Hex2vec embedder

In [1]:

Copied!





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.plotting import plot_numeric_data, plot_regions
from srai.regionalizers import H3Regionalizer, geocode_to_region_gdf
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.plotting import plot_numeric_data, plot_regions
from srai.regionalizers import H3Regionalizer, geocode_to_region_gdf

In [2]:

Copied!

SEED = 71
seed_everything(SEED)
SEED = 71
seed_everything(SEED)

Seed set to 71

Out[2]:

Load data from OSM¶

First use geocoding to get the area

In [3]:

Copied!

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]:

Copied!





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)

  0%|          | 0/7 [00:00<?, ?it/s]

Downloading leisure: park      :   0%|          | 0/7 [00:00<?, ?it/s]

Downloading leisure: park      :  14%|█▍        | 1/7 [00:00<00:02,  2.78it/s]

Downloading landuse: forest    :  14%|█▍        | 1/7 [00:00<00:02,  2.78it/s]

Downloading landuse: forest    :  29%|██▊       | 2/7 [00:00<00:01,  3.18it/s]

Downloading amenity: bar       :  29%|██▊       | 2/7 [00:00<00:01,  3.18it/s]

Downloading amenity: bar       :  43%|████▎     | 3/7 [00:00<00:00,  4.13it/s]

Downloading amenity: restaurant:  43%|████▎     | 3/7 [00:00<00:00,  4.13it/s]

Downloading amenity: restaurant:  57%|█████▋    | 4/7 [00:00<00:00,  4.63it/s]

Downloading amenity: cafe      :  57%|█████▋    | 4/7 [00:00<00:00,  4.63it/s]

Downloading amenity: cafe      :  71%|███████▏  | 5/7 [00:01<00:00,  4.93it/s]

Downloading water: river       :  71%|███████▏  | 5/7 [00:01<00:00,  4.93it/s]

Downloading water: river       :  86%|████████▌ | 6/7 [00:01<00:00,  4.87it/s]

Downloading sport: soccer      :  86%|████████▌ | 6/7 [00:01<00:00,  4.87it/s]

Downloading sport: soccer      : 100%|██████████| 7/7 [00:01<00:00,  5.13it/s]

Downloading sport: soccer      : 100%|██████████| 7/7 [00:01<00:00,  4.55it/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]:

Copied!

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]:

Copied!

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
891e2040083ffff	way/638731660
	way/854890878
	way/357822164
891e2040dcbffff	way/310783404
891e2040dcbffff	node/5451542294
...	...
891e204e133ffff	way/561854384
891e204e133ffff	way/561837447
891e2051b4bffff	way/222450303
891e204202fffff	relation/14983408
891e204220fffff	way/264158238

4045 rows × 0 columns

Embedding¶

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

In [7]:

Copied!





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

  0%|          | 0/3168 [00:00<?, ?it/s]

100%|██████████| 3168/3168 [00:00<00:00, 32668.59it/s]

GPU available: False, used: False

TPU available: False, using: 0 TPU cores

HPU available: False, using: 0 HPUs

  | Name    | Type       | Params | Mode 
-----------------------------------------------
0 | encoder | Sequential | 280    | train
-----------------------------------------------
280       Trainable params
0         Non-trainable params
280       Total params
0.001     Total estimated model params size (MB)
4         Modules in train mode
0         Modules in eval mode

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

Out[7]:

	0	1	2	3	4	5	6	7	8	9
region_id
891e2040083ffff	0.152695	0.251775	0.541692	-0.187316	-0.639290	0.079395	0.696558	-0.162220	0.199217	-0.864125
891e2040b23ffff	0.340756	-0.257625	-0.027997	0.305648	0.210122	-0.132536	-0.278368	-0.089754	-0.236633	0.326764
891e2040dcbffff	0.296672	0.557211	0.520201	0.672710	-0.278723	-0.342790	0.951536	-0.507101	0.749205	-0.198950
891e2055b17ffff	0.340756	-0.257625	-0.027997	0.305648	0.210122	-0.132536	-0.278368	-0.089754	-0.236633	0.326764
891e204219bffff	-0.290594	-0.075575	-0.319353	-0.476729	-0.005199	0.241066	-0.384562	0.375875	-0.086437	0.004702
...	...	...	...	...	...	...	...	...	...	...
891e20451abffff	0.340756	-0.257625	-0.027997	0.305648	0.210122	-0.132536	-0.278368	-0.089754	-0.236633	0.326764
891e2051b4bffff	-0.290594	-0.075575	-0.319353	-0.476729	-0.005199	0.241066	-0.384562	0.375875	-0.086437	0.004702
891e204202fffff	-0.290594	-0.075575	-0.319353	-0.476729	-0.005199	0.241066	-0.384562	0.375875	-0.086437	0.004702
891e204e49bffff	0.340756	-0.257625	-0.027997	0.305648	0.210122	-0.132536	-0.278368	-0.089754	-0.236633	0.326764
891e204220fffff	-0.290594	-0.075575	-0.319353	-0.476729	-0.005199	0.241066	-0.384562	0.375875	-0.086437	0.004702

3168 rows × 10 columns

Visualizing the embeddings' similarity¶

In [8]:

Copied!

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

Out[8]:

	0	1	2	3	4	5	6	7	8	9	cluster
region_id
891e2040083ffff	0.152695	0.251775	0.541692	-0.187316	-0.639290	0.079395	0.696558	-0.162220	0.199217	-0.864125	4
891e2040b23ffff	0.340756	-0.257625	-0.027997	0.305648	0.210122	-0.132536	-0.278368	-0.089754	-0.236633	0.326764	0
891e2040dcbffff	0.296672	0.557211	0.520201	0.672710	-0.278723	-0.342790	0.951536	-0.507101	0.749205	-0.198950	2
891e2055b17ffff	0.340756	-0.257625	-0.027997	0.305648	0.210122	-0.132536	-0.278368	-0.089754	-0.236633	0.326764	0
891e204219bffff	-0.290594	-0.075575	-0.319353	-0.476729	-0.005199	0.241066	-0.384562	0.375875	-0.086437	0.004702	1
...	...	...	...	...	...	...	...	...	...	...	...
891e20451abffff	0.340756	-0.257625	-0.027997	0.305648	0.210122	-0.132536	-0.278368	-0.089754	-0.236633	0.326764	0
891e2051b4bffff	-0.290594	-0.075575	-0.319353	-0.476729	-0.005199	0.241066	-0.384562	0.375875	-0.086437	0.004702	1
891e204202fffff	-0.290594	-0.075575	-0.319353	-0.476729	-0.005199	0.241066	-0.384562	0.375875	-0.086437	0.004702	1
891e204e49bffff	0.340756	-0.257625	-0.027997	0.305648	0.210122	-0.132536	-0.278368	-0.089754	-0.236633	0.326764	0
891e204220fffff	-0.290594	-0.075575	-0.319353	-0.476729	-0.005199	0.241066	-0.384562	0.375875	-0.086437	0.004702	1

3168 rows × 11 columns

In [9]:

Copied!

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