wrap scoring functionality in a class to be called by frontend

data_processing/data_provider.py

@@ -0,0 +1,94 @@
+from get_smallAreaInfo import get_smallAreas
+from point_scoring import score_current
+from get_station_coverage import get_station_coverage
+from aggregate_data import get_feature_df
+import os
+import pandas as pd
+from pyproj import Transformer
+
+
+class data_provider():
+
+    def __init__(self):
+        self.smsv_list = get_smallAreas()
+        self.df = get_feature_df()
+        self.transformer_to_3057 = Transformer.from_crs("EPSG:4326", "EPSG:3057", always_xy=True)
+        self.transformer_to_4326 = Transformer.from_crs("EPSG:3057", "EPSG:4326", always_xy=True)
+
+    def get_station_score(self, station_coord, w_density=1, w_income=1, w_age=1, radius=400, EPSG_4326=True):
+        """
+        Calculate the score for a station based on the given weights and radius.
+
+        Parameters:
+        ----------
+        station_coord : tuple
+            Coordinates of the station in EPSG:4326 format (north, east) = (lat, long).
+        w_density : float
+            Weight for the density factor.
+        w_income : float
+            Weight for the income factor.
+        w_age : float
+            Weight for the age factor.
+        radius : float
+            The radius (in meters) around the station to consider.
+        EPSG_4326 : bool
+            if a true, station coord of format EPSG:4326 is expected, else EPSG:3057
+
+        Returns:
+        -------
+        dict
+            Dictionary that contains total score and subscores
+            {"total_score": total_score, "income_score": income_score, "age_score": age_score, "density_score": density_score}
+        """
+        if EPSG_4326:
+            station_coord = self.__convert_to_3057(station_coord)
+        cov = get_station_coverage(self.smsv_list, station_coord, radius)
+        scores = score_current(station_coord, self.df, cov, w_density, w_income, w_age)
+        return scores
+
+    def __convert_to_3057(self, station_coord):
+        """
+        Convert coordinates from EPSG:4326 (lon, lat) to EPSG:3057 (x, y).
+
+        Parameters:
+        ----------
+        station_coord : tuple
+            Coordinates in EPSG:4326 format (lon, lat).
+
+        Returns:
+        -------
+        tuple
+            Coordinates in EPSG:3057 format (x, y).
+        """
+        return self.transformer_to_3057.transform(*station_coord)
+
+    def __convert_to_4326(self, station_coord):
+        """
+        Convert coordinates from EPSG:3057 (x, y) to EPSG:4326 (lon, lat).
+
+        Parameters:
+        ----------
+        station_coord : tuple
+            Coordinates in EPSG:3057 format (x, y).
+
+        Returns:
+        -------
+        tuple
+            Coordinates in EPSG:4326 format (lon, lat).
+        """
+        return self.transformer_to_4326.transform(*station_coord)
+
+
+
+
+if __name__ == '__main__':
+    dummy_coord1 = (356250.0, 408250.0)  # EPSG:3057 coordinates
+    dummy_coord2 = (-21.910388, 64.144947)  # EPSG:4326 coordinates
+    dummy_coord3 = (358374.26032876654, 407938.72289760906) # ISN93/Lambert
+    # dummy_coord3 = 
+    backend = data_provider()
+    print("dummy_coord1: ", backend.get_station_score(dummy_coord1, EPSG_4326=False))
+    print("dummy_coord2: ", backend.get_station_score(dummy_coord2))
+    print("dummy_coord3: ", backend.get_station_score(dummy_coord3, EPSG_4326=False))
+
+

data_processing/point_scoring.py

@@ -35,7 +35,10 @@ def score_current(station_coord, df_features, cov_smsv, w_density, w_income, w_a
     # Score = [for all areas in range((density) * coverage percentage)]
 
     # TODO: take into account fjoldi starfandi, if there are more people who work than live => many people need to get there, also works the other way around.
-    final_score = 0
+    total_score = 0
+    income_score = 0
+    density_score = 0
+    age_score = 0
     for smsv in cov_smsv:
         
 
@@ -50,8 +53,8 @@ def score_current(station_coord, df_features, cov_smsv, w_density, w_income, w_a
         income_score = get_income_score(income_dist) * w_income
 
         density_score = smsv_info["density"].iloc[0] * w_density
-        final_score += (age_score + income_score + density_score) * smsv["coverage_percentage"] # TODO: Area of the cricle * percent covered / total area of the small area
-    return final_score
+        total_score += (age_score + income_score + density_score) * smsv["coverage_percentage"] # TODO: Area of the cricle * percent covered / total area of the small area
+    return {"total_score": total_score, "income_score": income_score, "age_score": age_score, "density_score": density_score}
 
 def get_age_score(age_distribution):
     """

data_processing/test.py

@@ -1,25 +0,0 @@
-from get_smallAreaInfo import get_smallAreas
-from point_scoring import score_current
-from get_station_coverage import get_station_coverage
-from aggregate_data import get_feature_df
-import os
-import pandas as pd
-
-
-smsv_list = get_smallAreas()
-df = get_feature_df()
-
-
-station_coords = (356250.0, 408250.0)  # EPSG:3057 coordinates
-w_density = 1
-w_income = 1
-w_age = 1
-radius = 400
-
-if __name__ == '__main__':
-
-    cov = get_station_coverage(smsv_list, station_coords, radius)
-    # print(cov)
-    final_score = score_current(station_coords, df, cov, w_density, w_income, w_age)
-
-    print(f'final score: {final_score}')