Improving ownership matching algorithm

etl/customers/gla/proposal_investigation.py

@@ -74,3 +74,32 @@ matches = ownership.matched_addresses.copy()
 matches = matches[matches["epc_postcode"].str.lower().isin(postcodes["postcode"].str.lower())]
 # Remove any social transactions
 matches = matches[~matches["TENURE"].isin(["Rented (social)", "rental (social)"])]
+
+matches.head()
+owners_count = matches.groupby(['Proprietor Name (1)', 'Company Registration No. (1)']).size().reset_index()
+owners_count.columns = ['Owner', 'Owner Registration #', 'Count']
+owners_count = owners_count.sort_values('Count', ascending=False)
+owners_count["Percentage"] = owners_count["Count"] / owners_count["Count"].sum() * 100
+
+companies_house_api_key = "1d9c2877-3271-4642-80ed-a6170971653f"
+
+import requests
+import json
+
+company_number = "13197205"
+url = f'https://api.company-information.service.gov.uk/company/{company_number}'
+
+# Make the API request
+response = requests.get(url, auth=(companies_house_api_key, ''))
+
+# Check if the request was successful
+if response.status_code == 200:
+    company_data = response.json()
+    # Pretty-print the fetched data
+    print(json.dumps(company_data, indent=4))
+else:
+    print(f"Failed to fetch data. Status code: {response.status_code}")
+
+psc_url = f'https://api.company-information.service.gov.uk/company/{company_number}/persons-with-significant-control'
+psc_response = requests.get(psc_url, auth=(companies_house_api_key, ''))
+psc_data = psc_response.json()

etl/ownership/Ownership.py

@@ -488,11 +488,11 @@ class Ownership:
                 house_no = house_no.replace(",", "")
 
             if house_no is None:
-                # It's hard for us to get a reliable match
-                # filtered = filtered[filtered["Property Address"].str.contains(address["ADDRESS1"])]
-                # if filtered.shape[0] > 1:
-                #     raise Exception("No valid - maybe we should do levenstein?")
-                continue
+                # If the house number is missing, it means that we usually have a named property so we look for an
+                # exact match on that name
+                filtered = filtered[filtered["Property Address"].str.lower().str.contains(address["ADDRESS"].lower())]
+                if filtered.shape[0] != 1:
+                    continue
 
             else: