Merge pull request #628 from Klimatbyran/staging

Deploy to prod

data/climate_data_calculations.py

@@ -8,10 +8,8 @@
 import pandas as pd
 
 from solutions.cars.electric_car_change_rate import get_electric_car_change_rate
-from solutions.cars.electric_vehicle_per_charge_points import (
-    get_electric_vehicle_per_charge_points,
-)
-from solutions.bicycles.bicycle_data_calculations import bicycle_calculations
+from solutions.cars.electric_vehicle_per_charge_points import get_electric_vehicle_per_charge_points
+from solutions.bicycles.bicycle_data_calculations import calculate_bike_lane_per_capita
 from facts.plans.plans_data_prep import get_climate_plans
 from facts.municipalities_counties import get_municipalities
 from facts.procurements.climate_requirements_in_procurements import get_procurement_data
@@ -35,7 +33,8 @@ def create_dataframe(to_percentage: bool) -> pd.DataFrame:
     df = get_climate_plans(df)
     print('4. Climate plans added')
 
-    df = bicycle_calculations(df)
+    df_bike_lanes = calculate_bike_lane_per_capita()
+    df = df.merge(df_bike_lanes, on='Kommun', how='left')
     print('5. Bicycle data added')
 
     df = get_consumption_emissions(df)
@@ -84,7 +83,7 @@ def series_to_dict(row: pd.Series, numeric_columns: List[Any]) -> Dict:
         'climatePlanLink': row['Länk till aktuell klimatplan'],
         'climatePlanYear': row['Antagen år'],
         'climatePlanComment': row['Namn, giltighetsår, kommentar'],
-        'bicycleMetrePerCapita': row['metrePerCapita'],
+        'bicycleMetrePerCapita': row['bikeMetrePerCapita'],
         'totalConsumptionEmission': row['Total emissions'],
         'electricVehiclePerChargePoints': row['EVPC'],
         'procurementScore': row['procurementScore'],

data/solutions/bicycles/bicycle_data_calculations.py

@@ -1,14 +1,42 @@
-import numpy as np
 import pandas as pd
 
 
-PATH_BICYCLE_DATA = 'solutions/bicycles/cykelstatistik.xlsx'
+PATH_BICYCLE_DATA = 'solutions/bicycles/Cykelnät per komun 20231231.xlsx'
+PATH_POPULATION_DATA = 'solutions/bicycles/be0101_tabhel2023.xlsx'
 
 
-def bicycle_calculations(df):
-    df_raw_bicycles = pd.read_excel(PATH_BICYCLE_DATA)
-    df_raw_bicycles['metrePerCapita'] = df_raw_bicycles['Meter per capita']
-    df_bicycles = df_raw_bicycles.filter(
-        ['Kommun', 'metrePerCapita'], axis=1)
-    df = df.merge(df_bicycles, on='Kommun', how='left')
-    return df
+def calculate_bike_lane_per_capita():
+    """
+    Perform calculations on bicycle data and population data on municipality level.
+
+    This function reads bicycle data and population data from Excel files, performs
+    data cleaning and merging, and calculates the bike lane per capita per municipality.
+
+    Returns:
+        pandas.DataFrame: A DataFrame containing the merged data and the calculated bike lane per capita.
+    """
+
+    df_raw_bicycles = pd.read_excel(PATH_BICYCLE_DATA, skiprows=3)
+    df_bicycles = df_raw_bicycles[['Kommun', 'Totalsumma']]
+    df_bicycles.loc[df_bicycles['Kommun'] == 'Malung', 'Kommun'] = 'Malung-Sälen'
+    df_bicycles.loc[df_bicycles['Kommun'] == 'Upplands-Väsby', 'Kommun'] = 'Upplands Väsby'
+
+    df_raw_population = pd.read_excel(PATH_POPULATION_DATA, skiprows=5)
+    # Drop unnecessary rows
+    df_population_drop = df_raw_population.drop([0, 1, 2, 3])
+    # Filter out county rows (that have 2 codes in the 'Kommun' column instead of 4)
+    df_population_municipality = df_population_drop[df_population_drop['Kommun'].str.len() == 4]
+    # Filter out unnecessary columns
+    df_population_filter = df_population_municipality[['Kommunnamn', 'Folkmängd']]
+    # Rename 'Kommunnamn' to 'Kommun' to match the bicycle dataframe
+    df_population_renamed = df_population_filter.rename(columns={'Kommunnamn': 'Kommun'})
+    # Strip 'Kommun' column of whitespaces
+    df_population_renamed['Kommun'] = df_population_renamed['Kommun'].str.strip()
+
+    # Merge bicycle and population dataframes
+    df_merged = df_bicycles.merge(df_population_renamed, on='Kommun', how='left')
+
+    # Calculate bike lane per capita
+    df_merged['bikeMetrePerCapita'] = df_merged['Totalsumma'] / df_merged['Folkmängd']
+
+    return df_merged[['Kommun', 'bikeMetrePerCapita']]

data/tests/test_bike_lane_per_capita.py

@@ -0,0 +1,23 @@
+# -*- coding: utf-8 -*-
+import unittest
+import pandas as pd
+
+from solutions.bicycles.bicycle_data_calculations import calculate_bike_lane_per_capita
+
+
+class TestBicycleCalculations(unittest.TestCase):
+
+    def test_calculate_bike_lane_per_capita(self):
+        df_expected = pd.DataFrame(
+            {
+                "Kommun": ["Ale", "Alingsås", "Alvesta"],
+                "bikeMetrePerCapita": [91548/32446, 122012/42382, 66699/20040],
+            }
+        )
+
+        df_result = calculate_bike_lane_per_capita()
+
+        pd.testing.assert_frame_equal(df_result.iloc[:3], df_expected, check_dtype=False)
+
+if __name__ == "__main__":
+    unittest.main()

public/locales/sv/municipality.json

@@ -70,7 +70,7 @@
   "solutions": {
     "bikes": {
       "heading": "Antal meter cykelväg per invånare",
-      "info": "Antal meter cykelväg per invånare år 2022 totalt för alla väghållare (statlig, kommunal, enskild). Högre är generellt bättre.",
+      "info": "Antal meter cykelväg per invånare år 2023 totalt för alla väghållare (statlig, kommunal, enskild). Högre är generellt bättre.",
       "meters": "{{meters}} meter",
       "title": "Cyklarna"
     },