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]:
71
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 [00:03<00:22, 3.71s/it]
Downloading landuse: forest : 14%|█▍ | 1/7 [00:03<00:22, 3.71s/it]
Downloading landuse: forest : 29%|██▊ | 2/7 [00:08<00:21, 4.23s/it]
Downloading amenity: bar : 29%|██▊ | 2/7 [00:08<00:21, 4.23s/it]
Downloading amenity: bar : 43%|████▎ | 3/7 [00:10<00:13, 3.40s/it]
Downloading amenity: restaurant: 43%|████▎ | 3/7 [00:10<00:13, 3.40s/it]
Downloading amenity: restaurant: 57%|█████▋ | 4/7 [00:35<00:35, 11.74s/it]
Downloading amenity: cafe : 57%|█████▋ | 4/7 [00:35<00:35, 11.74s/it]
Downloading amenity: cafe : 71%|███████▏ | 5/7 [00:37<00:16, 8.40s/it]
Downloading water: river : 71%|███████▏ | 5/7 [00:37<00:16, 8.40s/it]
Downloading water: river : 86%|████████▌ | 6/7 [00:41<00:06, 6.71s/it]
Downloading sport: soccer : 86%|████████▌ | 6/7 [00:41<00:06, 6.71s/it]
Downloading sport: soccer : 100%|██████████| 7/7 [00:43<00:00, 5.43s/it]
Downloading sport: soccer : 100%|██████████| 7/7 [00:43<00:00, 6.28s/it]
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 |
|---|---|
| 891e2055b27ffff | relation/14339424 |
| node/4222190396 | |
| 891e2050b47ffff | relation/1559777 |
| way/29404332 | |
| way/311761149 | |
| ... | ... |
| 891e204251bffff | way/435495732 |
| 891e2042827ffff | way/1056180351 |
| 891e20442d7ffff | way/381939983 |
| way/381939938 | |
| way/110501826 |
4024 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, 32033.87it/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
Missing logger folder: /home/runner/work/srai/srai/examples/embedders/lightning_logs
| 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 | ||||||||||
| 891e2040317ffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 |
| 891e2055b27ffff | 0.054981 | 0.117424 | 0.444978 | 0.618073 | -0.105195 | -0.071252 | 0.464371 | -0.347658 | 0.463530 | 0.032849 |
| 891e20402b3ffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 |
| 891e204282fffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 |
| 891e2050b47ffff | -0.416563 | -0.140404 | -0.116602 | -1.032999 | -0.311619 | 0.297523 | 0.209845 | 0.541330 | -0.121695 | -0.735279 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 891e20429a7ffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 |
| 891e20473dbffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 |
| 891e204244bffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 |
| 891e2042827ffff | 0.061202 | 0.109862 | 0.451535 | 0.578636 | -0.160396 | -0.004274 | 0.358026 | -0.382113 | 0.400536 | 0.051121 |
| 891e20442d7ffff | -0.550784 | 0.390015 | -0.488195 | -0.784662 | -0.095169 | 0.233162 | -0.221192 | 0.374109 | -0.156548 | -0.249141 |
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 | |||||||||||
| 891e2040317ffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 | 0 |
| 891e2055b27ffff | 0.054981 | 0.117424 | 0.444978 | 0.618073 | -0.105195 | -0.071252 | 0.464371 | -0.347658 | 0.463530 | 0.032849 | 2 |
| 891e20402b3ffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 | 0 |
| 891e204282fffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 | 0 |
| 891e2050b47ffff | -0.416563 | -0.140404 | -0.116602 | -1.032999 | -0.311619 | 0.297523 | 0.209845 | 0.541330 | -0.121695 | -0.735279 | 1 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 891e20429a7ffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 | 0 |
| 891e20473dbffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 | 0 |
| 891e204244bffff | 0.334799 | -0.238250 | -0.035819 | 0.275658 | 0.219949 | -0.132110 | -0.270282 | -0.069363 | -0.221657 | 0.328926 | 0 |
| 891e2042827ffff | 0.061202 | 0.109862 | 0.451535 | 0.578636 | -0.160396 | -0.004274 | 0.358026 | -0.382113 | 0.400536 | 0.051121 | 2 |
| 891e20442d7ffff | -0.550784 | 0.390015 | -0.488195 | -0.784662 | -0.095169 | 0.233162 | -0.221192 | 0.374109 | -0.156548 | -0.249141 | 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