setup OpenUprnClient

model_data/OpenUprnClient.py

@@ -0,0 +1,27 @@
+import pandas as pd
+from model_data.utils import setup_logger
+
+logger = setup_logger()
+
+
+class OpenUprnClient:
+    COLUMN_NAMES = [
+
+    ]
+
+    def __init__(self, path, urpns):
+        self.path = path
+        self.urpns = [int(x) for x in urpns]
+        self.data = None
+
+    def read(self):
+        """
+        This methodology is placeholder, while data sits localls
+        :return:
+        """
+        logger.info("Reading in open uprn data")
+
+        df = pd.read_csv(self.path)
+        df = df[df["UPRN"].isin(self.urpns)]
+
+        self.data = df

model_data/Property.py

@@ -1,5 +1,6 @@
 from epc_api.client import EpcClient
 from model_data.config import EPC_AUTH_TOKEN
+from model_data.OpenUprnClient import OpenUprnClient
 
 
 class Property:
@@ -35,3 +36,12 @@ class Property:
             response["rows"] = newest_response
 
         self.data = response["rows"][0]
+
+    def get_coordinates(self, open_oprn_client: OpenUprnClient):
+        """
+        This method utlises the OpenOprnClient to get the coordinates of the property
+        The OpenOprnClient interfactes with the Ordinance Survey Open UPRN database to extract
+        property coordinates. This database holds lookups between UPRN and coordinates.
+        :param open_oprn_client:
+        :return:
+        """

model_data/app.py

@@ -1,5 +1,6 @@
 import pandas as pd
 from tqdm import tqdm
+import os
 
 from model_data.temp_inputs import input_data
 from model_data.Property import Property
@@ -7,6 +8,7 @@ from model_data.config import EPC_AUTH_TOKEN
 from epc_api.client import EpcClient
 from model_data.downloader import pagenated_epc_download
 from model_data.EpcClean import EpcClean
+from model_data.OpenUprnClient import OpenUprnClient
 
 
 def handler():
@@ -22,6 +24,16 @@ def handler():
     for p in input_properties:
         p.search_address_epc()
 
+    urpns = [p.data['uprn'] for p in input_properties]
+
+    open_urpn_client = OpenUprnClient(
+        path=os.path.abspath(
+            os.path.dirname(__file__)
+        ) + "/model_data/local_data/osopenuprn_202306_csv/osopenuprn_202305.csv",
+        urpns=urpns
+    )
+    open_urpn_client.read()
+
     local_authorities = {p.data['local-authority'] for p in input_properties}
 
     data = []
@@ -40,7 +52,6 @@ def handler():
     cleaner.clean()
 
     import pickle
-    import os
     with open(os.path.abspath(os.path.dirname(__file__)) + "/data.pkl", "rb") as f:
         data = pickle.load(f)
 
@@ -91,9 +102,8 @@ def handler():
     #
     # df.to_dict("records")
 
-    ## Land registry
+    # Land registry
     from model_data.LandRegistryClient import LandRegistryClient
-    import os
 
     land_registry_client = LandRegistryClient(
         paths=[
@@ -110,8 +120,7 @@ def handler():
     )
 
     from dbfread import DBF
-    import os
-    from tqdm import tqdm
+
     import pandas as pd
     borehole_file = os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/borehole/borehole.dbf"
     table = DBF(borehole_file)
@@ -125,3 +134,28 @@ def handler():
 
     borehole_shape_file = os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/borehole/borehole.shp"
     boreholes = gpd.read_file(borehole_shape_file)
+
+    from geopy.geocoders import Nominatim
+    from geopy.extra.rate_limiter import RateLimiter
+
+    geolocator = Nominatim(user_agent="myGeocoder")
+
+    # The rate limiter will ensure you're not making too many requests too quickly
+    geocode = RateLimiter(geolocator.geocode, min_delay_seconds=0.5)
+
+    for address_config in input_data:
+        location = geocode(" ".join([address_config["address1"], address_config["postcode"]]))
+        geocode("28 distillery wharf, regtta lane, hammersmith, london, w6 9bf")
+
+        print((location.latitude, location.longitude))
+
+    from geopy.geocoders import Nominatim
+    from geopy.extra.rate_limiter import RateLimiter
+
+    geolocator = Nominatim(user_agent="myGeocoder")
+
+    geocode = RateLimiter(geolocator.geocode, min_delay_seconds=1)
+
+    # Full address
+    location = geocode(", ".join([p.data["address"], p.data["postcode"]]))
+    print((location.latitude, location.longitude))