Add POI pipeline

2026-01-26 21:31:00 +00:00 · 2026-01-26 21:31:00 +00:00 · 4d8b626150
commit 4d8b626150
parent 8a8df2ebfa
4 changed files with 124 additions and 0 deletions
--- a/Taskfile.yml
+++ b/Taskfile.yml
@ -15,6 +15,7 @@ tasks:
    cmds:
      - uv run python download_land_registry.py
      - uv run python download_arcgis_data.py
+      - uv run python download_pois.py

  pipeline:
    desc: Run data processing pipeline
--- a/download_pois.py
+++ b/download_pois.py
@ -0,0 +1,54 @@
+"""Download POI data for the UK from Overture Maps."""
+
+from pathlib import Path
+
+import overturemaps
+import pyarrow as pa
+import pyarrow.parquet as pq
+from tqdm import tqdm
+
+# UK bounding box (west, south, east, north)
+UK_BBOX = (-8.65, 49.86, 1.77, 60.86)
+
+OUTPUT_DIR = Path("data_sources")
+OUTPUT_FILE = OUTPUT_DIR / "uk_pois.parquet"
+
+
+def main():
+    OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
+
+    if OUTPUT_FILE.exists():
+        print(f"POI file already exists: {OUTPUT_FILE}")
+        print("Delete it manually to re-download.")
+        return
+
+    print("Downloading UK POI data from Overture Maps...")
+    print(f"Bounding box: {UK_BBOX}")
+    print("This may take several minutes...")
+
+    reader = overturemaps.record_batch_reader("place", bbox=UK_BBOX)
+
+    # Read all batches
+    batches = []
+    with tqdm(desc="Downloading batches", unit=" batches") as pbar:
+        for batch in reader:
+            batches.append(batch)
+            pbar.update(1)
+            pbar.set_postfix(rows=sum(b.num_rows for b in batches))
+
+    if not batches:
+        print("No data found in bounding box!")
+        return
+
+    # Combine batches into a table and write
+    table = pa.Table.from_batches(batches, schema=reader.schema)
+
+    print(f"\nWriting {table.num_rows:,} POIs to {OUTPUT_FILE}...")
+    pq.write_table(table, OUTPUT_FILE)
+
+    print(f"Download complete: {OUTPUT_FILE}")
+    print(f"File size: {OUTPUT_FILE.stat().st_size / 1024 / 1024:.1f} MB")
+
+
+if __name__ == "__main__":
+    main()
--- a/pyproject.toml
+++ b/pyproject.toml
@ -21,6 +21,7 @@ dependencies = [
    "fastapi[standard]>=0.115.0",
    "uvicorn>=0.34.0",
    "h3>=3.7.0",
+    "overturemaps>=0.18.0",
 ]

 [dependency-groups]
--- a/uv.lock
+++ b/uv.lock
@ -1309,6 +1309,21 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/ad/0d/eca3d962f9eef265f01a8e0d20085c6dd1f443cbffc11b6dede81fd82356/numpy-2.4.1-cp314-cp314t-win_arm64.whl", hash = "sha256:6436cffb4f2bf26c974344439439c95e152c9a527013f26b3577be6c2ca64295", size = 10667121, upload-time = "2026-01-10T06:44:41.644Z" },
 ]

+[[package]]
+name = "overturemaps"
+version = "0.18.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "click" },
+    { name = "numpy" },
+    { name = "pyarrow" },
+    { name = "shapely" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/bb/8b/0fe655d3cb35fa020f529447b9f36f6b8865b5393634e3e2c40e1f41a281/overturemaps-0.18.0.tar.gz", hash = "sha256:0f65807aec13d2e8ebdf46225a532e20cde8168853ace04a752956e802fd06b0", size = 13764, upload-time = "2025-12-08T21:23:11.402Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ab/d0/0def77066338456becee87e7686c55561d5ddf13a67360e705bfe7044e87/overturemaps-0.18.0-py3-none-any.whl", hash = "sha256:793db5be74ad48a63dc37e1877b3a48cb93ab0bef1ab3da8e772890e00467200", size = 14331, upload-time = "2025-12-08T21:23:10.536Z" },
+]
+
 [[package]]
 name = "packaging"
 version = "26.0"
@ -1485,6 +1500,7 @@ dependencies = [
    { name = "jupyter" },
    { name = "nest-asyncio" },
    { name = "numpy" },
+    { name = "overturemaps" },
    { name = "pandas" },
    { name = "plotly" },
    { name = "polars" },
@ -1510,6 +1526,7 @@ requires-dist = [
    { name = "jupyter", specifier = ">=1.0.0" },
    { name = "nest-asyncio", specifier = ">=1.6.0" },
    { name = "numpy", specifier = ">=1.26.0" },
+    { name = "overturemaps", specifier = ">=0.18.0" },
    { name = "pandas", specifier = ">=2.0.0" },
    { name = "plotly", specifier = ">=6.5.2" },
    { name = "polars", specifier = ">=1.37.1" },
@ -2183,6 +2200,57 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/e0/76/f963c61683a39084aa575f98089253e1e852a4417cb8a3a8a422923a5246/setuptools-80.10.1-py3-none-any.whl", hash = "sha256:fc30c51cbcb8199a219c12cc9c281b5925a4978d212f84229c909636d9f6984e", size = 1099859, upload-time = "2026-01-21T09:42:00.688Z" },
 ]

+[[package]]
+name = "shapely"
+version = "2.1.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/4d/bc/0989043118a27cccb4e906a46b7565ce36ca7b57f5a18b78f4f1b0f72d9d/shapely-2.1.2.tar.gz", hash = "sha256:2ed4ecb28320a433db18a5bf029986aa8afcfd740745e78847e330d5d94922a9", size = 315489, upload-time = "2025-09-24T13:51:41.432Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/24/c0/f3b6453cf2dfa99adc0ba6675f9aaff9e526d2224cbd7ff9c1a879238693/shapely-2.1.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fe2533caae6a91a543dec62e8360fe86ffcdc42a7c55f9dfd0128a977a896b94", size = 1833550, upload-time = "2025-09-24T13:50:30.019Z" },
+    { url = "https://files.pythonhosted.org/packages/86/07/59dee0bc4b913b7ab59ab1086225baca5b8f19865e6101db9ebb7243e132/shapely-2.1.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ba4d1333cc0bc94381d6d4308d2e4e008e0bd128bdcff5573199742ee3634359", size = 1643556, upload-time = "2025-09-24T13:50:32.291Z" },
+    { url = "https://files.pythonhosted.org/packages/26/29/a5397e75b435b9895cd53e165083faed5d12fd9626eadec15a83a2411f0f/shapely-2.1.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0bd308103340030feef6c111d3eb98d50dc13feea33affc8a6f9fa549e9458a3", size = 2988308, upload-time = "2025-09-24T13:50:33.862Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/37/e781683abac55dde9771e086b790e554811a71ed0b2b8a1e789b7430dd44/shapely-2.1.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:1e7d4d7ad262a48bb44277ca12c7c78cb1b0f56b32c10734ec9a1d30c0b0c54b", size = 3099844, upload-time = "2025-09-24T13:50:35.459Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/f3/9876b64d4a5a321b9dc482c92bb6f061f2fa42131cba643c699f39317cb9/shapely-2.1.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e9eddfe513096a71896441a7c37db72da0687b34752c4e193577a145c71736fc", size = 3988842, upload-time = "2025-09-24T13:50:37.478Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/a0/704c7292f7014c7e74ec84eddb7b109e1fbae74a16deae9c1504b1d15565/shapely-2.1.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:980c777c612514c0cf99bc8a9de6d286f5e186dcaf9091252fcd444e5638193d", size = 4152714, upload-time = "2025-09-24T13:50:39.9Z" },
+    { url = "https://files.pythonhosted.org/packages/53/46/319c9dc788884ad0785242543cdffac0e6530e4d0deb6c4862bc4143dcf3/shapely-2.1.2-cp312-cp312-win32.whl", hash = "sha256:9111274b88e4d7b54a95218e243282709b330ef52b7b86bc6aaf4f805306f454", size = 1542745, upload-time = "2025-09-24T13:50:41.414Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/bf/cb6c1c505cb31e818e900b9312d514f381fbfa5c4363edfce0fcc4f8c1a4/shapely-2.1.2-cp312-cp312-win_amd64.whl", hash = "sha256:743044b4cfb34f9a67205cee9279feaf60ba7d02e69febc2afc609047cb49179", size = 1722861, upload-time = "2025-09-24T13:50:43.35Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/90/98ef257c23c46425dc4d1d31005ad7c8d649fe423a38b917db02c30f1f5a/shapely-2.1.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:b510dda1a3672d6879beb319bc7c5fd302c6c354584690973c838f46ec3e0fa8", size = 1832644, upload-time = "2025-09-24T13:50:44.886Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/ab/0bee5a830d209adcd3a01f2d4b70e587cdd9fd7380d5198c064091005af8/shapely-2.1.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:8cff473e81017594d20ec55d86b54bc635544897e13a7cfc12e36909c5309a2a", size = 1642887, upload-time = "2025-09-24T13:50:46.735Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/5e/7d7f54ba960c13302584c73704d8c4d15404a51024631adb60b126a4ae88/shapely-2.1.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fe7b77dc63d707c09726b7908f575fc04ff1d1ad0f3fb92aec212396bc6cfe5e", size = 2970931, upload-time = "2025-09-24T13:50:48.374Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/a2/83fc37e2a58090e3d2ff79175a95493c664bcd0b653dd75cb9134645a4e5/shapely-2.1.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7ed1a5bbfb386ee8332713bf7508bc24e32d24b74fc9a7b9f8529a55db9f4ee6", size = 3082855, upload-time = "2025-09-24T13:50:50.037Z" },
+    { url = "https://files.pythonhosted.org/packages/44/2b/578faf235a5b09f16b5f02833c53822294d7f21b242f8e2d0cf03fb64321/shapely-2.1.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a84e0582858d841d54355246ddfcbd1fce3179f185da7470f41ce39d001ee1af", size = 3979960, upload-time = "2025-09-24T13:50:51.74Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/04/167f096386120f692cc4ca02f75a17b961858997a95e67a3cb6a7bbd6b53/shapely-2.1.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:dc3487447a43d42adcdf52d7ac73804f2312cbfa5d433a7d2c506dcab0033dfd", size = 4142851, upload-time = "2025-09-24T13:50:53.49Z" },
+    { url = "https://files.pythonhosted.org/packages/48/74/fb402c5a6235d1c65a97348b48cdedb75fb19eca2b1d66d04969fc1c6091/shapely-2.1.2-cp313-cp313-win32.whl", hash = "sha256:9c3a3c648aedc9f99c09263b39f2d8252f199cb3ac154fadc173283d7d111350", size = 1541890, upload-time = "2025-09-24T13:50:55.337Z" },
+    { url = "https://files.pythonhosted.org/packages/41/47/3647fe7ad990af60ad98b889657a976042c9988c2807cf322a9d6685f462/shapely-2.1.2-cp313-cp313-win_amd64.whl", hash = "sha256:ca2591bff6645c216695bdf1614fca9c82ea1144d4a7591a466fef64f28f0715", size = 1722151, upload-time = "2025-09-24T13:50:57.153Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/49/63953754faa51ffe7d8189bfbe9ca34def29f8c0e34c67cbe2a2795f269d/shapely-2.1.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:2d93d23bdd2ed9dc157b46bc2f19b7da143ca8714464249bef6771c679d5ff40", size = 1834130, upload-time = "2025-09-24T13:50:58.49Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/ee/dce001c1984052970ff60eb4727164892fb2d08052c575042a47f5a9e88f/shapely-2.1.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:01d0d304b25634d60bd7cf291828119ab55a3bab87dc4af1e44b07fb225f188b", size = 1642802, upload-time = "2025-09-24T13:50:59.871Z" },
+    { url = "https://files.pythonhosted.org/packages/da/e7/fc4e9a19929522877fa602f705706b96e78376afb7fad09cad5b9af1553c/shapely-2.1.2-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8d8382dd120d64b03698b7298b89611a6ea6f55ada9d39942838b79c9bc89801", size = 3018460, upload-time = "2025-09-24T13:51:02.08Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/18/7519a25db21847b525696883ddc8e6a0ecaa36159ea88e0fef11466384d0/shapely-2.1.2-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:19efa3611eef966e776183e338b2d7ea43569ae99ab34f8d17c2c054d3205cc0", size = 3095223, upload-time = "2025-09-24T13:51:04.472Z" },
+    { url = "https://files.pythonhosted.org/packages/48/de/b59a620b1f3a129c3fecc2737104a0a7e04e79335bd3b0a1f1609744cf17/shapely-2.1.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:346ec0c1a0fcd32f57f00e4134d1200e14bf3f5ae12af87ba83ca275c502498c", size = 4030760, upload-time = "2025-09-24T13:51:06.455Z" },
+    { url = "https://files.pythonhosted.org/packages/96/b3/c6655ee7232b417562bae192ae0d3ceaadb1cc0ffc2088a2ddf415456cc2/shapely-2.1.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:6305993a35989391bd3476ee538a5c9a845861462327efe00dd11a5c8c709a99", size = 4170078, upload-time = "2025-09-24T13:51:08.584Z" },
+    { url = "https://files.pythonhosted.org/packages/a0/8e/605c76808d73503c9333af8f6cbe7e1354d2d238bda5f88eea36bfe0f42a/shapely-2.1.2-cp313-cp313t-win32.whl", hash = "sha256:c8876673449f3401f278c86eb33224c5764582f72b653a415d0e6672fde887bf", size = 1559178, upload-time = "2025-09-24T13:51:10.73Z" },
+    { url = "https://files.pythonhosted.org/packages/36/f7/d317eb232352a1f1444d11002d477e54514a4a6045536d49d0c59783c0da/shapely-2.1.2-cp313-cp313t-win_amd64.whl", hash = "sha256:4a44bc62a10d84c11a7a3d7c1c4fe857f7477c3506e24c9062da0db0ae0c449c", size = 1739756, upload-time = "2025-09-24T13:51:12.105Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/c4/3ce4c2d9b6aabd27d26ec988f08cb877ba9e6e96086eff81bfea93e688c7/shapely-2.1.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:9a522f460d28e2bf4e12396240a5fc1518788b2fcd73535166d748399ef0c223", size = 1831290, upload-time = "2025-09-24T13:51:13.56Z" },
+    { url = "https://files.pythonhosted.org/packages/17/b9/f6ab8918fc15429f79cb04afa9f9913546212d7fb5e5196132a2af46676b/shapely-2.1.2-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:1ff629e00818033b8d71139565527ced7d776c269a49bd78c9df84e8f852190c", size = 1641463, upload-time = "2025-09-24T13:51:14.972Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/57/91d59ae525ca641e7ac5551c04c9503aee6f29b92b392f31790fcb1a4358/shapely-2.1.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f67b34271dedc3c653eba4e3d7111aa421d5be9b4c4c7d38d30907f796cb30df", size = 2970145, upload-time = "2025-09-24T13:51:16.961Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/cb/4948be52ee1da6927831ab59e10d4c29baa2a714f599f1f0d1bc747f5777/shapely-2.1.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:21952dc00df38a2c28375659b07a3979d22641aeb104751e769c3ee825aadecf", size = 3073806, upload-time = "2025-09-24T13:51:18.712Z" },
+    { url = "https://files.pythonhosted.org/packages/03/83/f768a54af775eb41ef2e7bec8a0a0dbe7d2431c3e78c0a8bdba7ab17e446/shapely-2.1.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:1f2f33f486777456586948e333a56ae21f35ae273be99255a191f5c1fa302eb4", size = 3980803, upload-time = "2025-09-24T13:51:20.37Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/cb/559c7c195807c91c79d38a1f6901384a2878a76fbdf3f1048893a9b7534d/shapely-2.1.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:cf831a13e0d5a7eb519e96f58ec26e049b1fad411fc6fc23b162a7ce04d9cffc", size = 4133301, upload-time = "2025-09-24T13:51:21.887Z" },
+    { url = "https://files.pythonhosted.org/packages/80/cd/60d5ae203241c53ef3abd2ef27c6800e21afd6c94e39db5315ea0cbafb4a/shapely-2.1.2-cp314-cp314-win32.whl", hash = "sha256:61edcd8d0d17dd99075d320a1dd39c0cb9616f7572f10ef91b4b5b00c4aeb566", size = 1583247, upload-time = "2025-09-24T13:51:23.401Z" },
+    { url = "https://files.pythonhosted.org/packages/74/d4/135684f342e909330e50d31d441ace06bf83c7dc0777e11043f99167b123/shapely-2.1.2-cp314-cp314-win_amd64.whl", hash = "sha256:a444e7afccdb0999e203b976adb37ea633725333e5b119ad40b1ca291ecf311c", size = 1773019, upload-time = "2025-09-24T13:51:24.873Z" },
+    { url = "https://files.pythonhosted.org/packages/a3/05/a44f3f9f695fa3ada22786dc9da33c933da1cbc4bfe876fe3a100bafe263/shapely-2.1.2-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:5ebe3f84c6112ad3d4632b1fd2290665aa75d4cef5f6c5d77c4c95b324527c6a", size = 1834137, upload-time = "2025-09-24T13:51:26.665Z" },
+    { url = "https://files.pythonhosted.org/packages/52/7e/4d57db45bf314573427b0a70dfca15d912d108e6023f623947fa69f39b72/shapely-2.1.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:5860eb9f00a1d49ebb14e881f5caf6c2cf472c7fd38bd7f253bbd34f934eb076", size = 1642884, upload-time = "2025-09-24T13:51:28.029Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/27/4e29c0a55d6d14ad7422bf86995d7ff3f54af0eba59617eb95caf84b9680/shapely-2.1.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:b705c99c76695702656327b819c9660768ec33f5ce01fa32b2af62b56ba400a1", size = 3018320, upload-time = "2025-09-24T13:51:29.903Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/bb/992e6a3c463f4d29d4cd6ab8963b75b1b1040199edbd72beada4af46bde5/shapely-2.1.2-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a1fd0ea855b2cf7c9cddaf25543e914dd75af9de08785f20ca3085f2c9ca60b0", size = 3094931, upload-time = "2025-09-24T13:51:32.699Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/16/82e65e21070e473f0ed6451224ed9fa0be85033d17e0c6e7213a12f59d12/shapely-2.1.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:df90e2db118c3671a0754f38e36802db75fe0920d211a27481daf50a711fdf26", size = 4030406, upload-time = "2025-09-24T13:51:34.189Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/75/c24ed871c576d7e2b64b04b1fe3d075157f6eb54e59670d3f5ffb36e25c7/shapely-2.1.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:361b6d45030b4ac64ddd0a26046906c8202eb60d0f9f53085f5179f1d23021a0", size = 4169511, upload-time = "2025-09-24T13:51:36.297Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/f7/b3d1d6d18ebf55236eec1c681ce5e665742aab3c0b7b232720a7d43df7b6/shapely-2.1.2-cp314-cp314t-win32.whl", hash = "sha256:b54df60f1fbdecc8ebc2c5b11870461a6417b3d617f555e5033f1505d36e5735", size = 1602607, upload-time = "2025-09-24T13:51:37.757Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/f6/f09272a71976dfc138129b8faf435d064a811ae2f708cb147dccdf7aacdb/shapely-2.1.2-cp314-cp314t-win_amd64.whl", hash = "sha256:0036ac886e0923417932c2e6369b6c52e38e0ff5d9120b90eef5cd9a5fc5cae9", size = 1796682, upload-time = "2025-09-24T13:51:39.233Z" },
+]
+
 [[package]]
 name = "shellingham"
 version = "1.5.4"