Merge pull request #45 from swiss-territorial-data-lab/gs/make_examples

Correct log output

Author: clmarmy

README.md

@@ -19,14 +19,14 @@ generate_tilesets.py:
   datasets:
     aoi_tiles: trne/tiles.geojson
     ground_truth_labels: trne/labels.geojson
-    # fp_labels:
-    #   fp_shp: trne/FP.geojson 
+    # add_fp_labels:
+    #   fp_labels: trne/FP.geojson 
     #   frac_trn: 0.7        # fraction of fp tiles to add to the trn dataset, then the remaining tiles will be split in 2 and added to tst and val datasets                          
     image_source:
       type: XYZ                             # supported values: 1. MIL = Map Image Layer 2. WMS 3. XYZ 4. FOLDER
       year: 2020                   # supported values: 1. multi-year (tiles of different year), 2. <year> (i.e. 2020)
       location: https://wmts.geo.admin.ch/1.0.0/ch.swisstopo.swissimage-product/default/{year}/3857/{z}/{x}/{y}.jpeg
-  # empty_tiles:            # add empty tiles to datasets
+  # add_empty_tiles:            # add empty tiles to datasets
   #   tiles_frac: 0.5       # fraction (relative to the number of tiles intersecting labels) of empty tiles to add
   #   frac_trn: 0.7         # fraction of empty tiles to add to the trn dataset, then the remaining tiles will be split in 2 and added to tst and val datasets
   #   keep_oth_tiles: False # keep tiles in oth dataset not intersecting oth labels

examples/mineral-extract-sites-detection/config_trne.yaml

@@ -264,7 +264,7 @@ def bbox(bounds):
     logger.info(f"There were {nb_tiles} tiles created")
 
     # Get the number of tiles intersecting labels
-    tiles_4326_gt_gdf = gpd.sjoin(tiles_4326_all_gdf, gt_labels_4326_gdf, how='inner', predicate='intersects')
+    tiles_4326_gt_gdf = gpd.sjoin(tiles_4326_all_gdf, gt_labels_4326_gdf[['geometry', 'CATEGORY', 'SUPERCATEGORY']], how='inner', predicate='intersects')
     tiles_4326_gt_gdf.drop_duplicates(['id'], inplace=True)
     logger.info(f"- Number of tiles intersecting GT labels = {len(tiles_4326_gt_gdf)}")
 

examples/mineral-extract-sites-detection/prepare_data.py

@@ -22,6 +22,7 @@ generate_tilesets.py:
     enable: False  # sample of tiles
     nb_tiles_max: 500
   working_directory: outputs_RS
+  output_folder: .
   datasets:
     aoi_tiles: json_inputs/tiles_aoi.geojson
     ground_truth_labels: json_inputs/ground_truth_labels.geojson
@@ -31,7 +32,6 @@ generate_tilesets.py:
       year: 2018
       location: https://wmts.geo.admin.ch/1.0.0/ch.swisstopo.swissimage-product/default/{year}/3857/{z}/{x}/{y}.jpeg
       srs: "EPSG:3857"
-  output_folder: .
   tile_size: 256 # per side, in pixels
   overwrite: False
   n_jobs: 10

examples/road-surface-classification/config_rs.yaml

@@ -23,4 +23,6 @@ nobody@<id>:/app# exit
 $ sudo chmod -R a+w examples
 ```
 
-We strongly encourage the end-user to review the provided `config_GE.yaml` file as well as the various output files, a list of which is printed by each script before exiting. 
+We strongly encourage the end-user to review the provided `config_GE.yaml` file as well as the various output files, a list of which is printed by each script before exiting.
+
+Due to timeout of the WMS service, the user might have to run the tileset generation several times.

examples/swimming-pool-detection/GE/README.md

@@ -2,7 +2,7 @@ prepare_data.py:
   datasets:
     lakes_shapefile: https://ge.ch/sitg/geodata/SITG/OPENDATA/3951/SHP_GEO_LAC_LEMAN.zip
     parcels_shapefile: https://ge.ch/sitg/geodata/SITG/OPENDATA/8450/SHP_CAD_PARCELLE_MENSU.zip
-    swimmingpools_shapefile: https://ge.ch/sitg/geodata/SITG/OPENDATA/1836/SHP_CAD_PISCINE.zip
+    swimming_pools_shapefile: https://ge.ch/sitg/geodata/SITG/OPENDATA/1836/SHP_CAD_PISCINE.zip
     OK_z18_tile_IDs_csv: data/OK_z18_tile_IDs.csv
   output_folder: output_GE
 

examples/swimming-pool-detection/GE/config_GE.yaml

@@ -35,7 +35,7 @@
     OUTPUT_DIR = cfg['output_folder']
     LAKES_SHPFILE = cfg['datasets']['lakes_shapefile']
     PARCELS_SHPFILE = cfg['datasets']['parcels_shapefile']
-    SWIMMINGPOOLS_SHPFILE = cfg['datasets']['swimmingpools_shapefile']
+    SWIMMING_POOLS_SHPFILE = cfg['datasets']['swimming_pools_shapefile']
     OK_TILE_IDS_CSV = cfg['datasets']['OK_z18_tile_IDs_csv']
     ZOOM_LEVEL = 18 # this is hard-coded 'cause we only know "OK tile IDs" for this zoom level
 
@@ -49,27 +49,27 @@
 
     dataset_dict = {}
 
-    for dataset in ['lakes', 'parcels', 'swimmingpools']:
+    for dataset in ['lakes', 'parcels', 'swimming_pools']:
 
         shpfile_name = eval(f'{dataset.upper()}_SHPFILE').split('/')[-1]
         shpfile_path = os.path.join(OUTPUT_DIR, shpfile_name)
 
         if eval(f'{dataset.upper()}_SHPFILE').startswith('http'):
 
-            logger.info(f"Downloading the {dataset} dataset...")
+            logger.info(f"Downloading the {dataset.replace('_', ' ')} dataset...")
             r = requests.get(eval(f'{dataset.upper()}_SHPFILE'), timeout=30)  
             with open(shpfile_path, 'wb') as f:
                 f.write(r.content)
 
             written_files.append(shpfile_path)
             logger.success(f"...done. A file was written: {shpfile_path}")
 
-        logger.info(f"Loading the {dataset} dataset as a GeoPandas DataFrame...")
+        logger.info(f"Loading the {dataset.replace('_', ' ')} dataset as a GeoPandas DataFrame...")
         dataset_dict[dataset] = gpd.read_file(f'zip://{shpfile_path}')
         logger.success(f"...done. {len(dataset_dict[dataset])} records were found.")
 
-    dataset_dict['swimmingpools']['CATEGORY'] = "swimming pool"
-    dataset_dict['swimmingpools']['SUPERCATEGORY'] = "facility"
+    dataset_dict['swimming_pools']['CATEGORY'] = "swimming pool"
+    dataset_dict['swimming_pools']['SUPERCATEGORY'] = "facility"
 
     # ------ Computing the Area of Interest (AoI) = cadastral parcels - Léman lake
 
@@ -123,7 +123,7 @@
     OK_tiles_gdf.to_crs(epsg=4326).to_file(OK_TILES_GEOJSON, driver='GeoJSON')
     written_files.append(OK_TILES_GEOJSON)
 
-    labels_gdf = dataset_dict['swimmingpools'].copy()
+    labels_gdf = dataset_dict['swimming_pools'].copy()
     labels_gdf = labels_gdf.to_crs(epsg=4326)
 
     # Ground Truth Labels = Labels intersecting OK tiles