feat: add osm data loader based on pbf files

.gitignore

@@ -142,4 +142,7 @@ requirements.txt
 cache/
 
 # pytorch lightning
-lightning_logs/
+lightning_logs/
+
+# files_cache
+files/

CHANGELOG.md

@@ -1,4 +1,5 @@
 # Changelog
+
 All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
@@ -7,15 +8,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased] - 2022-MM-DD
 
 ### Added
+
 - GTFS Loader from gtfs2vec paper
 - GTFS2Vec Model from gtfs2vec paper
 - GTFS2Vec Embedder using gtfs2vec model
-- OSMTagLoader
+- OSMOnlineLoader
+- OSMPbfLoader
 - Neighbourhood
 - H3Neighbourhood
 - AdjacencyNeighbourhood
 
 ### Changed
+
 - Change embedders and joiners interface to have `.transform` method
 
 ### Deprecated
@@ -29,6 +33,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [0.0.1] - 2022-11-23
 
 ### Added
+
 - PDM as a dependency management tool
 - black, flake8, isort, mypy, pytest-cov
 - pre-commit configuration
@@ -42,5 +47,5 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Intersection Joiner
 - Geoparquet Loader
 
-[Unreleased]: https://github.com/srai-lab/srai/compare/0.0.1...HEAD
+[unreleased]: https://github.com/srai-lab/srai/compare/0.0.1...HEAD
 [0.0.1]: https://github.com/srai-lab/srai/compare/687500b...0.0.1

examples/embedders/count_embedder.ipynb

@@ -8,8 +8,8 @@
    "source": [
     "from shapely import geometry\n",
     "import geopandas as gpd\n",
-    "from srai.utils.constants import WGS84_CRS\n",
-    "from srai.loaders.osm_tag_loader import OSMTagLoader\n",
+    "from srai.constants import WGS84_CRS\n",
+    "from srai.loaders.osm_loaders import OSMOnlineLoader\n",
     "from srai.regionizers import H3Regionizer\n",
     "from srai.joiners import IntersectionJoiner\n",
     "from srai.embedders import CountEmbedder"
@@ -93,7 +93,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = OSMTagLoader()\n",
+    "loader = OSMOnlineLoader()\n",
     "tags = {\n",
     "    \"leisure\": [\"playground\", \"adult_gaming_centre\"],\n",
     "    \"amenity\": \"pub\",\n",

examples/loaders/README.md

@@ -4,3 +4,5 @@ Examples illustrating the usage of every Loader.
 
 - [GeoparquetLoader](geoparquet_loader.ipynb)
 - [GTFSLoader](gtfs_loader.ipynb)
+- [OSMOnlineLoader](osm_online_loader.ipynb)
+- [OSMPbfLoader](osm_pbf_loader.ipynb)

examples/loaders/geoparquet_loader.ipynb

@@ -36,7 +36,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "base_gdf = gpql.load(file_path=\"files/example.parquet\")\n",
+    "base_gdf = gpql.load(file_path=\"example_files/example.parquet\")\n",
     "base_gdf"
    ]
   },
@@ -55,7 +55,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "indexed_gdf = gpql.load(file_path=\"files/example.parquet\", index_column=\"name\")\n",
+    "indexed_gdf = gpql.load(file_path=\"example_files/example.parquet\", index_column=\"name\")\n",
     "indexed_gdf"
    ]
   },
@@ -65,7 +65,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "limited_gdf = gpql.load(file_path=\"files/example.parquet\", columns=[\"continent\", \"name\", \"pop_est\"])\n",
+    "limited_gdf = gpql.load(\n",
+    "    file_path=\"example_files/example.parquet\", columns=[\"continent\", \"name\", \"pop_est\"]\n",
+    ")\n",
     "limited_gdf"
    ]
   },
@@ -79,7 +81,7 @@
     "bbox = box(minx=-106.645646, maxx=-93.508292, miny=25.837377, maxy=36.500704)\n",
     "bbox_gdf = gpd.GeoDataFrame({\"geometry\": [bbox]}, crs=\"EPSG:4326\")\n",
     "\n",
-    "cut_gdf = gpql.load(file_path=\"files/example.parquet\", area=bbox_gdf)\n",
+    "cut_gdf = gpql.load(file_path=\"example_files/example.parquet\", area=bbox_gdf)\n",
     "cut_gdf"
    ]
   },

examples/loaders/gtfs_loader.ipynb

@@ -20,8 +20,8 @@
     "import geopandas as gpd\n",
     "import numpy as np\n",
     "from shapely.geometry import Point\n",
-    "from srai.utils.constants import WGS84_CRS\n",
-    "from utils import download"
+    "from srai.constants import WGS84_CRS\n",
+    "from srai.utils import download_file"
    ]
   },
   {
@@ -46,7 +46,7 @@
     "wroclaw_gtfs = Path().resolve() / \"files\" / \"example.zip\"\n",
     "gtfs_url = \"https://transitfeeds.com/p/mpk-wroc-aw/663/20221221/download\"\n",
     "\n",
-    "download(gtfs_url, wroclaw_gtfs.as_posix())"
+    "download_file(gtfs_url, wroclaw_gtfs.as_posix())"
    ]
   },
   {

examples/loaders/osm_tag_loader.ipynb → examples/loaders/osm_online_loader.ipynb

@@ -5,7 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# OSM Tag Loader"
+    "# OSM Online Loader"
    ]
   },
   {
@@ -14,10 +14,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from srai.loaders.osm_tag_loader.filters.popular import get_popular_tags\n",
-    "from srai.loaders.osm_tag_loader.filters import HEX2VEC_FILTER\n",
-    "from srai.loaders.osm_tag_loader import OSMTagLoader\n",
-    "from srai.utils.geocode import geocode_to_region_gdf\n",
+    "from srai.loaders.osm_loaders.filters.popular import get_popular_tags\n",
+    "from srai.loaders.osm_loaders.filters import HEX2VEC_FILTER\n",
+    "from srai.loaders.osm_loaders import OSMOnlineLoader\n",
+    "from srai.utils import geocode_to_region_gdf\n",
     "from functional import seq"
    ]
   },
@@ -95,7 +95,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Using OSMTagLoader to download data for a specific area"
+    "## Using OSMOnlineLoader to download data for a specific area"
    ]
   },
   {
@@ -112,7 +112,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = OSMTagLoader()\n",
+    "loader = OSMOnlineLoader()\n",
     "parks_filter = {\"leisure\": \"park\"}\n",
     "wroclaw_gdf = geocode_to_region_gdf(\"Wrocław, Poland\")\n",
     "parks_gdf = loader.load(wroclaw_gdf, parks_filter)\n",