issue 5 resolved

#3
Ausgabeforma:
{ids: [84, 43...44], lat:[...], lon[...]}

etl/src/data/database.py

@@ -418,6 +418,16 @@ class Database:
 				consultancy_d.properties p
 		""")
 
+	def properties_geo_seeds(self):
+		return self.connection.sql("""
+			SELECT
+				p.id,
+				p.seed_id,
+				p.check_data as coordinates
+			FROM
+				consultancy_d.properties p
+		""")
+
 	def capacity_of_region(self, region_id):
 		return self.connection.sql(f"""
 			SELECT 

etl/src/data/etl_property_neighbours.py

@@ -0,0 +1,64 @@
+import polars as pl
+from math import radians, cos, sin, asin, sqrt, degrees, atan2
+
+import data
+
+d = data.load()
+
+
+def calcHaversinDistance(latMain, lonMain, lat, lon):
+    R = 6371
+
+    # convert decimal degrees to radians
+    latMain, lonMain, lat, lon = map(radians, [latMain, lonMain, lat, lon])
+
+    # haversine formula
+    dlon = lonMain - lon
+    dlat = latMain - lat
+
+    a = sin(dlat / 2) ** 2 + cos(lat) * cos(latMain) * sin(dlon / 2) ** 2
+    c = 2 * asin(sqrt(a))  # 2 * atan2(sqrt(a), sqrt(1-a))
+    d = R * c
+
+    return d
+
+def property_neighbours(id: int):
+    extractions = d.properties_geo_seeds().pl()
+
+    # Get lat, long and region from main property
+    latMain, lonMain = extractions.filter(pl.col('id') == str(id))['coordinates'][0].split(',')
+    latMain, lonMain = map(float, [latMain, lonMain])
+    region = extractions.filter(pl.col('id') == str(id))['seed_id'][0]
+
+    # Prefilter the dataframe to only the correct region
+    extractions = extractions.filter(pl.col('seed_id') == str(region))
+    extractions = extractions.drop('seed_id')
+
+    # Remove main property from DF
+    extractions = extractions.filter(pl.col('id') != str(id))
+
+    # Split coordinate into lat and lon
+    #extractions = extractions.with_columns((pl.col('coordinates').str.split(','))[0].alias("coordinates")).unnest("fields")
+    extractions = extractions.with_columns(pl.col("coordinates").str.split_exact(",", 1).struct.rename_fields(["lat", "lon"]).alias("lat/lon")).unnest("lat/lon")
+    extractions = extractions.drop('coordinates')
+    extractions = extractions.with_columns(pl.col("lat").cast(pl.Float32))
+    extractions = extractions.with_columns(pl.col("lon").cast(pl.Float32))
+
+    # Calculate distances
+    distances = []
+    for row in extractions.rows(named=True):
+        lat = row['lat']
+        lon = row['lon']
+        dist = calcHaversinDistance(latMain, lonMain, lat, lon)
+        distances.append(dist)
+
+    # Add distance to DF
+    extractions = extractions.with_columns(pl.Series(name="distances", values=distances))
+
+    # Sort for distance and give only first 10
+    extractions = extractions.sort("distances").head(10)
+    extractions = extractions.drop('distances')
+
+    result = {"ids": extractions['id'].to_list(), "lat": extractions['lat'].to_list(), "lon": extractions['lon'].to_list()}
+
+    return result