fix import script errors due to new cons

hub/management/commands/import_area_age_data.py

@@ -3,7 +3,7 @@
 import pandas as pd
 from tqdm import tqdm
 
-from hub.models import Area, AreaData, DataSet, DataType
+from hub.models import Area, AreaData, AreaType, DataSet, DataType
 
 
 class Command(BaseCommand):
@@ -49,13 +49,16 @@ def handle(self, quiet=False, *args, **options):
         df = df.loc[df["Date"] == 2020]
         if not self._quiet:
             self.stdout.write("Importing constituency age distribution")
+
+        area_type = AreaType.objects.get(code=self.area_type)
         for index, row in tqdm(df.iterrows(), disable=self._quiet, total=df.shape[0]):
             age_group = row["Age group"]
             gss = row["ONSConstID"]
 
             data_type, created = DataType.objects.update_or_create(
                 data_set=data_set,
                 name=f"ages_{age_group}",
+                area_type=area_type,
                 defaults={
                     "data_type": "percent",
                     "label": f"Ages {age_group}",
@@ -78,6 +81,6 @@ def handle(self, quiet=False, *args, **options):
             )
 
         for name, average in averages.items():
-            data_type = DataType.objects.get(name=name)
+            data_type = DataType.objects.get(name=name, area_type=area_type)
             data_type.average = average
             data_type.save()

hub/management/commands/import_christian_aid_group_locations.py

@@ -131,7 +131,7 @@ def process_data(self):
         # Group by the area, and add the data from there
         for area_name, data in tqdm(df.groupby("area")):
             try:
-                area = Area.objects.get(name=area_name)
+                area = Area.objects.get(name=area_name, area_type__code=self.area_type)
             except Area.DoesNotExist:
                 continue
 

hub/management/commands/import_foe_groups.py

@@ -62,7 +62,9 @@ def process_data(self):
         for index, row in tqdm(df.iterrows(), disable=self._quiet):
             json_data, created = AreaData.objects.update_or_create(
                 data_type=self.data_types["constituency_foe_groups"],
-                area=Area.objects.get(name=row.constituency),
+                area=Area.objects.get(
+                    name=row.constituency, area_type__code=self.area_type
+                ),
                 json=row.groups,
             )
 

hub/management/commands/import_gbgw_events.py

@@ -48,6 +48,7 @@ def add_data_sets(self, df):
         data_type, created = DataType.objects.update_or_create(
             data_set=data_set,
             name="constituency_gbgw_2022_event_count",
+            area_type=self.get_area_type(),
             defaults={
                 "data_type": "integer",
                 "label": "Number of Great Big Green Week 2022 events",

hub/management/commands/import_hnh_polling_data.py

@@ -1,5 +1,5 @@
 from django.conf import settings
-from django.db.models import Avg, Max, Min
+from django.db.models import Avg, FloatField, Max, Min
 from django.db.models.functions import Cast, Coalesce
 
 import pandas as pd
@@ -28,6 +28,7 @@ class Command(BaseImportFromDataFrameCommand):
 
     help = "Import Hope Not Hate polling data, from February 2023"
     message = "Importing Hope Not Hate polling data"
+    cast_field = FloatField
 
     defaults = {
         "data_type": "percent",
@@ -369,6 +370,7 @@ def extract_and_save_data(self):
                     data_type, created = DataType.objects.update_or_create(
                         data_set=data_set,
                         name=data_type_slug,
+                        area_type=self.get_area_type(),
                         defaults={
                             "data_type": "percent",
                             "label": col["label"],
@@ -426,7 +428,10 @@ def update_averages(self):
                         file["data_set_name"], col["slug"]
                     )
                     self.log(f"    {data_type_slug}")
-                    data_type = DataType.objects.get(name=data_type_slug)
+                    data_type = DataType.objects.get(
+                        name=data_type_slug,
+                        area_type__code=file.get("area_type", "WMC"),
+                    )
                     average = (
                         AreaData.objects.filter(data_type=data_type)
                         .annotate(
@@ -450,7 +455,10 @@ def update_max_min(self):
                         file["data_set_name"], col["slug"]
                     )
                     self.log(f"    {data_type_slug}")
-                    data_type = DataType.objects.get(name=data_type_slug)
+                    data_type = DataType.objects.get(
+                        name=data_type_slug,
+                        area_type__code=file.get("area_type", "WMC"),
+                    )
                     base = (
                         AreaData.objects.filter(data_type=data_type)
                         .annotate(

hub/management/commands/import_mp_job_titles.py

@@ -3,7 +3,7 @@
 import pandas as pd
 from tqdm import tqdm
 
-from hub.models import Area, DataSet, DataType, Person, PersonData
+from hub.models import Area, AreaType, DataSet, DataType, Person, PersonData
 
 CONSTITUENCY_CORRECTIONS_DICT = {
     "Beverly and Holderness": "Beverley and Holderness",
@@ -24,6 +24,9 @@ def handle(self, quiet=False, *args, **options):
         self._quiet = quiet
         self.import_results()
 
+    def get_area_type(self):
+        return AreaType.objects.get(code="WMC")
+
     def get_df(self):
         df = pd.read_csv("data/mp_job_titles.csv", usecols=["Constituency", "Title"])
         df = df.query(
@@ -51,10 +54,12 @@ def create_data_type(self):
                 "comparators": DataSet.string_comparators(),
             },
         )
+        mp_job_titles_ds.areas_available.add(self.get_area_type())
 
         mp_job_titles, created = DataType.objects.update_or_create(
             data_set=mp_job_titles_ds,
             name="job_titles",
+            area_type=self.get_area_type(),
             defaults={"data_type": "text"},
         )
 
@@ -65,9 +70,12 @@ def get_results(self):
         df = self.get_df()
         results = {}
         print("Matching MPs with titles")
+        area_type = self.get_area_type()
         for index, row in df.iterrows():
             try:
-                area = Area.objects.get(name__iexact=row.Constituency)
+                area = Area.objects.get(
+                    name__iexact=row.Constituency, area_type=area_type
+                )
                 results[mps.get(area=area)] = row.Title
             except Area.DoesNotExist:
                 print(f"Constituency: {row.Constituency} not found.")

hub/management/commands/import_nt_property_locations.py

@@ -79,9 +79,10 @@ def process_data(self):
             self.stdout.write("Importing National Trust property data")
 
         # Group by the area, and add the data from there
+        area_type = self.get_area_type()
         for area_name, data in tqdm(df.groupby("area")):
             try:
-                area = Area.objects.get(name=area_name)
+                area = Area.objects.get(name=area_name, area_type=area_type)
             except Area.DoesNotExist:
                 continue
 

hub/management/commands/import_renewables_polling_data.py

@@ -5,7 +5,7 @@
 import pandas as pd
 
 from hub.management.commands.base_importers import BaseImportFromDataFrameCommand
-from hub.models import AreaData, DataSet, DataType
+from hub.models import AreaData, AreaType, DataSet, DataType
 
 SUBCATEGORIES_DICT = {
     "would-change-party": "voting",
@@ -91,6 +91,7 @@ def get_dataframe(self):
 
     def add_data_sets(self, df):
         order = 1
+        area_type = AreaType.objects.get(code=self.area_type)
         for column in df.columns:
             if column in ("id-name", "gss", "constituency-name"):
                 continue
@@ -125,6 +126,7 @@ def add_data_sets(self, df):
             data_type, created = DataType.objects.update_or_create(
                 data_set=data_set,
                 name=column,
+                area_type=area_type,
                 defaults={
                     "data_type": "percent",
                     "label": label,

hub/management/commands/import_wi_group_locations.py

@@ -82,9 +82,10 @@ def process_data(self):
             self.stdout.write("Importing women's institute group data")
 
         # Group by the area, and add the data from there
+        area_type = self.get_area_type()
         for area_name, data in tqdm(df.groupby("area")):
             try:
-                area = Area.objects.get(name=area_name)
+                area = Area.objects.get(name=area_name, area_type=area_type)
             except Area.DoesNotExist:
                 continue