Geometric Properties¶

This notebook demonstrates how to calculate geometric properties of objects in a vector dataset and filter out unwanted objects based on these properties.

Install package¶

To use the geoai-py package, ensure it is installed in your environment. Uncomment the command below if needed.

In [1]:

# %pip install geoai-py

# %pip install geoai-py

Import package¶

In [2]:

import geoai

import geoai

Load data¶

In [3]:

vector_url = "https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip_buildings_masks.geojson"
raster_url = (
    "https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip_train.tif"
)

vector_url = "https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip_buildings_masks.geojson" raster_url = ( "https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip_train.tif" )

In [4]:

gdf = geoai.read_vector(vector_url)

gdf = geoai.read_vector(vector_url)

In [5]:

gdf.head()

gdf.head()

Out[5]:

	confidence	class	geometry
0	0.994213	1	POLYGON ((455181.6 5277618.6, 455177.4 5277614...
1	0.992599	1	POLYGON ((454990.2 5277628.2, 454990.2 5277627...
2	0.989381	1	POLYGON ((454855.8 5277628.2, 454855.8 5277626...
3	0.986561	1	POLYGON ((454981.8 5277798, 454981.2 5277797.4...
4	0.982763	1	POLYGON ((455052 5277904.8, 455050.8 5277903.6...

Visualize data¶

In [6]:

geoai.view_vector_interactive(gdf, column="confidence", tiles=raster_url)

geoai.view_vector_interactive(gdf, column="confidence", tiles=raster_url)

Out[6]:

Make this Notebook Trusted to load map: File -> Trust Notebook

Add geometric properties¶

In [7]:

gdf_props = geoai.add_geometric_properties(gdf, area_unit="m2", length_unit="m")

gdf_props = geoai.add_geometric_properties(gdf, area_unit="m2", length_unit="m")

In [8]:

gdf_props.head()

gdf_props.head()

Out[8]:

	confidence	class	geometry	area_m2	length_m	perimeter_m	area_bbox_m2	area_convex_m2	area_filled_m2	major_length_m	minor_length_m	eccentricity	orientation	elongation	extent	solidity	complexity
0	0.994213	1	POLYGON ((455181.6 5277618.6, 455177.4 5277614...	184.50	53.407316	53.407316	241.92	189.18	184.50	19.2	12.6	0.754544	0.0	1.523810	0.762649	0.975262	1.109169
1	0.992599	1	POLYGON ((454990.2 5277628.2, 454990.2 5277627...	527.22	92.836753	92.836753	546.84	533.52	527.22	29.4	18.6	0.774435	90.0	1.580645	0.964121	0.988192	1.140562
2	0.989381	1	POLYGON ((454855.8 5277628.2, 454855.8 5277626...	599.40	97.988225	97.988225	617.40	604.44	599.40	29.4	21.0	0.699854	90.0	1.400000	0.970845	0.991662	1.129043
3	0.986561	1	POLYGON ((454981.8 5277798, 454981.2 5277797.4...	741.96	129.976450	129.976450	866.52	786.24	741.96	49.8	17.4	0.936975	0.0	2.862069	0.856253	0.943681	1.346076
4	0.982763	1	POLYGON ((455052 5277904.8, 455050.8 5277903.6...	748.98	130.122035	130.122035	876.96	795.78	748.98	50.4	17.4	0.938515	90.0	2.896552	0.854064	0.941190	1.341253

Visualize geometric properties¶

In [9]:

geoai.view_vector_interactive(gdf_props, column="area_m2", tiles=raster_url)

geoai.view_vector_interactive(gdf_props, column="area_m2", tiles=raster_url)

Out[9]:

Make this Notebook Trusted to load map: File -> Trust Notebook

In [10]:

geoai.view_vector_interactive(gdf_props, column="elongation", tiles=raster_url)

geoai.view_vector_interactive(gdf_props, column="elongation", tiles=raster_url)

Out[10]:

Make this Notebook Trusted to load map: File -> Trust Notebook

Filter objects based on geometric properties¶

In [11]:

gdf_filtered = gdf_props[(gdf_props["area_m2"] < 2000) & (gdf_props["elongation"] < 5)]

gdf_filtered = gdf_props[(gdf_props["area_m2"] < 2000) & (gdf_props["elongation"] < 5)]

Visualize filtered objects¶

In [12]:

geoai.view_vector_interactive(gdf_filtered, column="elongation", tiles=raster_url)

geoai.view_vector_interactive(gdf_filtered, column="elongation", tiles=raster_url)

Out[12]:

Make this Notebook Trusted to load map: File -> Trust Notebook