Hex2vec embedder

In [1]:

from srai.embedders import Hex2VecEmbedder
from srai.joiners import IntersectionJoiner
from srai.loaders import OSMOnlineLoader
from srai.neighbourhoods import H3Neighbourhood
from srai.regionalizers import H3Regionalizer, geocode_to_region_gdf
from srai.plotting import plot_regions, plot_numeric_data
from pytorch_lightning import seed_everything

from srai.embedders import Hex2VecEmbedder from srai.joiners import IntersectionJoiner from srai.loaders import OSMOnlineLoader from srai.neighbourhoods import H3Neighbourhood from srai.regionalizers import H3Regionalizer, geocode_to_region_gdf from srai.plotting import plot_regions, plot_numeric_data from pytorch_lightning import seed_everything

In [2]:

SEED = 71
seed_everything(SEED)

SEED = 71 seed_everything(SEED)

Seed set to 71

Out[2]:

71

Load data from OSM¶

First use geocoding to get the area

In [3]:

area_gdf = geocode_to_region_gdf("Wrocław, Poland")
plot_regions(area_gdf, tiles_style="CartoDB positron")

area_gdf = geocode_to_region_gdf("Wrocław, Poland") plot_regions(area_gdf, tiles_style="CartoDB positron")

Out[3]:

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

Next, download the data for the selected region and the specified tags. We're using OSMOnlineLoader here, as it's faster for low numbers of tags. In a real life scenario with more tags, you would likely want to use the OSMPbfLoader.

In [4]:

tags = {
    "leisure": "park",
    "landuse": "forest",
    "amenity": ["bar", "restaurant", "cafe"],
    "water": "river",
    "sport": "soccer",
}
loader = OSMOnlineLoader()

features_gdf = loader.load(area_gdf, tags)

folium_map = plot_regions(area_gdf, colormap=["rgba(0,0,0,0)"], tiles_style="CartoDB positron")
features_gdf.explore(m=folium_map)

tags = { "leisure": "park", "landuse": "forest", "amenity": ["bar", "restaurant", "cafe"], "water": "river", "sport": "soccer", } loader = OSMOnlineLoader() features_gdf = loader.load(area_gdf, tags) folium_map = plot_regions(area_gdf, colormap=["rgba(0,0,0,0)"], tiles_style="CartoDB positron") features_gdf.explore(m=folium_map)

Downloading sport: soccer      : 100%|██████████| 7/7 [00:03<00:00,  1.86it/s]

Out[4]:

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

Prepare the data for embedding¶

After downloading the data, we need to prepare it for embedding. Namely - we need to regionalize the selected area, and join the features with regions.

In [5]:

regionalizer = H3Regionalizer(resolution=9)
regions_gdf = regionalizer.transform(area_gdf)
plot_regions(regions_gdf, tiles_style="CartoDB positron")

regionalizer = H3Regionalizer(resolution=9) regions_gdf = regionalizer.transform(area_gdf) plot_regions(regions_gdf, tiles_style="CartoDB positron")

Out[5]:

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

In [6]:

joiner = IntersectionJoiner()
joint_gdf = joiner.transform(regions_gdf, features_gdf)
joint_gdf

joiner = IntersectionJoiner() joint_gdf = joiner.transform(regions_gdf, features_gdf) joint_gdf

Out[6]:

region_id	feature_id
891e2047087ffff	way/520612441
891e204708fffff	way/520612441
891e2050a13ffff	way/727025008
891e2050a03ffff	way/727025008
891e2050a1bffff	way/727025008
...	...
891e2047547ffff	way/772238372
	way/772238371
	way/772238373
891e2040abbffff	way/310591107
891e2043203ffff	way/1033837570

3797 rows × 0 columns

Embedding¶

After preparing the data we can proceed with generating embeddings for the regions.

In [7]:

import warnings

neighbourhood = H3Neighbourhood(regions_gdf)
embedder = Hex2VecEmbedder([15, 10])

with warnings.catch_warnings():
    warnings.simplefilter("ignore")
    embeddings = embedder.fit_transform(
        regions_gdf,
        features_gdf,
        joint_gdf,
        neighbourhood,
        trainer_kwargs={"max_epochs": 5, "accelerator": "cpu"},
        batch_size=100,
    )
embeddings

import warnings neighbourhood = H3Neighbourhood(regions_gdf) embedder = Hex2VecEmbedder([15, 10]) with warnings.catch_warnings(): warnings.simplefilter("ignore") embeddings = embedder.fit_transform( regions_gdf, features_gdf, joint_gdf, neighbourhood, trainer_kwargs={"max_epochs": 5, "accelerator": "cpu"}, batch_size=100, ) embeddings

100%|██████████| 3168/3168 [00:00<00:00, 17682.67it/s]
GPU available: False, used: False
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
HPU available: False, using: 0 HPUs

  | Name    | Type       | Params
---------------------------------------
0 | encoder | Sequential | 280   
---------------------------------------
280       Trainable params
0         Non-trainable params
280       Total params
0.001     Total estimated model params size (MB)

`Trainer.fit` stopped: `max_epochs=5` reached.

Out[7]:

	0	1	2	3	4	5	6	7	8	9
region_id
891e2047087ffff	-0.315386	-0.081035	-0.296213	-0.498415	-0.012670	0.267480	-0.401396	0.361879	-0.110500	0.018470
891e2050a13ffff	-0.569938	0.208577	-0.496939	-0.810638	-0.079023	0.246054	-0.229530	0.369954	-0.173344	-0.238820
891e2040947ffff	-0.625594	0.941852	0.871613	0.023387	-0.982461	0.105278	1.244328	-0.402938	0.797777	-1.042796
891e2040c7bffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457
891e2042617ffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457
...	...	...	...	...	...	...	...	...	...	...
891e2042b03ffff	0.074926	0.229409	0.447267	0.620098	-0.135165	-0.056325	0.305491	-0.386047	0.382916	0.102599
891e205534fffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457
891e20472a3ffff	-0.460802	0.354916	0.190510	0.051184	-0.286301	0.226548	0.064835	-0.048162	0.393264	-0.032893
891e2041d4fffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457
891e2043483ffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457

3168 rows × 10 columns

Visualizing the embeddings' similarity¶

In [8]:

from sklearn.cluster import KMeans

clusterizer = KMeans(n_clusters=5, random_state=SEED)
clusterizer.fit(embeddings)

embeddings["cluster"] = clusterizer.labels_
embeddings

from sklearn.cluster import KMeans clusterizer = KMeans(n_clusters=5, random_state=SEED) clusterizer.fit(embeddings) embeddings["cluster"] = clusterizer.labels_ embeddings

/opt/hostedtoolcache/Python/3.10.13/x64/lib/python3.10/site-packages/sklearn/cluster/_kmeans.py:1412: FutureWarning: The default value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n_init` explicitly to suppress the warning
  super()._check_params_vs_input(X, default_n_init=10)

Out[8]:

	0	1	2	3	4	5	6	7	8	9	cluster
region_id
891e2047087ffff	-0.315386	-0.081035	-0.296213	-0.498415	-0.012670	0.267480	-0.401396	0.361879	-0.110500	0.018470	1
891e2050a13ffff	-0.569938	0.208577	-0.496939	-0.810638	-0.079023	0.246054	-0.229530	0.369954	-0.173344	-0.238820	1
891e2040947ffff	-0.625594	0.941852	0.871613	0.023387	-0.982461	0.105278	1.244328	-0.402938	0.797777	-1.042796	3
891e2040c7bffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457	0
891e2042617ffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457	0
...	...	...	...	...	...	...	...	...	...	...	...
891e2042b03ffff	0.074926	0.229409	0.447267	0.620098	-0.135165	-0.056325	0.305491	-0.386047	0.382916	0.102599	3
891e205534fffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457	0
891e20472a3ffff	-0.460802	0.354916	0.190510	0.051184	-0.286301	0.226548	0.064835	-0.048162	0.393264	-0.032893	3
891e2041d4fffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457	0
891e2043483ffff	0.359040	-0.197065	0.003509	0.324392	0.206475	-0.135264	-0.225939	-0.111279	-0.187345	0.335457	0

3168 rows × 11 columns

In [9]:

plot_numeric_data(regions_gdf, "cluster", embeddings)

plot_numeric_data(regions_gdf, "cluster", embeddings)

Out[9]:

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