without filling array of the same length as the points GeoDataFrame/GeoSeries. Results in marginal speed up but the current approach may become an issue with large point datasets.

geokde/_kernels.py

@@ -1,22 +1,118 @@
+"""Kernels for density estimation.
+
+All kernels accept the following parameters:
+
+Parameters
+----------
+distance : int | float
+    Euclidean distance value for a given point from the reference point.
+radius : int | float
+    Search window radius for the reference point.
+weight : int | float
+    Value with which the KDE value for a point will be weighted.
+
+And provide the following return:
+
+Returns
+-------
+value : float
+    Specified kernel's density estimation value.
+"""
+
+from math import pi
+
 import numpy as np
 
 
+VALID_KERNELS = [
+    "epanechnikov",
+    "quartic",
+    "triweight",
+]
+
+
+@np.vectorize
+def quartic_raw(
+        distance: int | float,
+        radius: int | float,
+        weight: int | float,
+) -> float:
+    """Raw Quartic kernel."""
+    if distance:
+        value = weight * pow(1 - pow(distance / radius, 2), 2)
+    else:
+        value = 0.0
+    return value
+
+
+@np.vectorize
+def quartic_scaled(
+        distance: int | float,
+        radius: int | float,
+        weight: int | float,
+) -> float:
+    """Scaled Quartic kernel."""
+    if distance:
+        norm_const = 116 / (5 * pi * pow(radius, 2))
+        value = weight * (norm_const * (15 / 16) * pow(1 - pow(distance / radius, 2), 2))
+    else:
+        value = 0.0
+    return value
+
+
+@np.vectorize
+def epanechnikov_raw(
+        distance: int | float,
+        radius: int | float,
+        weight: int | float,
+) -> float:
+    """Raw Epanechnikov kernel."""
+    if distance:
+        value = weight * (1 - pow(distance / radius, 2))
+    else:
+        value = 0.0
+    return value
+
+
+@np.vectorize
+def epanechnikov_scaled(
+        distance: int | float,
+        radius: int | float,
+        weight: int | float,
+) -> float:
+    """Scaled Epanechnikov kernel."""
+    if distance:
+        norm_const = 8 / (3 * pi * pow(radius, 2))
+        value = weight * (norm_const * (3 / 4) * (1 - pow(distance / radius, 2)))
+    else:
+        value = 0.0
+    return value
+
+
+@np.vectorize
+def triweight_raw(
+        distance: int | float,
+        radius: int | float,
+        weight: int | float,
+) -> float:
+    """Raw triweight kernel."""
+    if distance:
+        value = weight * pow(1 - pow(distance / radius, 2), 3)
+    else:
+        value = 0.0
+    return value
+
+
 @np.vectorize
-def quartic(distance: int | float, radius: int | float, weight: int | float) -> float:
-    """Quartic kernel.
-
-    Parameters
-    ----------
-    distance : int | float
-    radius : int | float
-    weight : int | float
-
-    Returns
-    -------
-    value : float
-    """
+def triweight_scaled(
+        distance: int | float,
+        radius: int | float,
+        weight: int | float,
+) -> float:
+    """Scaled triweight kernel."""
     if distance:
-        value = weight * ((1 - ((distance / radius) ** 2)) ** 2)
+        norm_const = 128 / (35 * pi * pow(radius, 2))
+        value = weight * (norm_const * (35 / 32) * pow(1 - pow(distance / radius, 2), 3))
     else:
         value = 0.0
     return value