momepy.weighted_character

momepy.weighted_character(y, area, graph)

Calculates the weighted character.

Character weighted by the area of the objects within neighbors defined in graph. Results are index based on graph.

\[\frac{\sum_{i=1}^{n} {character_{i} * area_{i}}}{\sum_{i=1}^{n} area_{i}}\]

Adapted from [Dibble et al., 2017].

Parameters:

yNDArray[np.float64] | Series

The character values to be weighted.

areaNDArray[np.float64] | Series

The area values to be used as weightss

graphlibpysal.graph.Graph

A spatial weights matrix for values and areas.

Returns:

Series

A Series containing the resulting values.

Notes

The index of y and area must match the index along which the graph is built.

Examples

Area-weighted elongation within 5 nearest neighbors:

>>> from libpysal import graph
>>> path = momepy.datasets.get_path("bubenec")
>>> buildings = geopandas.read_file(path, layer="buildings")
>>> buildings.head()
   uID                                           geometry
0    1  POLYGON ((1603599.221 6464369.816, 1603602.984...
1    2  POLYGON ((1603042.88 6464261.498, 1603038.961 ...
2    3  POLYGON ((1603044.65 6464178.035, 1603049.192 ...
3    4  POLYGON ((1603036.557 6464141.467, 1603036.969...
4    5  POLYGON ((1603082.387 6464142.022, 1603081.574...

Measure elongation (or anything else):

>>> elongation = momepy.elongation(buildings)
>>> elongation.head()
0    0.908244
1    0.581318
2    0.726527
3    0.838840
4    0.727294
Name: elongation, dtype: float64

Define spatial graph:

>>> knn5 = graph.Graph.build_knn(buildings.centroid, k=5)
>>> knn5
<Graph of 144 nodes and 720 nonzero edges indexed by
 [0, 1, 2, 3, 4, ...]>

Measure the area-weighted character:

>>> momepy.weighted_character(elongation, buildings.area, knn5)
focal
0      0.808190
1      0.817309
2      0.627589
3      0.794769
4      0.806403
         ...
139    0.780744
140    0.875046
141    0.753670
142    0.440000
143    0.901127
Name: sum, Length: 144, dtype: float64