Added checks for proper lat/lon.

grompy/__init__.py

@@ -3,7 +3,7 @@
 # Allard de Wit (allard.dewit@wur.nl), October 2021
 """Grompy is a tool to process and access parcel-based satellite observations from GroenMonitor.nl.
 """
-__version__ = "1.6.1"
+__version__ = "1.6.2"
 
 from .dap import DataAccessProvider
 from .cmd import cli

grompy/dap.py

@@ -233,7 +233,11 @@ class DataAccessProvider:
                     d[dataset_name] =  df
                 c = SimpleNamespace(**d)
 
+                assert (50 < parcel_info.latitude < 54), f"Latitude out of range {parcel_info.latitude}, did you invert x and y?"
+                assert (3.0 < parcel_info.longitude < 7.5), f"Longitude out of range {parcel_info.longitude}, did you invert x and y?"
+
                 yield parcel_info, c
+
             rows = r.fetchmany(100)
 
     def __len__(self):

grompy/load_data.py

@@ -13,7 +13,7 @@ import numpy as np
 import yaml
 import duckdb
 
-from .util import prepare_db, make_path_absolute, get_latlon_from_RD
+from .util import prepare_db, make_path_absolute, get_latlon_from_RD, check_naam, check_PC4
 
 
 class CSVLoadingError(Exception):
@@ -53,7 +53,9 @@ def load_parcel_info(grompy_yaml, gpkg_fname, counts_file_10m, counts_file_20m,
     r = []
     for row in df.itertuples():
         x, y = float(row.geometry.centroid.x), float(row.geometry.centroid.y)
-        lon, lat = get_latlon_from_RD(x, y)
+        lat, lon = get_latlon_from_RD(x, y)
+        assert (50 < lat < 54), f"Latitude out of range {lat}, did you invert x and y?"
+        assert (3.0 < lon < 7.5), f"Longitude out of range {lon}, did you invert x and y?"
         r.append({"fieldid": row.Index, "latitude": lat, "longitude":lon, "rdx": x, "rdy": y})
     df_latlon = pd.DataFrame(r).set_index("fieldid")
     df = df.join(df_latlon)
@@ -82,15 +84,15 @@ def load_parcel_info(grompy_yaml, gpkg_fname, counts_file_10m, counts_file_20m,
                                "rdy": df.rdy,
                                "longitude": df.longitude,
                                "latitude": df.latitude,
-                               "cat_gewasc": df.cat_gewasc.apply(str),
+                               "cat_gewasc": df.cat_gewasc.apply(check_naam),
                                "gws_gewasc": df.gws_gewasc.astype(np.int32),
-                               "provincie": df.provincie.apply(str),
-                               "gemeente": df.gemeente.apply(str),
-                               "regio": df.regio.apply(str),
-                               "pc4": df.PC4.apply(lambda pc4: str(int(pc4))),
+                               "provincie": df.provincie.apply(check_naam),
+                               "gemeente": df.gemeente.apply(check_naam),
+                               "regio": df.regio.apply(check_naam),
+                               "pc4": df.PC4.apply(check_PC4),
                                "AHN2": df.AHN2,
-                               "woonplaats": df.woonplaats.apply(str),
-                               "waterschap": df.waterschap.apply(str),
+                               "woonplaats": df.woonplaats.apply(check_naam),
+                               "waterschap": df.waterschap.apply(check_naam),
                                "S2_Tiles": df.S2_Tiles.apply(str),
                                "geometry": df.geometry
                               }, crs=df.crs)

grompy/util.py

@@ -105,6 +105,8 @@ def open_DB_connection(grompy_yaml, dsn):
 def get_latlon_from_RD(x, y, _cache={}):
     """Converts given X,Y in the Dutch RD coordinate system towards latitude longitude in WGS84
 
+    returns: (latitude, longitude)
+
     For checking:
     in RD coordinate system X, Y: 197903, 309096
     should be in WGS84 latitude, longitude: 50.770195900951045, 5.995343676754713
@@ -128,4 +130,20 @@ def check_grompy_version(grompy_yaml):
         msg = f"grompy.yaml ({v1}) does not match grompy version ({v2})! " \
               "Generate a new grompy.yaml file with `grompy init` " \
               "and adapt it."
-        raise RuntimeError(msg)
\ No newline at end of file
+        raise RuntimeError(msg)
+
+def check_PC4(postal_code):
+    try:
+        pc4 = str(int(postal_code))
+    except ValueError as e:
+        pc4 = "0000"
+    return pc4
+
+
+def check_naam(name):
+    try:
+        n = str(name)
+    except ValueError as e:
+        n = "Unknown"
+    return n
+

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "grompy"
-version = "1.6.1"
+version = "1.6.2"
 description = "GROMPY is a tool for storing and accessing Groenmonitor satellite time-series for agricultural parcels."
 authors = [
   {name = "Allard de Wit", email = "allard.dewit@wur.nl"},