OSM Online Loader¶

In [1]:

Copied!





from srai.loaders.osm_loaders.filters.popular import get_popular_tags
from srai.loaders.osm_loaders.filters import GEOFABRIK_LAYERS, HEX2VEC_FILTER
from srai.loaders.osm_loaders import OSMOnlineLoader
from srai.regionalizers import geocode_to_region_gdf
from srai.plotting.folium_wrapper import plot_regions
from functional import seq
from srai.loaders.osm_loaders.filters.popular import get_popular_tags
from srai.loaders.osm_loaders.filters import GEOFABRIK_LAYERS, HEX2VEC_FILTER
from srai.loaders.osm_loaders import OSMOnlineLoader
from srai.regionalizers import geocode_to_region_gdf
from srai.plotting.folium_wrapper import plot_regions
from functional import seq

Filters¶

Filters are dictionaries used for specifying what type of objects one would like to download from OpenStreetMap.
There is currently one predefined filter (from Hex2Vec paper) and one way to download a filter - using popular tags from taginfo API.
They can also be defined manually in code.

Additionally, few predefined grouped filters are available (eg. BASE_OSM_GROUPS_FILTER and GEOFABRIK_LAYERS). Grouped filters categorize base filters into groups.

Get popular tags from taginfo API¶

In [2]:

Copied!





all_popular_tags = get_popular_tags()
num_keys = len(all_popular_tags)
num_values = seq(all_popular_tags.values()).map(len).sum()
f"Unique keys: {num_keys}. Key/value pairs: {num_values}"
all_popular_tags = get_popular_tags()
num_keys = len(all_popular_tags)
num_values = seq(all_popular_tags.values()).map(len).sum()
f"Unique keys: {num_keys}. Key/value pairs: {num_values}"

Out[2]:

'Unique keys: 1144. Key/value pairs: 11415'

In [3]:

Copied!

seq(all_popular_tags.items()).take(10).dict()
seq(all_popular_tags.items()).take(10).dict()

Out[3]:

{'4wd_only': ['yes'],
 'CLC:code': ['112', '211', '221', '231', '243', '311', '312', '313'],
 'CLC:explanation': ['See http://wiki.openstreetmap.org/wiki/Romania_CLC_Import.'],
 'CLC:year': ['2006'],
 'FIXME': ['Shape Bing outline.'],
 'FMMP_modified': ['no'],
 'FMMP_reviewed': ['no'],
 'GNS:dsg_code': ['PPL', 'WAD'],
 'GNS:dsg_name': ['populated place', 'wadi'],
 'GNS:dsg_string': ['populated place']}

In [4]:

Copied!

frequent_in_wiki_only_tags = get_popular_tags(in_wiki_only=True, min_fraction=0.001)
frequent_in_wiki_only_tags
frequent_in_wiki_only_tags = get_popular_tags(in_wiki_only=True, min_fraction=0.001)
frequent_in_wiki_only_tags

Out[4]:

{'access': ['private'],
 'building': ['house', 'residential', 'yes'],
 'highway': ['footway',
  'path',
  'residential',
  'service',
  'track',
  'unclassified'],
 'natural': ['tree', 'water', 'wood'],
 'oneway': ['yes'],
 'power': ['pole', 'tower'],
 'service': ['driveway'],
 'source': ['BAG', 'Bing'],
 'surface': ['asphalt', 'unpaved'],
 'wall': ['no'],
 'waterway': ['stream']}

Import a predefined filter¶

In [5]:

Copied!

hex_2_vec_keys = len(HEX2VEC_FILTER)
hex_2_vec_key_values = seq(HEX2VEC_FILTER.values()).map(len).sum()
f"Unique keys: {hex_2_vec_keys}. Key/value pairs: {hex_2_vec_key_values}"
hex_2_vec_keys = len(HEX2VEC_FILTER)
hex_2_vec_key_values = seq(HEX2VEC_FILTER.values()).map(len).sum()
f"Unique keys: {hex_2_vec_keys}. Key/value pairs: {hex_2_vec_key_values}"

Out[5]:

'Unique keys: 15. Key/value pairs: 725'

In [6]:

Copied!





geofabrik_layers_keys = len(GEOFABRIK_LAYERS)
geofabrik_layers_key_values = (
    seq(GEOFABRIK_LAYERS.values()).flat_map(lambda filter: filter.items()).map(len).sum()
)
f"Unique groups: {geofabrik_layers_keys}. Key/value pairs: {geofabrik_layers_key_values}"
geofabrik_layers_keys = len(GEOFABRIK_LAYERS)
geofabrik_layers_key_values = (
    seq(GEOFABRIK_LAYERS.values()).flat_map(lambda filter: filter.items()).map(len).sum()
)
f"Unique groups: {geofabrik_layers_keys}. Key/value pairs: {geofabrik_layers_key_values}"

Out[6]:

'Unique groups: 28. Key/value pairs: 116'

Using OSMOnlineLoader to download data for a specific area¶

Download all parks in Wrocław, Poland¶

In [7]:

Copied!





loader = OSMOnlineLoader()
parks_filter = {"leisure": "park"}
wroclaw_gdf = geocode_to_region_gdf("Wrocław, Poland")
parks_gdf = loader.load(wroclaw_gdf, parks_filter)
parks_gdf
loader = OSMOnlineLoader()
parks_filter = {"leisure": "park"}
wroclaw_gdf = geocode_to_region_gdf("Wrocław, Poland")
parks_gdf = loader.load(wroclaw_gdf, parks_filter)
parks_gdf

Downloading leisure: park: 100%|██████████| 1/1 [00:00<00:00,  2.95it/s]

Out[7]:

	geometry	leisure
feature_id
relation/1348101	POLYGON ((17.07422 51.08476, 17.07431 51.08479...	park
relation/3654662	MULTIPOLYGON (((17.05660 51.11998, 17.05674 51...	park
relation/4552866	POLYGON ((16.87549 51.13633, 16.87538 51.13640...	park
relation/6629819	POLYGON ((16.97217 51.08334, 16.97213 51.08324...	park
relation/6727464	POLYGON ((16.97677 51.09440, 16.97681 51.09440...	park
...	...	...
way/1126150757	POLYGON ((16.95842 51.13166, 16.95822 51.13131...	park
way/1158135958	POLYGON ((17.05039 51.11758, 17.05023 51.11760...	park
way/1161782832	POLYGON ((16.99525 51.07389, 16.99542 51.07414...	park
way/1162122133	POLYGON ((16.84424 51.12090, 16.84419 51.12084...	park
way/1184167518	POLYGON ((17.02414 51.11386, 17.02409 51.11356...	park

285 rows × 2 columns

In [8]:

Copied!

folium_map = plot_regions(wroclaw_gdf, colormap=["lightgray"], tiles_style="CartoDB positron")
parks_gdf.explore(m=folium_map, color="forestgreen")
folium_map = plot_regions(wroclaw_gdf, colormap=["lightgray"], tiles_style="CartoDB positron")
parks_gdf.explore(m=folium_map, color="forestgreen")

Out[8]:

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

Uses grouped filters as an example.

In [9]:

Copied!





barcelona_gdf = geocode_to_region_gdf("Barcelona")
barcelona_filter = {
    "tourism": {"building": "hotel", "amenity": ["bar", "cafe", "pub"]},
    "sport": {"sport": "soccer", "leisure": ["pitch", "sports_centre", "stadium"]},
}

barcelona_objects_gdf = loader.load(barcelona_gdf, barcelona_filter)
barcelona_objects_gdf
barcelona_gdf = geocode_to_region_gdf("Barcelona")
barcelona_filter = {
    "tourism": {"building": "hotel", "amenity": ["bar", "cafe", "pub"]},
    "sport": {"sport": "soccer", "leisure": ["pitch", "sports_centre", "stadium"]},
}

barcelona_objects_gdf = loader.load(barcelona_gdf, barcelona_filter)
barcelona_objects_gdf

Downloading leisure: stadium      : 100%|██████████| 8/8 [00:01<00:00,  4.57it/s]
Grouping features: 100%|██████████| 3898/3898 [00:00<00:00, 5657.53it/s]

Out[9]:

	geometry	tourism	sport
feature_id
node/216330105	POINT (2.17484 41.38580)	amenity=bar	NaN
node/432592965	POINT (2.17077 41.38035)	amenity=cafe	NaN
node/499122827	POINT (2.17440 41.43041)	amenity=bar	NaN
node/499122828	POINT (2.17371 41.43198)	amenity=bar	NaN
node/499122829	POINT (2.17252 41.43052)	amenity=cafe	NaN
...	...	...	...
way/1180781727	POLYGON ((2.09863 41.42333, 2.09831 41.42327, ...	NaN	leisure=pitch
way/1182888351	POLYGON ((2.16370 41.43251, 2.16387 41.43256, ...	NaN	leisure=pitch
way/1182888352	POLYGON ((2.16365 41.43267, 2.16376 41.43271, ...	NaN	leisure=pitch
way/1182888353	POLYGON ((2.16358 41.43279, 2.16368 41.43283, ...	NaN	leisure=pitch
way/1190348351	POLYGON ((2.15381 41.38153, 2.15392 41.38161, ...	NaN	leisure=pitch

3898 rows × 3 columns

Tourism group¶

In [10]:

Copied!





folium_map = plot_regions(barcelona_gdf, colormap=["lightgray"], tiles_style="CartoDB positron")
barcelona_objects_gdf.query("tourism.notna()").explore(
    m=folium_map,
    color="orangered",
    marker_kwds=dict(radius=1),
)
folium_map = plot_regions(barcelona_gdf, colormap=["lightgray"], tiles_style="CartoDB positron")
barcelona_objects_gdf.query("tourism.notna()").explore(
    m=folium_map,
    color="orangered",
    marker_kwds=dict(radius=1),
)

Out[10]: