mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-06-08 11:17:27 +00:00
105 lines
2.9 KiB
Python
105 lines
2.9 KiB
Python
import pandas as pd
|
|
import requests
|
|
from backend.address2UPRN.main import resolve_uprns_for_postcode_group, get_epc_data_with_postcode
|
|
from tqdm import tqdm
|
|
|
|
|
|
|
|
def sanitise_postcode(postcode: str) -> str | None:
|
|
"""
|
|
Normalise postcode for grouping.
|
|
|
|
- Uppercase
|
|
- Remove all whitespace
|
|
"""
|
|
if pd.isna(postcode):
|
|
return None
|
|
|
|
return postcode.upper().replace(" ", "")
|
|
|
|
|
|
def is_valid_postcode(postcode_clean: str) -> bool:
|
|
"""
|
|
Validate postcode using postcodes.io.
|
|
|
|
Expects a sanitised postcode (e.g. E84SQ).
|
|
Returns True if valid, False otherwise.
|
|
"""
|
|
POSTCODES_IO_VALIDATE_URL = "https://api.postcodes.io/postcodes/{postcode}/validate"
|
|
if not postcode_clean:
|
|
return False
|
|
|
|
try:
|
|
resp = requests.get(
|
|
POSTCODES_IO_VALIDATE_URL.format(postcode=postcode_clean),
|
|
timeout=5,
|
|
)
|
|
resp.raise_for_status()
|
|
return resp.json().get("result", False)
|
|
except requests.RequestException:
|
|
# Network issues, rate limits, etc.
|
|
return False
|
|
|
|
|
|
def main():
|
|
df = pd.read_excel("hackney.xlsx", sheet_name="Sustainability")
|
|
df = df.head(500)
|
|
|
|
# Sanitise postcodes
|
|
df["postcode_clean"] = df["Postcode"].apply(sanitise_postcode)
|
|
|
|
# --- validate AFTER grouping (save API calls) ---
|
|
|
|
# Get unique, non-null postcodes
|
|
unique_postcodes = (
|
|
df["postcode_clean"]
|
|
.dropna()
|
|
.unique()
|
|
)
|
|
|
|
# Validate each postcode once, TODOadd a progress bar
|
|
postcode_validity = {
|
|
pc: is_valid_postcode(pc)
|
|
for pc in tqdm(unique_postcodes, total=len(unique_postcodes))
|
|
}
|
|
|
|
# Map validity back onto dataframe
|
|
df["postcode_valid"] = df["postcode_clean"].map(postcode_validity)
|
|
|
|
|
|
results = []
|
|
|
|
for postcode, group_df in tqdm(
|
|
df[df["postcode_valid"]].groupby("postcode_clean"),
|
|
desc="Resolving UPRNs by postcode",
|
|
):
|
|
try:
|
|
epc_df = get_epc_data_with_postcode(postcode)
|
|
|
|
if epc_df.empty:
|
|
tmp = group_df.copy()
|
|
tmp["found_uprn"] = None
|
|
tmp["status"] = "no_epc_results"
|
|
results.append(tmp)
|
|
continue
|
|
|
|
resolved = resolve_uprns_for_postcode_group(
|
|
group_df=group_df,
|
|
epc_df=epc_df,
|
|
)
|
|
|
|
results.append(resolved)
|
|
|
|
except Exception as e:
|
|
tmp = group_df.copy()
|
|
tmp["found_uprn"] = None
|
|
tmp["status"] = "exception"
|
|
tmp["error"] = str(e)
|
|
results.append(tmp)
|
|
|
|
final_df = pd.concat(results, ignore_index=True)
|
|
a = final_df[["best_match_lexiscore","Address 1", "best_match_address", "Postcode", "UPRN", "best_match_uprn"]] # add levi score to viewing
|
|
b = final_df[final_df["best_match_lexiscore"]>0] # add levi score to viewing
|
|
|
|
if __name__ == "__main__":
|
|
main()
|