Merge pull request #7 from hotosm/enhance/vectorizer

Enhance : Vectorizer

.github/workflows/unit-test.yml

@@ -0,0 +1,27 @@
+name: Run Tests
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tensorflow==2.12.0 efficientnet==1.1.1
+          pip install -e .
+
+      - name: Run tests
+        run: python -m unittest discover -s tests -p 'test_*.py'

API/main.py

@@ -184,15 +184,14 @@ async def predict_api(request: PredictionRequest):
     - Predicted results.
     """
     try:
-        predictions = predict(
+        predictions = await predict(
             bbox=request.bbox,
             model_path=request.checkpoint,
             zoom_level=request.zoom_level,
             tms_url=request.source,
             tile_size=256,
             confidence=request.confidence,
             tile_overlap_distance=request.tile_overlap_distance,
-            merge_adjancent_polygons=request.merge_adjacent_polygons,
             max_angle_change=request.max_angle_change,
             skew_tolerance=request.skew_tolerance,
             tolerance=request.tolerance,

predictor/app.py

@@ -24,7 +24,6 @@ def predict(
     area_threshold=3,
     tolerance=0.5,
     tile_overlap_distance=0.15,
-    merge_adjancent_polygons=True,
     use_raster2polygon=False,
     remove_metadata=True,
     use_josm_q=False,
@@ -43,7 +42,6 @@ def predict(
         area_threshold (float, optional): Threshold for filtering polygon areas. Defaults to 3 sqm.
         tolerance (float, optional): Tolerance parameter for simplifying polygons. Defaults to 0.5 m. Percentage Tolerance = (Tolerance in Meters / Arc Length in Meters ​)×100
         tile_overlap_distance : Provides tile overlap distance to remove the strip between predictions, Defaults to 0.15m
-        merge_adjancent_polygons(bool,optional) : Merges adjacent self intersecting or containing each other polygons
     """
     if base_path:
         base_path = os.path.join(base_path, "prediction", str(uuid.uuid4()))
@@ -93,7 +91,6 @@ def predict(
             output_path=geojson_path,
             area_threshold=area_threshold,
             tolerance=tolerance,
-            merge_adjancent_polygons=merge_adjancent_polygons,
         )
     print(f"It took {round(time.time()-start)} sec to extract polygons")
     with open(geojson_path, "r") as f:

predictor/vectorizer.py

@@ -23,7 +23,6 @@ def vectorize(
     output_path: str = None,
     tolerance: float = 0.5,
     area_threshold: float = 5,
-    merge_adjancent_polygons=True,
 ) -> None:
     """Polygonize raster tiles from the input path.
 
@@ -35,7 +34,6 @@ def vectorize(
         output_path: Path of the output file.
         tolerance (float, optional): Tolerance parameter for simplifying polygons. Defaults to 0.5 m. Percentage Tolerance = (Tolerance in Meters / Arc Length in Meters ​)×100
         area_threshold (float, optional): Threshold for filtering polygon areas. Defaults to 5 sqm.
-        merge_adjancent_polygons(bool,optional) : Merges adjacent self intersecting or containing each other polygons
 
     Example::
 
@@ -64,45 +62,15 @@ def vectorize(
         raster.close()
 
     polygons = [shape(s) for s, _ in shapes(mosaic, transform=output)]
-    merged_polygons = polygons
-    if merge_adjancent_polygons:
-        # Merge adjacent polygons
-        merged_polygons = []
+    gs = gpd.GeoSeries(polygons, crs=kwargs["crs"])
 
-        for polygon in polygons:
-            if not merged_polygons:
-                merged_polygons.append(polygon)
-            else:
-                merged = False
-                for i, merged_polygon in enumerate(merged_polygons):
-                    if (
-                        polygon.intersects(merged_polygon)
-                        or polygon.contains(merged_polygon)
-                        or merged_polygon.contains(polygon)
-                    ):
-                        merged_polygons[i] = merged_polygon.union(polygon)
-                        merged = True
-                        break
-                if not merged:
-                    merged_polygons.append(polygon)
+    # Explode MultiPolygons
+    gs = gs.explode()
 
-    # areas = [poly.area for poly in merged_polygons]
-    # max_area, median_area = np.max(areas), np.median(areas)
-    polygons_filtered = []
-    for multi_polygon in merged_polygons:
-        if multi_polygon.is_empty:
-            continue
+    # Filter by area threshold
+    gs = gs[gs.area >= area_threshold]
 
-        # If it's a MultiPolygon, iterate through individual polygons
-        if multi_polygon.geom_type == "MultiPolygon":
-            for polygon in multi_polygon.geoms:
-                if polygon.area > area_threshold:
-                    polygons_filtered.append(Polygon(polygon.exterior))
-        # If it's a single Polygon, directly append it
-        elif multi_polygon.area > area_threshold:
-            polygons_filtered.append(Polygon(multi_polygon.exterior))
-
-    gs = gpd.GeoSeries(polygons_filtered, crs=kwargs["crs"]).simplify(tolerance)
+    gs = gs.simplify(tolerance)
     if gs.empty:
         raise ValueError("No Features Found")
     gs.to_crs("EPSG:4326").to_file(output_path)

setup.py

@@ -7,7 +7,7 @@
 
 setup(
     name="fairpredictor",
-    version="0.0.30",
+    version="0.0.31",
     url="https://github.com/kshitijrajsharma/fairpredictor",
     author="Kshitij Raj Sharma",
     author_email="[email protected]",

tests/test_predict.py

@@ -1,12 +1,42 @@
-bbox = [-84.1334429383278, 9.953153171808898, -84.13033694028854, 9.954719779271468]
-zoom_level = 19
-from predictor import download
-
-image_download_path = download(
-    bbox,
-    zoom_level=zoom_level,
-    tms_url="bing",
-    tile_size=256,
-    download_path="/Users/kshitij/hotosm/fairpredictor/download/test",
-)
-print(image_download_path)
+import os
+import shutil
+import tempfile
+import unittest
+
+import efficientnet.tfkeras as efn
+import requests
+
+from predictor import predict
+
+# Global variables
+TMS_URL = "https://tiles.openaerialmap.org/6501a65c0906de000167e64d/0/6501a65c0906de000167e64e/{z}/{x}/{y}"
+BBOX = [100.56228021333352, 13.685230854641182, 100.56383321235313, 13.685961853747969]
+FAIR_BASE_URL = "https://fair-dev.hotosm.org/api/v1/workspace/download"
+DATASET_ID = "dataset_65"
+TRAINING_ID = "training_297"
+
+
+class TestPredictor(unittest.TestCase):
+    def setUp(self):
+        model_url = f"{FAIR_BASE_URL}/{DATASET_ID}/output/{TRAINING_ID}/checkpoint.h5"
+        self.model_path = tempfile.NamedTemporaryFile(suffix=".h5").name
+        response = requests.get(model_url, stream=True)
+        with open(self.model_path, "wb") as out_file:
+            shutil.copyfileobj(response.raw, out_file)
+
+    def tearDown(self):
+        if self.model_path:
+            try:
+                os.remove(self.model_path)
+            except OSError:
+                pass
+
+    def test_predict(self):
+        zoom_level = 20
+        predictions = predict(BBOX, self.model_path, zoom_level, TMS_URL)
+        self.assertIsInstance(predictions, dict)
+        self.assertTrue(len(predictions["features"]) > 0)
+
+
+if __name__ == "__main__":
+    unittest.main()