From e6261c826d750e0e3032c5343614e4a41e15ff55 Mon Sep 17 00:00:00 2001
From: Alexander Griffen <alexander@mysociety.org>
Date: Thu, 21 Dec 2023 16:23:39 +0000
Subject: [PATCH] DATASET: RSPB nature reserves

---
 .../commands/import_rspb_nature_reserves.py   | 100 ++++++++++++++++++
 1 file changed, 100 insertions(+)
 create mode 100644 hub/management/commands/import_rspb_nature_reserves.py

diff --git a/hub/management/commands/import_rspb_nature_reserves.py b/hub/management/commands/import_rspb_nature_reserves.py
new file mode 100644
index 000000000..1cd5aba34
--- /dev/null
+++ b/hub/management/commands/import_rspb_nature_reserves.py
@@ -0,0 +1,100 @@
+from time import sleep
+
+from django.conf import settings
+
+import pandas as pd
+from tqdm import tqdm
+
+from hub.models import Area, AreaData, DataSet, DataType
+
+from .base_importers import BaseLatLongImportCommand
+
+
+class Command(BaseLatLongImportCommand):
+    help = "Import number of RSPB reserves by constituency"
+
+    data_file = settings.BASE_DIR / "data" / "rspb_reserves_centroids.csv"
+    message = "Importing RSPB reserves data"
+    uses_gss = False
+
+    defaults = {}
+
+    data_sets = {
+        "": {
+            "defaults": defaults,
+        },
+    }
+
+    def add_data_sets(self):
+        data_set, created = DataSet.objects.update_or_create(
+            name="rspb_nature_reserves",
+            defaults={
+                "label": "RSPB Reserves",
+                "data_type": "integer",
+                "category": "place",
+                "label": "RSPB Reserves",
+                "description": "Number of RSPB reserves by constituency.",
+                "source_label": "Data from the RSPB.",
+                "release_date": "September 2023",
+                "source": "https://www.rspb.org.uk",
+                "source_type": "csv",
+                "table": "areadata",
+                "default_value": {},
+                "data_url": "",
+                "is_filterable": False,
+                "comparators": DataSet.comparators_default,
+            },
+        )
+
+        data_type, created = DataType.objects.update_or_create(
+            data_set=data_set,
+            name="rspb_nature_reserves",
+            defaults={
+                "data_type": "integer",
+                "label": "RSPB Reserves",
+                "description": "Number of RSPB reserves by constituency.",
+            },
+        )
+
+        self.data_type = data_type
+        self.data_types[data_type.name] = data_type
+
+    def get_dataframe(self):
+        df = pd.read_csv(
+            self.data_file,
+            usecols=["xcoord", "ycoord"],
+        )
+        df.columns = ["Longitude", "Latitude"]
+        return df
+
+    def process_data(self, df):
+        df = self.get_dataframe()
+
+        if not self._quiet:
+            self.stdout.write("Importing RSPB reserve count data")
+
+        for index, row in tqdm(df.iterrows(), disable=self._quiet):
+            lat = row["Latitude"]
+            lon = row["Longitude"]
+
+            self.process_lat_long(lat=lat, lon=lon, row_name=index)
+
+            if index > 0 and index % 50 == 0:
+                sleep(10)
+
+    def add_arguments(self, parser):
+        parser.add_argument(
+            "-q", "--quiet", action="store_true", help="Silence progress bars."
+        )
+
+    def handle(self, quiet=False, *args, **options):
+        self._quiet = quiet
+        self.add_data_sets()
+        self.delete_data()
+        df = self.get_dataframe()
+        self.process_data(df)
+        self.update_averages()
+        self.update_max_min()
+
+    def delete_data(self):
+        AreaData.objects.filter(data_type__in=self.data_types.values()).delete()