Load and save

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
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 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 [00:02<00:00,  2.97it/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
891e2040aabffff	way/89992942
891e2040c63ffff	way/312187824
	way/309078337
891e2040c77ffff	way/309078337
891e2040c63ffff	way/309078320
...	...
891e204046fffff	way/101422637
891e20408abffff	node/11142405502
	node/8412148483
	node/8632996865
	node/10073860264

3949 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, 31194.67it/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
891e2040aabffff	0.447068	-0.305122	0.263580	0.492332	0.254893	-0.224263	0.125341	-0.248551	-0.011803	0.247726
891e2040c63ffff	-0.192849	0.653400	0.774197	0.662766	-0.575397	-0.001775	0.858742	-0.646547	0.738399	-0.383873
891e2043033ffff	-0.443108	-0.052730	-0.331275	-0.868652	-0.111211	0.258344	-0.086322	0.491270	-0.171393	-0.398249
891e2051b93ffff	-0.304543	-0.012448	-0.310694	-0.465949	0.003444	0.229322	-0.405792	0.379708	-0.092514	0.016726
891e20405afffff	0.447068	-0.305122	0.263580	0.492332	0.254893	-0.224263	0.125341	-0.248551	-0.011803	0.247726
...	...	...	...	...	...	...	...	...	...	...
891e2042513ffff	0.358636	-0.217853	0.003421	0.314216	0.221823	-0.131576	-0.251689	-0.131575	-0.186415	0.367329
891e20433cfffff	0.358636	-0.217854	0.003421	0.314216	0.221823	-0.131576	-0.251689	-0.131575	-0.186415	0.367329
891e2040837ffff	0.358636	-0.217853	0.003421	0.314216	0.221823	-0.131576	-0.251689	-0.131575	-0.186415	0.367329
891e204297bffff	0.111245	0.192230	0.490220	0.641814	-0.148619	-0.045905	0.342148	-0.457559	0.367655	0.119616
891e204060fffff	0.358636	-0.217853	0.003421	0.314216	0.221823	-0.131576	-0.251689	-0.131575	-0.186415	0.367329

3168 rows × 10 columns

Visualizing the embeddings' similarity¶

In [8]:

embedder.save("./modello")

embedder.save("./modello")

In [9]:

embedder_loaded = Hex2VecEmbedder.load("./modello")
embedder_loaded

embedder_loaded = Hex2VecEmbedder.load("./modello") embedder_loaded

Out[9]:

<srai.embedders.hex2vec.embedder.Hex2VecEmbedder at 0x7f9bca8a7e80>

In [10]:

from srai.embedders import Highway2VecEmbedder
from srai.loaders import OSMNetworkType, OSMWayLoader

d = OSMWayLoader(OSMNetworkType.DRIVE).load(area_gdf)

from srai.embedders import Highway2VecEmbedder from srai.loaders import OSMNetworkType, OSMWayLoader d = OSMWayLoader(OSMNetworkType.DRIVE).load(area_gdf)

/opt/hostedtoolcache/Python/3.10.13/x64/lib/python3.10/site-packages/srai/loaders/osm_way_loader/osm_way_loader.py:219: UserWarning: The clean_periphery argument has been deprecated and will be removed in a future release. Future behavior will be as though clean_periphery=True.
  G_directed = ox.graph_from_polygon(

In [11]:

joint = joiner.transform(regions_gdf, d[1])

joint = joiner.transform(regions_gdf, d[1])

In [12]:

highway2vec = Highway2VecEmbedder()
highway2vec.fit(regions_gdf, d[1], joint)

highway2vec = Highway2VecEmbedder() highway2vec.fit(regions_gdf, d[1], joint)

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 | 16.0 K
1 | decoder | Sequential | 16.2 K
---------------------------------------
32.1 K    Trainable params
0         Non-trainable params
32.1 K    Total params
0.128     Total estimated model params size (MB)
/opt/hostedtoolcache/Python/3.10.13/x64/lib/python3.10/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:441: The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=3` in the `DataLoader` to improve performance.

`Trainer.fit` stopped: `max_epochs=10` reached.

In [13]:

highway2vec.save("highway2vec")

highway2vec.save("highway2vec")

In [14]:

vars(highway2vec)

vars(highway2vec)

Out[14]:

{'_model': Highway2VecModel(
   (encoder): Sequential(
     (0): Linear(in_features=218, out_features=64, bias=True)
     (1): ReLU()
     (2): Linear(in_features=64, out_features=30, bias=True)
   )
   (decoder): Sequential(
     (0): Linear(in_features=30, out_features=64, bias=True)
     (1): ReLU()
     (2): Linear(in_features=64, out_features=218, bias=True)
   )
 ),
 '_hidden_size': 64,
 '_embedding_size': 30,
 '_is_fitted': True}

In [15]:

Highway2VecEmbedder.load("highway2vec")

Highway2VecEmbedder.load("highway2vec")

Out[15]:

<srai.embedders.highway2vec.embedder.Highway2VecEmbedder at 0x7f9bd486c760>

In [16]:

import geopandas as gpd
import pandas as pd
from srai.embedders import GTFS2VecEmbedder
from srai.constants import REGIONS_INDEX
from shapely.geometry import Polygon

features_gdf = gpd.GeoDataFrame(
    {
        "trip_count_at_6": [1, 0, 0],
        "trip_count_at_7": [1, 1, 0],
        "trip_count_at_8": [0, 0, 1],
        "directions_at_6": [
            {"A", "A1"},
            {"B", "B1"},
            {"C"},
        ],
    },
    geometry=gpd.points_from_xy([1, 2, 5], [1, 2, 2]),
    index=pd.Index(name="stop_id", data=[1, 2, 3]),
)
regions_gdf = gpd.GeoDataFrame(
    geometry=[
        Polygon([(0, 0), (0, 3), (3, 3), (3, 0)]),
        Polygon([(4, 0), (4, 3), (7, 3), (7, 0)]),
        Polygon([(8, 0), (8, 3), (11, 3), (11, 0)]),
    ],
    index=pd.Index(name=REGIONS_INDEX, data=["ff1", "ff2", "ff3"]),
)

joint_gdf = gpd.GeoDataFrame()
joint_gdf.index = pd.MultiIndex.from_tuples(
    [("ff1", 1), ("ff1", 2), ("ff2", 3)],
    names=[REGIONS_INDEX, "stop_id"],
)

embedder = GTFS2VecEmbedder(hidden_size=2, embedding_size=4)
embedder.fit(regions_gdf, features_gdf, joint_gdf)
res = embedder.transform(regions_gdf, features_gdf, joint_gdf)
res

import geopandas as gpd import pandas as pd from srai.embedders import GTFS2VecEmbedder from srai.constants import REGIONS_INDEX from shapely.geometry import Polygon features_gdf = gpd.GeoDataFrame( { "trip_count_at_6": [1, 0, 0], "trip_count_at_7": [1, 1, 0], "trip_count_at_8": [0, 0, 1], "directions_at_6": [ {"A", "A1"}, {"B", "B1"}, {"C"}, ], }, geometry=gpd.points_from_xy([1, 2, 5], [1, 2, 2]), index=pd.Index(name="stop_id", data=[1, 2, 3]), ) regions_gdf = gpd.GeoDataFrame( geometry=[ Polygon([(0, 0), (0, 3), (3, 3), (3, 0)]), Polygon([(4, 0), (4, 3), (7, 3), (7, 0)]), Polygon([(8, 0), (8, 3), (11, 3), (11, 0)]), ], index=pd.Index(name=REGIONS_INDEX, data=["ff1", "ff2", "ff3"]), ) joint_gdf = gpd.GeoDataFrame() joint_gdf.index = pd.MultiIndex.from_tuples( [("ff1", 1), ("ff1", 2), ("ff2", 3)], names=[REGIONS_INDEX, "stop_id"], ) embedder = GTFS2VecEmbedder(hidden_size=2, embedding_size=4) embedder.fit(regions_gdf, features_gdf, joint_gdf) res = embedder.transform(regions_gdf, features_gdf, joint_gdf) res

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 | 16    
1 | decoder | Sequential | 13    
---------------------------------------
29        Trainable params
0         Non-trainable params
29        Total params
0.000     Total estimated model params size (MB)
/opt/hostedtoolcache/Python/3.10.13/x64/lib/python3.10/site-packages/pytorch_lightning/loops/fit_loop.py:293: The number of training batches (1) is smaller than the logging interval Trainer(log_every_n_steps=50). Set a lower value for log_every_n_steps if you want to see logs for the training epoch.

`Trainer.fit` stopped: `max_epochs=10` reached.

Out[16]:

	0	1	2	3
region_id
ff1	0.687915	0.153115	-0.648070	-0.417944
ff2	0.849668	0.173882	-0.952428	-0.055791
ff3	0.913412	0.186434	-1.057311	0.080431

In [17]:

embedder.save("gtfs2vec")

embedder.save("gtfs2vec")

In [18]:

a = embedder.load("gtfs2vec")

a = embedder.load("gtfs2vec")

In [19]:

a = embedder.transform(regions_gdf, features_gdf, joint_gdf)

a = embedder.transform(regions_gdf, features_gdf, joint_gdf)

In [20]:

a

a

Out[20]:

	0	1	2	3
region_id
ff1	0.687915	0.153115	-0.648070	-0.417944
ff2	0.849668	0.173882	-0.952428	-0.055791
ff3	0.913412	0.186434	-1.057311	0.080431